Publikationen

[ 2024 ]
[ 2023 ]
[ 2022 ]
[ 2021 ]
[ 2020 ]
[ 2019 ]
[ 2018 ]
[ 2017 ]
[ 2016 ]
[ 2015 ]
[ 2014 ]
[ 2013 ]
[ 2012 ]
[ 2011 ]
[ 2010 ]
[ 2007 ]
[ 2006 ]

2024[ to top ]

Weisfeiler–Lehman goes dynamic: An analysis of the expressive power of Graph Neural Networks for attributed and dynamic graphs. Beddar-Wiesing, Silvia; D’Inverno, Alessio; Graziani, Caterina; Lachi, Veronica; Moallemy-Oureh, Alice; Scarselli, Franco; Thomas, Josephine. In Neural Networks, 173, bl 106213. Elsevier, 2024.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Graph Neural Networks (GNNs) are a large class of relational models for graph processing. Recent theoretical studies on the expressive power of GNNs have focused on two issues. On the one hand, it has been proven that GNNs are as powerful as the Weisfeiler–Lehman test (1-WL) in their ability to distinguish graphs. Moreover, it has been shown that the equivalence enforced by 1-WL equals unfolding equivalence. On the other hand, GNNs turned out to be universal approximators on graphs modulo the constraints enforced by 1-WL/unfolding equivalence. However, these results only apply to Static Attributed Undirected Homogeneous Graphs (SAUHG) with node attributes. In contrast, real-life applications often involve a much larger variety of graph types. In this paper, we conduct a theoretical analysis of the expressive power of GNNs for two other graph domains that are particularly interesting in practical applications, namely dynamic graphs and SAUGHs with edge attributes. Dynamic graphs are widely used in modern applications; hence, the study of the expressive capability of GNNs in this domain is essential for practical reasons and, in addition, it requires a new analyzing approach due to the difference in the architecture of dynamic GNNs compared to static ones. On the other hand, the examination of SAUHGs is of particular relevance since they act as a standard form for all graph types: it has been shown that all graph types can be transformed without loss of information to SAUHGs with both attributes on nodes and edges. This paper considers generic GNN models and appropriate 1-WL tests for those domains. Then, the known results on the expressive power of GNNs are extended to the mentioned domains: it is proven that GNNs have the same capability as the 1-WL test, the 1-WL equivalence equals unfolding equivalence and that GNNs are universal approximators modulo 1-WL/unfolding equivalence. Moreover, the proof of the approximation capability is mostly constructive and allows us to deduce hints on the architecture of GNNs that can achieve the desired approximation.
@article{beddarwiesing2024weisfeiler, abstract = {Graph Neural Networks (GNNs) are a large class of relational models for graph processing. Recent theoretical studies on the expressive power of GNNs have focused on two issues. On the one hand, it has been proven that GNNs are as powerful as the Weisfeiler–Lehman test (1-WL) in their ability to distinguish graphs. Moreover, it has been shown that the equivalence enforced by 1-WL equals unfolding equivalence. On the other hand, GNNs turned out to be universal approximators on graphs modulo the constraints enforced by 1-WL/unfolding equivalence. However, these results only apply to Static Attributed Undirected Homogeneous Graphs (SAUHG) with node attributes. In contrast, real-life applications often involve a much larger variety of graph types. In this paper, we conduct a theoretical analysis of the expressive power of GNNs for two other graph domains that are particularly interesting in practical applications, namely dynamic graphs and SAUGHs with edge attributes. Dynamic graphs are widely used in modern applications; hence, the study of the expressive capability of GNNs in this domain is essential for practical reasons and, in addition, it requires a new analyzing approach due to the difference in the architecture of dynamic GNNs compared to static ones. On the other hand, the examination of SAUHGs is of particular relevance since they act as a standard form for all graph types: it has been shown that all graph types can be transformed without loss of information to SAUHGs with both attributes on nodes and edges. This paper considers generic GNN models and appropriate 1-WL tests for those domains. Then, the known results on the expressive power of GNNs are extended to the mentioned domains: it is proven that GNNs have the same capability as the 1-WL test, the 1-WL equivalence equals unfolding equivalence and that GNNs are universal approximators modulo 1-WL/unfolding equivalence. Moreover, the proof of the approximation capability is mostly constructive and allows us to deduce hints on the architecture of GNNs that can achieve the desired approximation.}, author = {Beddar-Wiesing, Silvia and D'Inverno, Alessio and Graziani, Caterina and Lachi, Veronica and Moallemy-Oureh, Alice and Scarselli, Franco and Thomas, Josephine}, journal = {Neural Networks}, keywords = {Graph_Neural_Network}, pages = 106213, publisher = {Elsevier}, title = {Weisfeiler–Lehman goes dynamic: An analysis of the expressive power of Graph Neural Networks for attributed and dynamic graphs}, volume = 173, year = 2024 }
%0 Journal Article %1 beddarwiesing2024weisfeiler %A Beddar-Wiesing, Silvia %A D'Inverno, Alessio %A Graziani, Caterina %A Lachi, Veronica %A Moallemy-Oureh, Alice %A Scarselli, Franco %A Thomas, Josephine %D 2024 %I Elsevier %J Neural Networks %P 106213 %R 10.1016/j.neunet.2024.106213 %T Weisfeiler–Lehman goes dynamic: An analysis of the expressive power of Graph Neural Networks for attributed and dynamic graphs %U https://www.sciencedirect.com/science/article/pii/S0893608024001370 %V 173 %X Graph Neural Networks (GNNs) are a large class of relational models for graph processing. Recent theoretical studies on the expressive power of GNNs have focused on two issues. On the one hand, it has been proven that GNNs are as powerful as the Weisfeiler–Lehman test (1-WL) in their ability to distinguish graphs. Moreover, it has been shown that the equivalence enforced by 1-WL equals unfolding equivalence. On the other hand, GNNs turned out to be universal approximators on graphs modulo the constraints enforced by 1-WL/unfolding equivalence. However, these results only apply to Static Attributed Undirected Homogeneous Graphs (SAUHG) with node attributes. In contrast, real-life applications often involve a much larger variety of graph types. In this paper, we conduct a theoretical analysis of the expressive power of GNNs for two other graph domains that are particularly interesting in practical applications, namely dynamic graphs and SAUGHs with edge attributes. Dynamic graphs are widely used in modern applications; hence, the study of the expressive capability of GNNs in this domain is essential for practical reasons and, in addition, it requires a new analyzing approach due to the difference in the architecture of dynamic GNNs compared to static ones. On the other hand, the examination of SAUHGs is of particular relevance since they act as a standard form for all graph types: it has been shown that all graph types can be transformed without loss of information to SAUHGs with both attributes on nodes and edges. This paper considers generic GNN models and appropriate 1-WL tests for those domains. Then, the known results on the expressive power of GNNs are extended to the mentioned domains: it is proven that GNNs have the same capability as the 1-WL test, the 1-WL equivalence equals unfolding equivalence and that GNNs are universal approximators modulo 1-WL/unfolding equivalence. Moreover, the proof of the approximation capability is mostly constructive and allows us to deduce hints on the architecture of GNNs that can achieve the desired approximation.
Time-Series Representation Learning via Heterogeneous Spatial-Temporal Contrasting for Remaining Useful Life Prediction. Huang, Zhixin; He, Yujiang; Nivarthi, Chandana Priya; Gruhl, Christian; Sick, Bernhard. In International Conference on Pattern Recognition (ICPR). 2024.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
Classical contrastive learning paradigms rely on manual augmentations like cropping, masking, dropping, or adding noise randomly to create divergent sample views from original data. However, the choice of which method to manipulate samples is often subjective and may destroy the latent pattern of the sample. In response, this paper introduces a novel contrastive learning paradigm without choosing sample view augmentation methods, termed Heterogeneous Spatial-Temporal Representation Contrasting (HSTRC). Instead of sample view augmentation, we employ dual branches with a heterogeneous spatial-temporal flipped structure to extract two distinct hidden feature views from the same source data, which avoids disturbing the original time series. Leveraging a combination of cross-branch spatial-temporal contrastive and projected feature contrastive loss functions, HSTRC can effectively extract robust representations from unlabeled time series data. Remarkably, by only fine-tuning the fully connected layers on top of extracted representations by HSTRC, we achieve the best performance across several Remaining Useful Life prediction datasets, showing up to 19.2% improvements over the state-of-the-art supervised learning methods and classical contrastive learning paradigms. Besides, further intensive experiments demonstrate HSTRC's effectiveness in active learning, out-of-distribution testing, and transfer learning scenarios.
@inproceedings{huang2024time, abstract = {Classical contrastive learning paradigms rely on manual augmentations like cropping, masking, dropping, or adding noise randomly to create divergent sample views from original data. However, the choice of which method to manipulate samples is often subjective and may destroy the latent pattern of the sample. In response, this paper introduces a novel contrastive learning paradigm without choosing sample view augmentation methods, termed Heterogeneous Spatial-Temporal Representation Contrasting (HSTRC). Instead of sample view augmentation, we employ dual branches with a heterogeneous spatial-temporal flipped structure to extract two distinct hidden feature views from the same source data, which avoids disturbing the original time series. Leveraging a combination of cross-branch spatial-temporal contrastive and projected feature contrastive loss functions, HSTRC can effectively extract robust representations from unlabeled time series data. Remarkably, by only fine-tuning the fully connected layers on top of extracted representations by HSTRC, we achieve the best performance across several Remaining Useful Life prediction datasets, showing up to 19.2% improvements over the state-of-the-art supervised learning methods and classical contrastive learning paradigms. Besides, further intensive experiments demonstrate HSTRC's effectiveness in active learning, out-of-distribution testing, and transfer learning scenarios.}, author = {Huang, Zhixin and He, Yujiang and Nivarthi, Chandana Priya and Gruhl, Christian and Sick, Bernhard}, booktitle = {International Conference on Pattern Recognition (ICPR)}, keywords = {itegpub}, note = {(accepted)}, title = {Time-Series Representation Learning via Heterogeneous Spatial-Temporal Contrasting for Remaining Useful Life Prediction}, year = 2024 }
%0 Conference Paper %1 huang2024time %A Huang, Zhixin %A He, Yujiang %A Nivarthi, Chandana Priya %A Gruhl, Christian %A Sick, Bernhard %B International Conference on Pattern Recognition (ICPR) %D 2024 %T Time-Series Representation Learning via Heterogeneous Spatial-Temporal Contrasting for Remaining Useful Life Prediction %X Classical contrastive learning paradigms rely on manual augmentations like cropping, masking, dropping, or adding noise randomly to create divergent sample views from original data. However, the choice of which method to manipulate samples is often subjective and may destroy the latent pattern of the sample. In response, this paper introduces a novel contrastive learning paradigm without choosing sample view augmentation methods, termed Heterogeneous Spatial-Temporal Representation Contrasting (HSTRC). Instead of sample view augmentation, we employ dual branches with a heterogeneous spatial-temporal flipped structure to extract two distinct hidden feature views from the same source data, which avoids disturbing the original time series. Leveraging a combination of cross-branch spatial-temporal contrastive and projected feature contrastive loss functions, HSTRC can effectively extract robust representations from unlabeled time series data. Remarkably, by only fine-tuning the fully connected layers on top of extracted representations by HSTRC, we achieve the best performance across several Remaining Useful Life prediction datasets, showing up to 19.2% improvements over the state-of-the-art supervised learning methods and classical contrastive learning paradigms. Besides, further intensive experiments demonstrate HSTRC's effectiveness in active learning, out-of-distribution testing, and transfer learning scenarios.
The Interplay of Uncertainty Modeling and Deep Active Learning: An Empirical Analysis in Image Classification. Huseljic, Denis; Herde, Marek; Nagel, Yannick; Rauch, Lukas; Strimaitis, Paulius; Sick, Bernhard. In Transactions on Machine Learning Research. 2024.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Deep active learning (AL) seeks to reduce the annotation costs required for training deep neural networks (DNNs). Often, deep AL strategies focus on instances where the predictive uncertainty of a DNN is high. Furthermore, Bayesian concepts to model uncertainty are frequently adopted. Despite considerable research, a detailed analysis of the role of uncertainty in deep AL is still missing, especially regarding aleatoric and epistemic uncertainty, both related to predictive uncertainty. This article provides an in-depth empirical study analyzing the interplay of uncertainty and deep AL in image classification. Our study investigates four hypotheses that provide an intuitive understanding of the effects of accurately estimating aleatoric and epistemic uncertainty on existing uncertainty-based AL strategies but also, in the opposite direction, the impact of uncertainty-based AL on the quality of uncertainty estimates that are needed in many applications. By analyzing these hypotheses on synthetic and real-world data, we find that accurate aleatoric estimates can even impair instance selection, while accurate epistemic estimates have negligible effects. Moreover, we provide a publicly available toolbox for deep AL with various models and strategies to facilitate further research and practical applications. Code is available at https://github.com/dhuseljic/dal-toolbox.
@article{huseljic2024interplay, abstract = {Deep active learning (AL) seeks to reduce the annotation costs required for training deep neural networks (DNNs). Often, deep AL strategies focus on instances where the predictive uncertainty of a DNN is high. Furthermore, Bayesian concepts to model uncertainty are frequently adopted. Despite considerable research, a detailed analysis of the role of uncertainty in deep AL is still missing, especially regarding aleatoric and epistemic uncertainty, both related to predictive uncertainty. This article provides an in-depth empirical study analyzing the interplay of uncertainty and deep AL in image classification. Our study investigates four hypotheses that provide an intuitive understanding of the effects of accurately estimating aleatoric and epistemic uncertainty on existing uncertainty-based AL strategies but also, in the opposite direction, the impact of uncertainty-based AL on the quality of uncertainty estimates that are needed in many applications. By analyzing these hypotheses on synthetic and real-world data, we find that accurate aleatoric estimates can even impair instance selection, while accurate epistemic estimates have negligible effects. Moreover, we provide a publicly available toolbox for deep AL with various models and strategies to facilitate further research and practical applications. Code is available at https://github.com/dhuseljic/dal-toolbox.}, author = {Huseljic, Denis and Herde, Marek and Nagel, Yannick and Rauch, Lukas and Strimaitis, Paulius and Sick, Bernhard}, journal = {Transactions on Machine Learning Research}, keywords = {itegpub}, title = {The Interplay of Uncertainty Modeling and Deep Active Learning: An Empirical Analysis in Image Classification}, year = 2024 }
%0 Journal Article %1 huseljic2024interplay %A Huseljic, Denis %A Herde, Marek %A Nagel, Yannick %A Rauch, Lukas %A Strimaitis, Paulius %A Sick, Bernhard %D 2024 %J Transactions on Machine Learning Research %T The Interplay of Uncertainty Modeling and Deep Active Learning: An Empirical Analysis in Image Classification %U https://openreview.net/forum?id=KLBD13bsVl %X Deep active learning (AL) seeks to reduce the annotation costs required for training deep neural networks (DNNs). Often, deep AL strategies focus on instances where the predictive uncertainty of a DNN is high. Furthermore, Bayesian concepts to model uncertainty are frequently adopted. Despite considerable research, a detailed analysis of the role of uncertainty in deep AL is still missing, especially regarding aleatoric and epistemic uncertainty, both related to predictive uncertainty. This article provides an in-depth empirical study analyzing the interplay of uncertainty and deep AL in image classification. Our study investigates four hypotheses that provide an intuitive understanding of the effects of accurately estimating aleatoric and epistemic uncertainty on existing uncertainty-based AL strategies but also, in the opposite direction, the impact of uncertainty-based AL on the quality of uncertainty estimates that are needed in many applications. By analyzing these hypotheses on synthetic and real-world data, we find that accurate aleatoric estimates can even impair instance selection, while accurate epistemic estimates have negligible effects. Moreover, we provide a publicly available toolbox for deep AL with various models and strategies to facilitate further research and practical applications. Code is available at https://github.com/dhuseljic/dal-toolbox.
Spatial-Temporal Attention Graph Neural Network with Uncertainty Estimation for Remaining Useful Life Prediction. Huang, Zhixin; Nivarthi, Chandana Priya; Gruhl, Christian; Sick, Bernhard. In International Joint Conference on Neural Networks (IJCNN), bll 1–9. IEEE, 2024.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
In the increasingly complex industrial system health management domain, accurate prediction of remaining useful life plays an essential role. This paper analyzes the methods to improve the predictive performance of remaining useful life from three aspects: optimizing model structures, augmenting uncertainty estimation in predictions, and transitioning normalization methods. Based on our analysis, we propose a novel model, the Uncertainty Spatial-Temporal Attention Graph Neural Network (USTAGNN), which consists of three primary components: sensor graph construction, a spatio-temporal feature extractor, and a probabilistic prediction module. The feature extractor leverages graph neural networks and temporal convolutional networks as a foundation to extract spatial and temporal features, further enhanced by attention mechanisms, spectral normalization, and residual connections to bolster its distance awareness. Following extensive experimental comparisons, we utilized the parameter-driven dynamic adjacency matrix for sensor graph construction and the deep kernel Gaussian process for precise uncertainty estimation. USTAGNN tries to resolve issues not thoroughly addressed in existing research, such as comparative analyses of sensor graph construction methods, accurate uncertainty estimation, and the model’s generalization under different preprocessing conditions. The proposed model demonstrated state-of-the-art performance on various subsets of the C-MAPSS dataset, achieving up to a 35.9% improvement in prediction score.
@inproceedings{huang2024spatial, abstract = {In the increasingly complex industrial system health management domain, accurate prediction of remaining useful life plays an essential role. This paper analyzes the methods to improve the predictive performance of remaining useful life from three aspects: optimizing model structures, augmenting uncertainty estimation in predictions, and transitioning normalization methods. Based on our analysis, we propose a novel model, the Uncertainty Spatial-Temporal Attention Graph Neural Network (USTAGNN), which consists of three primary components: sensor graph construction, a spatio-temporal feature extractor, and a probabilistic prediction module. The feature extractor leverages graph neural networks and temporal convolutional networks as a foundation to extract spatial and temporal features, further enhanced by attention mechanisms, spectral normalization, and residual connections to bolster its distance awareness. Following extensive experimental comparisons, we utilized the parameter-driven dynamic adjacency matrix for sensor graph construction and the deep kernel Gaussian process for precise uncertainty estimation. USTAGNN tries to resolve issues not thoroughly addressed in existing research, such as comparative analyses of sensor graph construction methods, accurate uncertainty estimation, and the model’s generalization under different preprocessing conditions. The proposed model demonstrated state-of-the-art performance on various subsets of the C-MAPSS dataset, achieving up to a 35.9% improvement in prediction score.}, author = {Huang, Zhixin and Nivarthi, Chandana Priya and Gruhl, Christian and Sick, Bernhard}, booktitle = {International Joint Conference on Neural Networks (IJCNN)}, keywords = {itegpub}, pages = {1–9}, publisher = {IEEE}, title = {Spatial-Temporal Attention Graph Neural Network with Uncertainty Estimation for Remaining Useful Life Prediction}, year = 2024 }
%0 Conference Paper %1 huang2024spatial %A Huang, Zhixin %A Nivarthi, Chandana Priya %A Gruhl, Christian %A Sick, Bernhard %B International Joint Conference on Neural Networks (IJCNN) %D 2024 %I IEEE %P 1--9 %R 10.1109/IJCNN60899.2024.10650622 %T Spatial-Temporal Attention Graph Neural Network with Uncertainty Estimation for Remaining Useful Life Prediction %X In the increasingly complex industrial system health management domain, accurate prediction of remaining useful life plays an essential role. This paper analyzes the methods to improve the predictive performance of remaining useful life from three aspects: optimizing model structures, augmenting uncertainty estimation in predictions, and transitioning normalization methods. Based on our analysis, we propose a novel model, the Uncertainty Spatial-Temporal Attention Graph Neural Network (USTAGNN), which consists of three primary components: sensor graph construction, a spatio-temporal feature extractor, and a probabilistic prediction module. The feature extractor leverages graph neural networks and temporal convolutional networks as a foundation to extract spatial and temporal features, further enhanced by attention mechanisms, spectral normalization, and residual connections to bolster its distance awareness. Following extensive experimental comparisons, we utilized the parameter-driven dynamic adjacency matrix for sensor graph construction and the deep kernel Gaussian process for precise uncertainty estimation. USTAGNN tries to resolve issues not thoroughly addressed in existing research, such as comparative analyses of sensor graph construction methods, accurate uncertainty estimation, and the model’s generalization under different preprocessing conditions. The proposed model demonstrated state-of-the-art performance on various subsets of the C-MAPSS dataset, achieving up to a 35.9% improvement in prediction score.
PrOuD: Probabilistic Outlier Detection Solution for Time Series Analysis on Real-world Photovoltaic Inverters. He, Yujiang; Huang, Zhixin; Vogt, Stephan; Sick, Bernhard. In Energies (MDPI), 17(1), bl 64. MDPI, 2024.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Anomaly detection methods applied to time series are mostly viewed as a black box, which solely provides a deterministic answer to the detected target. Without a convincing explanation, domain experts can hardly trust the detection results and conduct a further time series diagnosis in real-world applications. To overcome the challenge, we mathematically analyzed the sources of anomalies and novelties in multivariate time series as well as their relationships from the perspective of Gaussian-distributed non-stationary noise. Furthermore, we proposed mathematical methods to generate artificial time series and synthetic anomalies, with the goal of solving the problem that it is difficult to train and evaluate models in real-world applications due to the lack of sufficient data. In addition, we designed extbfProbabilistic extbfOutlier extbfDetection (PrOuD), which is a general solution to provide interpretable detection results to assist domain experts in time series analysis. PrOuD can convert a predictive uncertainty of a trained model about a time series value into an estimated uncertainty of the detected outlier through Monte Carlo Estimation. The experimental results obtained on both artificial time series and real-world photovoltaic inverter data demonstrated that the proposed solution could detect emerging anomalies accurately and quickly. The implemented PrOuD demo case shows the potential to makes the detection results of the existing detection methods more convincing so that domain experts can more efficiently complete their tasks, such as time series diagnosis and anomalous pattern clustering.
@article{he2023proud, abstract = {Anomaly detection methods applied to time series are mostly viewed as a black box, which solely provides a deterministic answer to the detected target. Without a convincing explanation, domain experts can hardly trust the detection results and conduct a further time series diagnosis in real-world applications. To overcome the challenge, we mathematically analyzed the sources of anomalies and novelties in multivariate time series as well as their relationships from the perspective of Gaussian-distributed non-stationary noise. Furthermore, we proposed mathematical methods to generate artificial time series and synthetic anomalies, with the goal of solving the problem that it is difficult to train and evaluate models in real-world applications due to the lack of sufficient data. In addition, we designed extbf{Pr}obabilistic extbf{Ou}tlier extbf{D}etection (PrOuD), which is a general solution to provide interpretable detection results to assist domain experts in time series analysis. PrOuD can convert a predictive uncertainty of a trained model about a time series value into an estimated uncertainty of the detected outlier through Monte Carlo Estimation. The experimental results obtained on both artificial time series and real-world photovoltaic inverter data demonstrated that the proposed solution could detect emerging anomalies accurately and quickly. The implemented PrOuD demo case shows the potential to makes the detection results of the existing detection methods more convincing so that domain experts can more efficiently complete their tasks, such as time series diagnosis and anomalous pattern clustering.}, author = {He, Yujiang and Huang, Zhixin and Vogt, Stephan and Sick, Bernhard}, journal = {Energies (MDPI)}, keywords = {itegpub}, number = 1, pages = 64, publisher = {MDPI}, title = {PrOuD: Probabilistic Outlier Detection Solution for Time Series Analysis on Real-world Photovoltaic Inverters}, volume = 17, year = 2024 }
%0 Journal Article %1 he2023proud %A He, Yujiang %A Huang, Zhixin %A Vogt, Stephan %A Sick, Bernhard %D 2024 %I MDPI %J Energies (MDPI) %N 1 %P 64 %R 10.3390/en17010064 %T PrOuD: Probabilistic Outlier Detection Solution for Time Series Analysis on Real-world Photovoltaic Inverters %U https://www.mdpi.com/1996-1073/17/1/64 %V 17 %X Anomaly detection methods applied to time series are mostly viewed as a black box, which solely provides a deterministic answer to the detected target. Without a convincing explanation, domain experts can hardly trust the detection results and conduct a further time series diagnosis in real-world applications. To overcome the challenge, we mathematically analyzed the sources of anomalies and novelties in multivariate time series as well as their relationships from the perspective of Gaussian-distributed non-stationary noise. Furthermore, we proposed mathematical methods to generate artificial time series and synthetic anomalies, with the goal of solving the problem that it is difficult to train and evaluate models in real-world applications due to the lack of sufficient data. In addition, we designed extbfProbabilistic extbfOutlier extbfDetection (PrOuD), which is a general solution to provide interpretable detection results to assist domain experts in time series analysis. PrOuD can convert a predictive uncertainty of a trained model about a time series value into an estimated uncertainty of the detected outlier through Monte Carlo Estimation. The experimental results obtained on both artificial time series and real-world photovoltaic inverter data demonstrated that the proposed solution could detect emerging anomalies accurately and quickly. The implemented PrOuD demo case shows the potential to makes the detection results of the existing detection methods more convincing so that domain experts can more efficiently complete their tasks, such as time series diagnosis and anomalous pattern clustering.
Organic Computing -- Doctoral Dissertation Colloquium 2023. Tomforde, Sven; Krupitzer, Christian. In Vol. 26Intelligent Embedded Systems. kassel university press, 2024.
- [ BibTeX ]
- [ EndNote ]
@book{tomforde2024organic, editor = {Tomforde, Sven and Krupitzer, Christian}, keywords = {itegpub}, publisher = {kassel university press}, series = {Intelligent Embedded Systems}, title = {Organic Computing – Doctoral Dissertation Colloquium 2023}, volume = 26, year = 2024 }
%0 Book %1 tomforde2024organic %B Intelligent Embedded Systems %D 2024 %E Tomforde, Sven %E Krupitzer, Christian %I kassel university press %R 10.17170/kobra-202402269661 %T Organic Computing -- Doctoral Dissertation Colloquium 2023 %V 26
Optical Detection of the Body Mass Index and Related Parameters Using Multiple Spatially Resolved Reflection Spectroscopy. Magnussen, Birk Martin; Möckel, Frank; Jessulat, Maik; Stern, Claudius; Sick, Bernhard. In International Conference on Bioinformatics and Computational Biology (ICBCB). IEEE, 2024.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
Obesity is a common problem for many people. In order to assist people combating obesity, providing methods to quickly, easily, and inexpensively assess their body composition is important. This article investigates how noninvasive, optical sensors based on multiple spatially resolved reflection spectroscopy can be used to measure the body mass index and body composition parameters. Using machine learning to train continuous feature networks, it is possible to predict the body mass index of a subject, with a correlation of $$R=0.61$$ with $$p<0.0001$$. Similarly, the predicted body mass index shows correlations to both the subject's visceral fat ($$R=0.44,p=0.0023$$) and skeletal muscle mass index ($$R=0.52,p=0.0003$$), indicating that the trained neural network is capable of identifying both types of tissue. Strategies to independently detect either type of tissue are discussed.
@inproceedings{magnussen2024optical, abstract = {Obesity is a common problem for many people. In order to assist people combating obesity, providing methods to quickly, easily, and inexpensively assess their body composition is important. This article investigates how noninvasive, optical sensors based on multiple spatially resolved reflection spectroscopy can be used to measure the body mass index and body composition parameters. Using machine learning to train continuous feature networks, it is possible to predict the body mass index of a subject, with a correlation of $R=0.61$ with $p<0.0001$. Similarly, the predicted body mass index shows correlations to both the subject's visceral fat ($R=0.44,p=0.0023$) and skeletal muscle mass index ($R=0.52,p=0.0003$), indicating that the trained neural network is capable of identifying both types of tissue. Strategies to independently detect either type of tissue are discussed.}, author = {Magnussen, Birk Martin and Möckel, Frank and Jessulat, Maik and Stern, Claudius and Sick, Bernhard}, booktitle = {International Conference on Bioinformatics and Computational Biology (ICBCB)}, keywords = {itegpub}, note = {(accepted)}, publisher = {IEEE}, title = {Optical Detection of the Body Mass Index and Related Parameters Using Multiple Spatially Resolved Reflection Spectroscopy}, year = 2024 }
%0 Conference Paper %1 magnussen2024optical %A Magnussen, Birk Martin %A Möckel, Frank %A Jessulat, Maik %A Stern, Claudius %A Sick, Bernhard %B International Conference on Bioinformatics and Computational Biology (ICBCB) %D 2024 %I IEEE %T Optical Detection of the Body Mass Index and Related Parameters Using Multiple Spatially Resolved Reflection Spectroscopy %X Obesity is a common problem for many people. In order to assist people combating obesity, providing methods to quickly, easily, and inexpensively assess their body composition is important. This article investigates how noninvasive, optical sensors based on multiple spatially resolved reflection spectroscopy can be used to measure the body mass index and body composition parameters. Using machine learning to train continuous feature networks, it is possible to predict the body mass index of a subject, with a correlation of $$R=0.61$$ with $$p<0.0001$$. Similarly, the predicted body mass index shows correlations to both the subject's visceral fat ($$R=0.44,p=0.0023$$) and skeletal muscle mass index ($$R=0.52,p=0.0003$$), indicating that the trained neural network is capable of identifying both types of tissue. Strategies to independently detect either type of tissue are discussed.
Multi-Task Representation Learning with Temporal Attention for Zero-Shot Time Series Anomaly Detection. Nivarthi, Chandana Priya; Huang, Zhixin; Gruhl, Christian; Sick, Bernhard. In International Joint Conference on Neural Networks (IJCNN), bll 1–10. IEEE, 2024.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
Ensuring the reliability of critical industrial systems across various sectors is crucial. It is essential to detect deviations from regular behaviour to mitigate disruptions and preserve infrastructure integrity. However, accurately labelling anomaly datasets is challenging due to their rarity and manual annotation subjectivity. The conventional approach of training separate models for each dataset entity further complicates model development. This paper presents a novel Multi-task Learning framework combining LSTM Autoencoder with temporal attention mechanism (MTL-LATAM) for effective time series anomaly detection. Multitask learning models improve adaptability and generalizability, leading to reduced runtime and compute power while supporting zero-shot evaluation. These models offer flexibility in detecting emerging anomalies. Additionally, we introduce a dynamic thresholding mechanism to incorporate temporal context for anomaly detection and provide visualizations of attention weights to enhance interpretability. The study compares MTL- LATAM, with other multi-task models, evaluates multi-task versus single-task models and assesses the performance of the proposed frame- work in zero-shot learning scenarios. The findings indicate MTL- LATAM’s effectiveness across real-world and open-source datasets, achieving 95% and 97% task synergy. The results underscore the superior performance of multi-task models in zero-shot tasks compared to individual models trained exclusively on their respective datasets.
@inproceedings{nivarthi2024multi, abstract = {Ensuring the reliability of critical industrial systems across various sectors is crucial. It is essential to detect deviations from regular behaviour to mitigate disruptions and preserve infrastructure integrity. However, accurately labelling anomaly datasets is challenging due to their rarity and manual annotation subjectivity. The conventional approach of training separate models for each dataset entity further complicates model development. This paper presents a novel Multi-task Learning framework combining LSTM Autoencoder with temporal attention mechanism (MTL-LATAM) for effective time series anomaly detection. Multitask learning models improve adaptability and generalizability, leading to reduced runtime and compute power while supporting zero-shot evaluation. These models offer flexibility in detecting emerging anomalies. Additionally, we introduce a dynamic thresholding mechanism to incorporate temporal context for anomaly detection and provide visualizations of attention weights to enhance interpretability. The study compares MTL- LATAM, with other multi-task models, evaluates multi-task versus single-task models and assesses the performance of the proposed frame- work in zero-shot learning scenarios. The findings indicate MTL- LATAM’s effectiveness across real-world and open-source datasets, achieving 95% and 97% task synergy. The results underscore the superior performance of multi-task models in zero-shot tasks compared to individual models trained exclusively on their respective datasets.}, author = {Nivarthi, Chandana Priya and Huang, Zhixin and Gruhl, Christian and Sick, Bernhard}, booktitle = {International Joint Conference on Neural Networks (IJCNN)}, keywords = {itegpub}, pages = {1–10}, publisher = {IEEE}, title = {Multi-Task Representation Learning with Temporal Attention for Zero-Shot Time Series Anomaly Detection}, year = 2024 }
%0 Conference Paper %1 nivarthi2024multi %A Nivarthi, Chandana Priya %A Huang, Zhixin %A Gruhl, Christian %A Sick, Bernhard %B International Joint Conference on Neural Networks (IJCNN) %D 2024 %I IEEE %P 1--10 %R 10.1109/IJCNN60899.2024.10651344 %T Multi-Task Representation Learning with Temporal Attention for Zero-Shot Time Series Anomaly Detection %X Ensuring the reliability of critical industrial systems across various sectors is crucial. It is essential to detect deviations from regular behaviour to mitigate disruptions and preserve infrastructure integrity. However, accurately labelling anomaly datasets is challenging due to their rarity and manual annotation subjectivity. The conventional approach of training separate models for each dataset entity further complicates model development. This paper presents a novel Multi-task Learning framework combining LSTM Autoencoder with temporal attention mechanism (MTL-LATAM) for effective time series anomaly detection. Multitask learning models improve adaptability and generalizability, leading to reduced runtime and compute power while supporting zero-shot evaluation. These models offer flexibility in detecting emerging anomalies. Additionally, we introduce a dynamic thresholding mechanism to incorporate temporal context for anomaly detection and provide visualizations of attention weights to enhance interpretability. The study compares MTL- LATAM, with other multi-task models, evaluates multi-task versus single-task models and assesses the performance of the proposed frame- work in zero-shot learning scenarios. The findings indicate MTL- LATAM’s effectiveness across real-world and open-source datasets, achieving 95% and 97% task synergy. The results underscore the superior performance of multi-task models in zero-shot tasks compared to individual models trained exclusively on their respective datasets.
Location based Probabilistic Load Forecasting of EV Charging Sites: Deep Transfer Learning with Multi-Quantile Temporal Convolutional Network. Ali, Mohammad Wazed; Mustafa, Mohammed Asif bin; Shuvo, Md. Aukerul Moin; Sick, Bernhard. In arXiv e-prints, bl arXiv:2409.11862. 2024.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Electrification of vehicles is a potential way of reducing fossil fuel usage and thus lessening environmental pollution. Electric Vehicles (EVs) of various types for different transport modes (including air, water, and land) are evolving. Moreover, different EV user groups (commuters, commercial or domestic users, drivers) may use different charging infrastructures (public, private, home, and workplace) at various times. Therefore, usage patterns and energy demand are very stochastic. Characterizing and forecasting the charging demand of these diverse EV usage profiles is essential in preventing power outages. Previously developed data-driven load models are limited to specific use cases and locations. None of these models are simultaneously adaptive enough to transfer knowledge of day-ahead forecasting among EV charging sites of diverse locations, trained with limited data, and cost-effective. This article presents a location-based load forecasting of EV charging sites using a deep Multi-Quantile Temporal Convolutional Network (MQ-TCN) to overcome the limitations of earlier models. We conducted our experiments on data from four charging sites, namely Caltech, JPL, Office-1, and NREL, which have diverse EV user types like students, full-time and part-time employees, random visitors, etc. With a Prediction Interval Coverage Probability (PICP) score of 93.62%, our proposed deep MQ-TCN model exhibited a remarkable 28.93% improvement over the XGBoost model for a day-ahead load forecasting at the JPL charging site. By transferring knowledge with the inductive Transfer Learning (TL) approach, the MQ-TCN model achieved a 96.88% PICP score for the load forecasting task at the NREL site using only two weeks of data.
@article{ali2024location, abstract = {Electrification of vehicles is a potential way of reducing fossil fuel usage and thus lessening environmental pollution. Electric Vehicles (EVs) of various types for different transport modes (including air, water, and land) are evolving. Moreover, different EV user groups (commuters, commercial or domestic users, drivers) may use different charging infrastructures (public, private, home, and workplace) at various times. Therefore, usage patterns and energy demand are very stochastic. Characterizing and forecasting the charging demand of these diverse EV usage profiles is essential in preventing power outages. Previously developed data-driven load models are limited to specific use cases and locations. None of these models are simultaneously adaptive enough to transfer knowledge of day-ahead forecasting among EV charging sites of diverse locations, trained with limited data, and cost-effective. This article presents a location-based load forecasting of EV charging sites using a deep Multi-Quantile Temporal Convolutional Network (MQ-TCN) to overcome the limitations of earlier models. We conducted our experiments on data from four charging sites, namely Caltech, JPL, Office-1, and NREL, which have diverse EV user types like students, full-time and part-time employees, random visitors, etc. With a Prediction Interval Coverage Probability (PICP) score of 93.62%, our proposed deep MQ-TCN model exhibited a remarkable 28.93% improvement over the XGBoost model for a day-ahead load forecasting at the JPL charging site. By transferring knowledge with the inductive Transfer Learning (TL) approach, the MQ-TCN model achieved a 96.88% PICP score for the load forecasting task at the NREL site using only two weeks of data.}, author = {Ali, Mohammad Wazed and Mustafa, Mohammed Asif bin and Shuvo, Md. Aukerul Moin and Sick, Bernhard}, journal = {arXiv e-prints}, keywords = {itegpub}, pages = {arXiv:2409.11862}, title = {Location based Probabilistic Load Forecasting of EV Charging Sites: Deep Transfer Learning with Multi-Quantile Temporal Convolutional Network.}, year = 2024 }
%0 Journal Article %1 ali2024location %A Ali, Mohammad Wazed %A Mustafa, Mohammed Asif bin %A Shuvo, Md. Aukerul Moin %A Sick, Bernhard %D 2024 %J arXiv e-prints %P arXiv:2409.11862 %T Location based Probabilistic Load Forecasting of EV Charging Sites: Deep Transfer Learning with Multi-Quantile Temporal Convolutional Network. %U https://arxiv.org/abs/2409.11862 %X Electrification of vehicles is a potential way of reducing fossil fuel usage and thus lessening environmental pollution. Electric Vehicles (EVs) of various types for different transport modes (including air, water, and land) are evolving. Moreover, different EV user groups (commuters, commercial or domestic users, drivers) may use different charging infrastructures (public, private, home, and workplace) at various times. Therefore, usage patterns and energy demand are very stochastic. Characterizing and forecasting the charging demand of these diverse EV usage profiles is essential in preventing power outages. Previously developed data-driven load models are limited to specific use cases and locations. None of these models are simultaneously adaptive enough to transfer knowledge of day-ahead forecasting among EV charging sites of diverse locations, trained with limited data, and cost-effective. This article presents a location-based load forecasting of EV charging sites using a deep Multi-Quantile Temporal Convolutional Network (MQ-TCN) to overcome the limitations of earlier models. We conducted our experiments on data from four charging sites, namely Caltech, JPL, Office-1, and NREL, which have diverse EV user types like students, full-time and part-time employees, random visitors, etc. With a Prediction Interval Coverage Probability (PICP) score of 93.62%, our proposed deep MQ-TCN model exhibited a remarkable 28.93% improvement over the XGBoost model for a day-ahead load forecasting at the JPL charging site. By transferring knowledge with the inductive Transfer Learning (TL) approach, the MQ-TCN model achieved a 96.88% PICP score for the load forecasting task at the NREL site using only two weeks of data.
LiST: An All-Linear-Layer Spatial-Temporal Feature Extractor with Uncertainty Estimation for RUL Prediction. Huang, Zhixin; Gruhl, Christian; Sick, Bernhard. In IEEE Conference on Industrial Electronics and Applications(ICIEA). IEEE, 2024.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
In the context of Remaining Useful Life (RUL) prediction for industrial systems, the pursuit of prediction accuracy must be balanced against the hardware costs of model operation and the reliability of prediction results. To resolve these challenges, we introduce LiST, an all-linear-layer spatial-temporal feature extractor integrated with uncertainty estimation, specifically designed for processing sensor multivariate time series (MTS) data. Unlike traditional linear models that flatten MTS and thus neglect their spatial-temporal dependencies, LiST's linear layers act on both the sensor and time dimensions of MTS that can extract spatial and temporal features like GNN and RNN models. Through performance comparisons on four RUL prediction datasets, LiST uses only 66.1% of the parameters, achieves comparable accuracy to state-of-the-art GNN and RNN models, obtains the best results on two datasets with up to a 21.6% improvement in Score, and enhances training efficiency by 3.2 times. Additionally, LiST can predict RUL with uncertainty estimation and precisely disentangle epistemic and aleatoric uncertainties, thus enhancing the model's practicality and reliability in real-world industrial applications.
@inproceedings{huang2024list, abstract = {In the context of Remaining Useful Life (RUL) prediction for industrial systems, the pursuit of prediction accuracy must be balanced against the hardware costs of model operation and the reliability of prediction results. To resolve these challenges, we introduce LiST, an all-linear-layer spatial-temporal feature extractor integrated with uncertainty estimation, specifically designed for processing sensor multivariate time series (MTS) data. Unlike traditional linear models that flatten MTS and thus neglect their spatial-temporal dependencies, LiST's linear layers act on both the sensor and time dimensions of MTS that can extract spatial and temporal features like GNN and RNN models. Through performance comparisons on four RUL prediction datasets, LiST uses only 66.1% of the parameters, achieves comparable accuracy to state-of-the-art GNN and RNN models, obtains the best results on two datasets with up to a 21.6% improvement in Score, and enhances training efficiency by 3.2 times. Additionally, LiST can predict RUL with uncertainty estimation and precisely disentangle epistemic and aleatoric uncertainties, thus enhancing the model's practicality and reliability in real-world industrial applications.}, author = {Huang, Zhixin and Gruhl, Christian and Sick, Bernhard}, booktitle = {IEEE Conference on Industrial Electronics and Applications(ICIEA)}, keywords = {itegpub}, note = {(accepted)}, publisher = {IEEE}, title = {LiST: An All-Linear-Layer Spatial-Temporal Feature Extractor with Uncertainty Estimation for RUL Prediction}, year = 2024 }
%0 Conference Paper %1 huang2024list %A Huang, Zhixin %A Gruhl, Christian %A Sick, Bernhard %B IEEE Conference on Industrial Electronics and Applications(ICIEA) %D 2024 %I IEEE %T LiST: An All-Linear-Layer Spatial-Temporal Feature Extractor with Uncertainty Estimation for RUL Prediction %X In the context of Remaining Useful Life (RUL) prediction for industrial systems, the pursuit of prediction accuracy must be balanced against the hardware costs of model operation and the reliability of prediction results. To resolve these challenges, we introduce LiST, an all-linear-layer spatial-temporal feature extractor integrated with uncertainty estimation, specifically designed for processing sensor multivariate time series (MTS) data. Unlike traditional linear models that flatten MTS and thus neglect their spatial-temporal dependencies, LiST's linear layers act on both the sensor and time dimensions of MTS that can extract spatial and temporal features like GNN and RNN models. Through performance comparisons on four RUL prediction datasets, LiST uses only 66.1% of the parameters, achieves comparable accuracy to state-of-the-art GNN and RNN models, obtains the best results on two datasets with up to a 21.6% improvement in Score, and enhances training efficiency by 3.2 times. Additionally, LiST can predict RUL with uncertainty estimation and precisely disentangle epistemic and aleatoric uncertainties, thus enhancing the model's practicality and reliability in real-world industrial applications.
From Structured to Unstructured: A Comparative Analysis of Computer Vision and Graph Models in solving Mesh-based PDEs. Decke, Jens; Wünsch, Olaf; Sick, Bernhard; Gruhl, Christian. In International Conference on Architecture of Computing Systems (ARCS), bll 82–96. Springer, 2024.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
This article investigates the application of computer vision and graph-based models in solving mesh-based partial differential equations within high-performance computing environments. Focusing on structured, graded structured, and unstructured meshes, the study compares the performance and computational efficiency of three computer vision-based models against three graph-based models across three datasets. The research aims to identify the most suitable models for different mesh topographies, particularly highlighting the exploration of graded meshes, a less studied area. Results demonstrate that computer vision-based models, notably U-Net, outperform the graph models in prediction performance and efficiency in two (structured and graded) out of three mesh topographies. The study also reveals the unexpected effectiveness of computer vision-based models in handling unstructured meshes, suggesting a potential shift in methodological approaches for data-driven partial differential equation learning. The article underscores deep learning as a viable and potentially sustainable way to enhance traditional high-performance computing methods, advocating for informed model selection based on the topography of the mesh.
@inproceedings{decke2024structured, abstract = {This article investigates the application of computer vision and graph-based models in solving mesh-based partial differential equations within high-performance computing environments. Focusing on structured, graded structured, and unstructured meshes, the study compares the performance and computational efficiency of three computer vision-based models against three graph-based models across three datasets. The research aims to identify the most suitable models for different mesh topographies, particularly highlighting the exploration of graded meshes, a less studied area. Results demonstrate that computer vision-based models, notably U-Net, outperform the graph models in prediction performance and efficiency in two (structured and graded) out of three mesh topographies. The study also reveals the unexpected effectiveness of computer vision-based models in handling unstructured meshes, suggesting a potential shift in methodological approaches for data-driven partial differential equation learning. The article underscores deep learning as a viable and potentially sustainable way to enhance traditional high-performance computing methods, advocating for informed model selection based on the topography of the mesh.}, author = {Decke, Jens and Wünsch, Olaf and Sick, Bernhard and Gruhl, Christian}, booktitle = {International Conference on Architecture of Computing Systems (ARCS)}, keywords = {itegpub}, pages = {82–96}, publisher = {Springer}, title = {From Structured to Unstructured: A Comparative Analysis of Computer Vision and Graph Models in solving Mesh-based PDEs}, year = 2024 }
%0 Conference Paper %1 decke2024structured %A Decke, Jens %A Wünsch, Olaf %A Sick, Bernhard %A Gruhl, Christian %B International Conference on Architecture of Computing Systems (ARCS) %D 2024 %I Springer %P 82--96 %R 10.1007/978-3-031-66146-4_6 %T From Structured to Unstructured: A Comparative Analysis of Computer Vision and Graph Models in solving Mesh-based PDEs %X This article investigates the application of computer vision and graph-based models in solving mesh-based partial differential equations within high-performance computing environments. Focusing on structured, graded structured, and unstructured meshes, the study compares the performance and computational efficiency of three computer vision-based models against three graph-based models across three datasets. The research aims to identify the most suitable models for different mesh topographies, particularly highlighting the exploration of graded meshes, a less studied area. Results demonstrate that computer vision-based models, notably U-Net, outperform the graph models in prediction performance and efficiency in two (structured and graded) out of three mesh topographies. The study also reveals the unexpected effectiveness of computer vision-based models in handling unstructured meshes, suggesting a potential shift in methodological approaches for data-driven partial differential equation learning. The article underscores deep learning as a viable and potentially sustainable way to enhance traditional high-performance computing methods, advocating for informed model selection based on the topography of the mesh.
Fault Detection for Agents in Power Grid Topology Optimization: A Comprehensive Analysis. Lehna, Malte; Hassouna, Mohamed; Degtyar, Dmitry; Tomforde, Sven; Scholz, Christoph. In Machine Learning for Sustainable Power Systems (ML4SPS), ECML. Springer, 2024.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
Optimizing the topology of transmission networks using Deep Reinforcement Learning (DRL) has increasingly come into focus. Various DRL agents have been proposed, which are mostly benchmarked on the Grid2Op environment from the Learning to Run a Power Network (L2RPN) challenges. The environments have many advantages with their realistic chronics and underlying power flow backends. However, the interpretation of agent survival or failure is not always clear, as there are a variety of potential causes. In this work, we focus on the failures of the power grid simulation to identify patterns and detect them in advance. We collect the failed chronics of three different agents on the WCCI 2022 L2RPN environment, totaling about 40k data points. By clustering, we are able to detect five distinct clusters, identifying common failure types. Further, we propose a multi-class prediction approach to detect failures beforehand and evaluate five different prediction models. Here, the Light Gradient-Boosting Machine (LightGBM) shows the best failure detection performance, with an accuracy of 86%. It also correctly identifies in 91% of the time failure and survival observations. Finally, we provide a detailed feature importance analysis that identifies critical features and regions in the grid.
@inproceedings{lehna2024fault, abstract = {Optimizing the topology of transmission networks using Deep Reinforcement Learning (DRL) has increasingly come into focus. Various DRL agents have been proposed, which are mostly benchmarked on the Grid2Op environment from the Learning to Run a Power Network (L2RPN) challenges. The environments have many advantages with their realistic chronics and underlying power flow backends. However, the interpretation of agent survival or failure is not always clear, as there are a variety of potential causes. In this work, we focus on the failures of the power grid simulation to identify patterns and detect them in advance. We collect the failed chronics of three different agents on the WCCI 2022 L2RPN environment, totaling about 40k data points. By clustering, we are able to detect five distinct clusters, identifying common failure types. Further, we propose a multi-class prediction approach to detect failures beforehand and evaluate five different prediction models. Here, the Light Gradient-Boosting Machine (LightGBM) shows the best failure detection performance, with an accuracy of 86%. It also correctly identifies in 91% of the time failure and survival observations. Finally, we provide a detailed feature importance analysis that identifies critical features and regions in the grid.}, author = {Lehna, Malte and Hassouna, Mohamed and Degtyar, Dmitry and Tomforde, Sven and Scholz, Christoph}, booktitle = {Machine Learning for Sustainable Power Systems (ML4SPS), ECML}, keywords = {itegpub}, note = {(accepted)}, publisher = {Springer}, title = {Fault Detection for Agents in Power Grid Topology Optimization: A Comprehensive Analysis}, year = 2024 }
%0 Conference Paper %1 lehna2024fault %A Lehna, Malte %A Hassouna, Mohamed %A Degtyar, Dmitry %A Tomforde, Sven %A Scholz, Christoph %B Machine Learning for Sustainable Power Systems (ML4SPS), ECML %D 2024 %I Springer %T Fault Detection for Agents in Power Grid Topology Optimization: A Comprehensive Analysis %X Optimizing the topology of transmission networks using Deep Reinforcement Learning (DRL) has increasingly come into focus. Various DRL agents have been proposed, which are mostly benchmarked on the Grid2Op environment from the Learning to Run a Power Network (L2RPN) challenges. The environments have many advantages with their realistic chronics and underlying power flow backends. However, the interpretation of agent survival or failure is not always clear, as there are a variety of potential causes. In this work, we focus on the failures of the power grid simulation to identify patterns and detect them in advance. We collect the failed chronics of three different agents on the WCCI 2022 L2RPN environment, totaling about 40k data points. By clustering, we are able to detect five distinct clusters, identifying common failure types. Further, we propose a multi-class prediction approach to detect failures beforehand and evaluate five different prediction models. Here, the Light Gradient-Boosting Machine (LightGBM) shows the best failure detection performance, with an accuracy of 86%. It also correctly identifies in 91% of the time failure and survival observations. Finally, we provide a detailed feature importance analysis that identifies critical features and regions in the grid.
Fast Fishing: Approximating BAIT for Efficient and Scalable Deep Active Image Classification. Huseljic, Denis; Hahn, Paul; Herde, Marek; Rauch, Lukas; Sick, Bernhard. In European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECMLPKDD), bll 280–296. 2024.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
Deep active learning (AL) seeks to minimize the annotation costs for training deep neural networks. \\textsc{Bait, a recently proposed AL strategy based on the Fisher Information, has demonstrated impressive performance across various datasets. However, \\textsc{Bait's high computational and memory requirements hinder its applicability on large-scale classification tasks, resulting in current research neglecting \\textsc{Bait in their evaluation. This paper introduces two methods to enhance \\textsc{Bait's computational efficiency and scalability. Notably, we significantly reduce its time complexity by approximating the Fisher Information. In particular, we adapt the original formulation by i) taking the expectation over the most probable classes, and ii) constructing a binary classification task, leading to an alternative likelihood for gradient computations. Consequently, this allows the efficient use of \\textsc{Bait on large-scale datasets, including ImageNet. Our unified and comprehensive evaluation across a variety of datasets demonstrates that our approximations achieve strong performance with considerably reduced time complexity. Furthermore, we provide an extensive open-source toolbox that implements recent state-of-the-art AL strategies, available at \\url{https://github.com/dhuseljic/dal-toolbox.
@inproceedings{huseljic2024fast, abstract = {Deep active learning (AL) seeks to minimize the annotation costs for training deep neural networks. \\textsc{Bait}, a recently proposed AL strategy based on the Fisher Information, has demonstrated impressive performance across various datasets. However, \\textsc{Bait}'s high computational and memory requirements hinder its applicability on large-scale classification tasks, resulting in current research neglecting \\textsc{Bait} in their evaluation. This paper introduces two methods to enhance \\textsc{Bait}'s computational efficiency and scalability. Notably, we significantly reduce its time complexity by approximating the Fisher Information. In particular, we adapt the original formulation by i) taking the expectation over the most probable classes, and ii) constructing a binary classification task, leading to an alternative likelihood for gradient computations. Consequently, this allows the efficient use of \\textsc{Bait} on large-scale datasets, including ImageNet. Our unified and comprehensive evaluation across a variety of datasets demonstrates that our approximations achieve strong performance with considerably reduced time complexity. Furthermore, we provide an extensive open-source toolbox that implements recent state-of-the-art AL strategies, available at \\url{https://github.com/dhuseljic/dal-toolbox}.}, author = {Huseljic, Denis and Hahn, Paul and Herde, Marek and Rauch, Lukas and Sick, Bernhard}, booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECMLPKDD)}, keywords = {itegpub}, pages = {280–296}, title = {Fast Fishing: Approximating BAIT for Efficient and Scalable Deep Active Image Classification}, year = 2024 }
%0 Conference Paper %1 huseljic2024fast %A Huseljic, Denis %A Hahn, Paul %A Herde, Marek %A Rauch, Lukas %A Sick, Bernhard %B European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECMLPKDD) %D 2024 %P 280--296 %R 10.1007/978-3-031-70368-3_17 %T Fast Fishing: Approximating BAIT for Efficient and Scalable Deep Active Image Classification %X Deep active learning (AL) seeks to minimize the annotation costs for training deep neural networks. \\textsc{Bait, a recently proposed AL strategy based on the Fisher Information, has demonstrated impressive performance across various datasets. However, \\textsc{Bait's high computational and memory requirements hinder its applicability on large-scale classification tasks, resulting in current research neglecting \\textsc{Bait in their evaluation. This paper introduces two methods to enhance \\textsc{Bait's computational efficiency and scalability. Notably, we significantly reduce its time complexity by approximating the Fisher Information. In particular, we adapt the original formulation by i) taking the expectation over the most probable classes, and ii) constructing a binary classification task, leading to an alternative likelihood for gradient computations. Consequently, this allows the efficient use of \\textsc{Bait on large-scale datasets, including ImageNet. Our unified and comprehensive evaluation across a variety of datasets demonstrates that our approximations achieve strong performance with considerably reduced time complexity. Furthermore, we provide an extensive open-source toolbox that implements recent state-of-the-art AL strategies, available at \\url{https://github.com/dhuseljic/dal-toolbox.
Enhancing Multi-Objective Optimization through Machine Learning-Supported Multiphysics Simulation. Botache, Diego; Decke, Jens; Ripken, Winfried; Dornipati, Abhinay; Götz-Hahn, Franz; Ayeb, Mohamed; Sick, Bernhard. In arXiv e-prints, bl arXiv:2309.13179v2. 2024.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
This paper presents a methodological framework for training, self-optimising, and self-organising surrogate models to approximate and speed up multiobjective optimisation of technical systems based on multiphysics simulations. At the hand of two real-world datasets, we illustrate that surrogate models can be trained on relatively small amounts of data to approximate the underlying simulations accurately. Including explainable AI techniques allow for highlighting feature relevancy or dependencies and supporting the possible extension of the used datasets. One of the datasets was created for this paper and is made publicly available for the broader scientific community. Extensive experiments combine four machine learning and deep learning algorithms with an evolutionary optimisation algorithm. The performance of the combined training and optimisation pipeline is evaluated by verifying the generated Pareto-optimal results using the ground truth simulations. The results from our pipeline and a comprehensive evaluation strategy show the potential for efficiently acquiring solution candidates in multiobjective optimisation tasks by reducing the number of simulations and conserving a higher prediction accuracy, i.e., with a MAPE score under 5% for one of the presented use cases.
@article{botache2024enhancing, abstract = {This paper presents a methodological framework for training, self-optimising, and self-organising surrogate models to approximate and speed up multiobjective optimisation of technical systems based on multiphysics simulations. At the hand of two real-world datasets, we illustrate that surrogate models can be trained on relatively small amounts of data to approximate the underlying simulations accurately. Including explainable AI techniques allow for highlighting feature relevancy or dependencies and supporting the possible extension of the used datasets. One of the datasets was created for this paper and is made publicly available for the broader scientific community. Extensive experiments combine four machine learning and deep learning algorithms with an evolutionary optimisation algorithm. The performance of the combined training and optimisation pipeline is evaluated by verifying the generated Pareto-optimal results using the ground truth simulations. The results from our pipeline and a comprehensive evaluation strategy show the potential for efficiently acquiring solution candidates in multiobjective optimisation tasks by reducing the number of simulations and conserving a higher prediction accuracy, i.e., with a MAPE score under 5% for one of the presented use cases.}, author = {Botache, Diego and Decke, Jens and Ripken, Winfried and Dornipati, Abhinay and Götz-Hahn, Franz and Ayeb, Mohamed and Sick, Bernhard}, journal = {arXiv e-prints}, keywords = {itegpub}, pages = {arXiv:2309.13179v2}, title = {Enhancing Multi-Objective Optimization through Machine Learning-Supported Multiphysics Simulation}, year = 2024 }
%0 Journal Article %1 botache2024enhancing %A Botache, Diego %A Decke, Jens %A Ripken, Winfried %A Dornipati, Abhinay %A Götz-Hahn, Franz %A Ayeb, Mohamed %A Sick, Bernhard %D 2024 %J arXiv e-prints %P arXiv:2309.13179v2 %T Enhancing Multi-Objective Optimization through Machine Learning-Supported Multiphysics Simulation %U https://arxiv.org/abs/2309.13179 %X This paper presents a methodological framework for training, self-optimising, and self-organising surrogate models to approximate and speed up multiobjective optimisation of technical systems based on multiphysics simulations. At the hand of two real-world datasets, we illustrate that surrogate models can be trained on relatively small amounts of data to approximate the underlying simulations accurately. Including explainable AI techniques allow for highlighting feature relevancy or dependencies and supporting the possible extension of the used datasets. One of the datasets was created for this paper and is made publicly available for the broader scientific community. Extensive experiments combine four machine learning and deep learning algorithms with an evolutionary optimisation algorithm. The performance of the combined training and optimisation pipeline is evaluated by verifying the generated Pareto-optimal results using the ground truth simulations. The results from our pipeline and a comprehensive evaluation strategy show the potential for efficiently acquiring solution candidates in multiobjective optimisation tasks by reducing the number of simulations and conserving a higher prediction accuracy, i.e., with a MAPE score under 5% for one of the presented use cases.
Enhancing Maritime Behaviour Analysis through Novel Feature Engineering and Digital Shadow Modelling: A Case Study in Kiel Fjord. Al-Falouji, Ghassan; Gao, Shang; Haschke, Lukas; Nowotka, Dirk; Tomforde, Sven. In International Conference on Architecture of Computing Systems (ARCS), bll 97–111. Springer, 2024.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
With the continuous evolution of maritime technology, there is a growing need for analysing and modelling vessel behaviour in complex waterway systems. This paper presents an extension and utilisation of the Surface Vessel Nautical Behaviour Analysis (SV-NBA) framework for in-depth spatio-temporal analysis of maritime surface vessels’ behaviour in Kiel Fjord. Leveraging one year of collected Automatic Identification System (AIS) data, we extracted features from the recorded data. Three feature sets are generated and compared using expert-knowledge fea- tures, methods for feature selection, and Denoising Autoencoder latent space representation. Behaviour modelling and analysis utilises clustered data from the three feature sets, employing Gaussian Mixture Models (GMM). The trained GMM models serve as digital shadows, enabling storage-efficient representation of vessel behaviour and facilitates appli- cations such as online situational awareness and marine-traffic manage- ment. These digital shadows serve as observer-layer in a dynamic au- tonomous system of system, offering insights into maritime activities and enhancing navigation safety in busy waterways. This research contributes to the advancement of autonomous navigation systems and supports ef- ficient maritime traffic management strategies.
@inproceedings{AlFalouji2024Behaviour, abstract = {With the continuous evolution of maritime technology, there is a growing need for analysing and modelling vessel behaviour in complex waterway systems. This paper presents an extension and utilisation of the Surface Vessel Nautical Behaviour Analysis (SV-NBA) framework for in-depth spatio-temporal analysis of maritime surface vessels’ behaviour in Kiel Fjord. Leveraging one year of collected Automatic Identification System (AIS) data, we extracted features from the recorded data. Three feature sets are generated and compared using expert-knowledge fea- tures, methods for feature selection, and Denoising Autoencoder latent space representation. Behaviour modelling and analysis utilises clustered data from the three feature sets, employing Gaussian Mixture Models (GMM). The trained GMM models serve as digital shadows, enabling storage-efficient representation of vessel behaviour and facilitates appli- cations such as online situational awareness and marine-traffic manage- ment. These digital shadows serve as observer-layer in a dynamic au- tonomous system of system, offering insights into maritime activities and enhancing navigation safety in busy waterways. This research contributes to the advancement of autonomous navigation systems and supports ef- ficient maritime traffic management strategies.}, author = {Al-Falouji, Ghassan and Gao, Shang and Haschke, Lukas and Nowotka, Dirk and Tomforde, Sven}, booktitle = {International Conference on Architecture of Computing Systems (ARCS)}, keywords = {DigitalShadows}, pages = {97–111}, publisher = {Springer}, title = {Enhancing Maritime Behaviour Analysis through Novel Feature Engineering and Digital Shadow Modelling: A Case Study in Kiel Fjord}, year = 2024 }
%0 Conference Paper %1 AlFalouji2024Behaviour %A Al-Falouji, Ghassan %A Gao, Shang %A Haschke, Lukas %A Nowotka, Dirk %A Tomforde, Sven %B International Conference on Architecture of Computing Systems (ARCS) %D 2024 %I Springer %P 97--111 %R 10.1007/978-3-031-66146-4_7 %T Enhancing Maritime Behaviour Analysis through Novel Feature Engineering and Digital Shadow Modelling: A Case Study in Kiel Fjord %X With the continuous evolution of maritime technology, there is a growing need for analysing and modelling vessel behaviour in complex waterway systems. This paper presents an extension and utilisation of the Surface Vessel Nautical Behaviour Analysis (SV-NBA) framework for in-depth spatio-temporal analysis of maritime surface vessels’ behaviour in Kiel Fjord. Leveraging one year of collected Automatic Identification System (AIS) data, we extracted features from the recorded data. Three feature sets are generated and compared using expert-knowledge fea- tures, methods for feature selection, and Denoising Autoencoder latent space representation. Behaviour modelling and analysis utilises clustered data from the three feature sets, employing Gaussian Mixture Models (GMM). The trained GMM models serve as digital shadows, enabling storage-efficient representation of vessel behaviour and facilitates appli- cations such as online situational awareness and marine-traffic manage- ment. These digital shadows serve as observer-layer in a dynamic au- tonomous system of system, offering insights into maritime activities and enhancing navigation safety in busy waterways. This research contributes to the advancement of autonomous navigation systems and supports ef- ficient maritime traffic management strategies.
Criteria for Uncertainty-based Corner Cases Detection in Instance Segmentation. Heidecker, Florian; El-Khateeb, Ahmad; Bieshaar, Maarten; Sick, Bernhard. In arXiv e-prints, bl arXiv:2404.11266. 2024.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
The operating environment of a highly automated vehicle is subject to change, e.g., weather, illumination, or the scenario containing different objects and other participants in which the highly automated vehicle has to navigate its passengers safely. These situations must be considered when developing and validating highly automated driving functions. This already poses a problem for training and evaluating deep learning models because without the costly labeling of thousands of recordings, not knowing whether the data contains relevant, interesting data for further model training, it is a guess under which conditions and situations the model performs poorly. For this purpose, we present corner case criteria based on the predictive uncertainty. With our corner case criteria, we are able to detect uncertainty-based corner cases of an object instance segmentation model without relying on ground truth (GT) data. We evaluated each corner case criterion using the COCO and the NuImages dataset to analyze the potential of our approach. We also provide a corner case decision function that allows us to distinguish each object into True Positive (TP), localization and/or classification corner case, or False Positive (FP). We also present our first results of an iterative training cycle that outperforms the baseline and where the data added to the training dataset is selected based on the corner case decision function.
@article{heidecker2024criteria, abstract = {The operating environment of a highly automated vehicle is subject to change, e.g., weather, illumination, or the scenario containing different objects and other participants in which the highly automated vehicle has to navigate its passengers safely. These situations must be considered when developing and validating highly automated driving functions. This already poses a problem for training and evaluating deep learning models because without the costly labeling of thousands of recordings, not knowing whether the data contains relevant, interesting data for further model training, it is a guess under which conditions and situations the model performs poorly. For this purpose, we present corner case criteria based on the predictive uncertainty. With our corner case criteria, we are able to detect uncertainty-based corner cases of an object instance segmentation model without relying on ground truth (GT) data. We evaluated each corner case criterion using the COCO and the NuImages dataset to analyze the potential of our approach. We also provide a corner case decision function that allows us to distinguish each object into True Positive (TP), localization and/or classification corner case, or False Positive (FP). We also present our first results of an iterative training cycle that outperforms the baseline and where the data added to the training dataset is selected based on the corner case decision function.}, author = {Heidecker, Florian and El-Khateeb, Ahmad and Bieshaar, Maarten and Sick, Bernhard}, journal = {arXiv e-prints}, keywords = {itegpub}, pages = {arXiv:2404.11266}, title = {Criteria for Uncertainty-based Corner Cases Detection in Instance Segmentation}, year = 2024 }
%0 Journal Article %1 heidecker2024criteria %A Heidecker, Florian %A El-Khateeb, Ahmad %A Bieshaar, Maarten %A Sick, Bernhard %D 2024 %J arXiv e-prints %P arXiv:2404.11266 %T Criteria for Uncertainty-based Corner Cases Detection in Instance Segmentation %U https://arxiv.org/abs/2404.11266 %X The operating environment of a highly automated vehicle is subject to change, e.g., weather, illumination, or the scenario containing different objects and other participants in which the highly automated vehicle has to navigate its passengers safely. These situations must be considered when developing and validating highly automated driving functions. This already poses a problem for training and evaluating deep learning models because without the costly labeling of thousands of recordings, not knowing whether the data contains relevant, interesting data for further model training, it is a guess under which conditions and situations the model performs poorly. For this purpose, we present corner case criteria based on the predictive uncertainty. With our corner case criteria, we are able to detect uncertainty-based corner cases of an object instance segmentation model without relying on ground truth (GT) data. We evaluated each corner case criterion using the COCO and the NuImages dataset to analyze the potential of our approach. We also provide a corner case decision function that allows us to distinguish each object into True Positive (TP), localization and/or classification corner case, or False Positive (FP). We also present our first results of an iterative training cycle that outperforms the baseline and where the data added to the training dataset is selected based on the corner case decision function.
Casimir Effect in MEMS: Materials, Geometries, and Metrologies—A Review. Elsaka, Basma; Yang, Xiaohui; Kästner, Philipp; Dingel, Kristina; Sick, Bernhard; Lehmann, Peter; Buhmann, Stefan Yoshi; Hillmer, Hartmut. In Materials, 17(14), bl 3393. 2024.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Casimir force densities, i.e., force per area, become very large if two solid material surfaces come closer together to each other than 10 nm. In most cases, the forces are attractive. In some cases, they can be repulsive depending on the solid materials and the fluid medium in between. This review provides an overview of experimental and theoretical studies that have been performed and focuses on four main aspects: (i) the combinations of different materials, (ii) the considered geometries, (iii) the applied experimental measurement methodologies and (iv) a novel self-assembly methodology based on Casimir forces. Briefly reviewed is also the influence of additional parameters such as temperature, conductivity, and surface roughness. The Casimir effect opens many application possibilities in microelectromechanical systems (MEMS) and nanoelectromechanical systems (NEMS), where an overview is also provided. The knowledge generation in this fascinating field requires interdisciplinary approaches to generate synergetic effects between technological fabrication metrology, theoretical simulations, the establishment of adequate models, artificial intelligence, and machine learning. Finally, multiple applications are addressed as a research roadmap.
@article{elsaka2024casimir, abstract = {Casimir force densities, i.e., force per area, become very large if two solid material surfaces come closer together to each other than 10 nm. In most cases, the forces are attractive. In some cases, they can be repulsive depending on the solid materials and the fluid medium in between. This review provides an overview of experimental and theoretical studies that have been performed and focuses on four main aspects: (i) the combinations of different materials, (ii) the considered geometries, (iii) the applied experimental measurement methodologies and (iv) a novel self-assembly methodology based on Casimir forces. Briefly reviewed is also the influence of additional parameters such as temperature, conductivity, and surface roughness. The Casimir effect opens many application possibilities in microelectromechanical systems (MEMS) and nanoelectromechanical systems (NEMS), where an overview is also provided. The knowledge generation in this fascinating field requires interdisciplinary approaches to generate synergetic effects between technological fabrication metrology, theoretical simulations, the establishment of adequate models, artificial intelligence, and machine learning. Finally, multiple applications are addressed as a research roadmap.}, author = {Elsaka, Basma and Yang, Xiaohui and Kästner, Philipp and Dingel, Kristina and Sick, Bernhard and Lehmann, Peter and Buhmann, Stefan Yoshi and Hillmer, Hartmut}, journal = {Materials}, keywords = {itegpub}, number = 14, pages = 3393, title = {Casimir Effect in MEMS: Materials, Geometries, and Metrologies—A Review}, volume = 17, year = 2024 }
%0 Journal Article %1 elsaka2024casimir %A Elsaka, Basma %A Yang, Xiaohui %A Kästner, Philipp %A Dingel, Kristina %A Sick, Bernhard %A Lehmann, Peter %A Buhmann, Stefan Yoshi %A Hillmer, Hartmut %D 2024 %J Materials %N 14 %P 3393 %R 10.3390/ma17143393 %T Casimir Effect in MEMS: Materials, Geometries, and Metrologies—A Review %U https://www.mdpi.com/1996-1944/17/14/3393 %V 17 %X Casimir force densities, i.e., force per area, become very large if two solid material surfaces come closer together to each other than 10 nm. In most cases, the forces are attractive. In some cases, they can be repulsive depending on the solid materials and the fluid medium in between. This review provides an overview of experimental and theoretical studies that have been performed and focuses on four main aspects: (i) the combinations of different materials, (ii) the considered geometries, (iii) the applied experimental measurement methodologies and (iv) a novel self-assembly methodology based on Casimir forces. Briefly reviewed is also the influence of additional parameters such as temperature, conductivity, and surface roughness. The Casimir effect opens many application possibilities in microelectromechanical systems (MEMS) and nanoelectromechanical systems (NEMS), where an overview is also provided. The knowledge generation in this fascinating field requires interdisciplinary approaches to generate synergetic effects between technological fabrication metrology, theoretical simulations, the establishment of adequate models, artificial intelligence, and machine learning. Finally, multiple applications are addressed as a research roadmap.
Capturing Nonlinear Electron Dynamics with Fully Characterised Attosecond X-ray Pulses. Funke, Lars; Ilchen, Markus; Dingel, Kristina; Mazza, Tommaso; Mullins, Terence; Otto, Thorsten; Rivas, Daniel; Savio, Sara; Serkez, Svitozar; Walter, Peter; Wieland, Niclas; Wülfing, Lasse; Bari, Sadia; Boll, Rebecca; Braune, Markus; Calegari, Francesca; De Fanis, Alberto; Decking, Winfried; Duensing, Andreas; Düsterer, Stefan; Ehresmann, Arno; Erk, Benjamin; Ferreira de Lima, Danilo Enoque; Galler, Andreas; Geloni, Gianluca; Grünert, Jan; Guetg, Marc; Grychtol, Patrik; Hans, Andreas; Held, Arne; Hindriksson, Ruda; Inhester, Ludger; Jahnke, Till; Laksman, Joakim; Larsson, Mats; Liu, Jia; Marangos, Jon P.; Marder, Lutz; Meier, David; Meyer, Michael; Mirian, Najmeh; Ott, Christian; Passow, Christopher; Pfeifer, Thomas; Rupprecht, Patrick; Schletter, Albert; Schmidt, Philipp; Scholz, Frank; Schott, Simon; Schneidmiller, Evgeny; Sick, Bernhard; Son, Sang-Kil; Tiedtke, Kai; Usenko, Sergey; Wanie, Vincent; Wurzer, Markus; Yurkov, Mikhail; Zhaunerchyk, Vitali; Helml, Wolfram. In arXiv e-prints, bl arXiv:2408.03858. 2024.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Attosecond X-ray pulses are the key to studying electron dynamics at their natural time scale involving specific electronic states. They are promising to build the conceptual bridge between physical and chemical photo-reaction processes. Free-electron lasers have demonstrated their capability of generating intense attosecond X-ray pulses. However, harnessing them for time-resolving experiments and investigations of nonlinear X-ray absorption mechanisms remains a cutting-edge challenge. We have characterised X-ray pulses with durations of down to 700attoseconds and peak powers up to 200GW at ∼ 1keV photon energy via angular streaking at the SQS instrument of the European XFEL. As direct application, we present results of nonlinear X-ray-matter interaction via state-specific spectroscopy on a transient system. Using the derived spectral and temporal information of each pulse, we deliberately steer the probability for formation of double-core vacancies in neon gas atoms through excitation or ionisation of the second inner-shell electron after K-shell ionisation. Our results advance the field of attosecond science with highly intense and fully characterised X-ray pulses to the site-specific investigation of electronic motion in transient media.
@article{funke2024capturing, abstract = {Attosecond X-ray pulses are the key to studying electron dynamics at their natural time scale involving specific electronic states. They are promising to build the conceptual bridge between physical and chemical photo-reaction processes. Free-electron lasers have demonstrated their capability of generating intense attosecond X-ray pulses. However, harnessing them for time-resolving experiments and investigations of nonlinear X-ray absorption mechanisms remains a cutting-edge challenge. We have characterised X-ray pulses with durations of down to 700attoseconds and peak powers up to 200GW at ∼ 1keV photon energy via angular streaking at the SQS instrument of the European XFEL. As direct application, we present results of nonlinear X-ray-matter interaction via state-specific spectroscopy on a transient system. Using the derived spectral and temporal information of each pulse, we deliberately steer the probability for formation of double-core vacancies in neon gas atoms through excitation or ionisation of the second inner-shell electron after K-shell ionisation. Our results advance the field of attosecond science with highly intense and fully characterised X-ray pulses to the site-specific investigation of electronic motion in transient media.}, author = {Funke, Lars and Ilchen, Markus and Dingel, Kristina and Mazza, Tommaso and Mullins, Terence and Otto, Thorsten and Rivas, Daniel and Savio, Sara and Serkez, Svitozar and Walter, Peter and Wieland, Niclas and Wülfing, Lasse and Bari, Sadia and Boll, Rebecca and Braune, Markus and Calegari, Francesca and De Fanis, Alberto and Decking, Winfried and Duensing, Andreas and Düsterer, Stefan and Ehresmann, Arno and Erk, Benjamin and Ferreira de Lima, Danilo Enoque and Galler, Andreas and Geloni, Gianluca and Grünert, Jan and Guetg, Marc and Grychtol, Patrik and Hans, Andreas and Held, Arne and Hindriksson, Ruda and Inhester, Ludger and Jahnke, Till and Laksman, Joakim and Larsson, Mats and Liu, Jia and Marangos, Jon P. and Marder, Lutz and Meier, David and Meyer, Michael and Mirian, Najmeh and Ott, Christian and Passow, Christopher and Pfeifer, Thomas and Rupprecht, Patrick and Schletter, Albert and Schmidt, Philipp and Scholz, Frank and Schott, Simon and Schneidmiller, Evgeny and Sick, Bernhard and Son, Sang-Kil and Tiedtke, Kai and Usenko, Sergey and Wanie, Vincent and Wurzer, Markus and Yurkov, Mikhail and Zhaunerchyk, Vitali and Helml, Wolfram}, journal = {arXiv e-prints}, keywords = {itegpub}, pages = {arXiv:2408.03858}, title = {Capturing Nonlinear Electron Dynamics with Fully Characterised Attosecond X-ray Pulses}, year = 2024 }
%0 Journal Article %1 funke2024capturing %A Funke, Lars %A Ilchen, Markus %A Dingel, Kristina %A Mazza, Tommaso %A Mullins, Terence %A Otto, Thorsten %A Rivas, Daniel %A Savio, Sara %A Serkez, Svitozar %A Walter, Peter %A Wieland, Niclas %A Wülfing, Lasse %A Bari, Sadia %A Boll, Rebecca %A Braune, Markus %A Calegari, Francesca %A De Fanis, Alberto %A Decking, Winfried %A Duensing, Andreas %A Düsterer, Stefan %A Ehresmann, Arno %A Erk, Benjamin %A Ferreira de Lima, Danilo Enoque %A Galler, Andreas %A Geloni, Gianluca %A Grünert, Jan %A Guetg, Marc %A Grychtol, Patrik %A Hans, Andreas %A Held, Arne %A Hindriksson, Ruda %A Inhester, Ludger %A Jahnke, Till %A Laksman, Joakim %A Larsson, Mats %A Liu, Jia %A Marangos, Jon P. %A Marder, Lutz %A Meier, David %A Meyer, Michael %A Mirian, Najmeh %A Ott, Christian %A Passow, Christopher %A Pfeifer, Thomas %A Rupprecht, Patrick %A Schletter, Albert %A Schmidt, Philipp %A Scholz, Frank %A Schott, Simon %A Schneidmiller, Evgeny %A Sick, Bernhard %A Son, Sang-Kil %A Tiedtke, Kai %A Usenko, Sergey %A Wanie, Vincent %A Wurzer, Markus %A Yurkov, Mikhail %A Zhaunerchyk, Vitali %A Helml, Wolfram %D 2024 %J arXiv e-prints %P arXiv:2408.03858 %T Capturing Nonlinear Electron Dynamics with Fully Characterised Attosecond X-ray Pulses %U https://arxiv.org/abs/2408.03858 %X Attosecond X-ray pulses are the key to studying electron dynamics at their natural time scale involving specific electronic states. They are promising to build the conceptual bridge between physical and chemical photo-reaction processes. Free-electron lasers have demonstrated their capability of generating intense attosecond X-ray pulses. However, harnessing them for time-resolving experiments and investigations of nonlinear X-ray absorption mechanisms remains a cutting-edge challenge. We have characterised X-ray pulses with durations of down to 700attoseconds and peak powers up to 200GW at ∼ 1keV photon energy via angular streaking at the SQS instrument of the European XFEL. As direct application, we present results of nonlinear X-ray-matter interaction via state-specific spectroscopy on a transient system. Using the derived spectral and temporal information of each pulse, we deliberately steer the probability for formation of double-core vacancies in neon gas atoms through excitation or ionisation of the second inner-shell electron after K-shell ionisation. Our results advance the field of attosecond science with highly intense and fully characterised X-ray pulses to the site-specific investigation of electronic motion in transient media.
Annot-Mix: Learning with Noisy Class Labels from Multiple Annotators via a Mixup Extension. Herde, Marek; Lührs, Lukas; Huseljic, Denis; Sick, Bernhard. In arXiv e-prints, bl arXiv:2405.0338. 2024.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Training with noisy class labels impairs neural networks' generalization performance. In this context, mixup is a popular regularization technique to improve training robustness by making memorizing false class labels more difficult. However, mixup neglects that, typically, multiple annotators, e.g., crowdworkers, provide class labels. Therefore, we propose an extension of mixup, which handles multiple class labels per instance while considering which class label originates from which annotator. Integrated into our multi-annotator classification framework annot-mix, it performs superiorly to eight state-of-the-art approaches on eleven datasets with noisy class labels provided either by human or simulated annotators. Our code is publicly available through our repository at this https://github.com/ies-research/annot-mix..
@article{herde2024annot, abstract = {Training with noisy class labels impairs neural networks' generalization performance. In this context, mixup is a popular regularization technique to improve training robustness by making memorizing false class labels more difficult. However, mixup neglects that, typically, multiple annotators, e.g., crowdworkers, provide class labels. Therefore, we propose an extension of mixup, which handles multiple class labels per instance while considering which class label originates from which annotator. Integrated into our multi-annotator classification framework annot-mix, it performs superiorly to eight state-of-the-art approaches on eleven datasets with noisy class labels provided either by human or simulated annotators. Our code is publicly available through our repository at this https://github.com/ies-research/annot-mix..}, author = {Herde, Marek and Lührs, Lukas and Huseljic, Denis and Sick, Bernhard}, journal = {arXiv e-prints}, keywords = {itegpub}, pages = {arXiv:2405.0338}, title = {Annot-Mix: Learning with Noisy Class Labels from Multiple Annotators via a Mixup Extension}, year = 2024 }
%0 Journal Article %1 herde2024annot %A Herde, Marek %A Lührs, Lukas %A Huseljic, Denis %A Sick, Bernhard %D 2024 %J arXiv e-prints %P arXiv:2405.0338 %T Annot-Mix: Learning with Noisy Class Labels from Multiple Annotators via a Mixup Extension %U https://arxiv.org/abs/2405.03386 %X Training with noisy class labels impairs neural networks' generalization performance. In this context, mixup is a popular regularization technique to improve training robustness by making memorizing false class labels more difficult. However, mixup neglects that, typically, multiple annotators, e.g., crowdworkers, provide class labels. Therefore, we propose an extension of mixup, which handles multiple class labels per instance while considering which class label originates from which annotator. Integrated into our multi-annotator classification framework annot-mix, it performs superiorly to eight state-of-the-art approaches on eleven datasets with noisy class labels provided either by human or simulated annotators. Our code is publicly available through our repository at this https://github.com/ies-research/annot-mix..
An Efficient Multi Quantile Regression Network with Ad Hoc Prevention of Quantile Crossing. Decke, Jens; Jenß, Arne; Sick, Bernhard; Gruhl, Christian. In International Conference on Architecture of Computing Systems (ARCS), bll 51–66. Springer, 2024.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
This article presents the Sorting Composite Quantile Regression Neural Network (SCQRNN), an advanced quantile regression model designed to prevent quantile crossing and enhance computational efficiency. Integrating ad hoc sorting in training, the SCQRNN ensures non-intersecting quantiles, boosting model reliability and interpretability. We demonstrate that the SCQRNN not only prevents quantile crossing and reduces computational complexity but also achieves faster convergence than traditional models. This advancement meets the requirements of high-performance computing for sustainable, accurate computation. In organic computing, the SCQRNN enhances self-aware systems with predictive uncertainties, enriching applications across finance, meteorology, climate science, and engineering.
@inproceedings{decke2024efficient, abstract = {This article presents the Sorting Composite Quantile Regression Neural Network (SCQRNN), an advanced quantile regression model designed to prevent quantile crossing and enhance computational efficiency. Integrating ad hoc sorting in training, the SCQRNN ensures non-intersecting quantiles, boosting model reliability and interpretability. We demonstrate that the SCQRNN not only prevents quantile crossing and reduces computational complexity but also achieves faster convergence than traditional models. This advancement meets the requirements of high-performance computing for sustainable, accurate computation. In organic computing, the SCQRNN enhances self-aware systems with predictive uncertainties, enriching applications across finance, meteorology, climate science, and engineering.}, author = {Decke, Jens and Jenß, Arne and Sick, Bernhard and Gruhl, Christian}, booktitle = {International Conference on Architecture of Computing Systems (ARCS)}, keywords = {itegpub}, pages = {51–66}, publisher = {Springer}, title = {An Efficient Multi Quantile Regression Network with Ad Hoc Prevention of Quantile Crossing}, year = 2024 }
%0 Conference Paper %1 decke2024efficient %A Decke, Jens %A Jenß, Arne %A Sick, Bernhard %A Gruhl, Christian %B International Conference on Architecture of Computing Systems (ARCS) %D 2024 %I Springer %P 51--66 %R 10.1007/978-3-031-66146-4_4 %T An Efficient Multi Quantile Regression Network with Ad Hoc Prevention of Quantile Crossing %X This article presents the Sorting Composite Quantile Regression Neural Network (SCQRNN), an advanced quantile regression model designed to prevent quantile crossing and enhance computational efficiency. Integrating ad hoc sorting in training, the SCQRNN ensures non-intersecting quantiles, boosting model reliability and interpretability. We demonstrate that the SCQRNN not only prevents quantile crossing and reduces computational complexity but also achieves faster convergence than traditional models. This advancement meets the requirements of high-performance computing for sustainable, accurate computation. In organic computing, the SCQRNN enhances self-aware systems with predictive uncertainties, enriching applications across finance, meteorology, climate science, and engineering.
Adaptive Shapley: Using Explainable AI with Large Datasets to Quantify the Impact of Arbitrary Error Sources. Magnussen, Birk Martin; Jessulat, Maik; Stern, Claudius; Sick, Bernhard. In International Conference on Big Data Analytics (ICBDA), bll 305–310. IEEE, 2024.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
Almost all sensors suffer from some level of uncertainty introduced from production inaccuracies. When the sensor data is processed by machine learning, quantifying the impact of such production inaccuracies on the output of the machine learning model becomes difficult. Certain neural network architectures, such as continuous feature networks, allow individual features and data to be omitted while still being able to correctly predict the result without the need for retraining. Such features can, for example, be individual channels of a sensor. This article proposes a method to use the capability to omit arbitrary features or sensor channels to calculate Shapley values for each sensor channel. These Shapley values represent the contribution of each individual channel to the measurement. They are defined using an arbitrary function called the ``value function''. If the value function is defined as the error of the current measurement, the Shapley values will represent the contribution of each sensor channel to the error of the measurement result. By calculating Shapley values like this for a large unlabelled dataset of measurements, it is possible to understand how much measurement error was introduced by which channel of which sensor in each measurement. Averaging the Shapley values for each sensor in the dataset will then result in a metric for each channel of that sensor, which represents a contribution to measurement errors. By comparing these values to any arbitrary quality metrics for the sensor channels obtained in a calibration process or similar step, it is possible to correlate and quantify which value in the quality metric will cause how much of a measurement error, or whether the quality metric is even relevant for the measurement accuracy. This article will show the efficacy and use case of the method on an example of the production and quality control of optical sensors based on multiple spatially resolved reflection spectroscopy.
@inproceedings{magnussen2024adaptive, abstract = {Almost all sensors suffer from some level of uncertainty introduced from production inaccuracies. When the sensor data is processed by machine learning, quantifying the impact of such production inaccuracies on the output of the machine learning model becomes difficult. Certain neural network architectures, such as continuous feature networks, allow individual features and data to be omitted while still being able to correctly predict the result without the need for retraining. Such features can, for example, be individual channels of a sensor. This article proposes a method to use the capability to omit arbitrary features or sensor channels to calculate Shapley values for each sensor channel. These Shapley values represent the contribution of each individual channel to the measurement. They are defined using an arbitrary function called the ``value function''. If the value function is defined as the error of the current measurement, the Shapley values will represent the contribution of each sensor channel to the error of the measurement result. By calculating Shapley values like this for a large unlabelled dataset of measurements, it is possible to understand how much measurement error was introduced by which channel of which sensor in each measurement. Averaging the Shapley values for each sensor in the dataset will then result in a metric for each channel of that sensor, which represents a contribution to measurement errors. By comparing these values to any arbitrary quality metrics for the sensor channels obtained in a calibration process or similar step, it is possible to correlate and quantify which value in the quality metric will cause how much of a measurement error, or whether the quality metric is even relevant for the measurement accuracy. This article will show the efficacy and use case of the method on an example of the production and quality control of optical sensors based on multiple spatially resolved reflection spectroscopy.}, author = {Magnussen, Birk Martin and Jessulat, Maik and Stern, Claudius and Sick, Bernhard}, booktitle = {International Conference on Big Data Analytics (ICBDA)}, keywords = {itegpub}, pages = {305–310}, publisher = {IEEE}, title = {Adaptive Shapley: Using Explainable AI with Large Datasets to Quantify the Impact of Arbitrary Error Sources}, year = 2024 }
%0 Conference Paper %1 magnussen2024adaptive %A Magnussen, Birk Martin %A Jessulat, Maik %A Stern, Claudius %A Sick, Bernhard %B International Conference on Big Data Analytics (ICBDA) %D 2024 %I IEEE %P 305--310 %R 10.1109/ICBDA61153.2024.10607312 %T Adaptive Shapley: Using Explainable AI with Large Datasets to Quantify the Impact of Arbitrary Error Sources %X Almost all sensors suffer from some level of uncertainty introduced from production inaccuracies. When the sensor data is processed by machine learning, quantifying the impact of such production inaccuracies on the output of the machine learning model becomes difficult. Certain neural network architectures, such as continuous feature networks, allow individual features and data to be omitted while still being able to correctly predict the result without the need for retraining. Such features can, for example, be individual channels of a sensor. This article proposes a method to use the capability to omit arbitrary features or sensor channels to calculate Shapley values for each sensor channel. These Shapley values represent the contribution of each individual channel to the measurement. They are defined using an arbitrary function called the ``value function''. If the value function is defined as the error of the current measurement, the Shapley values will represent the contribution of each sensor channel to the error of the measurement result. By calculating Shapley values like this for a large unlabelled dataset of measurements, it is possible to understand how much measurement error was introduced by which channel of which sensor in each measurement. Averaging the Shapley values for each sensor in the dataset will then result in a metric for each channel of that sensor, which represents a contribution to measurement errors. By comparing these values to any arbitrary quality metrics for the sensor channels obtained in a calibration process or similar step, it is possible to correlate and quantify which value in the quality metric will cause how much of a measurement error, or whether the quality metric is even relevant for the measurement accuracy. This article will show the efficacy and use case of the method on an example of the production and quality control of optical sensors based on multiple spatially resolved reflection spectroscopy.

2023[ to top ]

Who knows best? A Case Study on Intelligent Crowdworker Selection via Deep Learning. Herde, Marek; Huseljic, Denis; Sick, Bernhard; Bretschneider, Ulrich; Oeste-Reiß, Sarah. In Workshop on Interactive Adapative Learning (IAL), ECML PKDD, bll 14–18. 2023.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Crowdworking is a popular approach for annotating large amounts of data to train deep neural networks. However, parts of the annotations are often erroneous. In a case study, we demonstrate how an intelligent crowdworker selection via deep learning reduces the number of erroneous annotations and, thus, the annotation costs of obtaining reliable data for training deep neural networks.
@inproceedings{herde2023who, abstract = {Crowdworking is a popular approach for annotating large amounts of data to train deep neural networks. However, parts of the annotations are often erroneous. In a case study, we demonstrate how an intelligent crowdworker selection via deep learning reduces the number of erroneous annotations and, thus, the annotation costs of obtaining reliable data for training deep neural networks.}, author = {Herde, Marek and Huseljic, Denis and Sick, Bernhard and Bretschneider, Ulrich and Oeste-Reiß, Sarah}, booktitle = {Workshop on Interactive Adapative Learning (IAL), ECML PKDD}, keywords = {itegpub}, pages = {14–18}, title = {Who knows best? A Case Study on Intelligent Crowdworker Selection via Deep Learning}, year = 2023 }
%0 Conference Paper %1 herde2023who %A Herde, Marek %A Huseljic, Denis %A Sick, Bernhard %A Bretschneider, Ulrich %A Oeste-Reiß, Sarah %B Workshop on Interactive Adapative Learning (IAL), ECML PKDD %D 2023 %P 14--18 %T Who knows best? A Case Study on Intelligent Crowdworker Selection via Deep Learning %U https://ceur-ws.org/Vol-3470/paper3.pdf %X Crowdworking is a popular approach for annotating large amounts of data to train deep neural networks. However, parts of the annotations are often erroneous. In a case study, we demonstrate how an intelligent crowdworker selection via deep learning reduces the number of erroneous annotations and, thus, the annotation costs of obtaining reliable data for training deep neural networks.
What Does Really Count? Estimating Relevance of Corner Cases for Semantic Segmentation in Automated Driving. Breitenstein, Jasmin; Heidecker, Florian; Lyssenko, Maria; Bogdoll, Daniel; Bieshaar, Maarten; Zöllner, J. Marius; Sick, Bernhard; Fingscheidt, Tim. In Workshop on roBustness and Reliability of Autonomous Vehicles in the Open-world (BRAVO), ICCV, bll 3991–4000. 2023.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
In safety-critical applications such as automated driving, perception errors may create an imminent risk to vulnerable road users (VRU). To mitigate the occurrence of unexpected and potentially dangerous situations, so-called corner cases, perception models are trained on a huge amount of data. However, the models are typically evaluated using task-agnostic metrics, which do not reflect the severity of safety-critical misdetections. Consequently, misdetections with particular relevance for the safe driving task should entail a more severe penalty during evaluation to pinpoint corner cases in large-scale datasets. In this work, we propose a novel metric IoUw that exploits relevance on the pixel level of the semantic segmentation output to extend the notion of the intersection over union (IoU) by emphasizing small areas of an image affected by corner cases. We (i) employ IoUw to measure the effect of pre-defined relevance criteria on the segmentation evaluation, and (ii) use the relevance-adapted IoUw to refine the identification of corner cases. In our experiments, we investigate vision-based relevance criteria and physical attributes as per-pixel criticality to factor in the imminent risk, showing that IoUw precisely accentuates the relevance of corner cases.
@inproceedings{breitenstein2023what, abstract = {In safety-critical applications such as automated driving, perception errors may create an imminent risk to vulnerable road users (VRU). To mitigate the occurrence of unexpected and potentially dangerous situations, so-called corner cases, perception models are trained on a huge amount of data. However, the models are typically evaluated using task-agnostic metrics, which do not reflect the severity of safety-critical misdetections. Consequently, misdetections with particular relevance for the safe driving task should entail a more severe penalty during evaluation to pinpoint corner cases in large-scale datasets. In this work, we propose a novel metric IoUw that exploits relevance on the pixel level of the semantic segmentation output to extend the notion of the intersection over union (IoU) by emphasizing small areas of an image affected by corner cases. We (i) employ IoUw to measure the effect of pre-defined relevance criteria on the segmentation evaluation, and (ii) use the relevance-adapted IoUw to refine the identification of corner cases. In our experiments, we investigate vision-based relevance criteria and physical attributes as per-pixel criticality to factor in the imminent risk, showing that IoUw precisely accentuates the relevance of corner cases.}, author = {Breitenstein, Jasmin and Heidecker, Florian and Lyssenko, Maria and Bogdoll, Daniel and Bieshaar, Maarten and Zöllner, J. Marius and Sick, Bernhard and Fingscheidt, Tim}, booktitle = {Workshop on roBustness and Reliability of Autonomous Vehicles in the Open-world (BRAVO), ICCV}, keywords = {itegpub}, pages = {3991–4000}, title = {What Does Really Count? Estimating Relevance of Corner Cases for Semantic Segmentation in Automated Driving}, year = 2023 }
%0 Conference Paper %1 breitenstein2023what %A Breitenstein, Jasmin %A Heidecker, Florian %A Lyssenko, Maria %A Bogdoll, Daniel %A Bieshaar, Maarten %A Zöllner, J. Marius %A Sick, Bernhard %A Fingscheidt, Tim %B Workshop on roBustness and Reliability of Autonomous Vehicles in the Open-world (BRAVO), ICCV %D 2023 %P 3991--4000 %T What Does Really Count? Estimating Relevance of Corner Cases for Semantic Segmentation in Automated Driving %U https://openaccess.thecvf.com/content/ICCV2023W/BRAVO/html/Breitenstein_What_Does_Really_Count_Estimating_Relevance_of_Corner_Cases_for_ICCVW_2023_paper.html %X In safety-critical applications such as automated driving, perception errors may create an imminent risk to vulnerable road users (VRU). To mitigate the occurrence of unexpected and potentially dangerous situations, so-called corner cases, perception models are trained on a huge amount of data. However, the models are typically evaluated using task-agnostic metrics, which do not reflect the severity of safety-critical misdetections. Consequently, misdetections with particular relevance for the safe driving task should entail a more severe penalty during evaluation to pinpoint corner cases in large-scale datasets. In this work, we propose a novel metric IoUw that exploits relevance on the pixel level of the semantic segmentation output to extend the notion of the intersection over union (IoU) by emphasizing small areas of an image affected by corner cases. We (i) employ IoUw to measure the effect of pre-defined relevance criteria on the segmentation evaluation, and (ii) use the relevance-adapted IoUw to refine the identification of corner cases. In our experiments, we investigate vision-based relevance criteria and physical attributes as per-pixel criticality to factor in the imminent risk, showing that IoUw precisely accentuates the relevance of corner cases.
Utilizing Continuous Kernels for Processing Irregularly and Inconsistently Sampled Data With Position-Dependent Features. Magnussen, Birk Martin; Stern, Claudius; Sick, Bernhard. In International Conference on Autonomic and Autonomous Systems (ICAS), bll 49–53. ThinkMind, 2023.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Continuous Kernels have been a recent development in convolutional neural networks. Such kernels are used to process data sampled at different resolutions as well as irregularly and inconsistently sampled data. Convolutional neural networks have the property of translational invariance (e.g., features are detected regardless of their position in the measurement domain), which is unsuitable for certain types of data, where the position of detected features is relevant. However, the capabilities of continuous kernels to process irregularly sampled data are still desired. This article introduces a novel method utilizing continuous kernels for detecting global features at absolute positions in the data domain. Through a use case in processing multiple spatially resolved reflection spectroscopy data, which is sampled irregularly and inconsistently, we show that the proposed method is capable of processing such data natively without additional preprocessing as is needed using comparable methods. In addition, we show that the proposed method is able to achieve a higher prediction accuracy than a comparable network on a dataset with position-dependent features. Furthermore, a higher robustness to missing data compared to a benchmark network using data interpolation is observed, which allows the network to adapt to sensors with individual failed components without the need for retraining.
@inproceedings{magnussen2023utilizing, abstract = {Continuous Kernels have been a recent development in convolutional neural networks. Such kernels are used to process data sampled at different resolutions as well as irregularly and inconsistently sampled data. Convolutional neural networks have the property of translational invariance (e.g., features are detected regardless of their position in the measurement domain), which is unsuitable for certain types of data, where the position of detected features is relevant. However, the capabilities of continuous kernels to process irregularly sampled data are still desired. This article introduces a novel method utilizing continuous kernels for detecting global features at absolute positions in the data domain. Through a use case in processing multiple spatially resolved reflection spectroscopy data, which is sampled irregularly and inconsistently, we show that the proposed method is capable of processing such data natively without additional preprocessing as is needed using comparable methods. In addition, we show that the proposed method is able to achieve a higher prediction accuracy than a comparable network on a dataset with position-dependent features. Furthermore, a higher robustness to missing data compared to a benchmark network using data interpolation is observed, which allows the network to adapt to sensors with individual failed components without the need for retraining.}, author = {Magnussen, Birk Martin and Stern, Claudius and Sick, Bernhard}, booktitle = {International Conference on Autonomic and Autonomous Systems (ICAS)}, keywords = {itegpub}, pages = {49–53}, publisher = {ThinkMind}, title = {Utilizing Continuous Kernels for Processing Irregularly and Inconsistently Sampled Data With Position-Dependent Features}, year = 2023 }
%0 Conference Paper %1 magnussen2023utilizing %A Magnussen, Birk Martin %A Stern, Claudius %A Sick, Bernhard %B International Conference on Autonomic and Autonomous Systems (ICAS) %D 2023 %I ThinkMind %P 49--53 %T Utilizing Continuous Kernels for Processing Irregularly and Inconsistently Sampled Data With Position-Dependent Features %U http://www.thinkmind.org/index.php?view=article&articleid=icas_2023_1_90_20043 %X Continuous Kernels have been a recent development in convolutional neural networks. Such kernels are used to process data sampled at different resolutions as well as irregularly and inconsistently sampled data. Convolutional neural networks have the property of translational invariance (e.g., features are detected regardless of their position in the measurement domain), which is unsuitable for certain types of data, where the position of detected features is relevant. However, the capabilities of continuous kernels to process irregularly sampled data are still desired. This article introduces a novel method utilizing continuous kernels for detecting global features at absolute positions in the data domain. Through a use case in processing multiple spatially resolved reflection spectroscopy data, which is sampled irregularly and inconsistently, we show that the proposed method is capable of processing such data natively without additional preprocessing as is needed using comparable methods. In addition, we show that the proposed method is able to achieve a higher prediction accuracy than a comparable network on a dataset with position-dependent features. Furthermore, a higher robustness to missing data compared to a benchmark network using data interpolation is observed, which allows the network to adapt to sensors with individual failed components without the need for retraining.
Unraveling the Complexity of Splitting Sequential Data: Tackling Challenges in Video and Time Series Analysis. Botache, Diego; Dingel, Kristina; Huhnstock, Rico; Ehresmann, Arno; Sick, Bernhard. In arXiv e-prints, bl arXiv:2307.14294. 2023.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Splitting of sequential data, such as videos and time series, is an essential step in various data analysis tasks, including object tracking and anomaly detection. However, splitting sequential data presents a variety of challenges that can impact the accuracy and reliability of subsequent analyses. This concept article examines the challenges associated with splitting sequential data, including data acquisition, data representation, split ratio selection, setting up quality criteria, and choosing suitable selection strategies. We explore these challenges through two real-world examples: motor test benches and particle tracking in liquids.
@article{botache2023unraveling, abstract = {Splitting of sequential data, such as videos and time series, is an essential step in various data analysis tasks, including object tracking and anomaly detection. However, splitting sequential data presents a variety of challenges that can impact the accuracy and reliability of subsequent analyses. This concept article examines the challenges associated with splitting sequential data, including data acquisition, data representation, split ratio selection, setting up quality criteria, and choosing suitable selection strategies. We explore these challenges through two real-world examples: motor test benches and particle tracking in liquids.}, author = {Botache, Diego and Dingel, Kristina and Huhnstock, Rico and Ehresmann, Arno and Sick, Bernhard}, journal = {arXiv e-prints}, keywords = {itegpub}, pages = {arXiv:2307.14294}, title = {Unraveling the Complexity of Splitting Sequential Data: Tackling Challenges in Video and Time Series Analysis}, year = 2023 }
%0 Journal Article %1 botache2023unraveling %A Botache, Diego %A Dingel, Kristina %A Huhnstock, Rico %A Ehresmann, Arno %A Sick, Bernhard %D 2023 %J arXiv e-prints %P arXiv:2307.14294 %T Unraveling the Complexity of Splitting Sequential Data: Tackling Challenges in Video and Time Series Analysis %U https://arxiv.org/abs/2307.14294 %X Splitting of sequential data, such as videos and time series, is an essential step in various data analysis tasks, including object tracking and anomaly detection. However, splitting sequential data presents a variety of challenges that can impact the accuracy and reliability of subsequent analyses. This concept article examines the challenges associated with splitting sequential data, including data acquisition, data representation, split ratio selection, setting up quality criteria, and choosing suitable selection strategies. We explore these challenges through two real-world examples: motor test benches and particle tracking in liquids.
Towards Few-Shot Time Series Anomaly Detection with Temporal Attention and Dynamic Thresholding. Nivarthi, Chandana Priya; Sick, Bernhard. In International Conference on Machine Learning and Applications (ICMLA), bll 1444–1450. IEEE, 2023.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
Anomaly detection plays a pivotal role in diverse realworld applications such as cybersecurity, fault detection, network monitoring, predictive maintenance, and highly automated driving. However, obtaining labeled anomalous data can be a formidable challenge, especially when anomalies exhibit temporal evolution. This paper introduces LATAM (Long short-term memory Autoencoder with Temporal Attention Mechanism) for few-shot anomaly detection, with the aim of enhancing detection performance in scenarios with limited labeled anomaly data. LATAM effectively captures temporal dependencies and emphasizes significant patterns in multivariate time series data. In our investigation, we comprehensively evaluate LATAM against other anomaly detection models, particularly assessing its capability in few-shot learning scenarios where we have minimal examples from the normal class and none from the anomalous class in the training data. Our experimental results, derived from real-world photovoltaic inverter data, highlight LATAM’s superiority, showcasing a substantial 27% mean F1 score improvement, even when trained on a mere two-week dataset. Furthermore, LATAM demonstrates remarkable results on the open-source SWaT dataset, achieving a 12% boost in accuracy with only two days of training data. Moreover, we introduce a simple yet effective dynamic thresholding mechanism, further enhancing the anomaly detection capabilities of LATAM. This underscores LATAM’s efficacy in addressing the challenges posed by limited labeled anomalies in practical scenarios and it proves valuable for downstream tasks involving temporal representation and time series prediction, extending its utility beyond anomaly detection applications.
@inproceedings{nivarthi2023towards, abstract = {Anomaly detection plays a pivotal role in diverse realworld applications such as cybersecurity, fault detection, network monitoring, predictive maintenance, and highly automated driving. However, obtaining labeled anomalous data can be a formidable challenge, especially when anomalies exhibit temporal evolution. This paper introduces LATAM (Long short-term memory Autoencoder with Temporal Attention Mechanism) for few-shot anomaly detection, with the aim of enhancing detection performance in scenarios with limited labeled anomaly data. LATAM effectively captures temporal dependencies and emphasizes significant patterns in multivariate time series data. In our investigation, we comprehensively evaluate LATAM against other anomaly detection models, particularly assessing its capability in few-shot learning scenarios where we have minimal examples from the normal class and none from the anomalous class in the training data. Our experimental results, derived from real-world photovoltaic inverter data, highlight LATAM’s superiority, showcasing a substantial 27% mean F1 score improvement, even when trained on a mere two-week dataset. Furthermore, LATAM demonstrates remarkable results on the open-source SWaT dataset, achieving a 12% boost in accuracy with only two days of training data. Moreover, we introduce a simple yet effective dynamic thresholding mechanism, further enhancing the anomaly detection capabilities of LATAM. This underscores LATAM’s efficacy in addressing the challenges posed by limited labeled anomalies in practical scenarios and it proves valuable for downstream tasks involving temporal representation and time series prediction, extending its utility beyond anomaly detection applications.}, author = {Nivarthi, Chandana Priya and Sick, Bernhard}, booktitle = {International Conference on Machine Learning and Applications (ICMLA)}, keywords = {itegpub}, pages = {1444–1450}, publisher = {IEEE}, title = {Towards Few-Shot Time Series Anomaly Detection with Temporal Attention and Dynamic Thresholding}, year = 2023 }
%0 Conference Paper %1 nivarthi2023towards %A Nivarthi, Chandana Priya %A Sick, Bernhard %B International Conference on Machine Learning and Applications (ICMLA) %D 2023 %I IEEE %P 1444--1450 %R 10.1109/ICMLA58977.2023.00218 %T Towards Few-Shot Time Series Anomaly Detection with Temporal Attention and Dynamic Thresholding %X Anomaly detection plays a pivotal role in diverse realworld applications such as cybersecurity, fault detection, network monitoring, predictive maintenance, and highly automated driving. However, obtaining labeled anomalous data can be a formidable challenge, especially when anomalies exhibit temporal evolution. This paper introduces LATAM (Long short-term memory Autoencoder with Temporal Attention Mechanism) for few-shot anomaly detection, with the aim of enhancing detection performance in scenarios with limited labeled anomaly data. LATAM effectively captures temporal dependencies and emphasizes significant patterns in multivariate time series data. In our investigation, we comprehensively evaluate LATAM against other anomaly detection models, particularly assessing its capability in few-shot learning scenarios where we have minimal examples from the normal class and none from the anomalous class in the training data. Our experimental results, derived from real-world photovoltaic inverter data, highlight LATAM’s superiority, showcasing a substantial 27% mean F1 score improvement, even when trained on a mere two-week dataset. Furthermore, LATAM demonstrates remarkable results on the open-source SWaT dataset, achieving a 12% boost in accuracy with only two days of training data. Moreover, we introduce a simple yet effective dynamic thresholding mechanism, further enhancing the anomaly detection capabilities of LATAM. This underscores LATAM’s efficacy in addressing the challenges posed by limited labeled anomalies in practical scenarios and it proves valuable for downstream tasks involving temporal representation and time series prediction, extending its utility beyond anomaly detection applications.
Towards Enhancing Deep Active Learning with Weak Supervision and Constrained Clustering. Aßenmacher, Matthias; Rauch, Lukas; Goschenhofer, Jann; Stephan, Andreas; Bischl, Bernd; Roth, Benjamin; Sick, Bernhard. In Workshop on Interactive Adapative Learning (IAL), ECML PKDD, bll 65–73. 2023.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Three fields revolving around the question of how to cope with limited amounts of labeled data are Deep Active Learning (DAL), deep Constrained Clustering (CC), and Weakly Supervised Learning (WSL). DAL tackles the problem by adaptively posing the question of which data samples to annotate next in order to achieve the best incremental learning improvement, although it suffers from several limitations that hinder its deployment in practical settings. We point out how CC algorithms and WSL could be employed to overcome these limitations and increase the practical applicability of DAL research. Specifically, we discuss the opportunities to use the class discovery capabilities of CC and the possibility of further reducing human annotation efforts by utilizing WSL. We argue that the practical applicability of DAL algorithms will benefit from employing CC and WSL methods for the learning and labeling process. We inspect the overlaps between the three research areas and identify relevant and exciting research questions at the intersection of these areas.
@inproceedings{assenmacher2023towards, abstract = {Three fields revolving around the question of how to cope with limited amounts of labeled data are Deep Active Learning (DAL), deep Constrained Clustering (CC), and Weakly Supervised Learning (WSL). DAL tackles the problem by adaptively posing the question of which data samples to annotate next in order to achieve the best incremental learning improvement, although it suffers from several limitations that hinder its deployment in practical settings. We point out how CC algorithms and WSL could be employed to overcome these limitations and increase the practical applicability of DAL research. Specifically, we discuss the opportunities to use the class discovery capabilities of CC and the possibility of further reducing human annotation efforts by utilizing WSL. We argue that the practical applicability of DAL algorithms will benefit from employing CC and WSL methods for the learning and labeling process. We inspect the overlaps between the three research areas and identify relevant and exciting research questions at the intersection of these areas.}, author = {Aßenmacher, Matthias and Rauch, Lukas and Goschenhofer, Jann and Stephan, Andreas and Bischl, Bernd and Roth, Benjamin and Sick, Bernhard}, booktitle = {Workshop on Interactive Adapative Learning (IAL), ECML PKDD}, keywords = {itegpub}, pages = {65–73}, title = {Towards Enhancing Deep Active Learning with Weak Supervision and Constrained Clustering}, year = 2023 }
%0 Conference Paper %1 assenmacher2023towards %A Aßenmacher, Matthias %A Rauch, Lukas %A Goschenhofer, Jann %A Stephan, Andreas %A Bischl, Bernd %A Roth, Benjamin %A Sick, Bernhard %B Workshop on Interactive Adapative Learning (IAL), ECML PKDD %D 2023 %P 65--73 %T Towards Enhancing Deep Active Learning with Weak Supervision and Constrained Clustering %U https://ceur-ws.org/Vol-3470/paper7.pdf %X Three fields revolving around the question of how to cope with limited amounts of labeled data are Deep Active Learning (DAL), deep Constrained Clustering (CC), and Weakly Supervised Learning (WSL). DAL tackles the problem by adaptively posing the question of which data samples to annotate next in order to achieve the best incremental learning improvement, although it suffers from several limitations that hinder its deployment in practical settings. We point out how CC algorithms and WSL could be employed to overcome these limitations and increase the practical applicability of DAL research. Specifically, we discuss the opportunities to use the class discovery capabilities of CC and the possibility of further reducing human annotation efforts by utilizing WSL. We argue that the practical applicability of DAL algorithms will benefit from employing CC and WSL methods for the learning and labeling process. We inspect the overlaps between the three research areas and identify relevant and exciting research questions at the intersection of these areas.
Time-aware Robustness of Temporal Graph Neural Networks for Link Prediction. Sälzer, Marco; Beddar-Wiesing, Silvia. In International Symposium on Temporal Representation and Reasoning (TIME), bll 19:1–19:3. 2023.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
Graph Neural Networks (GNNs) provide a framework for computing functions over graphs based on learnable parameters, which gained much attention in recent years. The most popular GNN models, so-called convolutional GNN or message-passing GNN apply a neighborhood aggregation procedure to each node in a graph to compute its output. Usually, such GNNs are used for classification or prediction tasks over static graphs. However, this limits their applicability in contexts like social networks or knowledge graphs, where underlying graphs change stepwise or time-continuously. Temporal Graph Neural Networks (TGNN) try to close this gap. The general idea of TGNN is to generalize the neighborhood aggregation procedure mentioned above to temporal graphs, usually represented as a tuple of a base graph with a series of time-stamped observed changes. In most applications involving Neural Network based models, giving reliable safety certificates are highly desirable but also a significant challenge, especially because of the blackbox nature of neural models. In this extended abstract, we address the topic of verifying TGNN, which is an unexplored area of research. We present a first notion of a time-aware robustness property for TGNN used for link prediction tasks, motivated by recent work on similar time-aware attacks. Furthermore, we discuss our ongoing work regarding promising verification approaches for the presented or similar safety properties and possible next steps in this research direction.
@inproceedings{salzer2023time, abstract = {Graph Neural Networks (GNNs) provide a framework for computing functions over graphs based on learnable parameters, which gained much attention in recent years. The most popular GNN models, so-called convolutional GNN or message-passing GNN apply a neighborhood aggregation procedure to each node in a graph to compute its output. Usually, such GNNs are used for classification or prediction tasks over static graphs. However, this limits their applicability in contexts like social networks or knowledge graphs, where underlying graphs change stepwise or time-continuously. Temporal Graph Neural Networks (TGNN) try to close this gap. The general idea of TGNN is to generalize the neighborhood aggregation procedure mentioned above to temporal graphs, usually represented as a tuple of a base graph with a series of time-stamped observed changes. In most applications involving Neural Network based models, giving reliable safety certificates are highly desirable but also a significant challenge, especially because of the blackbox nature of neural models. In this extended abstract, we address the topic of verifying TGNN, which is an unexplored area of research. We present a first notion of a time-aware robustness property for TGNN used for link prediction tasks, motivated by recent work on similar time-aware attacks. Furthermore, we discuss our ongoing work regarding promising verification approaches for the presented or similar safety properties and possible next steps in this research direction.}, author = {Sälzer, Marco and Beddar-Wiesing, Silvia}, booktitle = {International Symposium on Temporal Representation and Reasoning (TIME)}, keywords = {itegpub}, pages = {19:1–19:3}, title = {Time-aware Robustness of Temporal Graph Neural Networks for Link Prediction}, year = 2023 }
%0 Conference Paper %1 salzer2023time %A Sälzer, Marco %A Beddar-Wiesing, Silvia %B International Symposium on Temporal Representation and Reasoning (TIME) %D 2023 %P 19:1--19:3 %R 10.4230/LIPIcs.TIME.2023.19 %T Time-aware Robustness of Temporal Graph Neural Networks for Link Prediction %X Graph Neural Networks (GNNs) provide a framework for computing functions over graphs based on learnable parameters, which gained much attention in recent years. The most popular GNN models, so-called convolutional GNN or message-passing GNN apply a neighborhood aggregation procedure to each node in a graph to compute its output. Usually, such GNNs are used for classification or prediction tasks over static graphs. However, this limits their applicability in contexts like social networks or knowledge graphs, where underlying graphs change stepwise or time-continuously. Temporal Graph Neural Networks (TGNN) try to close this gap. The general idea of TGNN is to generalize the neighborhood aggregation procedure mentioned above to temporal graphs, usually represented as a tuple of a base graph with a series of time-stamped observed changes. In most applications involving Neural Network based models, giving reliable safety certificates are highly desirable but also a significant challenge, especially because of the blackbox nature of neural models. In this extended abstract, we address the topic of verifying TGNN, which is an unexplored area of research. We present a first notion of a time-aware robustness property for TGNN used for link prediction tasks, motivated by recent work on similar time-aware attacks. Furthermore, we discuss our ongoing work regarding promising verification approaches for the presented or similar safety properties and possible next steps in this research direction.
The IMPTC Dataset: An Infrastructural Multi-Person Trajectory and Context Dataset. Hetzel, Manuel; Reichert, Hannes; Reitberger, Günther; Doll, Konrad; Sick, Bernhard; Fuchs, Erich. In IEEE Intelligent Vehicles Symposium (IV), bll 1–7. IEEE, 2023.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
Inner-city intersections are among the most critical traffic areas for injury and fatal accidents. Automated vehicles struggle with the complex and hectic everyday life within those areas. Sensor-equipped smart infrastructures, which can cooperate with vehicles, can benefit automated traffic by extending the perception capabilities of drivers and vehicle perception systems. Additionally, they offer the opportunity to gather reproducible and precise data of a holistic scene understanding, including context information as a basis for training algorithms for various applications in automated traffic. Therefore, we introduce the Infrastructural Multi-Person Trajectory and Context Dataset (IMPTC). We use an intelligent public inner-city intersection in Germany with visual sensor technology. A multi-view camera and LiDAR system perceives traffic situations and road users’ behavior. Additional sensors monitor contextual information like weather, lighting, and traffic light signal status. The data acquisition system focuses on Vulnerable Road Users (VRUs) and multiagent interaction. The resulting dataset consists of eight hours of measurement data. It contains over 2,500 VRU trajectories, including pedestrians, cyclists, e-scooter riders, strollers, and wheelchair users, and over 20,000 vehicle trajectories at different day times, weather conditions, and seasons. In addition, to enable the entire stack of research capabilities, the dataset includes all data, starting from the sensor-, calibration- and detection data until trajectory and context data. The dataset is continuously expanded and is available online for non-commercial research at https://github.com/kav-institute/imptc-dataset
@inproceedings{hetzel2023imptc, abstract = {Inner-city intersections are among the most critical traffic areas for injury and fatal accidents. Automated vehicles struggle with the complex and hectic everyday life within those areas. Sensor-equipped smart infrastructures, which can cooperate with vehicles, can benefit automated traffic by extending the perception capabilities of drivers and vehicle perception systems. Additionally, they offer the opportunity to gather reproducible and precise data of a holistic scene understanding, including context information as a basis for training algorithms for various applications in automated traffic. Therefore, we introduce the Infrastructural Multi-Person Trajectory and Context Dataset (IMPTC). We use an intelligent public inner-city intersection in Germany with visual sensor technology. A multi-view camera and LiDAR system perceives traffic situations and road users’ behavior. Additional sensors monitor contextual information like weather, lighting, and traffic light signal status. The data acquisition system focuses on Vulnerable Road Users (VRUs) and multiagent interaction. The resulting dataset consists of eight hours of measurement data. It contains over 2,500 VRU trajectories, including pedestrians, cyclists, e-scooter riders, strollers, and wheelchair users, and over 20,000 vehicle trajectories at different day times, weather conditions, and seasons. In addition, to enable the entire stack of research capabilities, the dataset includes all data, starting from the sensor-, calibration- and detection data until trajectory and context data. The dataset is continuously expanded and is available online for non-commercial research at https://github.com/kav-institute/imptc-dataset}, author = {Hetzel, Manuel and Reichert, Hannes and Reitberger, Günther and Doll, Konrad and Sick, Bernhard and Fuchs, Erich}, booktitle = {IEEE Intelligent Vehicles Symposium (IV)}, keywords = {itegpub}, pages = {1–7}, publisher = {IEEE}, title = {The {IMPTC} Dataset: An Infrastructural Multi-Person Trajectory and Context Dataset}, year = 2023 }
%0 Conference Paper %1 hetzel2023imptc %A Hetzel, Manuel %A Reichert, Hannes %A Reitberger, Günther %A Doll, Konrad %A Sick, Bernhard %A Fuchs, Erich %B IEEE Intelligent Vehicles Symposium (IV) %D 2023 %I IEEE %P 1--7 %R 10.1109/IV55152.2023.10186776 %T The IMPTC Dataset: An Infrastructural Multi-Person Trajectory and Context Dataset %X Inner-city intersections are among the most critical traffic areas for injury and fatal accidents. Automated vehicles struggle with the complex and hectic everyday life within those areas. Sensor-equipped smart infrastructures, which can cooperate with vehicles, can benefit automated traffic by extending the perception capabilities of drivers and vehicle perception systems. Additionally, they offer the opportunity to gather reproducible and precise data of a holistic scene understanding, including context information as a basis for training algorithms for various applications in automated traffic. Therefore, we introduce the Infrastructural Multi-Person Trajectory and Context Dataset (IMPTC). We use an intelligent public inner-city intersection in Germany with visual sensor technology. A multi-view camera and LiDAR system perceives traffic situations and road users’ behavior. Additional sensors monitor contextual information like weather, lighting, and traffic light signal status. The data acquisition system focuses on Vulnerable Road Users (VRUs) and multiagent interaction. The resulting dataset consists of eight hours of measurement data. It contains over 2,500 VRU trajectories, including pedestrians, cyclists, e-scooter riders, strollers, and wheelchair users, and over 20,000 vehicle trajectories at different day times, weather conditions, and seasons. In addition, to enable the entire stack of research capabilities, the dataset includes all data, starting from the sensor-, calibration- and detection data until trajectory and context data. The dataset is continuously expanded and is available online for non-commercial research at https://github.com/kav-institute/imptc-dataset
Targeted Adversarial Attacks on Wind Power Forecasts. Heinrich, René; Scholz, Christoph; Vogt, Stephan; Lehna, Malte. In Machine Learning, 113(2), bll 863–889. Springer, 2023.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
In recent years, researchers proposed a variety of deep learning models for wind power forecasting. These models predict the wind power generation of wind farms or entire regions more accurately than traditional machine learning algorithms or physical models. However, latest research has shown that deep learning models can often be manipulated by adversarial attacks. Since wind power forecasts are essential for the stability of modern power systems, it is important to protect them from this threat. In this work, we investigate the vulnerability of two different forecasting models to targeted, semi-targeted, and untargeted adversarial attacks. We consider a Long Short-Term Memory (LSTM) network for predicting the power generation of individual wind farms and a Convolutional Neural Network (CNN) for forecasting the wind power generation throughout Germany. Moreover, we propose the Total Adversarial Robustness Score (TARS), an evaluation metric for quantifying the robustness of regression models to targeted and semi-targeted adversarial attacks. It assesses the impact of attacks on the model's performance, as well as the extent to which the attacker's goal was achieved, by assigning a score between 0 (very vulnerable) and 1 (very robust). In our experiments, the LSTM forecasting model was fairly robust and achieved a TARS value of over 0.78 for all adversarial attacks investigated. The CNN forecasting model only achieved TARS values below 0.10 when trained ordinarily, and was thus very vulnerable. Yet, its robustness could be significantly improved by adversarial training, which always resulted in a TARS above 0.46.
@article{heinrich2023targeted, abstract = {In recent years, researchers proposed a variety of deep learning models for wind power forecasting. These models predict the wind power generation of wind farms or entire regions more accurately than traditional machine learning algorithms or physical models. However, latest research has shown that deep learning models can often be manipulated by adversarial attacks. Since wind power forecasts are essential for the stability of modern power systems, it is important to protect them from this threat. In this work, we investigate the vulnerability of two different forecasting models to targeted, semi-targeted, and untargeted adversarial attacks. We consider a Long Short-Term Memory (LSTM) network for predicting the power generation of individual wind farms and a Convolutional Neural Network (CNN) for forecasting the wind power generation throughout Germany. Moreover, we propose the Total Adversarial Robustness Score (TARS), an evaluation metric for quantifying the robustness of regression models to targeted and semi-targeted adversarial attacks. It assesses the impact of attacks on the model's performance, as well as the extent to which the attacker's goal was achieved, by assigning a score between 0 (very vulnerable) and 1 (very robust). In our experiments, the LSTM forecasting model was fairly robust and achieved a TARS value of over 0.78 for all adversarial attacks investigated. The CNN forecasting model only achieved TARS values below 0.10 when trained ordinarily, and was thus very vulnerable. Yet, its robustness could be significantly improved by adversarial training, which always resulted in a TARS above 0.46.}, author = {Heinrich, René and Scholz, Christoph and Vogt, Stephan and Lehna, Malte}, journal = {Machine Learning}, keywords = {itegpub}, number = 2, pages = {863–889}, publisher = {Springer}, title = {Targeted Adversarial Attacks on Wind Power Forecasts}, volume = 113, year = 2023 }
%0 Journal Article %1 heinrich2023targeted %A Heinrich, René %A Scholz, Christoph %A Vogt, Stephan %A Lehna, Malte %D 2023 %I Springer %J Machine Learning %N 2 %P 863--889 %R 10.1007/s10994-023-06396-9 %T Targeted Adversarial Attacks on Wind Power Forecasts %V 113 %X In recent years, researchers proposed a variety of deep learning models for wind power forecasting. These models predict the wind power generation of wind farms or entire regions more accurately than traditional machine learning algorithms or physical models. However, latest research has shown that deep learning models can often be manipulated by adversarial attacks. Since wind power forecasts are essential for the stability of modern power systems, it is important to protect them from this threat. In this work, we investigate the vulnerability of two different forecasting models to targeted, semi-targeted, and untargeted adversarial attacks. We consider a Long Short-Term Memory (LSTM) network for predicting the power generation of individual wind farms and a Convolutional Neural Network (CNN) for forecasting the wind power generation throughout Germany. Moreover, we propose the Total Adversarial Robustness Score (TARS), an evaluation metric for quantifying the robustness of regression models to targeted and semi-targeted adversarial attacks. It assesses the impact of attacks on the model's performance, as well as the extent to which the attacker's goal was achieved, by assigning a score between 0 (very vulnerable) and 1 (very robust). In our experiments, the LSTM forecasting model was fairly robust and achieved a TARS value of over 0.78 for all adversarial attacks investigated. The CNN forecasting model only achieved TARS values below 0.10 when trained ordinarily, and was thus very vulnerable. Yet, its robustness could be significantly improved by adversarial training, which always resulted in a TARS above 0.46.
Spatio-Temporal Attention Graph Neural Network for Remaining Useful Life Prediction. Huang, Zhixin; He, Yujiang; Sick, Bernhard. In Computational Science and Computational Intelligence (CSCI), bll 99–105. IEEE, 2023.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
RUL prediction plays a crucial role in the health management of industrial systems. Given the increasing complexity of systems, data-driven predictive models have attracted significant research interest. Upon reviewing the existing literature, it appears that many studies either do not fully integrate both spatial and temporal features or employ only a single attention mechanism. Furthermore, there seems to be inconsistency in the choice of data normalization methods, particularly concerning operating conditions, which might influence predictive performance. To bridge these observations, this study presents the Spatio-Temporal Attention Graph Neural Network. Our model combines graph neural networks and temporal convolutional neural networks for spatial and temporal feature extraction, respectively. The cascade of these extractors, combined with multihead attention mechanisms for both spatio-temporal dimensions, aims to improve predictive precision and refine model explainability. Comprehensive experiments were conducted on the CMAPSS dataset to evaluate the impact of unified versus clustering normalization. The findings suggest that our model performs state-of-the-art results using only the unified normalization. Additionally, when dealing with datasets with multiple operating conditions, cluster normalization enhances the performance of our proposed model by up to 27%.
@inproceedings{huang2023spatio, abstract = {RUL prediction plays a crucial role in the health management of industrial systems. Given the increasing complexity of systems, data-driven predictive models have attracted significant research interest. Upon reviewing the existing literature, it appears that many studies either do not fully integrate both spatial and temporal features or employ only a single attention mechanism. Furthermore, there seems to be inconsistency in the choice of data normalization methods, particularly concerning operating conditions, which might influence predictive performance. To bridge these observations, this study presents the Spatio-Temporal Attention Graph Neural Network. Our model combines graph neural networks and temporal convolutional neural networks for spatial and temporal feature extraction, respectively. The cascade of these extractors, combined with multihead attention mechanisms for both spatio-temporal dimensions, aims to improve predictive precision and refine model explainability. Comprehensive experiments were conducted on the CMAPSS dataset to evaluate the impact of unified versus clustering normalization. The findings suggest that our model performs state-of-the-art results using only the unified normalization. Additionally, when dealing with datasets with multiple operating conditions, cluster normalization enhances the performance of our proposed model by up to 27%.}, author = {Huang, Zhixin and He, Yujiang and Sick, Bernhard}, booktitle = {Computational Science and Computational Intelligence (CSCI)}, keywords = {Graph_Neural_Network}, pages = {99–105}, publisher = {IEEE}, title = {Spatio-Temporal Attention Graph Neural Network for Remaining Useful Life Prediction}, year = 2023 }
%0 Conference Paper %1 huang2023spatio %A Huang, Zhixin %A He, Yujiang %A Sick, Bernhard %B Computational Science and Computational Intelligence (CSCI) %D 2023 %I IEEE %P 99--105 %R 10.1109/CSCI62032.2023.00022 %T Spatio-Temporal Attention Graph Neural Network for Remaining Useful Life Prediction %X RUL prediction plays a crucial role in the health management of industrial systems. Given the increasing complexity of systems, data-driven predictive models have attracted significant research interest. Upon reviewing the existing literature, it appears that many studies either do not fully integrate both spatial and temporal features or employ only a single attention mechanism. Furthermore, there seems to be inconsistency in the choice of data normalization methods, particularly concerning operating conditions, which might influence predictive performance. To bridge these observations, this study presents the Spatio-Temporal Attention Graph Neural Network. Our model combines graph neural networks and temporal convolutional neural networks for spatial and temporal feature extraction, respectively. The cascade of these extractors, combined with multihead attention mechanisms for both spatio-temporal dimensions, aims to improve predictive precision and refine model explainability. Comprehensive experiments were conducted on the CMAPSS dataset to evaluate the impact of unified versus clustering normalization. The findings suggest that our model performs state-of-the-art results using only the unified normalization. Additionally, when dealing with datasets with multiple operating conditions, cluster normalization enhances the performance of our proposed model by up to 27%.
Sensor Equivariance by LiDAR Projection Images. Reichert, Hannes; Hetzel, Manuel; Schreck, Steven; Doll, Konrad; Sick, Bernhard. In IEEE Intelligent Vehicles Symposium (IV), bll 1–6. IEEE, 2023.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
In this work, we propose an extension of conventional image data by an additional channel in which the associated projection properties are encoded. This addresses the issue of sensor-dependent object representation in projection-based sensors, such as LiDAR, which can lead to distorted physical and geometric properties due to variations in sensor resolution and field of view. To that end, we propose an architecture for processing this data in an instance segmentation framework. We focus specifically on LiDAR as a key sensor modality for machine vision tasks and highly automated driving (HAD). Through an experimental setup in a controlled synthetic environment, we identify a bias on sensor resolution and field of view and demonstrate that our proposed method can reduce said bias for the task of LiDAR instance segmentation. Furthermore, we define our method such that it can be applied to other projection-based sensors, such as cameras. To promote transparency, we make our code and dataset publicly available. This method shows the potential to improve performance and robustness in various machine vision tasks that utilize projection-based sensors.
@inproceedings{reichert2023sensor, abstract = {In this work, we propose an extension of conventional image data by an additional channel in which the associated projection properties are encoded. This addresses the issue of sensor-dependent object representation in projection-based sensors, such as LiDAR, which can lead to distorted physical and geometric properties due to variations in sensor resolution and field of view. To that end, we propose an architecture for processing this data in an instance segmentation framework. We focus specifically on LiDAR as a key sensor modality for machine vision tasks and highly automated driving (HAD). Through an experimental setup in a controlled synthetic environment, we identify a bias on sensor resolution and field of view and demonstrate that our proposed method can reduce said bias for the task of LiDAR instance segmentation. Furthermore, we define our method such that it can be applied to other projection-based sensors, such as cameras. To promote transparency, we make our code and dataset publicly available. This method shows the potential to improve performance and robustness in various machine vision tasks that utilize projection-based sensors.}, author = {Reichert, Hannes and Hetzel, Manuel and Schreck, Steven and Doll, Konrad and Sick, Bernhard}, booktitle = {IEEE Intelligent Vehicles Symposium (IV)}, keywords = {itegpub}, pages = {1–6}, publisher = {IEEE}, title = {Sensor Equivariance by {LiDAR} Projection Images}, year = 2023 }
%0 Conference Paper %1 reichert2023sensor %A Reichert, Hannes %A Hetzel, Manuel %A Schreck, Steven %A Doll, Konrad %A Sick, Bernhard %B IEEE Intelligent Vehicles Symposium (IV) %D 2023 %I IEEE %P 1--6 %R 10.1109/IV55152.2023.10186817 %T Sensor Equivariance by LiDAR Projection Images %X In this work, we propose an extension of conventional image data by an additional channel in which the associated projection properties are encoded. This addresses the issue of sensor-dependent object representation in projection-based sensors, such as LiDAR, which can lead to distorted physical and geometric properties due to variations in sensor resolution and field of view. To that end, we propose an architecture for processing this data in an instance segmentation framework. We focus specifically on LiDAR as a key sensor modality for machine vision tasks and highly automated driving (HAD). Through an experimental setup in a controlled synthetic environment, we identify a bias on sensor resolution and field of view and demonstrate that our proposed method can reduce said bias for the task of LiDAR instance segmentation. Furthermore, we define our method such that it can be applied to other projection-based sensors, such as cameras. To promote transparency, we make our code and dataset publicly available. This method shows the potential to improve performance and robustness in various machine vision tasks that utilize projection-based sensors.
Self-Integration and Agent Compatibility. Gruhl, Christian; Sick, Bernhard. In Autonomic Computing and Self-Organizing Systems Companion (ACSOS-C), bll 71–73. IEEE, 2023.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
This position paper addresses the issue of agent compatibility in the context of self-aware microsystems (SAMs), which are SISSY systems with self-awareness capabilities. SAMs are designed to adapt their behaviour and collaborate with other agents in multi-agent settings. Achieving compatibility and effective collaboration between agents pose significant challenges, such as detecting incompatibility and discerning it from malicious behaviour. We present our concept of agent compatibility, highlight future challenges, and propose directions for future research in this area. By focusing on agent compatibility, we aim to advance the understanding of SAMs and promote successful collaboration among agents.
@inproceedings{gruhl2023self, abstract = {This position paper addresses the issue of agent compatibility in the context of self-aware microsystems (SAMs), which are SISSY systems with self-awareness capabilities. SAMs are designed to adapt their behaviour and collaborate with other agents in multi-agent settings. Achieving compatibility and effective collaboration between agents pose significant challenges, such as detecting incompatibility and discerning it from malicious behaviour. We present our concept of agent compatibility, highlight future challenges, and propose directions for future research in this area. By focusing on agent compatibility, we aim to advance the understanding of SAMs and promote successful collaboration among agents.}, author = {Gruhl, Christian and Sick, Bernhard}, booktitle = {Autonomic Computing and Self-Organizing Systems Companion (ACSOS-C)}, keywords = {itegpub}, pages = {71–73}, publisher = {IEEE}, title = {Self-Integration and Agent Compatibility}, year = 2023 }
%0 Conference Paper %1 gruhl2023self %A Gruhl, Christian %A Sick, Bernhard %B Autonomic Computing and Self-Organizing Systems Companion (ACSOS-C) %D 2023 %I IEEE %P 71--73 %R 10.1109/ACSOS-C58168.2023.00039 %T Self-Integration and Agent Compatibility %U https://ieeexplore.ieee.org/abstract/document/10336212 %X This position paper addresses the issue of agent compatibility in the context of self-aware microsystems (SAMs), which are SISSY systems with self-awareness capabilities. SAMs are designed to adapt their behaviour and collaborate with other agents in multi-agent settings. Achieving compatibility and effective collaboration between agents pose significant challenges, such as detecting incompatibility and discerning it from malicious behaviour. We present our concept of agent compatibility, highlight future challenges, and propose directions for future research in this area. By focusing on agent compatibility, we aim to advance the understanding of SAMs and promote successful collaboration among agents.
Self-awareness in Cyber-Physical Systems: Recent Developments and Open Challenges. Esterle, Lukas; Dutt, Nikil; Gruhl, Christian; Lewis, Peter R.; Marcenaro, Lucio; Regazzoni, Carlo; Jantsch, Axel. In Design, Automation & Test in Europe Conference & Exhibition (DATE), bll 1–6. IEEE, 2023.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Self-aware computing systems enable computing systems to reflect on their actions and behavior. This becomes even more relevant in Cyber-Physical Systems where computing systems have to control and interact with elements in the real world. This paper reports on recent advances made in computational self-awareness for cyber-physical systems.
@inproceedings{esterle2023self, abstract = {Self-aware computing systems enable computing systems to reflect on their actions and behavior. This becomes even more relevant in Cyber-Physical Systems where computing systems have to control and interact with elements in the real world. This paper reports on recent advances made in computational self-awareness for cyber-physical systems.}, author = {Esterle, Lukas and Dutt, Nikil and Gruhl, Christian and Lewis, Peter R. and Marcenaro, Lucio and Regazzoni, Carlo and Jantsch, Axel}, booktitle = {Design, Automation & Test in Europe Conference & Exhibition (DATE)}, keywords = {itegpub}, pages = {1–6}, publisher = {IEEE}, title = {Self-awareness in Cyber-Physical Systems: Recent Developments and Open Challenges}, year = 2023 }
%0 Conference Paper %1 esterle2023self %A Esterle, Lukas %A Dutt, Nikil %A Gruhl, Christian %A Lewis, Peter R. %A Marcenaro, Lucio %A Regazzoni, Carlo %A Jantsch, Axel %B Design, Automation & Test in Europe Conference & Exhibition (DATE) %D 2023 %I IEEE %P 1--6 %R 10.23919/DATE56975.2023.10137197 %T Self-awareness in Cyber-Physical Systems: Recent Developments and Open Challenges %U https://ieeexplore.ieee.org/abstract/document/10137197 %X Self-aware computing systems enable computing systems to reflect on their actions and behavior. This becomes even more relevant in Cyber-Physical Systems where computing systems have to control and interact with elements in the real world. This paper reports on recent advances made in computational self-awareness for cyber-physical systems.
Sampling-based Uncertainty Estimation for an Instance Segmentation Network. Heidecker, Florian; El-Khateeb, Ahmad; Sick, Bernhard. In arXiv e-prints, bl arXiv:2305.14977. 2023.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
The examination of uncertainty in the predictions of machine learning (ML) models is receiving increasing attention. One uncertainty modeling technique used for this purpose is Monte-Carlo (MC)-Dropout, where repeated predictions are generated for a single input. Therefore, clustering is required to describe the resulting uncertainty, but only through efficient clustering is it possible to describe the uncertainty from the model attached to each object. This article uses Bayesian Gaussian Mixture (BGM) to solve this problem. In addition, we investigate different values for the dropout rate and other techniques, such as focal loss and calibration, which we integrate into the Mask-RCNN model to obtain the most accurate uncertainty approximation of each instance and showcase it graphically.
@article{heidecker2023sampling, abstract = {The examination of uncertainty in the predictions of machine learning (ML) models is receiving increasing attention. One uncertainty modeling technique used for this purpose is Monte-Carlo (MC)-Dropout, where repeated predictions are generated for a single input. Therefore, clustering is required to describe the resulting uncertainty, but only through efficient clustering is it possible to describe the uncertainty from the model attached to each object. This article uses Bayesian Gaussian Mixture (BGM) to solve this problem. In addition, we investigate different values for the dropout rate and other techniques, such as focal loss and calibration, which we integrate into the Mask-RCNN model to obtain the most accurate uncertainty approximation of each instance and showcase it graphically.}, author = {Heidecker, Florian and El-Khateeb, Ahmad and Sick, Bernhard}, journal = {arXiv e-prints}, keywords = {itegpub}, pages = {arXiv:2305.14977}, title = {Sampling-based Uncertainty Estimation for an Instance Segmentation Network}, year = 2023 }
%0 Journal Article %1 heidecker2023sampling %A Heidecker, Florian %A El-Khateeb, Ahmad %A Sick, Bernhard %D 2023 %J arXiv e-prints %P arXiv:2305.14977 %T Sampling-based Uncertainty Estimation for an Instance Segmentation Network %U https://arxiv.org/abs/2305.14977 %X The examination of uncertainty in the predictions of machine learning (ML) models is receiving increasing attention. One uncertainty modeling technique used for this purpose is Monte-Carlo (MC)-Dropout, where repeated predictions are generated for a single input. Therefore, clustering is required to describe the resulting uncertainty, but only through efficient clustering is it possible to describe the uncertainty from the model attached to each object. This article uses Bayesian Gaussian Mixture (BGM) to solve this problem. In addition, we investigate different values for the dropout rate and other techniques, such as focal loss and calibration, which we integrate into the Mask-RCNN model to obtain the most accurate uncertainty approximation of each instance and showcase it graphically.
Role of Hyperparameters in Deep Active Learning. Huseljic, Denis; Herde, Marek; Hahn, Paul; Sick, Bernhard. In Workshop on Interactive Adaptive Learning (IAL), ECML PKDD, bll 19–24. 2023.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Despite considerable research on pool-based deep active learning (DAL), deploying DAL into real applications still has several challenges. A frequently neglected aspect is the choice of training hyperparameters (HPs), such as the learning rate. Since these HPs determine how the deep neural network learns in each cycle, they must be chosen carefully. In this article, we analyze the role of HPs in DAL. We find that optimizing HPs reduces the performance gap between DAL strategies. Conversely, we highlight challenges in finding optimal HPs when using datasets selected via DAL strategies.
@inproceedings{huseljic2023role, abstract = {Despite considerable research on pool-based deep active learning (DAL), deploying DAL into real applications still has several challenges. A frequently neglected aspect is the choice of training hyperparameters (HPs), such as the learning rate. Since these HPs determine how the deep neural network learns in each cycle, they must be chosen carefully. In this article, we analyze the role of HPs in DAL. We find that optimizing HPs reduces the performance gap between DAL strategies. Conversely, we highlight challenges in finding optimal HPs when using datasets selected via DAL strategies.}, author = {Huseljic, Denis and Herde, Marek and Hahn, Paul and Sick, Bernhard}, booktitle = {Workshop on Interactive Adaptive Learning (IAL), ECML PKDD}, keywords = {itegpub}, pages = {19–24}, title = {Role of Hyperparameters in Deep Active Learning}, year = 2023 }
%0 Conference Paper %1 huseljic2023role %A Huseljic, Denis %A Herde, Marek %A Hahn, Paul %A Sick, Bernhard %B Workshop on Interactive Adaptive Learning (IAL), ECML PKDD %D 2023 %P 19--24 %T Role of Hyperparameters in Deep Active Learning %U https://ceur-ws.org/Vol-3470/paper4.pdf %X Despite considerable research on pool-based deep active learning (DAL), deploying DAL into real applications still has several challenges. A frequently neglected aspect is the choice of training hyperparameters (HPs), such as the learning rate. Since these HPs determine how the deep neural network learns in each cycle, they must be chosen carefully. In this article, we analyze the role of HPs in DAL. We find that optimizing HPs reduces the performance gap between DAL strategies. Conversely, we highlight challenges in finding optimal HPs when using datasets selected via DAL strategies.
Reconstruction of incomplete X-ray diffraction pole figures of oligocrystalline materials using deep learning. Meier, David; Ragunathan, Rishan; Degener, Sebastian; Liehr, Alexander; Vollmer, Malte; Niendorf, Thomas; Sick, Bernhard. In Scientific Reports, 13(1), bl 5410. Springer Nature, 2023.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
X‑ray diffraction crystallography allows non‑destructive examination of crystal structures. Furthermore, it has low requirements regarding surface preparation, especially compared to electron backscatter diffraction. However, up to now, X‑ray diffraction has been highly time‑ consuming in standard laboratory conditions since intensities on multiple lattice planes have to be recorded by rotating and tilting. Furthermore, examining oligocrystalline materials is challenging due to the limited number of diffraction spots. Moreover, commonly used evaluation methods for crystallographic orientation analysis need multiple lattice planes for a reliable pole figure reconstruction. In this article, we propose a deep‑learning‑based method for oligocrystalline specimens, i.e., specimens with up to three grains of arbitrary crystal orientations. Our approach allows faster experimentation due to accurate reconstructions of pole figure regions, which we did not probe experimentally. In contrast to other methods, the pole figure is reconstructed based on only a single incomplete pole figure. To speed up the development of our proposed method and for usage in other machine learning algorithms, we introduce a GPU‑based simulation for data generation. Furthermore, we present a pole widths standardization technique using a custom deep learning architecture that makes algorithms more robust against influences from the experiment setup and material.
@article{meier2023reconstruction, abstract = {X‑ray diffraction crystallography allows non‑destructive examination of crystal structures. Furthermore, it has low requirements regarding surface preparation, especially compared to electron backscatter diffraction. However, up to now, X‑ray diffraction has been highly time‑ consuming in standard laboratory conditions since intensities on multiple lattice planes have to be recorded by rotating and tilting. Furthermore, examining oligocrystalline materials is challenging due to the limited number of diffraction spots. Moreover, commonly used evaluation methods for crystallographic orientation analysis need multiple lattice planes for a reliable pole figure reconstruction. In this article, we propose a deep‑learning‑based method for oligocrystalline specimens, i.e., specimens with up to three grains of arbitrary crystal orientations. Our approach allows faster experimentation due to accurate reconstructions of pole figure regions, which we did not probe experimentally. In contrast to other methods, the pole figure is reconstructed based on only a single incomplete pole figure. To speed up the development of our proposed method and for usage in other machine learning algorithms, we introduce a GPU‑based simulation for data generation. Furthermore, we present a pole widths standardization technique using a custom deep learning architecture that makes algorithms more robust against influences from the experiment setup and material.}, author = {Meier, David and Ragunathan, Rishan and Degener, Sebastian and Liehr, Alexander and Vollmer, Malte and Niendorf, Thomas and Sick, Bernhard}, journal = {Scientific Reports}, keywords = {itegpub}, number = 1, pages = 5410, publisher = {Springer Nature}, title = {Reconstruction of incomplete {X}-ray diffraction pole figures of oligocrystalline materials using deep learning}, volume = 13, year = 2023 }
%0 Journal Article %1 meier2023reconstruction %A Meier, David %A Ragunathan, Rishan %A Degener, Sebastian %A Liehr, Alexander %A Vollmer, Malte %A Niendorf, Thomas %A Sick, Bernhard %D 2023 %I Springer Nature %J Scientific Reports %N 1 %P 5410 %R 10.1038/s41598-023-31580-1 %T Reconstruction of incomplete X-ray diffraction pole figures of oligocrystalline materials using deep learning %U https://www.nature.com/articles/s41598-023-31580-1 %V 13 %X X‑ray diffraction crystallography allows non‑destructive examination of crystal structures. Furthermore, it has low requirements regarding surface preparation, especially compared to electron backscatter diffraction. However, up to now, X‑ray diffraction has been highly time‑ consuming in standard laboratory conditions since intensities on multiple lattice planes have to be recorded by rotating and tilting. Furthermore, examining oligocrystalline materials is challenging due to the limited number of diffraction spots. Moreover, commonly used evaluation methods for crystallographic orientation analysis need multiple lattice planes for a reliable pole figure reconstruction. In this article, we propose a deep‑learning‑based method for oligocrystalline specimens, i.e., specimens with up to three grains of arbitrary crystal orientations. Our approach allows faster experimentation due to accurate reconstructions of pole figure regions, which we did not probe experimentally. In contrast to other methods, the pole figure is reconstructed based on only a single incomplete pole figure. To speed up the development of our proposed method and for usage in other machine learning algorithms, we introduce a GPU‑based simulation for data generation. Furthermore, we present a pole widths standardization technique using a custom deep learning architecture that makes algorithms more robust against influences from the experiment setup and material.
Power flow forecasts at transmission grid nodes using Graph Neural Networks. Beinert, Dominik; Holzhüter, Clara; Thomas, Josephine; Vogt, Stephan. In Energy and AI, 14(1), bl 100262. Elsevier, 2023.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
The increasing share of renewable energy in the electricity grid and progressing changes in power consumption have led to fluctuating, and weather-dependent power flows. To ensure grid stability, grid operators rely on power forecasts which are crucial for grid calculations and planning. In this paper, a Multi-Task Learning approach is combined with a Graph Neural Network (GNN) to predict vertical power flows at transformers connecting high and extra-high voltage levels. The proposed method accounts for local differences in power flow characteristics by using an Embedding Multi-Task Learning approach. The use of a Bayesian embedding to capture the latent node characteristics allows to share the weights across all transformers in the subsequent node-invariant GNN while still allowing the individual behavioral patterns of the transformers to be distinguished. At the same time, dependencies between transformers are considered by the GNN architecture which can learn relationships between different transformers and thus take into account that power flows in an electricity network are not independent from each other. The effectiveness of the proposed method is demonstrated through evaluation on two real-world data sets provided by two of four German Transmission System Operators, comprising large portions of the operated German transmission grid. The results show that the proposed Multi-Task Graph Neural Network is a suitable representation learner for electricity networks with a clear advantage provided by the preceding embedding layer. It is able to capture interconnections between correlated transformers and indeed improves the performance in power flow prediction compared to standard Neural Networks. A sign test shows that the proposed model reduces the test RMSE on both data sets compared to the benchmark models significantly.
@article{beinert2023power, abstract = {The increasing share of renewable energy in the electricity grid and progressing changes in power consumption have led to fluctuating, and weather-dependent power flows. To ensure grid stability, grid operators rely on power forecasts which are crucial for grid calculations and planning. In this paper, a Multi-Task Learning approach is combined with a Graph Neural Network (GNN) to predict vertical power flows at transformers connecting high and extra-high voltage levels. The proposed method accounts for local differences in power flow characteristics by using an Embedding Multi-Task Learning approach. The use of a Bayesian embedding to capture the latent node characteristics allows to share the weights across all transformers in the subsequent node-invariant GNN while still allowing the individual behavioral patterns of the transformers to be distinguished. At the same time, dependencies between transformers are considered by the GNN architecture which can learn relationships between different transformers and thus take into account that power flows in an electricity network are not independent from each other. The effectiveness of the proposed method is demonstrated through evaluation on two real-world data sets provided by two of four German Transmission System Operators, comprising large portions of the operated German transmission grid. The results show that the proposed Multi-Task Graph Neural Network is a suitable representation learner for electricity networks with a clear advantage provided by the preceding embedding layer. It is able to capture interconnections between correlated transformers and indeed improves the performance in power flow prediction compared to standard Neural Networks. A sign test shows that the proposed model reduces the test RMSE on both data sets compared to the benchmark models significantly.}, author = {Beinert, Dominik and Holzhüter, Clara and Thomas, Josephine and Vogt, Stephan}, journal = {Energy and AI}, keywords = {itegpub}, number = 1, pages = 100262, publisher = {Elsevier}, title = {Power flow forecasts at transmission grid nodes using Graph Neural Networks}, volume = 14, year = 2023 }
%0 Journal Article %1 beinert2023power %A Beinert, Dominik %A Holzhüter, Clara %A Thomas, Josephine %A Vogt, Stephan %D 2023 %I Elsevier %J Energy and AI %N 1 %P 100262 %R 10.1016/j.egyai.2023.100262 %T Power flow forecasts at transmission grid nodes using Graph Neural Networks %U https://www.sciencedirect.com/science/article/pii/S2666546823000344?via%3Dihub %V 14 %X The increasing share of renewable energy in the electricity grid and progressing changes in power consumption have led to fluctuating, and weather-dependent power flows. To ensure grid stability, grid operators rely on power forecasts which are crucial for grid calculations and planning. In this paper, a Multi-Task Learning approach is combined with a Graph Neural Network (GNN) to predict vertical power flows at transformers connecting high and extra-high voltage levels. The proposed method accounts for local differences in power flow characteristics by using an Embedding Multi-Task Learning approach. The use of a Bayesian embedding to capture the latent node characteristics allows to share the weights across all transformers in the subsequent node-invariant GNN while still allowing the individual behavioral patterns of the transformers to be distinguished. At the same time, dependencies between transformers are considered by the GNN architecture which can learn relationships between different transformers and thus take into account that power flows in an electricity network are not independent from each other. The effectiveness of the proposed method is demonstrated through evaluation on two real-world data sets provided by two of four German Transmission System Operators, comprising large portions of the operated German transmission grid. The results show that the proposed Multi-Task Graph Neural Network is a suitable representation learner for electricity networks with a clear advantage provided by the preceding embedding layer. It is able to capture interconnections between correlated transformers and indeed improves the performance in power flow prediction compared to standard Neural Networks. A sign test shows that the proposed model reduces the test RMSE on both data sets compared to the benchmark models significantly.
Organic Computing -- Doctoral Dissertation Colloquium 2022. Tomforde, Sven; Krupitzer, Christian. In Vol. 24Intelligent Embedded Systems. kassel university press, 2023.
- [ BibTeX ]
- [ EndNote ]
@book{tomforde2023organic, editor = {Tomforde, Sven and Krupitzer, Christian}, keywords = {itegpub}, publisher = {kassel university press}, series = {Intelligent Embedded Systems}, title = {Organic Computing – Doctoral Dissertation Colloquium 2022}, volume = 24, year = 2023 }
%0 Book %1 tomforde2023organic %B Intelligent Embedded Systems %D 2023 %E Tomforde, Sven %E Krupitzer, Christian %I kassel university press %R 10.17170/kobra-202302107484 %T Organic Computing -- Doctoral Dissertation Colloquium 2022 %V 24
On the Reliability of Automated Analysis of Fracture Surfaces Using a Novel Computer Vision-Based Tool. Engelhardt, Anna; Decke, Jens; Meier, David; Dulig, Franz; Ragunathan, Rishan; Wegener, Thomas; Sick, Bernhard; Niendorf, Thomas. In Advanced Engineering Materials, 25(21), bl 2300876. Wiley, 2023.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Fracture surface analysis is of utmost importance with respect to structural integrity of metallic materials. This especially holds true for additively manufactured materials. Despite an increasing trend of automatization of testing methods, the analysis and classification of fatigue fracture surface images is commonly done manually by experts. Although this leads to correct results in most cases, it has several disadvantages, e.g., the need of a huge knowledge base to interpret images correctly. In present work, an unsupervised tool for analysis of overview images of fatigue fracture surface images is developed to support nonexperienced users to identify the origin of the fracture. The tool is developed using fracture surface images of additively manufactured Ti6Al4V specimens fatigued in the high-cycle-fatigue regime and is based on the identification of river marks. Several recording parameters seem to have no significant influence on the results as long as preprocessing settings are adapted. Moreover, it is possible to analyze images of other materials with the tool as long as the fracture surfaces contain river marks. However, special features like multiple origins or origins located in direct vicinity to the surface, e.g., caused by increased plastic strains, require a further tool development or alternative approaches.
@article{engelhardt2023reliability, abstract = {Fracture surface analysis is of utmost importance with respect to structural integrity of metallic materials. This especially holds true for additively manufactured materials. Despite an increasing trend of automatization of testing methods, the analysis and classification of fatigue fracture surface images is commonly done manually by experts. Although this leads to correct results in most cases, it has several disadvantages, e.g., the need of a huge knowledge base to interpret images correctly. In present work, an unsupervised tool for analysis of overview images of fatigue fracture surface images is developed to support nonexperienced users to identify the origin of the fracture. The tool is developed using fracture surface images of additively manufactured Ti6Al4V specimens fatigued in the high-cycle-fatigue regime and is based on the identification of river marks. Several recording parameters seem to have no significant influence on the results as long as preprocessing settings are adapted. Moreover, it is possible to analyze images of other materials with the tool as long as the fracture surfaces contain river marks. However, special features like multiple origins or origins located in direct vicinity to the surface, e.g., caused by increased plastic strains, require a further tool development or alternative approaches.}, author = {Engelhardt, Anna and Decke, Jens and Meier, David and Dulig, Franz and Ragunathan, Rishan and Wegener, Thomas and Sick, Bernhard and Niendorf, Thomas}, journal = {Advanced Engineering Materials}, keywords = {ImageRecognition}, number = 21, pages = 2300876, publisher = {Wiley}, title = {On the Reliability of Automated Analysis of Fracture Surfaces Using a Novel Computer Vision-Based Tool}, volume = 25, year = 2023 }
%0 Journal Article %1 engelhardt2023reliability %A Engelhardt, Anna %A Decke, Jens %A Meier, David %A Dulig, Franz %A Ragunathan, Rishan %A Wegener, Thomas %A Sick, Bernhard %A Niendorf, Thomas %D 2023 %I Wiley %J Advanced Engineering Materials %N 21 %P 2300876 %R https://doi.org/10.1002/adem.202300876 %T On the Reliability of Automated Analysis of Fracture Surfaces Using a Novel Computer Vision-Based Tool %U https://onlinelibrary.wiley.com/doi/full/10.1002/adem.202300876 %V 25 %X Fracture surface analysis is of utmost importance with respect to structural integrity of metallic materials. This especially holds true for additively manufactured materials. Despite an increasing trend of automatization of testing methods, the analysis and classification of fatigue fracture surface images is commonly done manually by experts. Although this leads to correct results in most cases, it has several disadvantages, e.g., the need of a huge knowledge base to interpret images correctly. In present work, an unsupervised tool for analysis of overview images of fatigue fracture surface images is developed to support nonexperienced users to identify the origin of the fracture. The tool is developed using fracture surface images of additively manufactured Ti6Al4V specimens fatigued in the high-cycle-fatigue regime and is based on the identification of river marks. Several recording parameters seem to have no significant influence on the results as long as preprocessing settings are adapted. Moreover, it is possible to analyze images of other materials with the tool as long as the fracture surfaces contain river marks. However, special features like multiple origins or origins located in direct vicinity to the surface, e.g., caused by increased plastic strains, require a further tool development or alternative approaches.
Multi-Task Representation Learning for Renewable-Power Forecasting: A Comparative Analysis of Unified Autoencoder Variants and Task-Embedding Dimensions. Nivarthi, Chandana Priya; Vogt, Stephan; Sick, Bernhard. In Machine Learning and Knowledge Extraction (MAKE), 5(3), bll 1214–1233. MDPI, 2023.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Typically, renewable-power-generation forecasting using machine learning involves creating separate models for each photovoltaic or wind park, known as single-task learning models. However, transfer learning has gained popularity in recent years, as it allows for the transfer of knowledge from source parks to target parks. Nevertheless, determining the most similar source park(s) for transfer learning can be challenging, particularly when the target park has limited or no historical data samples. To address this issue, we propose a multi-task learning architecture that employs a Unified Autoencoder (UAE) to initially learn a common representation of input weather features among tasks and then utilizes a Task-Embedding layer in a Neural Network (TENN) to learn task-specific information. This proposed UAE-TENN architecture can be easily extended to new parks with or without historical data. We evaluate the performance of our proposed architecture and compare it to single-task learning models on six photovoltaic and wind farm datasets consisting of a total of 529 parks. Our results show that the UAE-TENN architecture significantly improves power-forecasting performance by 10 to 19% for photovoltaic parks and 5 to 15% for wind parks compared to baseline models. We also demonstrate that UAE-TENN improves forecast accuracy for a new park by 19% for photovoltaic parks, even in a zero-shot learning scenario where there is no historical data. Additionally, we propose variants of the Unified Autoencoder with convolutional and LSTM layers, compare their performance, and provide a comparison among architectures with different numbers of task-embedding dimensions. Finally, we demonstrate the utility of trained task embeddings for interpretation and visualization purposes.
@article{nivarthi2023multi, abstract = {Typically, renewable-power-generation forecasting using machine learning involves creating separate models for each photovoltaic or wind park, known as single-task learning models. However, transfer learning has gained popularity in recent years, as it allows for the transfer of knowledge from source parks to target parks. Nevertheless, determining the most similar source park(s) for transfer learning can be challenging, particularly when the target park has limited or no historical data samples. To address this issue, we propose a multi-task learning architecture that employs a Unified Autoencoder (UAE) to initially learn a common representation of input weather features among tasks and then utilizes a Task-Embedding layer in a Neural Network (TENN) to learn task-specific information. This proposed UAE-TENN architecture can be easily extended to new parks with or without historical data. We evaluate the performance of our proposed architecture and compare it to single-task learning models on six photovoltaic and wind farm datasets consisting of a total of 529 parks. Our results show that the UAE-TENN architecture significantly improves power-forecasting performance by 10 to 19% for photovoltaic parks and 5 to 15% for wind parks compared to baseline models. We also demonstrate that UAE-TENN improves forecast accuracy for a new park by 19% for photovoltaic parks, even in a zero-shot learning scenario where there is no historical data. Additionally, we propose variants of the Unified Autoencoder with convolutional and LSTM layers, compare their performance, and provide a comparison among architectures with different numbers of task-embedding dimensions. Finally, we demonstrate the utility of trained task embeddings for interpretation and visualization purposes.}, author = {Nivarthi, Chandana Priya and Vogt, Stephan and Sick, Bernhard}, journal = {Machine Learning and Knowledge Extraction (MAKE)}, keywords = {itegpub}, number = 3, pages = {1214–1233}, publisher = {MDPI}, title = {Multi-Task Representation Learning for Renewable-Power Forecasting: A Comparative Analysis of Unified Autoencoder Variants and Task-Embedding Dimensions}, volume = 5, year = 2023 }
%0 Journal Article %1 nivarthi2023multi %A Nivarthi, Chandana Priya %A Vogt, Stephan %A Sick, Bernhard %D 2023 %I MDPI %J Machine Learning and Knowledge Extraction (MAKE) %N 3 %P 1214--1233 %R 10.3390/make5030062 %T Multi-Task Representation Learning for Renewable-Power Forecasting: A Comparative Analysis of Unified Autoencoder Variants and Task-Embedding Dimensions %U https://www.mdpi.com/2504-4990/5/3/62 %V 5 %X Typically, renewable-power-generation forecasting using machine learning involves creating separate models for each photovoltaic or wind park, known as single-task learning models. However, transfer learning has gained popularity in recent years, as it allows for the transfer of knowledge from source parks to target parks. Nevertheless, determining the most similar source park(s) for transfer learning can be challenging, particularly when the target park has limited or no historical data samples. To address this issue, we propose a multi-task learning architecture that employs a Unified Autoencoder (UAE) to initially learn a common representation of input weather features among tasks and then utilizes a Task-Embedding layer in a Neural Network (TENN) to learn task-specific information. This proposed UAE-TENN architecture can be easily extended to new parks with or without historical data. We evaluate the performance of our proposed architecture and compare it to single-task learning models on six photovoltaic and wind farm datasets consisting of a total of 529 parks. Our results show that the UAE-TENN architecture significantly improves power-forecasting performance by 10 to 19% for photovoltaic parks and 5 to 15% for wind parks compared to baseline models. We also demonstrate that UAE-TENN improves forecast accuracy for a new park by 19% for photovoltaic parks, even in a zero-shot learning scenario where there is no historical data. Additionally, we propose variants of the Unified Autoencoder with convolutional and LSTM layers, compare their performance, and provide a comparison among architectures with different numbers of task-embedding dimensions. Finally, we demonstrate the utility of trained task embeddings for interpretation and visualization purposes.
Multi-annotator Deep Learning: A Probabilistic Framework for Classification. Herde, Marek; Huseljic, Denis; Sick, Bernhard. In Transactions on Machine Learning Research. 2023.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Solving complex classification tasks using deep neural networks typically requires large amounts of annotated data. However, corresponding class labels are noisy when provided by error-prone annotators, e.g., crowdworkers. Training standard deep neural networks leads to subpar performances in such multi-annotator supervised learning settings. We address this issue by presenting a probabilistic training framework named multi-annotator deep learning (MaDL). A downstream ground truth and an annotator performance model are jointly trained in an end-to-end learning approach. The ground truth model learns to predict instances' true class labels, while the annotator performance model infers probabilistic estimates of annotators' performances. A modular network architecture enables us to make varying assumptions regarding annotators' performances, e.g., an optional class or instance dependency. Further, we learn annotator embeddings to estimate annotators' densities within a latent space as proxies of their potentially correlated annotations. Together with a weighted loss function, we improve the learning from correlated annotation patterns. In a comprehensive evaluation, we examine three research questions about multi-annotator supervised learning. Our findings show MaDL's state-of-the-art performance and robustness against many correlated, spamming annotators.
@article{herde2023multi, abstract = {Solving complex classification tasks using deep neural networks typically requires large amounts of annotated data. However, corresponding class labels are noisy when provided by error-prone annotators, e.g., crowdworkers. Training standard deep neural networks leads to subpar performances in such multi-annotator supervised learning settings. We address this issue by presenting a probabilistic training framework named multi-annotator deep learning (MaDL). A downstream ground truth and an annotator performance model are jointly trained in an end-to-end learning approach. The ground truth model learns to predict instances' true class labels, while the annotator performance model infers probabilistic estimates of annotators' performances. A modular network architecture enables us to make varying assumptions regarding annotators' performances, e.g., an optional class or instance dependency. Further, we learn annotator embeddings to estimate annotators' densities within a latent space as proxies of their potentially correlated annotations. Together with a weighted loss function, we improve the learning from correlated annotation patterns. In a comprehensive evaluation, we examine three research questions about multi-annotator supervised learning. Our findings show MaDL's state-of-the-art performance and robustness against many correlated, spamming annotators.}, author = {Herde, Marek and Huseljic, Denis and Sick, Bernhard}, journal = {Transactions on Machine Learning Research}, keywords = {itegpub}, title = {Multi-annotator Deep Learning: A Probabilistic Framework for Classification}, year = 2023 }
%0 Journal Article %1 herde2023multi %A Herde, Marek %A Huseljic, Denis %A Sick, Bernhard %D 2023 %J Transactions on Machine Learning Research %T Multi-annotator Deep Learning: A Probabilistic Framework for Classification %U https://openreview.net/forum?id=MgdoxzImlK %X Solving complex classification tasks using deep neural networks typically requires large amounts of annotated data. However, corresponding class labels are noisy when provided by error-prone annotators, e.g., crowdworkers. Training standard deep neural networks leads to subpar performances in such multi-annotator supervised learning settings. We address this issue by presenting a probabilistic training framework named multi-annotator deep learning (MaDL). A downstream ground truth and an annotator performance model are jointly trained in an end-to-end learning approach. The ground truth model learns to predict instances' true class labels, while the annotator performance model infers probabilistic estimates of annotators' performances. A modular network architecture enables us to make varying assumptions regarding annotators' performances, e.g., an optional class or instance dependency. Further, we learn annotator embeddings to estimate annotators' densities within a latent space as proxies of their potentially correlated annotations. Together with a weighted loss function, we improve the learning from correlated annotation patterns. In a comprehensive evaluation, we examine three research questions about multi-annotator supervised learning. Our findings show MaDL's state-of-the-art performance and robustness against many correlated, spamming annotators.
Model selection, adaptation, and combination for transfer learning in wind and photovoltaic power forecasts. Schreiber, Jens; Sick, Bernhard. In Energy and AI, 14, bl 100249. 2023.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
There is recent interest in using model hubs – a collection of pre-trained models – in computer vision tasks. To employ a model hub, we first select a source model and then adapt the model for the target to compensate for differences. There still needs to be more research on model selection and adaption for renewable power forecasts. In particular, none of the related work examines different model selection and adaptation strategies for neural network architectures. Also, none of the current studies investigates the influence of available training samples and considers seasonality in the evaluation. We close these gaps by conducting the first thorough experiment for model selection and adaptation for transfer learning in renewable power forecast, adopting recent developments from the field of computer vision on 667 wind and photovoltaic parks from six datasets. We simulate different amounts of training samples for each season to calculate informative forecast errors. We examine the marginal likelihood and forecast error for model selection for those amounts. Furthermore, we study four adaption strategies. As an extension of the current state of the art, we utilize a Bayesian linear regression for forecasting the response based on features extracted from a neural network. This approach outperforms the baseline with only seven days of training data and shows that fine-tuning is not beneficial with less than three months of data. We further show how combining multiple models through ensembles can significantly improve the model selection and adaptation approach such that we have a similar mean error with only 30 days of training data which is otherwise only possible with an entire year of training data. We achieve a mean error of 9.8 and 14 percent for the most realistic dataset for PV and wind with only seven days of training data.
@article{schreiber2023model, abstract = {There is recent interest in using model hubs – a collection of pre-trained models – in computer vision tasks. To employ a model hub, we first select a source model and then adapt the model for the target to compensate for differences. There still needs to be more research on model selection and adaption for renewable power forecasts. In particular, none of the related work examines different model selection and adaptation strategies for neural network architectures. Also, none of the current studies investigates the influence of available training samples and considers seasonality in the evaluation. We close these gaps by conducting the first thorough experiment for model selection and adaptation for transfer learning in renewable power forecast, adopting recent developments from the field of computer vision on 667 wind and photovoltaic parks from six datasets. We simulate different amounts of training samples for each season to calculate informative forecast errors. We examine the marginal likelihood and forecast error for model selection for those amounts. Furthermore, we study four adaption strategies. As an extension of the current state of the art, we utilize a Bayesian linear regression for forecasting the response based on features extracted from a neural network. This approach outperforms the baseline with only seven days of training data and shows that fine-tuning is not beneficial with less than three months of data. We further show how combining multiple models through ensembles can significantly improve the model selection and adaptation approach such that we have a similar mean error with only 30 days of training data which is otherwise only possible with an entire year of training data. We achieve a mean error of 9.8 and 14 percent for the most realistic dataset for PV and wind with only seven days of training data.}, author = {Schreiber, Jens and Sick, Bernhard}, journal = {Energy and AI}, keywords = {itegpub}, pages = 100249, title = {Model selection, adaptation, and combination for transfer learning in wind and photovoltaic power forecasts}, volume = 14, year = 2023 }
%0 Journal Article %1 schreiber2023model %A Schreiber, Jens %A Sick, Bernhard %D 2023 %J Energy and AI %P 100249 %R 10.1016/j.egyai.2023.100249 %T Model selection, adaptation, and combination for transfer learning in wind and photovoltaic power forecasts %U https://www.sciencedirect.com/science/article/pii/S2666546823000216 %V 14 %X There is recent interest in using model hubs – a collection of pre-trained models – in computer vision tasks. To employ a model hub, we first select a source model and then adapt the model for the target to compensate for differences. There still needs to be more research on model selection and adaption for renewable power forecasts. In particular, none of the related work examines different model selection and adaptation strategies for neural network architectures. Also, none of the current studies investigates the influence of available training samples and considers seasonality in the evaluation. We close these gaps by conducting the first thorough experiment for model selection and adaptation for transfer learning in renewable power forecast, adopting recent developments from the field of computer vision on 667 wind and photovoltaic parks from six datasets. We simulate different amounts of training samples for each season to calculate informative forecast errors. We examine the marginal likelihood and forecast error for model selection for those amounts. Furthermore, we study four adaption strategies. As an extension of the current state of the art, we utilize a Bayesian linear regression for forecasting the response based on features extracted from a neural network. This approach outperforms the baseline with only seven days of training data and shows that fine-tuning is not beneficial with less than three months of data. We further show how combining multiple models through ensembles can significantly improve the model selection and adaptation approach such that we have a similar mean error with only 30 days of training data which is otherwise only possible with an entire year of training data. We achieve a mean error of 9.8 and 14 percent for the most realistic dataset for PV and wind with only seven days of training data.
Marked Neural Spatio-Temporal Point Process Involving a Dynamic Graph Neural Network. Moallemy-Oureh, Alice; Beddar-Wiesing, Silvia; Nather, Rüdiger; Thomas, Josephine. In Workshop on Temporal Graph Learning (TGL), NeurIPS, bll 1–7. 2023.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Temporal Point Processes (TPPs) have recently become increasingly interesting for learning dynamics in graph data. A reason for this is that learning on dynamic graph data is becoming more relevant, since data from many scientific fields, ranging from mathematics, biology, social sciences, and physics to computer science, is naturally related and inherently dynamic. In addition, TPPs provide a meaningful characterization of event streams and a prediction mechanism for future events. Therefore, (semi-)parameterized Neural TPPs have been introduced whose characterization can be (partially) learned and, thus, enable the representation of more complex phenomena. However, the research on modeling dynamic graphs with TPPs is relatively young, and only a few models for node attribute changes or evolving edges have been proposed yet. To allow for learning on fully dynamic graph streams, i.e., graphs that can change in their structure (addition/deletion of nodes/edge) and in their node/edge attributes, we propose a Marked Neural Spatio-Temporal Point Process (MNSTPP). It leverages a Dynamic Graph Neural Network to learn a Marked TPP that handles attributes and spatial data to model and predict any event in a graph stream.
@inproceedings{moallemyoureh2023marked, abstract = {Temporal Point Processes (TPPs) have recently become increasingly interesting for learning dynamics in graph data. A reason for this is that learning on dynamic graph data is becoming more relevant, since data from many scientific fields, ranging from mathematics, biology, social sciences, and physics to computer science, is naturally related and inherently dynamic. In addition, TPPs provide a meaningful characterization of event streams and a prediction mechanism for future events. Therefore, (semi-)parameterized Neural TPPs have been introduced whose characterization can be (partially) learned and, thus, enable the representation of more complex phenomena. However, the research on modeling dynamic graphs with TPPs is relatively young, and only a few models for node attribute changes or evolving edges have been proposed yet. To allow for learning on fully dynamic graph streams, i.e., graphs that can change in their structure (addition/deletion of nodes/edge) and in their node/edge attributes, we propose a Marked Neural Spatio-Temporal Point Process (MNSTPP). It leverages a Dynamic Graph Neural Network to learn a Marked TPP that handles attributes and spatial data to model and predict any event in a graph stream.}, author = {Moallemy-Oureh, Alice and Beddar-Wiesing, Silvia and Nather, Rüdiger and Thomas, Josephine}, booktitle = {Workshop on Temporal Graph Learning (TGL), NeurIPS}, keywords = {itegpub}, pages = {1–7}, title = {Marked Neural Spatio-Temporal Point Process Involving a Dynamic Graph Neural Network}, year = 2023 }
%0 Conference Paper %1 moallemyoureh2023marked %A Moallemy-Oureh, Alice %A Beddar-Wiesing, Silvia %A Nather, Rüdiger %A Thomas, Josephine %B Workshop on Temporal Graph Learning (TGL), NeurIPS %D 2023 %P 1--7 %T Marked Neural Spatio-Temporal Point Process Involving a Dynamic Graph Neural Network %U https://openreview.net/forum?id=QJx3Cmddsy %X Temporal Point Processes (TPPs) have recently become increasingly interesting for learning dynamics in graph data. A reason for this is that learning on dynamic graph data is becoming more relevant, since data from many scientific fields, ranging from mathematics, biology, social sciences, and physics to computer science, is naturally related and inherently dynamic. In addition, TPPs provide a meaningful characterization of event streams and a prediction mechanism for future events. Therefore, (semi-)parameterized Neural TPPs have been introduced whose characterization can be (partially) learned and, thus, enable the representation of more complex phenomena. However, the research on modeling dynamic graphs with TPPs is relatively young, and only a few models for node attribute changes or evolving edges have been proposed yet. To allow for learning on fully dynamic graph streams, i.e., graphs that can change in their structure (addition/deletion of nodes/edge) and in their node/edge attributes, we propose a Marked Neural Spatio-Temporal Point Process (MNSTPP). It leverages a Dynamic Graph Neural Network to learn a Marked TPP that handles attributes and spatial data to model and predict any event in a graph stream.
Managing power grids through topology actions: A comparative study between advanced rule-based and reinforcement learning agents. Lehna, Malte; Viebahn, Jan; Marot, Antoine; Tomforde, Sven; Scholz, Christoph. In Energy and AI, 14, bl 100276. Energy and AI, 2023.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
The operation of electricity grids has become increasingly complex due to the current upheaval and the increase in renewable energy production. As a consequence, active grid management is reaching its limits with conventional approaches. In the context of the Learning to Run a Power Network (L2RPN) challenge, it has been shown that Reinforcement Learning (RL) is an efficient and reliable approach with considerable potential for automatic grid operation. In this article, we analyse the submitted agent from Binbinchen and provide novel strategies to improve the agent, both for the RL and the rule-based approach. The main improvement is a N-1 strategy, where we consider topology actions that keep the grid stable, even if one line is disconnected. More, we also propose a topology reversion to the original grid, which proved to be beneficial. The improvements are tested against reference approaches on the challenge test sets and are able to increase the performance of the rule-based agent by 27%. In direct comparison between rule-based and RL agent we find similar performance. However, the RL agent has a clear computational advantage. We also analyse the behaviour in an exemplary case in more detail to provide additional insights. Here, we observe that through the N-1 strategy, the actions of both the rule-based and the RL agent become more diversified.
@article{lehna2023managing, abstract = {The operation of electricity grids has become increasingly complex due to the current upheaval and the increase in renewable energy production. As a consequence, active grid management is reaching its limits with conventional approaches. In the context of the Learning to Run a Power Network (L2RPN) challenge, it has been shown that Reinforcement Learning (RL) is an efficient and reliable approach with considerable potential for automatic grid operation. In this article, we analyse the submitted agent from Binbinchen and provide novel strategies to improve the agent, both for the RL and the rule-based approach. The main improvement is a N-1 strategy, where we consider topology actions that keep the grid stable, even if one line is disconnected. More, we also propose a topology reversion to the original grid, which proved to be beneficial. The improvements are tested against reference approaches on the challenge test sets and are able to increase the performance of the rule-based agent by 27%. In direct comparison between rule-based and RL agent we find similar performance. However, the RL agent has a clear computational advantage. We also analyse the behaviour in an exemplary case in more detail to provide additional insights. Here, we observe that through the N-1 strategy, the actions of both the rule-based and the RL agent become more diversified.}, author = {Lehna, Malte and Viebahn, Jan and Marot, Antoine and Tomforde, Sven and Scholz, Christoph}, journal = {Energy and AI}, keywords = {itegpub}, pages = 100276, publisher = {Energy and AI}, title = {Managing power grids through topology actions: A comparative study between advanced rule-based and reinforcement learning agents}, volume = 14, year = 2023 }
%0 Journal Article %1 lehna2023managing %A Lehna, Malte %A Viebahn, Jan %A Marot, Antoine %A Tomforde, Sven %A Scholz, Christoph %D 2023 %I Energy and AI %J Energy and AI %P 100276 %R 10.1016/j.egyai.2023.100276 %T Managing power grids through topology actions: A comparative study between advanced rule-based and reinforcement learning agents %U https://www.sciencedirect.com/science/article/pii/S2666546823000484?via%3Dihub %V 14 %X The operation of electricity grids has become increasingly complex due to the current upheaval and the increase in renewable energy production. As a consequence, active grid management is reaching its limits with conventional approaches. In the context of the Learning to Run a Power Network (L2RPN) challenge, it has been shown that Reinforcement Learning (RL) is an efficient and reliable approach with considerable potential for automatic grid operation. In this article, we analyse the submitted agent from Binbinchen and provide novel strategies to improve the agent, both for the RL and the rule-based approach. The main improvement is a N-1 strategy, where we consider topology actions that keep the grid stable, even if one line is disconnected. More, we also propose a topology reversion to the original grid, which proved to be beneficial. The improvements are tested against reference approaches on the challenge test sets and are able to increase the performance of the rule-based agent by 27%. In direct comparison between rule-based and RL agent we find similar performance. However, the RL agent has a clear computational advantage. We also analyse the behaviour in an exemplary case in more detail to provide additional insights. Here, we observe that through the N-1 strategy, the actions of both the rule-based and the RL agent become more diversified.
Machine Learning Supported Optimisation and Experimental Evaluation of Electrical Motors for Small Urban Passenger Vehicles. Botache, Diego. In Organic Computing -- Doctoral Dissertation Colloquium 2023, S. Tomforde, C. Krupitzer (reds.), bll 14–26. kassel university press, 2023.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
The increasing environmental pollution and rising global energy demands require the rapid development of novel and sustainable traction machines from urban transport up to large-scale transport vehicles. The optimisation of the development cycle of electrical traction machines plays a vital role in sustainable mobility. Still, developers have to face the difficulty of analysing time-consuming multiphysics simulations to assess the performance of many prototype variants. Accelerating this process involves implementing machine learning-supported strategies that can effectively acquire results and predictions about the performance and efficiency of prototypes in an iterative optimisation process and detect possible issues during the experimental procedure. The following research project streamlines the development cycle by identifying and presenting multiple strategies for applying and evaluating machine learning and deep learning techniques in different stages and areas in the development cycle including self-optimisation and self-adaptation capabilities. By implementing these strategies, the optimisation process can be further improved and become more efficient and robust, reducing the time and cost required for testing and validation. Therefore, this proposal addresses two application areas. The first area consists of the supported machine learning motor performance prediction at the topology design and optimisation stage of structural components. The second area corresponds to the machine learning-supported experimental evaluation process of prototypes at desired test benches.
@incollection{botache2023machine, abstract = {The increasing environmental pollution and rising global energy demands require the rapid development of novel and sustainable traction machines from urban transport up to large-scale transport vehicles. The optimisation of the development cycle of electrical traction machines plays a vital role in sustainable mobility. Still, developers have to face the difficulty of analysing time-consuming multiphysics simulations to assess the performance of many prototype variants. Accelerating this process involves implementing machine learning-supported strategies that can effectively acquire results and predictions about the performance and efficiency of prototypes in an iterative optimisation process and detect possible issues during the experimental procedure. The following research project streamlines the development cycle by identifying and presenting multiple strategies for applying and evaluating machine learning and deep learning techniques in different stages and areas in the development cycle including self-optimisation and self-adaptation capabilities. By implementing these strategies, the optimisation process can be further improved and become more efficient and robust, reducing the time and cost required for testing and validation. Therefore, this proposal addresses two application areas. The first area consists of the supported machine learning motor performance prediction at the topology design and optimisation stage of structural components. The second area corresponds to the machine learning-supported experimental evaluation process of prototypes at desired test benches.}, author = {Botache, Diego}, booktitle = {Organic Computing – Doctoral Dissertation Colloquium 2023}, editor = {Tomforde, Sven and Krupitzer, Christian}, keywords = {itegpub}, pages = {14–26}, publisher = {kassel university press}, title = {Machine Learning Supported Optimisation and Experimental Evaluation of Electrical Motors for Small Urban Passenger Vehicles}, year = 2023 }
%0 Book Section %1 botache2023machine %A Botache, Diego %B Organic Computing -- Doctoral Dissertation Colloquium 2023 %D 2023 %E Tomforde, Sven %E Krupitzer, Christian %I kassel university press %P 14--26 %T Machine Learning Supported Optimisation and Experimental Evaluation of Electrical Motors for Small Urban Passenger Vehicles %X The increasing environmental pollution and rising global energy demands require the rapid development of novel and sustainable traction machines from urban transport up to large-scale transport vehicles. The optimisation of the development cycle of electrical traction machines plays a vital role in sustainable mobility. Still, developers have to face the difficulty of analysing time-consuming multiphysics simulations to assess the performance of many prototype variants. Accelerating this process involves implementing machine learning-supported strategies that can effectively acquire results and predictions about the performance and efficiency of prototypes in an iterative optimisation process and detect possible issues during the experimental procedure. The following research project streamlines the development cycle by identifying and presenting multiple strategies for applying and evaluating machine learning and deep learning techniques in different stages and areas in the development cycle including self-optimisation and self-adaptation capabilities. By implementing these strategies, the optimisation process can be further improved and become more efficient and robust, reducing the time and cost required for testing and validation. Therefore, this proposal addresses two application areas. The first area consists of the supported machine learning motor performance prediction at the topology design and optimisation stage of structural components. The second area corresponds to the machine learning-supported experimental evaluation process of prototypes at desired test benches.
Leveraging Repeated Unlabelled Noisy Measurements to Augment Supervised Learning. Magnussen, Birk Martin; Stern, Claudius; Sick, Bernhard. In International Conference on Computational Intelligence and Intelligent Systems (CIIS), bll 1–6. ACM, 2023.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Often, producing large labelled datasets for supervised machine learning is difficult and expensive. In cases where the expensive part is due to labelling and obtaining ground truth, it is often comparably easy to acquire large datasets containing unlabelled data points. For reproducible measurements, it is possible to record information on multiple data points being from the same reproducible measurement series, which should thus have an equal but unknown ground truth. In this article, we propose a method to incorporate a dataset of such unlabelled data points for which some data points are known to be equal in end-to-end training of otherwise labelled data. We show that, with the example of predicting the carotenoid concentration in human skin from optical multiple spatially resolved reflection spectroscopy data, the proposed method is capable of reducing the required number of labelled data points to achieve the same prediction accuracy for different model architectures. In addition, we show that the proposed method is capable of reducing the negative impact of noisy data when performing a repeated measurement of the same sample.
@inproceedings{magnussen2023leveraging, abstract = {Often, producing large labelled datasets for supervised machine learning is difficult and expensive. In cases where the expensive part is due to labelling and obtaining ground truth, it is often comparably easy to acquire large datasets containing unlabelled data points. For reproducible measurements, it is possible to record information on multiple data points being from the same reproducible measurement series, which should thus have an equal but unknown ground truth. In this article, we propose a method to incorporate a dataset of such unlabelled data points for which some data points are known to be equal in end-to-end training of otherwise labelled data. We show that, with the example of predicting the carotenoid concentration in human skin from optical multiple spatially resolved reflection spectroscopy data, the proposed method is capable of reducing the required number of labelled data points to achieve the same prediction accuracy for different model architectures. In addition, we show that the proposed method is capable of reducing the negative impact of noisy data when performing a repeated measurement of the same sample.}, author = {Magnussen, Birk Martin and Stern, Claudius and Sick, Bernhard}, booktitle = {International Conference on Computational Intelligence and Intelligent Systems (CIIS)}, keywords = {itegpub}, pages = {1–6}, publisher = {ACM}, title = {Leveraging Repeated Unlabelled Noisy Measurements to Augment Supervised Learning}, year = 2023 }
%0 Conference Paper %1 magnussen2023leveraging %A Magnussen, Birk Martin %A Stern, Claudius %A Sick, Bernhard %B International Conference on Computational Intelligence and Intelligent Systems (CIIS) %D 2023 %I ACM %P 1--6 %R 10.1145/3638209.3638210 %T Leveraging Repeated Unlabelled Noisy Measurements to Augment Supervised Learning %U https://dl.acm.org/doi/10.1145/3638209.3638210 %X Often, producing large labelled datasets for supervised machine learning is difficult and expensive. In cases where the expensive part is due to labelling and obtaining ground truth, it is often comparably easy to acquire large datasets containing unlabelled data points. For reproducible measurements, it is possible to record information on multiple data points being from the same reproducible measurement series, which should thus have an equal but unknown ground truth. In this article, we propose a method to incorporate a dataset of such unlabelled data points for which some data points are known to be equal in end-to-end training of otherwise labelled data. We show that, with the example of predicting the carotenoid concentration in human skin from optical multiple spatially resolved reflection spectroscopy data, the proposed method is capable of reducing the required number of labelled data points to achieve the same prediction accuracy for different model architectures. In addition, we show that the proposed method is capable of reducing the negative impact of noisy data when performing a repeated measurement of the same sample.
It is the habit not the handle that affects tooth brushing. Results of a randomised counterbalanced cross over study. Deinzer, Renate; Eidenhardt, Zdenka; Sohrabi, Keywan; Stenger, Manuel; Kraft, Dominik; Sick, Bernhard; Götz-Hahn, Franz; Bottenbruch, Carlotta; Berneburg, Nils; Weik, Ulrike. In Research Square. 2023.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Objective: To assess the effect of the toothbrush handle on video-observed toothbrushing behaviour and toothbrushing effectiveness Methods: This is a randomized counterbalanced cross-over study. N = 50 university students brushed their teeth at two occasions, one week apart, using either a commercial ergonomically designed manual toothbrush (MT) or Brushalyze V1 (BV1), a manual toothbrush with a thick cylindrical handle without any specific ergonomic features. Brushing behaviour was video-analysed. Plaque was assessed at the second occasion immediately after brushing. Participants directly compared the two brushes regarding their handling and compared them to the brushed they used at home. Results: The study participants found the BV1 significantly more cumbersome than the M1 or their brush at home. (p < 0.05). However, correlation analyses revealed a strong consistency of brushing behavior with the two brushes (0.71 < r < 0.91). Means differed only slightly (all d < 0.36). These differences became statistically significant only for the brushing time at inner surfaces (d = 0.31 p = 0.03) and horizontal movements at inner surfaces (d = 0.35, p = 0.02). Plaque levels at the gingival margins did not differ while slightly more plaque persisted at the more coronal aspects of the crown after brushing with BV1 (d = 0.592; p 0.042) Discussion: The results of the study indicate that the brushing handle does not play a major role in brushing behavior or brushing effectiveness.
@article{deinzer2023it, abstract = {Objective: To assess the effect of the toothbrush handle on video-observed toothbrushing behaviour and toothbrushing effectiveness Methods: This is a randomized counterbalanced cross-over study. N = 50 university students brushed their teeth at two occasions, one week apart, using either a commercial ergonomically designed manual toothbrush (MT) or Brushalyze V1 (BV1), a manual toothbrush with a thick cylindrical handle without any specific ergonomic features. Brushing behaviour was video-analysed. Plaque was assessed at the second occasion immediately after brushing. Participants directly compared the two brushes regarding their handling and compared them to the brushed they used at home. Results: The study participants found the BV1 significantly more cumbersome than the M1 or their brush at home. (p < 0.05). However, correlation analyses revealed a strong consistency of brushing behavior with the two brushes (0.71 < r < 0.91). Means differed only slightly (all d < 0.36). These differences became statistically significant only for the brushing time at inner surfaces (d = 0.31 p = 0.03) and horizontal movements at inner surfaces (d = 0.35, p = 0.02). Plaque levels at the gingival margins did not differ while slightly more plaque persisted at the more coronal aspects of the crown after brushing with BV1 (d = 0.592; p 0.042) Discussion: The results of the study indicate that the brushing handle does not play a major role in brushing behavior or brushing effectiveness.}, author = {Deinzer, Renate and Eidenhardt, Zdenka and Sohrabi, Keywan and Stenger, Manuel and Kraft, Dominik and Sick, Bernhard and Götz-Hahn, Franz and Bottenbruch, Carlotta and Berneburg, Nils and Weik, Ulrike}, journal = {Research Square}, keywords = {itegpub}, note = {(preprint)}, title = {It is the habit not the handle that affects tooth brushing. Results of a randomised counterbalanced cross over study}, year = 2023 }
%0 Journal Article %1 deinzer2023it %A Deinzer, Renate %A Eidenhardt, Zdenka %A Sohrabi, Keywan %A Stenger, Manuel %A Kraft, Dominik %A Sick, Bernhard %A Götz-Hahn, Franz %A Bottenbruch, Carlotta %A Berneburg, Nils %A Weik, Ulrike %D 2023 %J Research Square %R 10.21203/rs.3.rs-3491691/v1 %T It is the habit not the handle that affects tooth brushing. Results of a randomised counterbalanced cross over study %U https://www.researchsquare.com/article/rs-3491691/v1 %X Objective: To assess the effect of the toothbrush handle on video-observed toothbrushing behaviour and toothbrushing effectiveness Methods: This is a randomized counterbalanced cross-over study. N = 50 university students brushed their teeth at two occasions, one week apart, using either a commercial ergonomically designed manual toothbrush (MT) or Brushalyze V1 (BV1), a manual toothbrush with a thick cylindrical handle without any specific ergonomic features. Brushing behaviour was video-analysed. Plaque was assessed at the second occasion immediately after brushing. Participants directly compared the two brushes regarding their handling and compared them to the brushed they used at home. Results: The study participants found the BV1 significantly more cumbersome than the M1 or their brush at home. (p < 0.05). However, correlation analyses revealed a strong consistency of brushing behavior with the two brushes (0.71 < r < 0.91). Means differed only slightly (all d < 0.36). These differences became statistically significant only for the brushing time at inner surfaces (d = 0.31 p = 0.03) and horizontal movements at inner surfaces (d = 0.35, p = 0.02). Plaque levels at the gingival margins did not differ while slightly more plaque persisted at the more coronal aspects of the crown after brushing with BV1 (d = 0.592; p 0.042) Discussion: The results of the study indicate that the brushing handle does not play a major role in brushing behavior or brushing effectiveness.
Height Change Feature Based Free Space Detection. Schreck, Steven; Reichert, Hannes; Hetzel, Manuel; Doll, Konrad; Sick, Bernhard. In International Conference on Control, Mechatronics and Automation (ICCMA), bll 171–176. IEEE, 2023.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
We present a novel method for free space detection in dynamic environments like factory sites, crucial for autonomous forklifts to avoid collisions. It introduces a technique for fast surface normal estimation using spherical projected LiDAR data, which helps in detecting free space efficiently and in real-time. The method's effectiveness is proven with a 50.90% mIoU score on the Semantic KITTI dataset at 105 Hz, and a 63.30% mIoU score on a factory site dataset at 54 Hz.
@inproceedings{schreck2023height, abstract = {We present a novel method for free space detection in dynamic environments like factory sites, crucial for autonomous forklifts to avoid collisions. It introduces a technique for fast surface normal estimation using spherical projected LiDAR data, which helps in detecting free space efficiently and in real-time. The method's effectiveness is proven with a 50.90% mIoU score on the Semantic KITTI dataset at 105 Hz, and a 63.30% mIoU score on a factory site dataset at 54 Hz.}, author = {Schreck, Steven and Reichert, Hannes and Hetzel, Manuel and Doll, Konrad and Sick, Bernhard}, booktitle = {International Conference on Control, Mechatronics and Automation (ICCMA)}, keywords = {itegpub}, pages = {171–176}, publisher = {IEEE}, title = {Height Change Feature Based Free Space Detection}, year = 2023 }
%0 Conference Paper %1 schreck2023height %A Schreck, Steven %A Reichert, Hannes %A Hetzel, Manuel %A Doll, Konrad %A Sick, Bernhard %B International Conference on Control, Mechatronics and Automation (ICCMA) %D 2023 %I IEEE %P 171--176 %R 10.1109/ICCMA59762.2023.10374705 %T Height Change Feature Based Free Space Detection %X We present a novel method for free space detection in dynamic environments like factory sites, crucial for autonomous forklifts to avoid collisions. It introduces a technique for fast surface normal estimation using spherical projected LiDAR data, which helps in detecting free space efficiently and in real-time. The method's effectiveness is proven with a 50.90% mIoU score on the Semantic KITTI dataset at 105 Hz, and a 63.30% mIoU score on a factory site dataset at 54 Hz.
Graph Pooling Provably Improves Expressivity. Lachi, Veronica; Moallemy-Oureh, Alice; Roth, Andreas; Welke, Pascal. In Workshop on New Frontiers in Graph Learning, NeurIPS, bll 1–7. 2023.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
In the domain of graph neural networks (GNNs), pooling operators are fundamental to reduce the size of the graph by simplifying graph structures and vertex features. Recent advances have shown that well-designed pooling operators, coupled with message-passing layers, can endow hierarchical GNNs with an expressive power regarding the graph isomorphism test that is equal to the Weisfeiler-Leman test. However, the ability of hierarchical GNNs to increase expressive power by utilizing graph coarsening was not yet explored. This results in uncertainties about the benefits of pooling operators and a lack of sufficient properties to guide their design. In this work, we identify conditions for pooling operators to generate WL-distinguishable coarsened graphs from originally WL-indistinguishable but non-isomorphic graphs. Our conditions are versatile and can be tailored to specific tasks and data characteristics, offering a promising avenue for further research.
@inproceedings{lachi2023graph, abstract = {In the domain of graph neural networks (GNNs), pooling operators are fundamental to reduce the size of the graph by simplifying graph structures and vertex features. Recent advances have shown that well-designed pooling operators, coupled with message-passing layers, can endow hierarchical GNNs with an expressive power regarding the graph isomorphism test that is equal to the Weisfeiler-Leman test. However, the ability of hierarchical GNNs to increase expressive power by utilizing graph coarsening was not yet explored. This results in uncertainties about the benefits of pooling operators and a lack of sufficient properties to guide their design. In this work, we identify conditions for pooling operators to generate WL-distinguishable coarsened graphs from originally WL-indistinguishable but non-isomorphic graphs. Our conditions are versatile and can be tailored to specific tasks and data characteristics, offering a promising avenue for further research.}, author = {Lachi, Veronica and Moallemy-Oureh, Alice and Roth, Andreas and Welke, Pascal}, booktitle = {Workshop on New Frontiers in Graph Learning, NeurIPS}, keywords = {itegpub}, pages = {1–7}, title = {Graph Pooling Provably Improves Expressivity}, year = 2023 }
%0 Conference Paper %1 lachi2023graph %A Lachi, Veronica %A Moallemy-Oureh, Alice %A Roth, Andreas %A Welke, Pascal %B Workshop on New Frontiers in Graph Learning, NeurIPS %D 2023 %P 1--7 %T Graph Pooling Provably Improves Expressivity %U https://openreview.net/forum?id=lR5NYB9zrv %X In the domain of graph neural networks (GNNs), pooling operators are fundamental to reduce the size of the graph by simplifying graph structures and vertex features. Recent advances have shown that well-designed pooling operators, coupled with message-passing layers, can endow hierarchical GNNs with an expressive power regarding the graph isomorphism test that is equal to the Weisfeiler-Leman test. However, the ability of hierarchical GNNs to increase expressive power by utilizing graph coarsening was not yet explored. This results in uncertainties about the benefits of pooling operators and a lack of sufficient properties to guide their design. In this work, we identify conditions for pooling operators to generate WL-distinguishable coarsened graphs from originally WL-indistinguishable but non-isomorphic graphs. Our conditions are versatile and can be tailored to specific tasks and data characteristics, offering a promising avenue for further research.
Graph Neural Networks Designed for Different Graph Types: A Survey. Thomas, Josephine; Moallemy-Oureh, Alice; Beddar-Wiesing, Silvia; Holzhüter, Clara. In Transactions on Machine Learning Research. 2023.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Graphs are ubiquitous in nature and can therefore serve as models for many practical but also theoretical problems. For this purpose, they can be defined as many different types which suitably reflect the individual contexts of the represented problem. To address cutting-edge problems based on graph data, the research field of Graph Neural Networks (GNNs) has emerged. Despite the field’s youth and the speed at which new models are developed, many recent surveys have been published to keep track of them. Nevertheless, it has not yet been gathered which GNN can process what kind of graph types. In this survey, we give a detailed overview of already existing GNNs and, unlike previous surveys, categorize them according to their ability to handle different graph types and properties. We consider GNNs operating on static and dynamic graphs of different structural constitutions, with or without node or edge attributes. Moreover, we distinguish between GNN models for discrete-time or continuous-time dynamic graphs and group the models according to their architecture. We find that there are still graph types that are not or only rarely covered by existing GNN models. We point out where models are missing and give potential reasons for their absence.
@article{thomas2023graph, abstract = {Graphs are ubiquitous in nature and can therefore serve as models for many practical but also theoretical problems. For this purpose, they can be defined as many different types which suitably reflect the individual contexts of the represented problem. To address cutting-edge problems based on graph data, the research field of Graph Neural Networks (GNNs) has emerged. Despite the field’s youth and the speed at which new models are developed, many recent surveys have been published to keep track of them. Nevertheless, it has not yet been gathered which GNN can process what kind of graph types. In this survey, we give a detailed overview of already existing GNNs and, unlike previous surveys, categorize them according to their ability to handle different graph types and properties. We consider GNNs operating on static and dynamic graphs of different structural constitutions, with or without node or edge attributes. Moreover, we distinguish between GNN models for discrete-time or continuous-time dynamic graphs and group the models according to their architecture. We find that there are still graph types that are not or only rarely covered by existing GNN models. We point out where models are missing and give potential reasons for their absence.}, author = {Thomas, Josephine and Moallemy-Oureh, Alice and Beddar-Wiesing, Silvia and Holzhüter, Clara}, journal = {Transactions on Machine Learning Research}, keywords = {itegpub}, title = {Graph Neural Networks Designed for Different Graph Types: A Survey}, year = 2023 }
%0 Journal Article %1 thomas2023graph %A Thomas, Josephine %A Moallemy-Oureh, Alice %A Beddar-Wiesing, Silvia %A Holzhüter, Clara %D 2023 %J Transactions on Machine Learning Research %T Graph Neural Networks Designed for Different Graph Types: A Survey %U https://openreview.net/pdf?id=h4BYtZ79uy %X Graphs are ubiquitous in nature and can therefore serve as models for many practical but also theoretical problems. For this purpose, they can be defined as many different types which suitably reflect the individual contexts of the represented problem. To address cutting-edge problems based on graph data, the research field of Graph Neural Networks (GNNs) has emerged. Despite the field’s youth and the speed at which new models are developed, many recent surveys have been published to keep track of them. Nevertheless, it has not yet been gathered which GNN can process what kind of graph types. In this survey, we give a detailed overview of already existing GNNs and, unlike previous surveys, categorize them according to their ability to handle different graph types and properties. We consider GNNs operating on static and dynamic graphs of different structural constitutions, with or without node or edge attributes. Moreover, we distinguish between GNN models for discrete-time or continuous-time dynamic graphs and group the models according to their architecture. We find that there are still graph types that are not or only rarely covered by existing GNN models. We point out where models are missing and give potential reasons for their absence.
Exploring the Potential of Optimal Active Learning via a Non-myopic Oracle Policy. Sandrock, Christoph; Herde, Marek; Kottke, Daniel; Sick, Bernhard. In Discovery Science (DS), bll 265–276. Springer, 2023.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Active learning aims to reduce the amount of labeled data while maximizing machine learning models’ performances. Currently, there is sparse research on the potential of an optimal active learning strategy. Therefore, we propose a non-myopic oracle policy that accesses the true labels of the data pool to approximate an optimal active learning strategy. We evaluate how the hyperparameters of this oracle policy influence its performance and empirically demonstrate that it is an upper baseline for common active learning strategies while being faster than a state-of-the-art oracle policy. For the sake of reproducibility, all the code related to our research is publicly available on our GitHub repository at https://github.com/ies-research/non-myopic-oracle-policy.
@inproceedings{sandrock2023exploring, abstract = {Active learning aims to reduce the amount of labeled data while maximizing machine learning models’ performances. Currently, there is sparse research on the potential of an optimal active learning strategy. Therefore, we propose a non-myopic oracle policy that accesses the true labels of the data pool to approximate an optimal active learning strategy. We evaluate how the hyperparameters of this oracle policy influence its performance and empirically demonstrate that it is an upper baseline for common active learning strategies while being faster than a state-of-the-art oracle policy. For the sake of reproducibility, all the code related to our research is publicly available on our GitHub repository at https://github.com/ies-research/non-myopic-oracle-policy.}, author = {Sandrock, Christoph and Herde, Marek and Kottke, Daniel and Sick, Bernhard}, booktitle = {Discovery Science (DS)}, keywords = {itegpub}, pages = {265–276}, publisher = {Springer}, title = {Exploring the Potential of Optimal Active Learning via a Non-myopic Oracle Policy}, year = 2023 }
%0 Conference Paper %1 sandrock2023exploring %A Sandrock, Christoph %A Herde, Marek %A Kottke, Daniel %A Sick, Bernhard %B Discovery Science (DS) %D 2023 %I Springer %P 265--276 %R 10.1007/978-3-031-45275-8_18 %T Exploring the Potential of Optimal Active Learning via a Non-myopic Oracle Policy %U https://link.springer.com/chapter/10.1007/978-3-031-45275-8_18 %X Active learning aims to reduce the amount of labeled data while maximizing machine learning models’ performances. Currently, there is sparse research on the potential of an optimal active learning strategy. Therefore, we propose a non-myopic oracle policy that accesses the true labels of the data pool to approximate an optimal active learning strategy. We evaluate how the hyperparameters of this oracle policy influence its performance and empirically demonstrate that it is an upper baseline for common active learning strategies while being faster than a state-of-the-art oracle policy. For the sake of reproducibility, all the code related to our research is publicly available on our GitHub repository at https://github.com/ies-research/non-myopic-oracle-policy.
Domain Imaging in Periodic Submicron Wide Nanostructures by Digital Drift Correction in Kerr Microscopy. Akhundzada, Sapida; Dingel, Kristina; Bischof, David; Janzen, Christian; Sick, Bernhard; Ehresmann, Arno. In Advanced Photonics Research, 4(10), bl 2300170. Wiley, 2023.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Magneto-optical Kerr microscopy is a powerful method for imaging magnetic domains. Even though domain imaging below the diffractive resolution limit is possible, such investigations are getting increasingly complex with decreasing structure size due to the decreasing Kerr contrast. As magnetic domain images free of topographical artifacts are obtained by subtracting a reference image from the actual image, the corresponding challenges are additionally increased by unavoidable sample motion in the time interval between acquiring the two images. Software-based drift corrections typically rely on a unique structure in the image's region of interest (ROI), recognized automatically or selected manually by the user. By digital image shifting, the ROI positions in the actual and reference images are aligned, and the sample motion is compensated. For magnetic domain imaging in periodically arranged micro- or nano-objects, unique topographical features are not given, making the drift correction by ROIs difficult, often even impossible. Herein, a novel software-based approach is presented for drift corrections to image domains with features close/below the optical resolution limit and for investigating periodically arranged micro- or nano-objects without utilizing ROIs. High-contrast images are obtained, enabling the characterization of periodically arranged 1D, 2D, and 3D magnetic objects with lateral dimensions below 100 nm.
@article{akhundzada2023domain, abstract = {Magneto-optical Kerr microscopy is a powerful method for imaging magnetic domains. Even though domain imaging below the diffractive resolution limit is possible, such investigations are getting increasingly complex with decreasing structure size due to the decreasing Kerr contrast. As magnetic domain images free of topographical artifacts are obtained by subtracting a reference image from the actual image, the corresponding challenges are additionally increased by unavoidable sample motion in the time interval between acquiring the two images. Software-based drift corrections typically rely on a unique structure in the image's region of interest (ROI), recognized automatically or selected manually by the user. By digital image shifting, the ROI positions in the actual and reference images are aligned, and the sample motion is compensated. For magnetic domain imaging in periodically arranged micro- or nano-objects, unique topographical features are not given, making the drift correction by ROIs difficult, often even impossible. Herein, a novel software-based approach is presented for drift corrections to image domains with features close/below the optical resolution limit and for investigating periodically arranged micro- or nano-objects without utilizing ROIs. High-contrast images are obtained, enabling the characterization of periodically arranged 1D, 2D, and 3D magnetic objects with lateral dimensions below 100 nm.}, author = {Akhundzada, Sapida and Dingel, Kristina and Bischof, David and Janzen, Christian and Sick, Bernhard and Ehresmann, Arno}, journal = {Advanced Photonics Research}, keywords = {itegpub}, number = 10, pages = 2300170, publisher = {Wiley}, title = {Domain Imaging in Periodic Submicron Wide Nanostructures by Digital Drift Correction in Kerr Microscopy}, volume = 4, year = 2023 }
%0 Journal Article %1 akhundzada2023domain %A Akhundzada, Sapida %A Dingel, Kristina %A Bischof, David %A Janzen, Christian %A Sick, Bernhard %A Ehresmann, Arno %D 2023 %I Wiley %J Advanced Photonics Research %N 10 %P 2300170 %R https://doi.org/10.1002/adpr.202300170 %T Domain Imaging in Periodic Submicron Wide Nanostructures by Digital Drift Correction in Kerr Microscopy %U https://onlinelibrary.wiley.com/doi/abs/10.1002/adpr.20230017 %V 4 %X Magneto-optical Kerr microscopy is a powerful method for imaging magnetic domains. Even though domain imaging below the diffractive resolution limit is possible, such investigations are getting increasingly complex with decreasing structure size due to the decreasing Kerr contrast. As magnetic domain images free of topographical artifacts are obtained by subtracting a reference image from the actual image, the corresponding challenges are additionally increased by unavoidable sample motion in the time interval between acquiring the two images. Software-based drift corrections typically rely on a unique structure in the image's region of interest (ROI), recognized automatically or selected manually by the user. By digital image shifting, the ROI positions in the actual and reference images are aligned, and the sample motion is compensated. For magnetic domain imaging in periodically arranged micro- or nano-objects, unique topographical features are not given, making the drift correction by ROIs difficult, often even impossible. Herein, a novel software-based approach is presented for drift corrections to image domains with features close/below the optical resolution limit and for investigating periodically arranged micro- or nano-objects without utilizing ROIs. High-contrast images are obtained, enabling the characterization of periodically arranged 1D, 2D, and 3D magnetic objects with lateral dimensions below 100 nm.
Dataset of a parameterized U-bend flow for deep learning application. Decke, Jens; Wünsch, Olaf; Sick, Bernhard. In Data in Brief, 50(1), bl 109477. 2023.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
This dataset contains 10,000 fluid flow and heat transfer simulations in U-bend shapes. Each of them is described by 28 design parameters, which are processed with the help of Computational Fluid Dynamics methods. The dataset provides a comprehensive benchmark for investigating various problems and methods from the field of design optimization. For these investigations supervised, semi-supervised and unsupervised deep learning approaches can be employed. One unique feature of this dataset is that each shape can be represented by three distinct data types including design parameter and objective combinations, five different resolutions of 2D images from the geometry and the solution variables of the numerical simulation, as well as a representation using the cell values of the numerical mesh. This third representation enables considering the specific data structure of numerical simulations for deep learning approaches. The source code and the container used to generate the data are published as part of this work.
@article{decke2023dataset, abstract = {This dataset contains 10,000 fluid flow and heat transfer simulations in U-bend shapes. Each of them is described by 28 design parameters, which are processed with the help of Computational Fluid Dynamics methods. The dataset provides a comprehensive benchmark for investigating various problems and methods from the field of design optimization. For these investigations supervised, semi-supervised and unsupervised deep learning approaches can be employed. One unique feature of this dataset is that each shape can be represented by three distinct data types including design parameter and objective combinations, five different resolutions of 2D images from the geometry and the solution variables of the numerical simulation, as well as a representation using the cell values of the numerical mesh. This third representation enables considering the specific data structure of numerical simulations for deep learning approaches. The source code and the container used to generate the data are published as part of this work.}, author = {Decke, Jens and Wünsch, Olaf and Sick, Bernhard}, journal = {Data in Brief}, keywords = {MachineLearning}, number = 1, pages = 109477, title = {Dataset of a parameterized U-bend flow for deep learning application}, volume = 50, year = 2023 }
%0 Journal Article %1 decke2023dataset %A Decke, Jens %A Wünsch, Olaf %A Sick, Bernhard %D 2023 %J Data in Brief %N 1 %P 109477 %R https://doi.org/10.1016/j.dib.2023.109477 %T Dataset of a parameterized U-bend flow for deep learning application %U https://www.sciencedirect.com/science/article/pii/S2352340923005772 %V 50 %X This dataset contains 10,000 fluid flow and heat transfer simulations in U-bend shapes. Each of them is described by 28 design parameters, which are processed with the help of Computational Fluid Dynamics methods. The dataset provides a comprehensive benchmark for investigating various problems and methods from the field of design optimization. For these investigations supervised, semi-supervised and unsupervised deep learning approaches can be employed. One unique feature of this dataset is that each shape can be represented by three distinct data types including design parameter and objective combinations, five different resolutions of 2D images from the geometry and the solution variables of the numerical simulation, as well as a representation using the cell values of the numerical mesh. This third representation enables considering the specific data structure of numerical simulations for deep learning approaches. The source code and the container used to generate the data are published as part of this work.
DADO – Low-Cost Query Strategies for Deep Active Design Optimization. Decke, Jens; Gruhl, Christian; Rauch, Lukas; Sick, Bernhard. In International Conference on Machine Learning and Applications (ICMLA), bll 1611–1618. IEEE, 2023.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
In this work, we apply deep active learning to the field of design optimization to reduce the number of computationally expensive numerical simulations widely used in industry and engineering. We are interested in optimizing the design of structural components, where a set of parameters describes the shape. If we can predict the performance based on these parameters and consider only the promising candidates for simulation, there is an enormous potential for saving computing power. We present two query strategies for self-optimization to reduce the computational cost in multi-objective design optimization problems. Our proposed methodology provides an intuitive approach that is easy to apply, offers significant improvements over random sampling, and circumvents the need for uncertainty estimation. We evaluate our strategies on a large dataset from the domain of fluid dynamics and introduce two new evaluation metrics to determine the model's performance. Findings from our evaluation highlights the effectiveness of our query strategies in accelerating design optimization. Furthermore, the introduced method is easily transferable to other self-optimization problems in industry and engineering.
@inproceedings{decke2023dado, abstract = {In this work, we apply deep active learning to the field of design optimization to reduce the number of computationally expensive numerical simulations widely used in industry and engineering. We are interested in optimizing the design of structural components, where a set of parameters describes the shape. If we can predict the performance based on these parameters and consider only the promising candidates for simulation, there is an enormous potential for saving computing power. We present two query strategies for self-optimization to reduce the computational cost in multi-objective design optimization problems. Our proposed methodology provides an intuitive approach that is easy to apply, offers significant improvements over random sampling, and circumvents the need for uncertainty estimation. We evaluate our strategies on a large dataset from the domain of fluid dynamics and introduce two new evaluation metrics to determine the model's performance. Findings from our evaluation highlights the effectiveness of our query strategies in accelerating design optimization. Furthermore, the introduced method is easily transferable to other self-optimization problems in industry and engineering.}, author = {Decke, Jens and Gruhl, Christian and Rauch, Lukas and Sick, Bernhard}, booktitle = {International Conference on Machine Learning and Applications (ICMLA)}, keywords = {itegpub}, pages = {1611–1618}, publisher = {IEEE}, title = {DADO – Low-Cost Query Strategies for Deep Active Design Optimization}, year = 2023 }
%0 Conference Paper %1 decke2023dado %A Decke, Jens %A Gruhl, Christian %A Rauch, Lukas %A Sick, Bernhard %B International Conference on Machine Learning and Applications (ICMLA) %D 2023 %I IEEE %P 1611--1618 %R 10.1109/ICMLA58977.2023.00244 %T DADO – Low-Cost Query Strategies for Deep Active Design Optimization %X In this work, we apply deep active learning to the field of design optimization to reduce the number of computationally expensive numerical simulations widely used in industry and engineering. We are interested in optimizing the design of structural components, where a set of parameters describes the shape. If we can predict the performance based on these parameters and consider only the promising candidates for simulation, there is an enormous potential for saving computing power. We present two query strategies for self-optimization to reduce the computational cost in multi-objective design optimization problems. Our proposed methodology provides an intuitive approach that is easy to apply, offers significant improvements over random sampling, and circumvents the need for uncertainty estimation. We evaluate our strategies on a large dataset from the domain of fluid dynamics and introduce two new evaluation metrics to determine the model's performance. Findings from our evaluation highlights the effectiveness of our query strategies in accelerating design optimization. Furthermore, the introduced method is easily transferable to other self-optimization problems in industry and engineering.
Corner Cases in Machine Learning Processes. Heidecker, Florian; Bieshaar, Maarten; Sick, Bernhard. In AI Perspectives & Advances, 6(1), bll 1–17. 2023.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Applications using machine learning (ML), such as highly autonomous driving, depend highly on the performance of the ML model. The data amount and quality used for model training and validation are crucial. If the model cannot detect and interpret a new, rare, or perhaps dangerous situation, often referred to as a corner case, we will likely blame the data for not being good enough or too small in number. However, the implemented ML model and its associated architecture also influence the behavior. Therefore, the occurrence of prediction errors resulting from the ML model itself is not surprising. This work addresses a corner case definition from an ML model's perspective to determine which aspects must be considered. To achieve this goal, we present an overview of properties for corner cases that are beneficial for the description, explanation, reproduction, or synthetic generation of corner cases. To define ML corner cases, we review different considerations in the literature and summarize them in a general description and mathematical formulation, whereby the expected relevance-weighted loss is the key to distinguishing corner cases from common data. Moreover, we show how to operationalize the corner case characteristics to determine the value of a corner case. To conclude, we present the extended taxonomy for ML corner cases by adding the input, model, and deployment levels, considering the influence of the corner case properties.
@article{heidecker2023corner, abstract = {Applications using machine learning (ML), such as highly autonomous driving, depend highly on the performance of the ML model. The data amount and quality used for model training and validation are crucial. If the model cannot detect and interpret a new, rare, or perhaps dangerous situation, often referred to as a corner case, we will likely blame the data for not being good enough or too small in number. However, the implemented ML model and its associated architecture also influence the behavior. Therefore, the occurrence of prediction errors resulting from the ML model itself is not surprising. This work addresses a corner case definition from an ML model's perspective to determine which aspects must be considered. To achieve this goal, we present an overview of properties for corner cases that are beneficial for the description, explanation, reproduction, or synthetic generation of corner cases. To define ML corner cases, we review different considerations in the literature and summarize them in a general description and mathematical formulation, whereby the expected relevance-weighted loss is the key to distinguishing corner cases from common data. Moreover, we show how to operationalize the corner case characteristics to determine the value of a corner case. To conclude, we present the extended taxonomy for ML corner cases by adding the input, model, and deployment levels, considering the influence of the corner case properties.}, author = {Heidecker, Florian and Bieshaar, Maarten and Sick, Bernhard}, journal = {AI Perspectives & Advances}, keywords = {itegpub}, number = 1, pages = {1–17}, title = {Corner Cases in Machine Learning Processes}, volume = 6, year = 2023 }
%0 Journal Article %1 heidecker2023corner %A Heidecker, Florian %A Bieshaar, Maarten %A Sick, Bernhard %D 2023 %J AI Perspectives & Advances %N 1 %P 1--17 %R 10.1186/s42467-023-00015-y %T Corner Cases in Machine Learning Processes %U https://aiperspectives.springeropen.com/articles/10.1186/s42467-023-00015-y %V 6 %X Applications using machine learning (ML), such as highly autonomous driving, depend highly on the performance of the ML model. The data amount and quality used for model training and validation are crucial. If the model cannot detect and interpret a new, rare, or perhaps dangerous situation, often referred to as a corner case, we will likely blame the data for not being good enough or too small in number. However, the implemented ML model and its associated architecture also influence the behavior. Therefore, the occurrence of prediction errors resulting from the ML model itself is not surprising. This work addresses a corner case definition from an ML model's perspective to determine which aspects must be considered. To achieve this goal, we present an overview of properties for corner cases that are beneficial for the description, explanation, reproduction, or synthetic generation of corner cases. To define ML corner cases, we review different considerations in the literature and summarize them in a general description and mathematical formulation, whereby the expected relevance-weighted loss is the key to distinguishing corner cases from common data. Moreover, we show how to operationalize the corner case characteristics to determine the value of a corner case. To conclude, we present the extended taxonomy for ML corner cases by adding the input, model, and deployment levels, considering the influence of the corner case properties.
Continuous Feature Networks: A Novel Method to Process Irregularly and Inconsistently Sampled Data With Position-Dependent Features. Magnussen, Birk Martin; Stern, Claudius; Sick, Bernhard. In International Journal On Advances in Intelligent Systems, 16(3&4), bll 43–50. ThinkMind, 2023.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Continuous Kernels have been a recent development in convolutional neural networks. Such kernels are used to process data sampled at different resolutions as well as irregularly and inconsistently sampled data. Convolutional neural networks have the property of translational invariance (e.g., features are detected regardless of their position in the measurement domain), which is unsuitable if the position of detected features is relevant for the prediction task. However, the capabilities of continuous kernels to process irregularly sampled data are still desired. This article introduces the continuous feature network, a novel method utilizing continuous kernels, for detecting global features at absolute positions in the data domain. Through a use case in processing multiple spatially resolved reflection spectroscopy data, which is sampled irregularly and inconsistently, we show that the proposed method is capable of processing such data directly without additional preprocessing or augmentation as is needed using comparable methods. In addition, we show that the proposed method is able to achieve a higher prediction accuracy than a comparable network on a dataset with position-dependent features. Furthermore, a higher robustness to missing data compared to a benchmark network using data interpolation is observed, which allows the network to adapt to sensors with a failure of individual light emitters or detectors without the need for retraining. The article shows how these capabilities stem from the continuous kernels used and how the number of available kernels to be trained affects the model. Finally, the article proposes a method to utilize the introduced method as a base for an interpretable model usable for explainable AI.
@article{magnussen2023continuous, abstract = {Continuous Kernels have been a recent development in convolutional neural networks. Such kernels are used to process data sampled at different resolutions as well as irregularly and inconsistently sampled data. Convolutional neural networks have the property of translational invariance (e.g., features are detected regardless of their position in the measurement domain), which is unsuitable if the position of detected features is relevant for the prediction task. However, the capabilities of continuous kernels to process irregularly sampled data are still desired. This article introduces the continuous feature network, a novel method utilizing continuous kernels, for detecting global features at absolute positions in the data domain. Through a use case in processing multiple spatially resolved reflection spectroscopy data, which is sampled irregularly and inconsistently, we show that the proposed method is capable of processing such data directly without additional preprocessing or augmentation as is needed using comparable methods. In addition, we show that the proposed method is able to achieve a higher prediction accuracy than a comparable network on a dataset with position-dependent features. Furthermore, a higher robustness to missing data compared to a benchmark network using data interpolation is observed, which allows the network to adapt to sensors with a failure of individual light emitters or detectors without the need for retraining. The article shows how these capabilities stem from the continuous kernels used and how the number of available kernels to be trained affects the model. Finally, the article proposes a method to utilize the introduced method as a base for an interpretable model usable for explainable AI.}, author = {Magnussen, Birk Martin and Stern, Claudius and Sick, Bernhard}, journal = {International Journal On Advances in Intelligent Systems}, keywords = {itegpub}, number = {3&4}, pages = {43–50}, publisher = {ThinkMind}, title = {Continuous Feature Networks: A Novel Method to Process Irregularly and Inconsistently Sampled Data With Position-Dependent Features}, volume = 16, year = 2023 }
%0 Journal Article %1 magnussen2023continuous %A Magnussen, Birk Martin %A Stern, Claudius %A Sick, Bernhard %D 2023 %I ThinkMind %J International Journal On Advances in Intelligent Systems %N 3&4 %P 43--50 %T Continuous Feature Networks: A Novel Method to Process Irregularly and Inconsistently Sampled Data With Position-Dependent Features %U http://www.thinkmind.org/index.php?view=article&articleid=intsys_v16_n34_2023_3 %V 16 %X Continuous Kernels have been a recent development in convolutional neural networks. Such kernels are used to process data sampled at different resolutions as well as irregularly and inconsistently sampled data. Convolutional neural networks have the property of translational invariance (e.g., features are detected regardless of their position in the measurement domain), which is unsuitable if the position of detected features is relevant for the prediction task. However, the capabilities of continuous kernels to process irregularly sampled data are still desired. This article introduces the continuous feature network, a novel method utilizing continuous kernels, for detecting global features at absolute positions in the data domain. Through a use case in processing multiple spatially resolved reflection spectroscopy data, which is sampled irregularly and inconsistently, we show that the proposed method is capable of processing such data directly without additional preprocessing or augmentation as is needed using comparable methods. In addition, we show that the proposed method is able to achieve a higher prediction accuracy than a comparable network on a dataset with position-dependent features. Furthermore, a higher robustness to missing data compared to a benchmark network using data interpolation is observed, which allows the network to adapt to sensors with a failure of individual light emitters or detectors without the need for retraining. The article shows how these capabilities stem from the continuous kernels used and how the number of available kernels to be trained affects the model. Finally, the article proposes a method to utilize the introduced method as a base for an interpretable model usable for explainable AI.
Context-aware recommendations for extended electric vehicle battery lifetime. Eider, Markus; Sick, Bernhard; Berl, Andreas. In Sustainable Computing: Informatics and Systems (SUSCOM), 37, bl 100845. Elsevier, 2023.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
Electric vehicles are a means of reducing CO2 emissions in transportation. However, the sustainability of electric vehicle batteries is affected by battery health degradation, which decreases their overall lifetime. This results in a substantial amount of depleted batteries due to replacements. Users have a major impact on battery health degradation through their actions while handling electric vehicles, such as the use of fast charging. To mitigate this problem, this article presents a methodology to generate user guidance for batteryfriendly actions in the upcoming use. Therefore, we first identify general recommendations from related work and combine them with the vehicle context in order to define context-aware recommendations in the form of if–then rules. These context-aware recommendations are then used to generate user advice. Second, the article covers how to predict the vehicle context in order to determine necessary recommendations. Third, a prescriptive recommendation system architecture is proposed, which takes vehicle context information, and produces user guidance. Finally, we test the proposed architecture using fuzzy logic as decision system. Overall, the architecture provides satisfactory user advice
@article{eider2023context, abstract = {Electric vehicles are a means of reducing CO2 emissions in transportation. However, the sustainability of electric vehicle batteries is affected by battery health degradation, which decreases their overall lifetime. This results in a substantial amount of depleted batteries due to replacements. Users have a major impact on battery health degradation through their actions while handling electric vehicles, such as the use of fast charging. To mitigate this problem, this article presents a methodology to generate user guidance for batteryfriendly actions in the upcoming use. Therefore, we first identify general recommendations from related work and combine them with the vehicle context in order to define context-aware recommendations in the form of if–then rules. These context-aware recommendations are then used to generate user advice. Second, the article covers how to predict the vehicle context in order to determine necessary recommendations. Third, a prescriptive recommendation system architecture is proposed, which takes vehicle context information, and produces user guidance. Finally, we test the proposed architecture using fuzzy logic as decision system. Overall, the architecture provides satisfactory user advice}, author = {Eider, Markus and Sick, Bernhard and Berl, Andreas}, journal = {Sustainable Computing: Informatics and Systems (SUSCOM)}, keywords = {itegpub}, pages = 100845, publisher = {Elsevier}, title = {Context-aware recommendations for extended electric vehicle battery lifetime}, volume = 37, year = 2023 }
%0 Journal Article %1 eider2023context %A Eider, Markus %A Sick, Bernhard %A Berl, Andreas %D 2023 %I Elsevier %J Sustainable Computing: Informatics and Systems (SUSCOM) %P 100845 %R 10.1016/j.suscom.2022.100845 %T Context-aware recommendations for extended electric vehicle battery lifetime %V 37 %X Electric vehicles are a means of reducing CO2 emissions in transportation. However, the sustainability of electric vehicle batteries is affected by battery health degradation, which decreases their overall lifetime. This results in a substantial amount of depleted batteries due to replacements. Users have a major impact on battery health degradation through their actions while handling electric vehicles, such as the use of fast charging. To mitigate this problem, this article presents a methodology to generate user guidance for batteryfriendly actions in the upcoming use. Therefore, we first identify general recommendations from related work and combine them with the vehicle context in order to define context-aware recommendations in the form of if–then rules. These context-aware recommendations are then used to generate user advice. Second, the article covers how to predict the vehicle context in order to determine necessary recommendations. Third, a prescriptive recommendation system architecture is proposed, which takes vehicle context information, and produces user guidance. Finally, we test the proposed architecture using fuzzy logic as decision system. Overall, the architecture provides satisfactory user advice
Context Information for Corner Case Detection in Highly Automated Driving. Heidecker, Florian; Susetzky, Tobias; Fuchs, Erich; Sick, Bernhard. In IEEE International Conference on Intelligent Transportation Systems (ITSC), bll 1522–1529. IEEE, 2023.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
Context information provided along with a dataset can be very helpful for solving a problem because the additional knowledge is already available and does not need to be extracted. Moreover, the context indicates how diverse a dataset is, i.e., how many samples per context category are available to train and test machine learning (ML) models. In this article, we present context annotations for the BDD100k image dataset. The annotations comprise, for instance, information about daytime, road condition (dry/wet), and dirt on the windshield. Sometimes, no or only little data are available for unique or rare combinations of these context attributes. However, data that matches these context conditions is crucial when discussing corner cases: Firstly, most ML models, e.g., object detectors, are not trained on such data, which leads to the assumption that they will perform poorly in those situations. Secondly, data containing corner cases are required for validating ML models. With this in mind, separate ML models dedicated to context detection are useful for expanding the training set with additional data of special interest, such as corner cases.
@inproceedings{heidecker2023context, abstract = {Context information provided along with a dataset can be very helpful for solving a problem because the additional knowledge is already available and does not need to be extracted. Moreover, the context indicates how diverse a dataset is, i.e., how many samples per context category are available to train and test machine learning (ML) models. In this article, we present context annotations for the BDD100k image dataset. The annotations comprise, for instance, information about daytime, road condition (dry/wet), and dirt on the windshield. Sometimes, no or only little data are available for unique or rare combinations of these context attributes. However, data that matches these context conditions is crucial when discussing corner cases: Firstly, most ML models, e.g., object detectors, are not trained on such data, which leads to the assumption that they will perform poorly in those situations. Secondly, data containing corner cases are required for validating ML models. With this in mind, separate ML models dedicated to context detection are useful for expanding the training set with additional data of special interest, such as corner cases.}, author = {Heidecker, Florian and Susetzky, Tobias and Fuchs, Erich and Sick, Bernhard}, booktitle = {IEEE International Conference on Intelligent Transportation Systems (ITSC)}, keywords = {itegpub}, pages = {1522–1529}, publisher = {IEEE}, title = {Context Information for Corner Case Detection in Highly Automated Driving}, year = 2023 }
%0 Conference Paper %1 heidecker2023context %A Heidecker, Florian %A Susetzky, Tobias %A Fuchs, Erich %A Sick, Bernhard %B IEEE International Conference on Intelligent Transportation Systems (ITSC) %D 2023 %I IEEE %P 1522--1529 %R 10.1109/ITSC57777.2023.10422414 %T Context Information for Corner Case Detection in Highly Automated Driving %X Context information provided along with a dataset can be very helpful for solving a problem because the additional knowledge is already available and does not need to be extracted. Moreover, the context indicates how diverse a dataset is, i.e., how many samples per context category are available to train and test machine learning (ML) models. In this article, we present context annotations for the BDD100k image dataset. The annotations comprise, for instance, information about daytime, road condition (dry/wet), and dirt on the windshield. Sometimes, no or only little data are available for unique or rare combinations of these context attributes. However, data that matches these context conditions is crucial when discussing corner cases: Firstly, most ML models, e.g., object detectors, are not trained on such data, which leads to the assumption that they will perform poorly in those situations. Secondly, data containing corner cases are required for validating ML models. With this in mind, separate ML models dedicated to context detection are useful for expanding the training set with additional data of special interest, such as corner cases.
An Examination of Organic Computing Strategies in Design Optimization. Decke, Jens. In Organic Computing -- Doctoral Dissertation Colloquium 2023, S. Tomforde, C. Krupitzer (reds.), bll 41–54. kassel university press, 2023.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
In the field of design optimization, numerical equation solvers, commonly used for finite element analysis and computational fluid dy- namics, impose significant computational demands. The iterative nature of design optimization, involving numerous simulations, magnifies re- source requirements in terms of time, energy, costs, and greenhouse gas emissions. Accelerating this process has been a long-standing research challenge, driven by the potential for resource savings and the ability to tackle increasingly complex problems. Recently, organic computing methods have gained prominence as promising approaches to address this challenge. This study aims to bridge the gap by integrating tech- niques from deep learning, active learning, and generative learning into the field of design optimization. The goal is to accelerate the design op- timization process while addressing specific challenges such as exploring large and complex design spaces and evaluating the advantages and con- straints of these methods. This research has the potential to significantly impact the industrial use of design optimization by providing faster and more efficient tools.
@incollection{decke2023examination, abstract = {In the field of design optimization, numerical equation solvers, commonly used for finite element analysis and computational fluid dy- namics, impose significant computational demands. The iterative nature of design optimization, involving numerous simulations, magnifies re- source requirements in terms of time, energy, costs, and greenhouse gas emissions. Accelerating this process has been a long-standing research challenge, driven by the potential for resource savings and the ability to tackle increasingly complex problems. Recently, organic computing methods have gained prominence as promising approaches to address this challenge. This study aims to bridge the gap by integrating tech- niques from deep learning, active learning, and generative learning into the field of design optimization. The goal is to accelerate the design op- timization process while addressing specific challenges such as exploring large and complex design spaces and evaluating the advantages and con- straints of these methods. This research has the potential to significantly impact the industrial use of design optimization by providing faster and more efficient tools.}, author = {Decke, Jens}, booktitle = {Organic Computing – Doctoral Dissertation Colloquium 2023}, editor = {Tomforde, Sven and Krupitzer, Christian}, keywords = {itegpub}, pages = {41–54}, publisher = {kassel university press}, title = {An Examination of Organic Computing Strategies in Design Optimization}, year = 2023 }
%0 Book Section %1 decke2023examination %A Decke, Jens %B Organic Computing -- Doctoral Dissertation Colloquium 2023 %D 2023 %E Tomforde, Sven %E Krupitzer, Christian %I kassel university press %P 41--54 %T An Examination of Organic Computing Strategies in Design Optimization %X In the field of design optimization, numerical equation solvers, commonly used for finite element analysis and computational fluid dy- namics, impose significant computational demands. The iterative nature of design optimization, involving numerous simulations, magnifies re- source requirements in terms of time, energy, costs, and greenhouse gas emissions. Accelerating this process has been a long-standing research challenge, driven by the potential for resource savings and the ability to tackle increasingly complex problems. Recently, organic computing methods have gained prominence as promising approaches to address this challenge. This study aims to bridge the gap by integrating tech- niques from deep learning, active learning, and generative learning into the field of design optimization. The goal is to accelerate the design op- timization process while addressing specific challenges such as exploring large and complex design spaces and evaluating the advantages and con- straints of these methods. This research has the potential to significantly impact the industrial use of design optimization by providing faster and more efficient tools.
ActiveGLAE: A Benchmark for Deep Active Learning with Transformers. Rauch, Lukas; Aßenmacher, Matthias; Huseljic, Denis; Wirth, Moritz; Bischl, Bernd; Sick, Bernhard. In European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECMLPKDD), bll 55–74. Springer, 2023.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Deep active learning (DAL) seeks to reduce annotation costs by enabling the model to actively query instance annotations from which it expects to learn the most. Despite extensive research, there is cur- rently no standardized evaluation protocol for transformer-based lan- guage models in the field of DAL. Diverse experimental settings lead to difficulties in comparing research and deriving recommendations for prac- titioners. To tackle this challenge, we propose the ActiveGLAE bench- mark, a comprehensive collection of data sets and evaluation guidelines for assessing DAL. Our benchmark aims to facilitate and streamline the evaluation process of novel DAL strategies. Additionally, we provide an extensive overview of current practice in DAL with transformer-based language models. We identify three key challenges - data set selection, model training, and DAL settings - that pose difficulties in comparing query strategies. We establish baseline results through an extensive set of experiments as a reference point for evaluating future work. Based on our findings, we provide guidelines for researchers and practitioners.
@inproceedings{rauch2023activeglae, abstract = {Deep active learning (DAL) seeks to reduce annotation costs by enabling the model to actively query instance annotations from which it expects to learn the most. Despite extensive research, there is cur- rently no standardized evaluation protocol for transformer-based lan- guage models in the field of DAL. Diverse experimental settings lead to difficulties in comparing research and deriving recommendations for prac- titioners. To tackle this challenge, we propose the ActiveGLAE bench- mark, a comprehensive collection of data sets and evaluation guidelines for assessing DAL. Our benchmark aims to facilitate and streamline the evaluation process of novel DAL strategies. Additionally, we provide an extensive overview of current practice in DAL with transformer-based language models. We identify three key challenges - data set selection, model training, and DAL settings - that pose difficulties in comparing query strategies. We establish baseline results through an extensive set of experiments as a reference point for evaluating future work. Based on our findings, we provide guidelines for researchers and practitioners.}, author = {Rauch, Lukas and Aßenmacher, Matthias and Huseljic, Denis and Wirth, Moritz and Bischl, Bernd and Sick, Bernhard}, booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECMLPKDD)}, keywords = {itegpub}, pages = {55–74}, publisher = {Springer}, title = {ActiveGLAE: A Benchmark for Deep Active Learning with Transformers}, year = 2023 }
%0 Conference Paper %1 rauch2023activeglae %A Rauch, Lukas %A Aßenmacher, Matthias %A Huseljic, Denis %A Wirth, Moritz %A Bischl, Bernd %A Sick, Bernhard %B European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECMLPKDD) %D 2023 %I Springer %P 55--74 %R 10.1007/978-3-031-43412-9_4 %T ActiveGLAE: A Benchmark for Deep Active Learning with Transformers %U https://link.springer.com/chapter/10.1007/978-3-031-43412-9_4 %X Deep active learning (DAL) seeks to reduce annotation costs by enabling the model to actively query instance annotations from which it expects to learn the most. Despite extensive research, there is cur- rently no standardized evaluation protocol for transformer-based lan- guage models in the field of DAL. Diverse experimental settings lead to difficulties in comparing research and deriving recommendations for prac- titioners. To tackle this challenge, we propose the ActiveGLAE bench- mark, a comprehensive collection of data sets and evaluation guidelines for assessing DAL. Our benchmark aims to facilitate and streamline the evaluation process of novel DAL strategies. Additionally, we provide an extensive overview of current practice in DAL with transformer-based language models. We identify three key challenges - data set selection, model training, and DAL settings - that pose difficulties in comparing query strategies. We establish baseline results through an extensive set of experiments as a reference point for evaluating future work. Based on our findings, we provide guidelines for researchers and practitioners.
Active Learning with Fast Model Updates and Class-Balanced Selection for Imbalanced Datasets. Huang, Zhixin; He, Yujiang; Herde, Marek; Huseljic, Denis; Sick, Bernhard. In Workshop on Interactive Adapative Learning (IAL), ECML PKDD, bll 28–45. 2023.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Active learning strategies aim to minimize the number of queried samples for model training. However, two challenges in pool-based deep active learning on imbalanced datasets are observed in experiments: (1) the declining performance of active learning strategies due to imbalanced class distribution; (2)~the lack of sample diversity in acquisition batches due to the absence of timely model updates. This paper proposes the AL-FaMoUS, a general solution combining fast model updates and class-balanced minibatch selection to the active learning process. Furthermore, a simplification of the AL-FaMoUS, which selects one single sample in each acquisition minibatch, is experimentally evaluated on four image and three time-series imbalanced datasets. The results demonstrate that the implemented AL-FaMoUS outperforms the other adopted AL strategies, including uncertainty sampling and BALD solely combined with either the fast model update or the class balance selection strategy, in terms of accuracy and Macro F1 score.
@inproceedings{huang2023active, abstract = {Active learning strategies aim to minimize the number of queried samples for model training. However, two challenges in pool-based deep active learning on imbalanced datasets are observed in experiments: (1) the declining performance of active learning strategies due to imbalanced class distribution; (2) the lack of sample diversity in acquisition batches due to the absence of timely model updates. This paper proposes the AL-FaMoUS, a general solution combining fast model updates and class-balanced minibatch selection to the active learning process. Furthermore, a simplification of the AL-FaMoUS, which selects one single sample in each acquisition minibatch, is experimentally evaluated on four image and three time-series imbalanced datasets. The results demonstrate that the implemented AL-FaMoUS outperforms the other adopted AL strategies, including uncertainty sampling and BALD solely combined with either the fast model update or the class balance selection strategy, in terms of accuracy and Macro F1 score.}, author = {Huang, Zhixin and He, Yujiang and Herde, Marek and Huseljic, Denis and Sick, Bernhard}, booktitle = {Workshop on Interactive Adapative Learning (IAL), ECML PKDD}, keywords = {itegpub}, pages = {28–45}, title = {Active Learning with Fast Model Updates and Class-Balanced Selection for Imbalanced Datasets}, year = 2023 }
%0 Conference Paper %1 huang2023active %A Huang, Zhixin %A He, Yujiang %A Herde, Marek %A Huseljic, Denis %A Sick, Bernhard %B Workshop on Interactive Adapative Learning (IAL), ECML PKDD %D 2023 %P 28--45 %T Active Learning with Fast Model Updates and Class-Balanced Selection for Imbalanced Datasets %U https://ceur-ws.org/Vol-3470/paper5.pdf %X Active learning strategies aim to minimize the number of queried samples for model training. However, two challenges in pool-based deep active learning on imbalanced datasets are observed in experiments: (1) the declining performance of active learning strategies due to imbalanced class distribution; (2)~the lack of sample diversity in acquisition batches due to the absence of timely model updates. This paper proposes the AL-FaMoUS, a general solution combining fast model updates and class-balanced minibatch selection to the active learning process. Furthermore, a simplification of the AL-FaMoUS, which selects one single sample in each acquisition minibatch, is experimentally evaluated on four image and three time-series imbalanced datasets. The results demonstrate that the implemented AL-FaMoUS outperforms the other adopted AL strategies, including uncertainty sampling and BALD solely combined with either the fast model update or the class balance selection strategy, in terms of accuracy and Macro F1 score.
Active Label Refinement for Semantic Segmentation of Satellite Images. Pham, Minh Tuan; Wijesingha, Jayan; Kottke, Daniel; Herde, Marek; Huseljic, Denis; Sick, Bernhard; Wachendorf, Michael; Esch, Thomas. In arXiv e-prints, bl arXiv:2309.06159. 2023.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Remote sensing through semantic segmentation of satellite images contributes to the understanding and utilisation of the earth's surface. For this purpose, semantic segmentation networks are typically trained on large sets of labelled satellite images. However, obtaining expert labels for these images is costly. Therefore, we propose to rely on a low-cost approach, e.g. crowdsourcing or pretrained networks, to label the images in the first step. Since these initial labels are partially erroneous, we use active learning strategies to cost-efficiently refine the labels in the second step. We evaluate the active learning strategies using satellite images of Bengaluru in India, labelled with land cover and land use labels. Our experimental results suggest that an active label refinement to improve the semantic segmentation network's performance is beneficial.
@article{pham2023active, abstract = {Remote sensing through semantic segmentation of satellite images contributes to the understanding and utilisation of the earth's surface. For this purpose, semantic segmentation networks are typically trained on large sets of labelled satellite images. However, obtaining expert labels for these images is costly. Therefore, we propose to rely on a low-cost approach, e.g. crowdsourcing or pretrained networks, to label the images in the first step. Since these initial labels are partially erroneous, we use active learning strategies to cost-efficiently refine the labels in the second step. We evaluate the active learning strategies using satellite images of Bengaluru in India, labelled with land cover and land use labels. Our experimental results suggest that an active label refinement to improve the semantic segmentation network's performance is beneficial.}, author = {Pham, Minh Tuan and Wijesingha, Jayan and Kottke, Daniel and Herde, Marek and Huseljic, Denis and Sick, Bernhard and Wachendorf, Michael and Esch, Thomas}, journal = {arXiv e-prints}, keywords = {itegpub}, pages = {arXiv:2309.06159}, title = {Active Label Refinement for Semantic Segmentation of Satellite Images}, year = 2023 }
%0 Journal Article %1 pham2023active %A Pham, Minh Tuan %A Wijesingha, Jayan %A Kottke, Daniel %A Herde, Marek %A Huseljic, Denis %A Sick, Bernhard %A Wachendorf, Michael %A Esch, Thomas %D 2023 %J arXiv e-prints %P arXiv:2309.06159 %T Active Label Refinement for Semantic Segmentation of Satellite Images %U https://arxiv.org/abs/2309.06159 %X Remote sensing through semantic segmentation of satellite images contributes to the understanding and utilisation of the earth's surface. For this purpose, semantic segmentation networks are typically trained on large sets of labelled satellite images. However, obtaining expert labels for these images is costly. Therefore, we propose to rely on a low-cost approach, e.g. crowdsourcing or pretrained networks, to label the images in the first step. Since these initial labels are partially erroneous, we use active learning strategies to cost-efficiently refine the labels in the second step. We evaluate the active learning strategies using satellite images of Bengaluru in India, labelled with land cover and land use labels. Our experimental results suggest that an active label refinement to improve the semantic segmentation network's performance is beneficial.
Active Bird2Vec: Towards End-To-End Bird Sound Monitoring with Transformers. Rauch, Lukas; Schwinger, Raphael; Wirth, Moritz; Sick, Bernhard; Tomforde, Sven; Scholz, Christoph. In Workshop on Artificial Intelligence for Sustainability (AI4S), ECAI, bll 1–6. 2023.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
We propose a shift towards end-to-end learning in bird sound monitoring by combining self-supervised (SSL) and deep active learning (DAL). Leveraging transformer models, we aim to bypass traditional spectrogram conversions, enabling direct raw audio processing. ACTIVE BIRD2VEC is set to generate high-quality bird sound representations through SSL, potentially accelerating the assessment of environmental changes and decision-making processes for wind farms. Additionally, we seek to utilize the wide variety of bird vocalizations through DAL, reducing the reliance on extensively labeled datasets by human experts. We plan to curate a comprehensive set of tasks through Huggingface Datasets, enhancing future comparability and reproducibility of bioacoustic research. A comparative analysis between various transformer models will be conducted to evaluate their proficiency in bird sound recognition tasks. We aim to accelerate the progression of avian bioacoustic research and contribute to more effective conservation strategies.
@inproceedings{rauch2023active, abstract = {We propose a shift towards end-to-end learning in bird sound monitoring by combining self-supervised (SSL) and deep active learning (DAL). Leveraging transformer models, we aim to bypass traditional spectrogram conversions, enabling direct raw audio processing. ACTIVE BIRD2VEC is set to generate high-quality bird sound representations through SSL, potentially accelerating the assessment of environmental changes and decision-making processes for wind farms. Additionally, we seek to utilize the wide variety of bird vocalizations through DAL, reducing the reliance on extensively labeled datasets by human experts. We plan to curate a comprehensive set of tasks through Huggingface Datasets, enhancing future comparability and reproducibility of bioacoustic research. A comparative analysis between various transformer models will be conducted to evaluate their proficiency in bird sound recognition tasks. We aim to accelerate the progression of avian bioacoustic research and contribute to more effective conservation strategies.}, author = {Rauch, Lukas and Schwinger, Raphael and Wirth, Moritz and Sick, Bernhard and Tomforde, Sven and Scholz, Christoph}, booktitle = {Workshop on Artificial Intelligence for Sustainability (AI4S), ECAI}, keywords = {itegpub}, pages = {1–6}, title = {Active Bird2Vec: Towards End-To-End Bird Sound Monitoring with Transformers}, year = 2023 }
%0 Conference Paper %1 rauch2023active %A Rauch, Lukas %A Schwinger, Raphael %A Wirth, Moritz %A Sick, Bernhard %A Tomforde, Sven %A Scholz, Christoph %B Workshop on Artificial Intelligence for Sustainability (AI4S), ECAI %D 2023 %P 1--6 %T Active Bird2Vec: Towards End-To-End Bird Sound Monitoring with Transformers %U https://arxiv.org/abs/2308.07121 %X We propose a shift towards end-to-end learning in bird sound monitoring by combining self-supervised (SSL) and deep active learning (DAL). Leveraging transformer models, we aim to bypass traditional spectrogram conversions, enabling direct raw audio processing. ACTIVE BIRD2VEC is set to generate high-quality bird sound representations through SSL, potentially accelerating the assessment of environmental changes and decision-making processes for wind farms. Additionally, we seek to utilize the wide variety of bird vocalizations through DAL, reducing the reliance on extensively labeled datasets by human experts. We plan to curate a comprehensive set of tasks through Huggingface Datasets, enhancing future comparability and reproducibility of bioacoustic research. A comparative analysis between various transformer models will be conducted to evaluate their proficiency in bird sound recognition tasks. We aim to accelerate the progression of avian bioacoustic research and contribute to more effective conservation strategies.

2022[ to top ]

Weisfeiler-Lehman goes Dynamic: An Analysis of the Expressive Power of Graph Neural Networks for Attributed and Dynamic Graphs. Beddar-Wiesing, Silvia; D’Inverno, Giuseppe Alessio; Graziani, Caterina; Lachi, Veronica; Moallemy-Oureh, Alice; Scarselli, Franco; Thomas, Josephine. In arXiv e-prints, bl arXiv:2210.03990. 2022.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Graph Neural Networks (GNNs) are a large class of relational models for graph processing. Recent theoretical studies on the expressive power of GNNs have focused on two issues. On the one hand, it has been proven that GNNs are as powerful as the Weisfeiler-Lehman test (1-WL) in their ability to distinguish graphs. Moreover, it has been shown that the equivalence enforced by 1-WL equals unfolding equivalence. On the other hand, GNNs turned out to be universal approximators on graphs modulo the constraints enforced by 1-WL/unfolding equivalence. However, these results only apply to Static Undirected Homogeneous Graphs with node attributes. In contrast, real-life applications often involve a variety of graph properties, such as, e.g., dynamics or node and edge attributes. In this paper, we conduct a theoretical analysis of the expressive power of GNNs for these two graph types that are particularly of interest. Dynamic graphs are widely used in modern applications, and its theoretical analysis requires new approaches. The attributed type acts as a standard form for all graph types since it has been shown that all graph types can be transformed without loss to Static Undirected Homogeneous Graphs with attributes on nodes and edges (SAUHG). The study considers generic GNN models and proposes appropriate 1-WL tests for those domains. Then, the results on the expressive power of GNNs are extended by proving that GNNs have the same capability as the 1-WL test in distinguishing dynamic and attributed graphs, the 1-WL equivalence equals unfolding equivalence and that GNNs are universal approximators modulo 1-WL/unfolding equivalence. Moreover, the proof of the approximation capability holds for SAUHGs, which include most of those used in practical applications, and it is constructive in nature allowing to deduce hints on the architecture of GNNs that can achieve the desired accuracy.
@article{beddarwiesing2022weisfeiler, abstract = {Graph Neural Networks (GNNs) are a large class of relational models for graph processing. Recent theoretical studies on the expressive power of GNNs have focused on two issues. On the one hand, it has been proven that GNNs are as powerful as the Weisfeiler-Lehman test (1-WL) in their ability to distinguish graphs. Moreover, it has been shown that the equivalence enforced by 1-WL equals unfolding equivalence. On the other hand, GNNs turned out to be universal approximators on graphs modulo the constraints enforced by 1-WL/unfolding equivalence. However, these results only apply to Static Undirected Homogeneous Graphs with node attributes. In contrast, real-life applications often involve a variety of graph properties, such as, e.g., dynamics or node and edge attributes. In this paper, we conduct a theoretical analysis of the expressive power of GNNs for these two graph types that are particularly of interest. Dynamic graphs are widely used in modern applications, and its theoretical analysis requires new approaches. The attributed type acts as a standard form for all graph types since it has been shown that all graph types can be transformed without loss to Static Undirected Homogeneous Graphs with attributes on nodes and edges (SAUHG). The study considers generic GNN models and proposes appropriate 1-WL tests for those domains. Then, the results on the expressive power of GNNs are extended by proving that GNNs have the same capability as the 1-WL test in distinguishing dynamic and attributed graphs, the 1-WL equivalence equals unfolding equivalence and that GNNs are universal approximators modulo 1-WL/unfolding equivalence. Moreover, the proof of the approximation capability holds for SAUHGs, which include most of those used in practical applications, and it is constructive in nature allowing to deduce hints on the architecture of GNNs that can achieve the desired accuracy.}, author = {Beddar-Wiesing, Silvia and D'Inverno, Giuseppe Alessio and Graziani, Caterina and Lachi, Veronica and Moallemy-Oureh, Alice and Scarselli, Franco and Thomas, Josephine}, journal = {arXiv e-prints}, keywords = {itegpub}, pages = {arXiv:2210.03990}, title = {{W}eisfeiler-{L}ehman goes Dynamic: An Analysis of the Expressive Power of Graph Neural Networks for Attributed and Dynamic Graphs}, year = 2022 }
%0 Journal Article %1 beddarwiesing2022weisfeiler %A Beddar-Wiesing, Silvia %A D'Inverno, Giuseppe Alessio %A Graziani, Caterina %A Lachi, Veronica %A Moallemy-Oureh, Alice %A Scarselli, Franco %A Thomas, Josephine %D 2022 %J arXiv e-prints %P arXiv:2210.03990 %T Weisfeiler-Lehman goes Dynamic: An Analysis of the Expressive Power of Graph Neural Networks for Attributed and Dynamic Graphs %U https://arxiv.org/abs/2210.03990 %X Graph Neural Networks (GNNs) are a large class of relational models for graph processing. Recent theoretical studies on the expressive power of GNNs have focused on two issues. On the one hand, it has been proven that GNNs are as powerful as the Weisfeiler-Lehman test (1-WL) in their ability to distinguish graphs. Moreover, it has been shown that the equivalence enforced by 1-WL equals unfolding equivalence. On the other hand, GNNs turned out to be universal approximators on graphs modulo the constraints enforced by 1-WL/unfolding equivalence. However, these results only apply to Static Undirected Homogeneous Graphs with node attributes. In contrast, real-life applications often involve a variety of graph properties, such as, e.g., dynamics or node and edge attributes. In this paper, we conduct a theoretical analysis of the expressive power of GNNs for these two graph types that are particularly of interest. Dynamic graphs are widely used in modern applications, and its theoretical analysis requires new approaches. The attributed type acts as a standard form for all graph types since it has been shown that all graph types can be transformed without loss to Static Undirected Homogeneous Graphs with attributes on nodes and edges (SAUHG). The study considers generic GNN models and proposes appropriate 1-WL tests for those domains. Then, the results on the expressive power of GNNs are extended by proving that GNNs have the same capability as the 1-WL test in distinguishing dynamic and attributed graphs, the 1-WL equivalence equals unfolding equivalence and that GNNs are universal approximators modulo 1-WL/unfolding equivalence. Moreover, the proof of the approximation capability holds for SAUHGs, which include most of those used in practical applications, and it is constructive in nature allowing to deduce hints on the architecture of GNNs that can achieve the desired accuracy.
Unified Autoencoder with Task Embeddings for Multi-Task Learning in Renewable Power Forecasting. Nivarthi, Chandana Priya; Vogt, Stephan; Sick, Bernhard. In International Conference on Machine Learning and Applications (ICMLA), bll 1530–1536. IEEE, 2022.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Renewable power generation forecasts using machine learning are typically implemented as single-task learning models, where a separate model is trained for each photovoltaic or wind park. In recent years, transfer learning is gaining popularity in these systems, as it can be used to transfer the knowledge gained from source parks to a target park. However, for transferring the knowledge to a target park, there is a need to determine the most similar source park(s) among the existing parks. This similarity determination using historical power measurements is challenging when the target park has limited to no historical data samples. Therefore, we propose a simple multi-task learning architecture that initially learns a common representation of input weather features among the tasks, using a Unified Autoencoder (UAE) and then learns the task specific information utilizing a Task Embedding layer in a Neural Network (TENN). This proposed architecture, UAE-TENN, can be easily extended to new parks with or without historical data. An elaborate performance comparison of single and multi-task learning models is performed on six photovoltaic and wind farm datasets comprising a total of 529 parks. UAE-TENN significantly improves the performance of power forecasting by 10 to 19% for photovoltaic parks and 5 to 22% for wind parks compared to the baseline models. Even in the zero-shot learning scenario, when there is no historical data, we successfully demonstrate that the UAE-TENN improves the forecast accuracy for a new park by 19% for photovoltaic parks.
@inproceedings{nivarthi2022unified, abstract = {Renewable power generation forecasts using machine learning are typically implemented as single-task learning models, where a separate model is trained for each photovoltaic or wind park. In recent years, transfer learning is gaining popularity in these systems, as it can be used to transfer the knowledge gained from source parks to a target park. However, for transferring the knowledge to a target park, there is a need to determine the most similar source park(s) among the existing parks. This similarity determination using historical power measurements is challenging when the target park has limited to no historical data samples. Therefore, we propose a simple multi-task learning architecture that initially learns a common representation of input weather features among the tasks, using a Unified Autoencoder (UAE) and then learns the task specific information utilizing a Task Embedding layer in a Neural Network (TENN). This proposed architecture, UAE-TENN, can be easily extended to new parks with or without historical data. An elaborate performance comparison of single and multi-task learning models is performed on six photovoltaic and wind farm datasets comprising a total of 529 parks. UAE-TENN significantly improves the performance of power forecasting by 10 to 19% for photovoltaic parks and 5 to 22% for wind parks compared to the baseline models. Even in the zero-shot learning scenario, when there is no historical data, we successfully demonstrate that the UAE-TENN improves the forecast accuracy for a new park by 19% for photovoltaic parks.}, author = {Nivarthi, Chandana Priya and Vogt, Stephan and Sick, Bernhard}, booktitle = {International Conference on Machine Learning and Applications (ICMLA)}, keywords = {itegpub}, pages = {1530–1536}, publisher = {IEEE}, title = {Unified Autoencoder with Task Embeddings for Multi-Task Learning in Renewable Power Forecasting}, year = 2022 }
%0 Conference Paper %1 nivarthi2022unified %A Nivarthi, Chandana Priya %A Vogt, Stephan %A Sick, Bernhard %B International Conference on Machine Learning and Applications (ICMLA) %D 2022 %I IEEE %P 1530--1536 %R 10.1109/ICMLA55696.2022.00240 %T Unified Autoencoder with Task Embeddings for Multi-Task Learning in Renewable Power Forecasting %U https://ieeexplore.ieee.org/document/10068974 %X Renewable power generation forecasts using machine learning are typically implemented as single-task learning models, where a separate model is trained for each photovoltaic or wind park. In recent years, transfer learning is gaining popularity in these systems, as it can be used to transfer the knowledge gained from source parks to a target park. However, for transferring the knowledge to a target park, there is a need to determine the most similar source park(s) among the existing parks. This similarity determination using historical power measurements is challenging when the target park has limited to no historical data samples. Therefore, we propose a simple multi-task learning architecture that initially learns a common representation of input weather features among the tasks, using a Unified Autoencoder (UAE) and then learns the task specific information utilizing a Task Embedding layer in a Neural Network (TENN). This proposed architecture, UAE-TENN, can be easily extended to new parks with or without historical data. An elaborate performance comparison of single and multi-task learning models is performed on six photovoltaic and wind farm datasets comprising a total of 529 parks. UAE-TENN significantly improves the performance of power forecasting by 10 to 19% for photovoltaic parks and 5 to 22% for wind parks compared to the baseline models. Even in the zero-shot learning scenario, when there is no historical data, we successfully demonstrate that the UAE-TENN improves the forecast accuracy for a new park by 19% for photovoltaic parks.
Transfer Learning as an Essential Tool for Digital Twins in Renewable Energy Systems. Nivarthi, Chandana Priya. In Organic Computing -- Doctoral Dissertation Colloquium 2021, S. Tomforde, C. Krupitzer (reds.), bll 47–59. kassel university press, 2022.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
Transfer learning (TL), the next frontier in machine learning (ML), has gained much popularity in recent years, due to the various challenges faced in ML, like the requirement of vast amounts of training data, expensive and time-consuming labelling processes for data samples, and long training duration for models. TL is useful in tackling these problems, as it focuses on transferring knowledge from previously solved tasks to new tasks. Digital twins and other intelligent systems need to utilise TL to use the previously gained knowledge and solve new tasks in a more self-reliant way, and to incrementally increase their knowledge base. Therefore, in this article, the critical challenges in power forecasting and anomaly detection in the context of renewable energy systems are identified, and a potential TL framework to meet these challenges is proposed. This article also proposes a feature embedding approach to handle the missing sensors data. The proposed TL methods help to make a system more autonomous in the context of organic computing.
@incollection{nivarthi2022transfer, abstract = {Transfer learning (TL), the next frontier in machine learning (ML), has gained much popularity in recent years, due to the various challenges faced in ML, like the requirement of vast amounts of training data, expensive and time-consuming labelling processes for data samples, and long training duration for models. TL is useful in tackling these problems, as it focuses on transferring knowledge from previously solved tasks to new tasks. Digital twins and other intelligent systems need to utilise TL to use the previously gained knowledge and solve new tasks in a more self-reliant way, and to incrementally increase their knowledge base. Therefore, in this article, the critical challenges in power forecasting and anomaly detection in the context of renewable energy systems are identified, and a potential TL framework to meet these challenges is proposed. This article also proposes a feature embedding approach to handle the missing sensors data. The proposed TL methods help to make a system more autonomous in the context of organic computing.}, author = {Nivarthi, Chandana Priya}, booktitle = {Organic Computing – Doctoral Dissertation Colloquium 2021}, editor = {Tomforde, Sven and Krupitzer, Christian}, keywords = {itegpub}, pages = {47–59}, publisher = {kassel university press}, title = {Transfer Learning as an Essential Tool for Digital Twins in Renewable Energy Systems}, year = 2022 }
%0 Book Section %1 nivarthi2022transfer %A Nivarthi, Chandana Priya %B Organic Computing -- Doctoral Dissertation Colloquium 2021 %D 2022 %E Tomforde, Sven %E Krupitzer, Christian %I kassel university press %P 47--59 %T Transfer Learning as an Essential Tool for Digital Twins in Renewable Energy Systems %X Transfer learning (TL), the next frontier in machine learning (ML), has gained much popularity in recent years, due to the various challenges faced in ML, like the requirement of vast amounts of training data, expensive and time-consuming labelling processes for data samples, and long training duration for models. TL is useful in tackling these problems, as it focuses on transferring knowledge from previously solved tasks to new tasks. Digital twins and other intelligent systems need to utilise TL to use the previously gained knowledge and solve new tasks in a more self-reliant way, and to incrementally increase their knowledge base. Therefore, in this article, the critical challenges in power forecasting and anomaly detection in the context of renewable energy systems are identified, and a potential TL framework to meet these challenges is proposed. This article also proposes a feature embedding approach to handle the missing sensors data. The proposed TL methods help to make a system more autonomous in the context of organic computing.
Three-dimensional close-to-substrate trajectories of magnetic microparticles in dynamically changing magnetic field landscapes. Huhnstock, Rico; Reginka, Meike; Sonntag, Claudius; Merkel, Maximilian; Dingel, Kristina; Sick, Bernhard; Vogel, Michael; Ehresmann, Arno. In Scientific Reports, 12(1), bll 1–10. Springer Nature, 2022.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
The transport of magnetic particles (MPs) by dynamic magnetic field landscapes (MFLs) using magnetically patterned substrates is promising for the development of Lab-on-a-chip (LOC) systems. The inherent close-to-substrate MP motion is sensitive to changing particle–substrate interactions. Thus, the detection of a modified particle–substrate separation distance caused by surface binding of an analyte is expected to be a promising probe in analytics and diagnostics. Here, we present an essential prerequisite for such an application, namely the label-free quantitative experimental determination of the three-dimensional trajectories of superparamagnetic particles (SPPs) transported by a dynamically changing MFL. The evaluation of defocused SPP images from optical bright-field microscopy revealed a “hopping”-like motion of the magnetic particles, previously predicted by theory, additionally allowing a quantification of maximum jump heights. As our findings pave the way towards precise determination of particle–substrate separations, they bear deep implications for future LOC detection schemes using only optical microscopy.
@article{huhnstock2022three, abstract = {The transport of magnetic particles (MPs) by dynamic magnetic field landscapes (MFLs) using magnetically patterned substrates is promising for the development of Lab-on-a-chip (LOC) systems. The inherent close-to-substrate MP motion is sensitive to changing particle–substrate interactions. Thus, the detection of a modified particle–substrate separation distance caused by surface binding of an analyte is expected to be a promising probe in analytics and diagnostics. Here, we present an essential prerequisite for such an application, namely the label-free quantitative experimental determination of the three-dimensional trajectories of superparamagnetic particles (SPPs) transported by a dynamically changing MFL. The evaluation of defocused SPP images from optical bright-field microscopy revealed a “hopping”-like motion of the magnetic particles, previously predicted by theory, additionally allowing a quantification of maximum jump heights. As our findings pave the way towards precise determination of particle–substrate separations, they bear deep implications for future LOC detection schemes using only optical microscopy.}, author = {Huhnstock, Rico and Reginka, Meike and Sonntag, Claudius and Merkel, Maximilian and Dingel, Kristina and Sick, Bernhard and Vogel, Michael and Ehresmann, Arno}, journal = {Scientific Reports}, keywords = {itegpub}, number = 1, pages = {1–10}, publisher = {Springer Nature}, title = {Three-dimensional close-to-substrate trajectories of magnetic microparticles in dynamically changing magnetic field landscapes}, volume = 12, year = 2022 }
%0 Journal Article %1 huhnstock2022three %A Huhnstock, Rico %A Reginka, Meike %A Sonntag, Claudius %A Merkel, Maximilian %A Dingel, Kristina %A Sick, Bernhard %A Vogel, Michael %A Ehresmann, Arno %D 2022 %I Springer Nature %J Scientific Reports %N 1 %P 1--10 %R 10.1038/s41598-022-25391-z %T Three-dimensional close-to-substrate trajectories of magnetic microparticles in dynamically changing magnetic field landscapes %U https://www.nature.com/articles/s41598-022-25391-z %V 12 %X The transport of magnetic particles (MPs) by dynamic magnetic field landscapes (MFLs) using magnetically patterned substrates is promising for the development of Lab-on-a-chip (LOC) systems. The inherent close-to-substrate MP motion is sensitive to changing particle–substrate interactions. Thus, the detection of a modified particle–substrate separation distance caused by surface binding of an analyte is expected to be a promising probe in analytics and diagnostics. Here, we present an essential prerequisite for such an application, namely the label-free quantitative experimental determination of the three-dimensional trajectories of superparamagnetic particles (SPPs) transported by a dynamically changing MFL. The evaluation of defocused SPP images from optical bright-field microscopy revealed a “hopping”-like motion of the magnetic particles, previously predicted by theory, additionally allowing a quantification of maximum jump heights. As our findings pave the way towards precise determination of particle–substrate separations, they bear deep implications for future LOC detection schemes using only optical microscopy.
The Vision of Self-Management in Cognitive Organic Power Distribution Systems. Loeser, Inga; Braun, Martin; Gruhl, Christian; Menke, Jan-Hendrik; Sick, Bernhard; Tomforde, Sven. In Energies, 15(3), bl 881. MDPI, 2022.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Due to the ongoing trend towards a decarbonisation of energy use, the power system is expected to become the backbone of all energy sectors and thus the fundamental critical infrastructure. High penetration with distributed energy resources demands the coordination of a large number of prosumers, partly controlled by home energy management systems (HEMS), to be designed in such a way that the power system’s operational limits are not violated. On the grid level, distribution management systems (DMS) seek to keep the power system in the normal operational state. On the prosumer level, distributed HEMS optimise the internal power flows by setpoint specification of batteries, photovoltaic generators, or flexible loads. The vision of the ODiS (Organic Distribution System) initiative is to develop an architecture to operate a distribution grid reliably, with high resiliency, and fully autonomously by developing “organic” HEMS and DMS which possess multiple self-x capabilities, collectively referred to as self-management. Thus, ODiS seeks answers to the following question: How can we create the most appropriate models, techniques, and algorithms to develop novel kinds of self-configuring, self-organising, self-healing, and self-optimising DMS that are integrally coupled with the distributed HEMS? In this concept paper, the vision of ODiS is presented in detail based on a thorough review of the state of the art.
@article{loeser2022vision, abstract = {Due to the ongoing trend towards a decarbonisation of energy use, the power system is expected to become the backbone of all energy sectors and thus the fundamental critical infrastructure. High penetration with distributed energy resources demands the coordination of a large number of prosumers, partly controlled by home energy management systems (HEMS), to be designed in such a way that the power system’s operational limits are not violated. On the grid level, distribution management systems (DMS) seek to keep the power system in the normal operational state. On the prosumer level, distributed HEMS optimise the internal power flows by setpoint specification of batteries, photovoltaic generators, or flexible loads. The vision of the ODiS (Organic Distribution System) initiative is to develop an architecture to operate a distribution grid reliably, with high resiliency, and fully autonomously by developing “organic” HEMS and DMS which possess multiple self-x capabilities, collectively referred to as self-management. Thus, ODiS seeks answers to the following question: How can we create the most appropriate models, techniques, and algorithms to develop novel kinds of self-configuring, self-organising, self-healing, and self-optimising DMS that are integrally coupled with the distributed HEMS? In this concept paper, the vision of ODiS is presented in detail based on a thorough review of the state of the art.}, author = {Loeser, Inga and Braun, Martin and Gruhl, Christian and Menke, Jan-Hendrik and Sick, Bernhard and Tomforde, Sven}, journal = {Energies}, keywords = {self-healing}, number = 3, pages = 881, publisher = {MDPI}, title = {The Vision of Self-Management in Cognitive Organic Power Distribution Systems}, volume = 15, year = 2022 }
%0 Journal Article %1 loeser2022vision %A Loeser, Inga %A Braun, Martin %A Gruhl, Christian %A Menke, Jan-Hendrik %A Sick, Bernhard %A Tomforde, Sven %D 2022 %I MDPI %J Energies %N 3 %P 881 %R 10.3390/en15030881 %T The Vision of Self-Management in Cognitive Organic Power Distribution Systems %U https://www.mdpi.com/1996-1073/15/3/881 %V 15 %X Due to the ongoing trend towards a decarbonisation of energy use, the power system is expected to become the backbone of all energy sectors and thus the fundamental critical infrastructure. High penetration with distributed energy resources demands the coordination of a large number of prosumers, partly controlled by home energy management systems (HEMS), to be designed in such a way that the power system’s operational limits are not violated. On the grid level, distribution management systems (DMS) seek to keep the power system in the normal operational state. On the prosumer level, distributed HEMS optimise the internal power flows by setpoint specification of batteries, photovoltaic generators, or flexible loads. The vision of the ODiS (Organic Distribution System) initiative is to develop an architecture to operate a distribution grid reliably, with high resiliency, and fully autonomously by developing “organic” HEMS and DMS which possess multiple self-x capabilities, collectively referred to as self-management. Thus, ODiS seeks answers to the following question: How can we create the most appropriate models, techniques, and algorithms to develop novel kinds of self-configuring, self-organising, self-healing, and self-optimising DMS that are integrally coupled with the distributed HEMS? In this concept paper, the vision of ODiS is presented in detail based on a thorough review of the state of the art.
Student Research Abstract: Using Local Activity Encoding for Dynamic Graph Pooling in Stuctural-Dynamic Graphs. Beddar-Wiesing, Silvia. In ACM/SIGAPP Symposium on Applied Computing (SAC), bll 604–609. ACM, 2022.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Graphs have recently become more popular for modeling real-world as well as theoretical problems, and several Machine Learning algorithms for learning on them have developed. For graphs that change over time, however, research is still at an early stage. This article proposes a framework DynHeatmaP that generates a constant-size graph sequence representation of graphs whose structure changes over time (structural-dynamic, SDG) in linear time. The framework uses a representation of additions and deletions of nodes and edges (events) to perform dynamic graph pooling. Our algorithm translates the dynamic changes of the nodes and edges to a heatmap representation of the current node activity, regarding additions and deletions in the neighborhood, respectively. The created activity heatmap is utilized as probabilities of the nodes to be sampled in the subsequent pooling step. In addition, the neighborhood of selected nodes has been sampled such that the ratio of additions and deletions is represented accordingly. The obtained downsampled graph sequence can then be used representatively as input to a GNN for learning on the original stream. Focussing on the active regions in a graph, the fast pooling process can reduce the training time significantly and addresses the problem of unbalanced datasets in real-world applications modeled as sparse graphs.
@inproceedings{beddarwiesing2022student, abstract = {Graphs have recently become more popular for modeling real-world as well as theoretical problems, and several Machine Learning algorithms for learning on them have developed. For graphs that change over time, however, research is still at an early stage. This article proposes a framework DynHeatmaP that generates a constant-size graph sequence representation of graphs whose structure changes over time (structural-dynamic, SDG) in linear time. The framework uses a representation of additions and deletions of nodes and edges (events) to perform dynamic graph pooling. Our algorithm translates the dynamic changes of the nodes and edges to a heatmap representation of the current node activity, regarding additions and deletions in the neighborhood, respectively. The created activity heatmap is utilized as probabilities of the nodes to be sampled in the subsequent pooling step. In addition, the neighborhood of selected nodes has been sampled such that the ratio of additions and deletions is represented accordingly. The obtained downsampled graph sequence can then be used representatively as input to a GNN for learning on the original stream. Focussing on the active regions in a graph, the fast pooling process can reduce the training time significantly and addresses the problem of unbalanced datasets in real-world applications modeled as sparse graphs.}, author = {Beddar-Wiesing, Silvia}, booktitle = {ACM/SIGAPP Symposium on Applied Computing (SAC)}, keywords = {itegpub}, pages = {604–609}, publisher = {ACM}, title = {Student Research Abstract: Using Local Activity Encoding for Dynamic Graph Pooling in Stuctural-Dynamic Graphs}, year = 2022 }
%0 Conference Paper %1 beddarwiesing2022student %A Beddar-Wiesing, Silvia %B ACM/SIGAPP Symposium on Applied Computing (SAC) %D 2022 %I ACM %P 604--609 %R 10.1145/3477314.3506969 %T Student Research Abstract: Using Local Activity Encoding for Dynamic Graph Pooling in Stuctural-Dynamic Graphs %U https://dl.acm.org/doi/abs/10.1145/3477314.3506969 %X Graphs have recently become more popular for modeling real-world as well as theoretical problems, and several Machine Learning algorithms for learning on them have developed. For graphs that change over time, however, research is still at an early stage. This article proposes a framework DynHeatmaP that generates a constant-size graph sequence representation of graphs whose structure changes over time (structural-dynamic, SDG) in linear time. The framework uses a representation of additions and deletions of nodes and edges (events) to perform dynamic graph pooling. Our algorithm translates the dynamic changes of the nodes and edges to a heatmap representation of the current node activity, regarding additions and deletions in the neighborhood, respectively. The created activity heatmap is utilized as probabilities of the nodes to be sampled in the subsequent pooling step. In addition, the neighborhood of selected nodes has been sampled such that the ratio of additions and deletions is represented accordingly. The obtained downsampled graph sequence can then be used representatively as input to a GNN for learning on the original stream. Focussing on the active regions in a graph, the fast pooling process can reduce the training time significantly and addresses the problem of unbalanced datasets in real-world applications modeled as sparse graphs.
Student Research Abstract: Continuous-Time Generative Graph Neural Network for Attributed Dynamic Graphs. Moallemy-Oureh, Alice. In ACM/SIGAPP Symposium on Applied Computing (SAC), bll 600–603. ACM, 2022.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
The history of neural networks dates back to the early 1940s and has not only evolved rapidly over time but they are now amongst one of the most popular and powerful machine learning techniques. In this area, graph representation learning (GRL) using graph neural networks (GNNs) has emerged during the early 90s and developed into an impactful approach for modeling graph-structured real-world data, such as social or biological networks. There are a variety of successful applications of GRL in computational neuroscience, chemistry, mathematics, and so on. While temporal changes (dynamics) play an essential role in many real-world applications, most of the literature on GNNs and GRL, deals with static graphs. Since the few GNN models on dynamic graphs only consider exceptional cases of dynamics (i.e., attribute-dynamic graphs in discrete-time representation or structure-dynamic graphs in continuous-time representation), we aim to present a novel GNN model that can handle attribute-dynamic graphs in continuous time. This model learns any kind of graph information embedding, performs node/edge attribute forecasts, and allows for attribute-dynamic graph generation in both discrete and continuous-time.
@inproceedings{moallemyoureh2022student, abstract = {The history of neural networks dates back to the early 1940s and has not only evolved rapidly over time but they are now amongst one of the most popular and powerful machine learning techniques. In this area, graph representation learning (GRL) using graph neural networks (GNNs) has emerged during the early 90s and developed into an impactful approach for modeling graph-structured real-world data, such as social or biological networks. There are a variety of successful applications of GRL in computational neuroscience, chemistry, mathematics, and so on. While temporal changes (dynamics) play an essential role in many real-world applications, most of the literature on GNNs and GRL, deals with static graphs. Since the few GNN models on dynamic graphs only consider exceptional cases of dynamics (i.e., attribute-dynamic graphs in discrete-time representation or structure-dynamic graphs in continuous-time representation), we aim to present a novel GNN model that can handle attribute-dynamic graphs in continuous time. This model learns any kind of graph information embedding, performs node/edge attribute forecasts, and allows for attribute-dynamic graph generation in both discrete and continuous-time.}, author = {Moallemy-Oureh, Alice}, booktitle = {ACM/SIGAPP Symposium on Applied Computing (SAC)}, keywords = {itegpub}, pages = {600–603}, publisher = {ACM}, title = {Student Research Abstract: Continuous-Time Generative Graph Neural Network for Attributed Dynamic Graphs}, year = 2022 }
%0 Conference Paper %1 moallemyoureh2022student %A Moallemy-Oureh, Alice %B ACM/SIGAPP Symposium on Applied Computing (SAC) %D 2022 %I ACM %P 600--603 %R 10.1145/3477314.3508018 %T Student Research Abstract: Continuous-Time Generative Graph Neural Network for Attributed Dynamic Graphs %U https://dl.acm.org/doi/abs/10.1145/3477314.3508018 %X The history of neural networks dates back to the early 1940s and has not only evolved rapidly over time but they are now amongst one of the most popular and powerful machine learning techniques. In this area, graph representation learning (GRL) using graph neural networks (GNNs) has emerged during the early 90s and developed into an impactful approach for modeling graph-structured real-world data, such as social or biological networks. There are a variety of successful applications of GRL in computational neuroscience, chemistry, mathematics, and so on. While temporal changes (dynamics) play an essential role in many real-world applications, most of the literature on GNNs and GRL, deals with static graphs. Since the few GNN models on dynamic graphs only consider exceptional cases of dynamics (i.e., attribute-dynamic graphs in discrete-time representation or structure-dynamic graphs in continuous-time representation), we aim to present a novel GNN model that can handle attribute-dynamic graphs in continuous time. This model learns any kind of graph information embedding, performs node/edge attribute forecasts, and allows for attribute-dynamic graph generation in both discrete and continuous-time.
Stream-Based Active Learning in Changing Environments under Verification Latency. Pham, Tuan. In Organic Computing -- Doctoral Dissertation Colloquium 2021, S. Tomforde, C. Krupitzer (reds.), bll 152–164. kassel university press, 2022.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
Labeling data often requires human interaction, which is slow and costly depending on the required expertise. Stream-based active learning reduces the cost of labeling for data stream mining by only querying the labels for instances that improve the classifier the most. However, state-of-the-art stream-based active learning strategies assume that verification latency, i.e., the time between a query and the availability of the queried label, is negligible. In reality, this is usually not the case as the experts who provide such labels are not available all the time, and the labeling process itself requires time. This article investigates the impact of verification latency within a stream-based active learning scenario for changing data streams. We focus on two different types of changes that occur over time, i.e., changes in the number of features and changes in the distribution of instances and/or labels. In particular, we identify challenges that occur due to verification latency and propose ideas to overcome these problems within a stream-based active learning strategy.
@incollection{pham2022stream-based, abstract = {Labeling data often requires human interaction, which is slow and costly depending on the required expertise. Stream-based active learning reduces the cost of labeling for data stream mining by only querying the labels for instances that improve the classifier the most. However, state-of-the-art stream-based active learning strategies assume that verification latency, i.e., the time between a query and the availability of the queried label, is negligible. In reality, this is usually not the case as the experts who provide such labels are not available all the time, and the labeling process itself requires time. This article investigates the impact of verification latency within a stream-based active learning scenario for changing data streams. We focus on two different types of changes that occur over time, i.e., changes in the number of features and changes in the distribution of instances and/or labels. In particular, we identify challenges that occur due to verification latency and propose ideas to overcome these problems within a stream-based active learning strategy.}, author = {Pham, Tuan}, booktitle = {Organic Computing – Doctoral Dissertation Colloquium 2021}, editor = {Tomforde, Sven and Krupitzer, Christian}, keywords = {itegpub}, pages = {152–164}, publisher = {kassel university press}, title = {Stream-Based Active Learning in Changing Environments under Verification Latency}, year = 2022 }
%0 Book Section %1 pham2022stream-based %A Pham, Tuan %B Organic Computing -- Doctoral Dissertation Colloquium 2021 %D 2022 %E Tomforde, Sven %E Krupitzer, Christian %I kassel university press %P 152--164 %T Stream-Based Active Learning in Changing Environments under Verification Latency %X Labeling data often requires human interaction, which is slow and costly depending on the required expertise. Stream-based active learning reduces the cost of labeling for data stream mining by only querying the labels for instances that improve the classifier the most. However, state-of-the-art stream-based active learning strategies assume that verification latency, i.e., the time between a query and the availability of the queried label, is negligible. In reality, this is usually not the case as the experts who provide such labels are not available all the time, and the labeling process itself requires time. This article investigates the impact of verification latency within a stream-based active learning scenario for changing data streams. We focus on two different types of changes that occur over time, i.e., changes in the number of features and changes in the distribution of instances and/or labels. In particular, we identify challenges that occur due to verification latency and propose ideas to overcome these problems within a stream-based active learning strategy.
Stream-based active learning for sliding windows under the influence of verification latency. Pham, Tuan; Kottke, Daniel; Krempl, Georg; Sick, Bernhard. In Machine Learning, 111(6), bll 2011–2036. Springer, 2022.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
Stream-based active learning (AL) strategies minimize the labeling effort by querying labels that improve the classifier's performance the most. So far, these strategies neglect the fact that an oracle or expert requires time to provide a queried label. We show that existing AL methods deteriorate or even fail under the influence of such verification latency. The problem with these methods is that they estimate a label's utility on the currently available labeled data. However, when this label would arrive, some of the current data may have gotten outdated and new labels have arrived. In this article, we propose to simulate the available data at the time when the label would arrive. Therefore, our method Forgetting and Simulating (FS) forgets outdated information and simulates the delayed labels to get more realistic utility estimates. We assume to know the label's arrival date a priori and the classifier's training data to be bounded by a sliding window. Our extensive experiments show that FS improves stream-based AL strategies in settings with both, constant and variable verification latency.
@article{pham2022stream, abstract = {Stream-based active learning (AL) strategies minimize the labeling effort by querying labels that improve the classifier's performance the most. So far, these strategies neglect the fact that an oracle or expert requires time to provide a queried label. We show that existing AL methods deteriorate or even fail under the influence of such verification latency. The problem with these methods is that they estimate a label's utility on the currently available labeled data. However, when this label would arrive, some of the current data may have gotten outdated and new labels have arrived. In this article, we propose to simulate the available data at the time when the label would arrive. Therefore, our method Forgetting and Simulating (FS) forgets outdated information and simulates the delayed labels to get more realistic utility estimates. We assume to know the label's arrival date a priori and the classifier's training data to be bounded by a sliding window. Our extensive experiments show that FS improves stream-based AL strategies in settings with both, constant and variable verification latency.}, author = {Pham, Tuan and Kottke, Daniel and Krempl, Georg and Sick, Bernhard}, journal = {Machine Learning}, keywords = {itegpub}, number = 6, pages = {2011–2036}, publisher = {Springer}, title = {Stream-based active learning for sliding windows under the influence of verification latency}, volume = 111, year = 2022 }
%0 Journal Article %1 pham2022stream %A Pham, Tuan %A Kottke, Daniel %A Krempl, Georg %A Sick, Bernhard %D 2022 %I Springer %J Machine Learning %N 6 %P 2011--2036 %R doi.org/10.1007/s10994-021-06099-z %T Stream-based active learning for sliding windows under the influence of verification latency %V 111 %X Stream-based active learning (AL) strategies minimize the labeling effort by querying labels that improve the classifier's performance the most. So far, these strategies neglect the fact that an oracle or expert requires time to provide a queried label. We show that existing AL methods deteriorate or even fail under the influence of such verification latency. The problem with these methods is that they estimate a label's utility on the currently available labeled data. However, when this label would arrive, some of the current data may have gotten outdated and new labels have arrived. In this article, we propose to simulate the available data at the time when the label would arrive. Therefore, our method Forgetting and Simulating (FS) forgets outdated information and simulates the delayed labels to get more realistic utility estimates. We assume to know the label's arrival date a priori and the classifier's training data to be bounded by a sliding window. Our extensive experiments show that FS improves stream-based AL strategies in settings with both, constant and variable verification latency.
Space, Time, and Interaction: A Taxonomy of Corner Cases in Trajectory Datasets for Automated Driving. Rösch, Kevin; Heidecker, Florian; Truetsch, Julian; Kowol, Kamil; Schicktanz, Clemens; Bieshaar, Maarten; Sick, Bernhard; Stiller, Christoph. In IEEE Symposium on Computational Intelligence in Vehicles and Transportation Systems (IEEE CIVTS), IEEE SSCI, bll 86–93. IEEE, 2022.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Trajectory data analysis is an essential component for highly automated driving. Complex models developed with these data predict other road users’ movement and behavior patterns. Based on these predictions — and additional contextual information such as the course of the road, (traffic) rules, and interaction with other road users — the highly automated vehicle (HAV) must be able to reliably and safely perform the task assigned to it, e.g., moving from point A to B. Ideally, the HAV moves safely through its environment, just as we would expect a human driver to do. However, if unusual trajectories occur, so-called trajectory corner cases, a human driver can usually cope well, but an HAV can quickly get into trouble. In the definition of trajectory corner cases, which we provide in this work, we will consider the relevance of unusual trajectories with respect to the task at hand. Based on this, we will also present a taxonomy of different trajectory corner cases. The categorization of corner cases into the taxonomy will be shown with examples and is done by cause and required data sources. To illustrate the complexity between the machine learning (ML) model and the corner case cause, we present a general processing chain underlying the taxonomy.
@inproceedings{rosch2022space, abstract = {Trajectory data analysis is an essential component for highly automated driving. Complex models developed with these data predict other road users’ movement and behavior patterns. Based on these predictions — and additional contextual information such as the course of the road, (traffic) rules, and interaction with other road users — the highly automated vehicle (HAV) must be able to reliably and safely perform the task assigned to it, e.g., moving from point A to B. Ideally, the HAV moves safely through its environment, just as we would expect a human driver to do. However, if unusual trajectories occur, so-called trajectory corner cases, a human driver can usually cope well, but an HAV can quickly get into trouble. In the definition of trajectory corner cases, which we provide in this work, we will consider the relevance of unusual trajectories with respect to the task at hand. Based on this, we will also present a taxonomy of different trajectory corner cases. The categorization of corner cases into the taxonomy will be shown with examples and is done by cause and required data sources. To illustrate the complexity between the machine learning (ML) model and the corner case cause, we present a general processing chain underlying the taxonomy.}, author = {Rösch, Kevin and Heidecker, Florian and Truetsch, Julian and Kowol, Kamil and Schicktanz, Clemens and Bieshaar, Maarten and Sick, Bernhard and Stiller, Christoph}, booktitle = {IEEE Symposium on Computational Intelligence in Vehicles and Transportation Systems (IEEE CIVTS), IEEE SSCI}, keywords = {itegpub}, pages = {86–93}, publisher = {IEEE}, title = {Space, Time, and Interaction: A Taxonomy of Corner Cases in Trajectory Datasets for Automated Driving}, year = 2022 }
%0 Conference Paper %1 rosch2022space %A Rösch, Kevin %A Heidecker, Florian %A Truetsch, Julian %A Kowol, Kamil %A Schicktanz, Clemens %A Bieshaar, Maarten %A Sick, Bernhard %A Stiller, Christoph %B IEEE Symposium on Computational Intelligence in Vehicles and Transportation Systems (IEEE CIVTS), IEEE SSCI %D 2022 %I IEEE %P 86--93 %R 10.1109/SSCI51031.2022.10022241 %T Space, Time, and Interaction: A Taxonomy of Corner Cases in Trajectory Datasets for Automated Driving %U https://ieeexplore.ieee.org/document/10022241 %X Trajectory data analysis is an essential component for highly automated driving. Complex models developed with these data predict other road users’ movement and behavior patterns. Based on these predictions — and additional contextual information such as the course of the road, (traffic) rules, and interaction with other road users — the highly automated vehicle (HAV) must be able to reliably and safely perform the task assigned to it, e.g., moving from point A to B. Ideally, the HAV moves safely through its environment, just as we would expect a human driver to do. However, if unusual trajectories occur, so-called trajectory corner cases, a human driver can usually cope well, but an HAV can quickly get into trouble. In the definition of trajectory corner cases, which we provide in this work, we will consider the relevance of unusual trajectories with respect to the task at hand. Based on this, we will also present a taxonomy of different trajectory corner cases. The categorization of corner cases into the taxonomy will be shown with examples and is done by cause and required data sources. To illustrate the complexity between the machine learning (ML) model and the corner case cause, we present a general processing chain underlying the taxonomy.
Social Machines. Draude, Claude; Gruhl, Christian; Hornung, Gerrit; Kropf, Jonathan; Lamla, Jörn; Leimeister, Jan Marco; Sick, Bernhard; Stumme, Gerd. In Informatik Spektrum, 45(1), bll 38–42. Springer, 2022.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
Social Machines sind ein Paradigma für die Gestaltung soziotechnischer Systeme, die unter Verwendung von Web- und Plattformlösungen das Potenzial digitaler Technologien mit der Eigenlogik sozialer Interaktion, Organisation und Struk- turbildung auf neue Weise zusammenführen. Im Folgenden diskutieren wir das Paradigma der Social Machine aus den Perspektiven der Informatik, der Wirtschaftsinformatik, der Soziologie und des Rechts, um Orientierungspunkte für seine Gestaltung zu identifizieren. Der Begriff ist in der Literatur jedoch bisher nicht abschließend definiert sondern nur durch Beispiele illustriert. In diesem Artikel stellen wir zunächst die folgende Definition zur Diskussion: Social Machines sind soziotechnische Sys- teme, in denen die Prozesse sozialer Interaktion hybrid zwischen menschlichen und maschinellen Akteuren ablaufen und teilweise algorithmisiert sind. Im Anschluss beleuchten wir drei aktuelle, sich gegenseitig bedingende Entwicklungen von Social Machines: die immer stärkere Verschmelzung von Sozialität und Maschine, die Vermessung von Nutzeraktivitäten als Grundstoff gesellschaftlichen Zusammenhalts und die zunehmende Algorithmisierung gesellschaftlicher Prozesse. Ab- schließend diskutieren wir, dass eine teilhabeorientierte, demokratischen Werten folgende Gestaltung von Social Machines die Perspektiven der Nutzungsakzeptanz, der gesellschaftlichen Akzeptabilität und der nachhaltigen Wirtschaftlichkeit adressieren und umsetzen muss.
@article{draude2022social, abstract = {Social Machines sind ein Paradigma für die Gestaltung soziotechnischer Systeme, die unter Verwendung von Web- und Plattformlösungen das Potenzial digitaler Technologien mit der Eigenlogik sozialer Interaktion, Organisation und Struk- turbildung auf neue Weise zusammenführen. Im Folgenden diskutieren wir das Paradigma der Social Machine aus den Perspektiven der Informatik, der Wirtschaftsinformatik, der Soziologie und des Rechts, um Orientierungspunkte für seine Gestaltung zu identifizieren. Der Begriff ist in der Literatur jedoch bisher nicht abschließend definiert sondern nur durch Beispiele illustriert. In diesem Artikel stellen wir zunächst die folgende Definition zur Diskussion: Social Machines sind soziotechnische Sys- teme, in denen die Prozesse sozialer Interaktion hybrid zwischen menschlichen und maschinellen Akteuren ablaufen und teilweise algorithmisiert sind. Im Anschluss beleuchten wir drei aktuelle, sich gegenseitig bedingende Entwicklungen von Social Machines: die immer stärkere Verschmelzung von Sozialität und Maschine, die Vermessung von Nutzeraktivitäten als Grundstoff gesellschaftlichen Zusammenhalts und die zunehmende Algorithmisierung gesellschaftlicher Prozesse. Ab- schließend diskutieren wir, dass eine teilhabeorientierte, demokratischen Werten folgende Gestaltung von Social Machines die Perspektiven der Nutzungsakzeptanz, der gesellschaftlichen Akzeptabilität und der nachhaltigen Wirtschaftlichkeit adressieren und umsetzen muss.}, author = {Draude, Claude and Gruhl, Christian and Hornung, Gerrit and Kropf, Jonathan and Lamla, Jörn and Leimeister, Jan Marco and Sick, Bernhard and Stumme, Gerd}, journal = {Informatik Spektrum}, keywords = {itegpub}, number = 1, pages = {38–42}, publisher = {Springer}, title = {Social Machines}, volume = 45, year = 2022 }
%0 Journal Article %1 draude2022social %A Draude, Claude %A Gruhl, Christian %A Hornung, Gerrit %A Kropf, Jonathan %A Lamla, Jörn %A Leimeister, Jan Marco %A Sick, Bernhard %A Stumme, Gerd %D 2022 %I Springer %J Informatik Spektrum %N 1 %P 38--42 %R https://doi.org/10.1007/s00287-021-01421-4 %T Social Machines %V 45 %X Social Machines sind ein Paradigma für die Gestaltung soziotechnischer Systeme, die unter Verwendung von Web- und Plattformlösungen das Potenzial digitaler Technologien mit der Eigenlogik sozialer Interaktion, Organisation und Struk- turbildung auf neue Weise zusammenführen. Im Folgenden diskutieren wir das Paradigma der Social Machine aus den Perspektiven der Informatik, der Wirtschaftsinformatik, der Soziologie und des Rechts, um Orientierungspunkte für seine Gestaltung zu identifizieren. Der Begriff ist in der Literatur jedoch bisher nicht abschließend definiert sondern nur durch Beispiele illustriert. In diesem Artikel stellen wir zunächst die folgende Definition zur Diskussion: Social Machines sind soziotechnische Sys- teme, in denen die Prozesse sozialer Interaktion hybrid zwischen menschlichen und maschinellen Akteuren ablaufen und teilweise algorithmisiert sind. Im Anschluss beleuchten wir drei aktuelle, sich gegenseitig bedingende Entwicklungen von Social Machines: die immer stärkere Verschmelzung von Sozialität und Maschine, die Vermessung von Nutzeraktivitäten als Grundstoff gesellschaftlichen Zusammenhalts und die zunehmende Algorithmisierung gesellschaftlicher Prozesse. Ab- schließend diskutieren wir, dass eine teilhabeorientierte, demokratischen Werten folgende Gestaltung von Social Machines die Perspektiven der Nutzungsakzeptanz, der gesellschaftlichen Akzeptabilität und der nachhaltigen Wirtschaftlichkeit adressieren und umsetzen muss.
Self-Aware Microsystems. Gruhl, Christian; Tomforde, Sven; Sick, Bernhard. In Workshop on Self-Improving System Integration (SISSY), ACSOS, bll 126–127. IEEE, 2022.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Besides infrastructure-based solutions, small-scale microsystems are increasingly connected and interoperating with others in changing environments. Following the same motivation as for self-adaptive systems, this demands novel attempts to counter complexity and provide autonomous decision freedom that paves the path towards resilient and flexible behaviour. In this article, we outline a vision for research on self-aware microsystems (SAM) that aims at providing technical solutions that are especially relevant for initiatives such as self-improving system integration.
@inproceedings{gruhl2022self, abstract = {Besides infrastructure-based solutions, small-scale microsystems are increasingly connected and interoperating with others in changing environments. Following the same motivation as for self-adaptive systems, this demands novel attempts to counter complexity and provide autonomous decision freedom that paves the path towards resilient and flexible behaviour. In this article, we outline a vision for research on self-aware microsystems (SAM) that aims at providing technical solutions that are especially relevant for initiatives such as self-improving system integration.}, author = {Gruhl, Christian and Tomforde, Sven and Sick, Bernhard}, booktitle = {Workshop on Self-Improving System Integration (SISSY), ACSOS}, keywords = {itegpub}, pages = {126–127}, publisher = {IEEE}, title = {Self-Aware Microsystems}, year = 2022 }
%0 Conference Paper %1 gruhl2022self %A Gruhl, Christian %A Tomforde, Sven %A Sick, Bernhard %B Workshop on Self-Improving System Integration (SISSY), ACSOS %D 2022 %I IEEE %P 126--127 %R 10.1109/ACSOSC56246.2022.00045 %T Self-Aware Microsystems %U https://ieeexplore.ieee.org/abstract/document/9934876/ %X Besides infrastructure-based solutions, small-scale microsystems are increasingly connected and interoperating with others in changing environments. Following the same motivation as for self-adaptive systems, this demands novel attempts to counter complexity and provide autonomous decision freedom that paves the path towards resilient and flexible behaviour. In this article, we outline a vision for research on self-aware microsystems (SAM) that aims at providing technical solutions that are especially relevant for initiatives such as self-improving system integration.
Self-Adaptive Charging Management in Electric Vehicle Infrastructures based on Reinforcement Learning. Hassouna, Mohamed. In Organic Computing -- Doctoral Dissertation Colloquium 2022, S. Tomforde, C. Krupitzer (reds.), bll 1–16. kassel university press, 2022.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
Electromobility plays an increasingly important role in the energy transition. Electric vehicle charging poses challenges to the electricity grid due to high peak demand situations. Therefore, it is crucial to leverage the vehicle's flexibility when charging can be delayed. Conventional charging management systems cannot adapt to frequently changing conditions such as fluctuating renewable energy output, electricity prices and user behavior. In this article, we investigate the application of reinforcement learning approaches for self-adaptive charging management. In particular, we identify challenges regarding realistic environments and adaption to varying topologies and connections among charging stations. We describe related approaches and propose ideas and planned experiments to overcome these problems by utilizing generative models and graph neural networks.
@incollection{hassouna2022self, abstract = {Electromobility plays an increasingly important role in the energy transition. Electric vehicle charging poses challenges to the electricity grid due to high peak demand situations. Therefore, it is crucial to leverage the vehicle's flexibility when charging can be delayed. Conventional charging management systems cannot adapt to frequently changing conditions such as fluctuating renewable energy output, electricity prices and user behavior. In this article, we investigate the application of reinforcement learning approaches for self-adaptive charging management. In particular, we identify challenges regarding realistic environments and adaption to varying topologies and connections among charging stations. We describe related approaches and propose ideas and planned experiments to overcome these problems by utilizing generative models and graph neural networks.}, author = {Hassouna, Mohamed}, booktitle = {Organic Computing – Doctoral Dissertation Colloquium 2022}, editor = {Tomforde, Sven and Krupitzer, Christian}, keywords = {itegpub}, pages = {1–16}, publisher = {kassel university press}, title = {Self-Adaptive Charging Management in Electric Vehicle Infrastructures based on Reinforcement Learning}, year = 2022 }
%0 Book Section %1 hassouna2022self %A Hassouna, Mohamed %B Organic Computing -- Doctoral Dissertation Colloquium 2022 %D 2022 %E Tomforde, Sven %E Krupitzer, Christian %I kassel university press %P 1--16 %T Self-Adaptive Charging Management in Electric Vehicle Infrastructures based on Reinforcement Learning %X Electromobility plays an increasingly important role in the energy transition. Electric vehicle charging poses challenges to the electricity grid due to high peak demand situations. Therefore, it is crucial to leverage the vehicle's flexibility when charging can be delayed. Conventional charging management systems cannot adapt to frequently changing conditions such as fluctuating renewable energy output, electricity prices and user behavior. In this article, we investigate the application of reinforcement learning approaches for self-adaptive charging management. In particular, we identify challenges regarding realistic environments and adaption to varying topologies and connections among charging stations. We describe related approaches and propose ideas and planned experiments to overcome these problems by utilizing generative models and graph neural networks.
Proactive hybrid learning and optimisation in self-adaptive systems: The swarm-fleet infrastructure scenario. Krupitzer, Christian; Gruhl, Christian; Sick, Bernhard; Tomforde, Sven. In Information and Software Technology, 145, bl 106826. Elsevier, 2022.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Context: Smart and adaptive Systems, such as self-adaptive and self-organising (SASO) systems, typically consist of a large set of highly autonomous and heterogeneous subsystems that are able to adapt their behaviour to the requirements of ever-changing, dynamic environments. Their successful operation is based on appropriate modelling of the internal and external conditions. Objective: The control problem for establishing a near-to-optimal coordinated behaviour of systems with multiple, potentially conflicting objectives is either approached in a distributed (i.e., fully autonomous by the autonomous subsystems) or in a centralised way (i.e. one instance controlling the optimisation and planning process). In the distributed approach, selfish behaviour and being limited to local knowledge may lead to sub-optimal system behaviour, while the centralised approach ignores the autonomy and the coordination efforts of parts of the system. Method: In this article, we present a concept for a hybrid (i.e., integrating a central optimisation with a distributed decision-making process) system management that combines local reinforcement learning and self-awareness mechanisms of fully autonomous subsystems with external system-wide planning and optimisation of adaptation freedom that steers the behaviour dynamically by issuing plans and guidelines augmented with incentivisation schemes. Results: This work addresses the inherent uncertainty of the dynamic system behaviour, the local autonomous and context-aware learning of subsystems, and proactive control based on adaptiveness. We provide the ‘swarm-fleet infrastructure’—a self-organised taxi service established by autonomous, privately-owned cars—as a testbed for structured comparison of systems. Conclusion: The ‘swarm-fleet infrastructure’ supports the advantages of a proactive hybrid self-adaptive and self-organising system operation. Further, we provide a system model to combine the system-wide optimisation while ensuring local decision-making through reinforcement learning for individualised configurations.
@article{krupitzer2022proactive, abstract = {Context: Smart and adaptive Systems, such as self-adaptive and self-organising (SASO) systems, typically consist of a large set of highly autonomous and heterogeneous subsystems that are able to adapt their behaviour to the requirements of ever-changing, dynamic environments. Their successful operation is based on appropriate modelling of the internal and external conditions. Objective: The control problem for establishing a near-to-optimal coordinated behaviour of systems with multiple, potentially conflicting objectives is either approached in a distributed (i.e., fully autonomous by the autonomous subsystems) or in a centralised way (i.e. one instance controlling the optimisation and planning process). In the distributed approach, selfish behaviour and being limited to local knowledge may lead to sub-optimal system behaviour, while the centralised approach ignores the autonomy and the coordination efforts of parts of the system. Method: In this article, we present a concept for a hybrid (i.e., integrating a central optimisation with a distributed decision-making process) system management that combines local reinforcement learning and self-awareness mechanisms of fully autonomous subsystems with external system-wide planning and optimisation of adaptation freedom that steers the behaviour dynamically by issuing plans and guidelines augmented with incentivisation schemes. Results: This work addresses the inherent uncertainty of the dynamic system behaviour, the local autonomous and context-aware learning of subsystems, and proactive control based on adaptiveness. We provide the ‘swarm-fleet infrastructure’—a self-organised taxi service established by autonomous, privately-owned cars—as a testbed for structured comparison of systems. Conclusion: The ‘swarm-fleet infrastructure’ supports the advantages of a proactive hybrid self-adaptive and self-organising system operation. Further, we provide a system model to combine the system-wide optimisation while ensuring local decision-making through reinforcement learning for individualised configurations.}, author = {Krupitzer, Christian and Gruhl, Christian and Sick, Bernhard and Tomforde, Sven}, journal = {Information and Software Technology}, keywords = {itegpub}, pages = 106826, publisher = {Elsevier}, title = {Proactive hybrid learning and optimisation in self-adaptive systems: The swarm-fleet infrastructure scenario}, volume = 145, year = 2022 }
%0 Journal Article %1 krupitzer2022proactive %A Krupitzer, Christian %A Gruhl, Christian %A Sick, Bernhard %A Tomforde, Sven %D 2022 %I Elsevier %J Information and Software Technology %P 106826 %R 10.1016/j.infsof.2022.106826 %T Proactive hybrid learning and optimisation in self-adaptive systems: The swarm-fleet infrastructure scenario %U https://www.sciencedirect.com/science/article/abs/pii/S0950584922000052 %V 145 %X Context: Smart and adaptive Systems, such as self-adaptive and self-organising (SASO) systems, typically consist of a large set of highly autonomous and heterogeneous subsystems that are able to adapt their behaviour to the requirements of ever-changing, dynamic environments. Their successful operation is based on appropriate modelling of the internal and external conditions. Objective: The control problem for establishing a near-to-optimal coordinated behaviour of systems with multiple, potentially conflicting objectives is either approached in a distributed (i.e., fully autonomous by the autonomous subsystems) or in a centralised way (i.e. one instance controlling the optimisation and planning process). In the distributed approach, selfish behaviour and being limited to local knowledge may lead to sub-optimal system behaviour, while the centralised approach ignores the autonomy and the coordination efforts of parts of the system. Method: In this article, we present a concept for a hybrid (i.e., integrating a central optimisation with a distributed decision-making process) system management that combines local reinforcement learning and self-awareness mechanisms of fully autonomous subsystems with external system-wide planning and optimisation of adaptation freedom that steers the behaviour dynamically by issuing plans and guidelines augmented with incentivisation schemes. Results: This work addresses the inherent uncertainty of the dynamic system behaviour, the local autonomous and context-aware learning of subsystems, and proactive control based on adaptiveness. We provide the ‘swarm-fleet infrastructure’—a self-organised taxi service established by autonomous, privately-owned cars—as a testbed for structured comparison of systems. Conclusion: The ‘swarm-fleet infrastructure’ supports the advantages of a proactive hybrid self-adaptive and self-organising system operation. Further, we provide a system model to combine the system-wide optimisation while ensuring local decision-making through reinforcement learning for individualised configurations.
Predicting flow stress behavior of an AA7075 alloy using machine learning methods. Decke, Jens; Engelhardt, Anna; Rauch, Lukas; Degener, Sebastian; Sajjadifar, Seyedvahid; Scharifi, Emad; Steinhoff, Kurt; Niendorf, Thomas; Sick, Bernhard. In Crystals, 9(12), bll 1–19. MDPI, 2022.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
This work focuses on the prediction of hot deformation behavior of thermo-mechanically processed precipitation hardenable aluminum alloy AA7075. Data available are focusing on a novel hot forming process at different tool temperatures ranging from 24°C to 350°C to set different cooling rates after solution-heat-treatment. Isothermal uniaxial tensile tests in the temperature range from 200°C to 400°C and at strain rates ranging from 0.001 s^-1 to 0.1 s^-1 were carried out on four different material conditions. The present paper mainly focuses on a comparative study of modeling techniques based on Machine Learning (ML) and the well-known Zerilli-Armstrong model (Z-A) as an empirically based reference. Work focused on predicting single data points of curves that the model was trained on. Due to the novel way data were split with respect to training and testing data, it becomes possible to predict entire stress-strain curves which leads to a reduction in the number of required laboratory experiments, finally saving costs and time in future experiments. While all investigated ML methods showed a higher performance than the Z-A model, the extreme Gradient Boosting model (XGB) showed the superior results, i.e., highest error reduction of 91% with respect to the Mean Squared Error.
@article{decke2022predicting, abstract = {This work focuses on the prediction of hot deformation behavior of thermo-mechanically processed precipitation hardenable aluminum alloy AA7075. Data available are focusing on a novel hot forming process at different tool temperatures ranging from 24°C to 350°C to set different cooling rates after solution-heat-treatment. Isothermal uniaxial tensile tests in the temperature range from 200°C to 400°C and at strain rates ranging from 0.001 s^{-1} to 0.1 s^{-1} were carried out on four different material conditions. The present paper mainly focuses on a comparative study of modeling techniques based on Machine Learning (ML) and the well-known Zerilli-Armstrong model (Z-A) as an empirically based reference. Work focused on predicting single data points of curves that the model was trained on. Due to the novel way data were split with respect to training and testing data, it becomes possible to predict entire stress-strain curves which leads to a reduction in the number of required laboratory experiments, finally saving costs and time in future experiments. While all investigated ML methods showed a higher performance than the Z-A model, the extreme Gradient Boosting model (XGB) showed the superior results, i.e., highest error reduction of 91% with respect to the Mean Squared Error.}, author = {Decke, Jens and Engelhardt, Anna and Rauch, Lukas and Degener, Sebastian and Sajjadifar, Seyedvahid and Scharifi, Emad and Steinhoff, Kurt and Niendorf, Thomas and Sick, Bernhard}, journal = {Crystals}, keywords = {itegpub}, number = 12, pages = {1–19}, publisher = {MDPI}, title = {Predicting flow stress behavior of an AA7075 alloy using machine learning methods}, volume = 9, year = 2022 }
%0 Journal Article %1 decke2022predicting %A Decke, Jens %A Engelhardt, Anna %A Rauch, Lukas %A Degener, Sebastian %A Sajjadifar, Seyedvahid %A Scharifi, Emad %A Steinhoff, Kurt %A Niendorf, Thomas %A Sick, Bernhard %D 2022 %I MDPI %J Crystals %N 12 %P 1--19 %R 10.3390/cryst12091281 %T Predicting flow stress behavior of an AA7075 alloy using machine learning methods %U https://www.mdpi.com/2073-4352/12/9/1281 %V 9 %X This work focuses on the prediction of hot deformation behavior of thermo-mechanically processed precipitation hardenable aluminum alloy AA7075. Data available are focusing on a novel hot forming process at different tool temperatures ranging from 24°C to 350°C to set different cooling rates after solution-heat-treatment. Isothermal uniaxial tensile tests in the temperature range from 200°C to 400°C and at strain rates ranging from 0.001 s^-1 to 0.1 s^-1 were carried out on four different material conditions. The present paper mainly focuses on a comparative study of modeling techniques based on Machine Learning (ML) and the well-known Zerilli-Armstrong model (Z-A) as an empirically based reference. Work focused on predicting single data points of curves that the model was trained on. Due to the novel way data were split with respect to training and testing data, it becomes possible to predict entire stress-strain curves which leads to a reduction in the number of required laboratory experiments, finally saving costs and time in future experiments. While all investigated ML methods showed a higher performance than the Z-A model, the extreme Gradient Boosting model (XGB) showed the superior results, i.e., highest error reduction of 91% with respect to the Mean Squared Error.
Pose and Semantic Map Based Probabilistic Forecast of Vulnerable Road Users Trajectories. Kress, Viktor; Jeske, Fabian; Zernetsch, Stefan; Doll, Konrad; Sick, Bernhard. In IEEE Transactions on Intelligent Vehicles, 8(3), bll 2592–2603. IEEE, 2022.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
In this article, an approach for probabilistic trajectory forecasting of vulnerable road users (VRUs) is presented, taking into consideration past movements and the surrounding environment. Past movements are represented by 3D poses reflecting the posture and movements of individual body parts. The surrounding environment is modeled in the form of semantic maps showing, e.g., the course of streets, sidewalks, and the occurrence of obstacles. Forecasts are generated in grids discretizing the space and in the form of arbitrary discrete probability distributions. The distributions are evaluated for their reliability, sharpness, and positional accuracy. We compare our method with two approaches providing forecasts in the form of continuous probability distributions, and we discuss their respective advantages and disadvantages. We thereby investigate the impact of poses and semantic maps. Using a technique we refer to as spatial label smoothing, our approach is able to achieve reliable forecasts. Overall, the 3D poses have a positive impact on the forecasts. The semantic maps facilitate the adaptation of the probability distributions to the individual situation and prevent forecasts of trajectories leading through obstacles. Our method is evaluated on a dataset recorded in inner-city traffic using a research vehicle. The dataset has been made publicly available.
@article{kress2022pose, abstract = {In this article, an approach for probabilistic trajectory forecasting of vulnerable road users (VRUs) is presented, taking into consideration past movements and the surrounding environment. Past movements are represented by 3D poses reflecting the posture and movements of individual body parts. The surrounding environment is modeled in the form of semantic maps showing, e.g., the course of streets, sidewalks, and the occurrence of obstacles. Forecasts are generated in grids discretizing the space and in the form of arbitrary discrete probability distributions. The distributions are evaluated for their reliability, sharpness, and positional accuracy. We compare our method with two approaches providing forecasts in the form of continuous probability distributions, and we discuss their respective advantages and disadvantages. We thereby investigate the impact of poses and semantic maps. Using a technique we refer to as spatial label smoothing, our approach is able to achieve reliable forecasts. Overall, the 3D poses have a positive impact on the forecasts. The semantic maps facilitate the adaptation of the probability distributions to the individual situation and prevent forecasts of trajectories leading through obstacles. Our method is evaluated on a dataset recorded in inner-city traffic using a research vehicle. The dataset has been made publicly available.}, author = {Kress, Viktor and Jeske, Fabian and Zernetsch, Stefan and Doll, Konrad and Sick, Bernhard}, journal = {IEEE Transactions on Intelligent Vehicles}, keywords = {itegpub}, number = 3, pages = {2592–2603}, publisher = {IEEE}, title = {Pose and Semantic Map Based Probabilistic Forecast of Vulnerable Road Users Trajectories}, volume = 8, year = 2022 }
%0 Journal Article %1 kress2022pose %A Kress, Viktor %A Jeske, Fabian %A Zernetsch, Stefan %A Doll, Konrad %A Sick, Bernhard %D 2022 %I IEEE %J IEEE Transactions on Intelligent Vehicles %N 3 %P 2592--2603 %R 10.1109/TIV.2022.3149624 %T Pose and Semantic Map Based Probabilistic Forecast of Vulnerable Road Users Trajectories %V 8 %X In this article, an approach for probabilistic trajectory forecasting of vulnerable road users (VRUs) is presented, taking into consideration past movements and the surrounding environment. Past movements are represented by 3D poses reflecting the posture and movements of individual body parts. The surrounding environment is modeled in the form of semantic maps showing, e.g., the course of streets, sidewalks, and the occurrence of obstacles. Forecasts are generated in grids discretizing the space and in the form of arbitrary discrete probability distributions. The distributions are evaluated for their reliability, sharpness, and positional accuracy. We compare our method with two approaches providing forecasts in the form of continuous probability distributions, and we discuss their respective advantages and disadvantages. We thereby investigate the impact of poses and semantic maps. Using a technique we refer to as spatial label smoothing, our approach is able to achieve reliable forecasts. Overall, the 3D poses have a positive impact on the forecasts. The semantic maps facilitate the adaptation of the probability distributions to the individual situation and prevent forecasts of trajectories leading through obstacles. Our method is evaluated on a dataset recorded in inner-city traffic using a research vehicle. The dataset has been made publicly available.
Organic Computing -- Doctoral Dissertation Colloquium 2021. Tomforde, Sven; Krupitzer, Christian. In Vol. 20Intelligent Embedded Systems. kassel university press, 2022.
- [ BibTeX ]
- [ EndNote ]
@book{tomforde2022organic, editor = {Tomforde, Sven and Krupitzer, Christian}, keywords = {itegpub}, publisher = {kassel university press}, series = {Intelligent Embedded Systems}, title = {Organic Computing – Doctoral Dissertation Colloquium 2021}, volume = 20, year = 2022 }
%0 Book %1 tomforde2022organic %B Intelligent Embedded Systems %D 2022 %E Tomforde, Sven %E Krupitzer, Christian %I kassel university press %R 10.17170/kobra-202202215780 %T Organic Computing -- Doctoral Dissertation Colloquium 2021 %V 20
Optimizing a superconducting radio-frequency gun using deep reinforcement learning. Meier, David; Ramirez, Luis Vera; Völker, Jens; Viefhaus, Jens; Sick, Bernhard; Hartmann, Gregor. In Physical Review Accelerators and Beams, 25(10), bl 104604. American Physical Society, 2022.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Superconducting photoelectron injectors are promising for generating highly brilliant pulsed electron beams with high repetition rates and low emittances. Experiments such as ultrafast electron diffraction, experiments at the Terahertz scale, and energy recovery linac applications require such properties. However, optimizing the beam properties is challenging due to the high number of possible machine parameter combinations. This article shows the successful automated optimization of beam properties utilizing an already existing simulation model. To reduce the required computation time, we replace the costly simulation with a faster approximation with a neural network. For optimization, we propose a reinforcement learning approach leveraging the simple computation of the derivative of the approximation. We prove that our approach outperforms standard optimization methods for the required function evaluations given a defined minimum accuracy.
@article{meier2022optimizing, abstract = {Superconducting photoelectron injectors are promising for generating highly brilliant pulsed electron beams with high repetition rates and low emittances. Experiments such as ultrafast electron diffraction, experiments at the Terahertz scale, and energy recovery linac applications require such properties. However, optimizing the beam properties is challenging due to the high number of possible machine parameter combinations. This article shows the successful automated optimization of beam properties utilizing an already existing simulation model. To reduce the required computation time, we replace the costly simulation with a faster approximation with a neural network. For optimization, we propose a reinforcement learning approach leveraging the simple computation of the derivative of the approximation. We prove that our approach outperforms standard optimization methods for the required function evaluations given a defined minimum accuracy.}, author = {Meier, David and Ramirez, Luis Vera and Völker, Jens and Viefhaus, Jens and Sick, Bernhard and Hartmann, Gregor}, journal = {Physical Review Accelerators and Beams}, keywords = {SimulationTechniques}, number = 10, pages = 104604, publisher = {American Physical Society}, title = {Optimizing a superconducting radio-frequency gun using deep reinforcement learning}, volume = 25, year = 2022 }
%0 Journal Article %1 meier2022optimizing %A Meier, David %A Ramirez, Luis Vera %A Völker, Jens %A Viefhaus, Jens %A Sick, Bernhard %A Hartmann, Gregor %D 2022 %I American Physical Society %J Physical Review Accelerators and Beams %N 10 %P 104604 %R 10.1103/PhysRevAccelBeams.25.104604 %T Optimizing a superconducting radio-frequency gun using deep reinforcement learning %U https://journals.aps.org/prab/abstract/10.1103/PhysRevAccelBeams.25.104604 %V 25 %X Superconducting photoelectron injectors are promising for generating highly brilliant pulsed electron beams with high repetition rates and low emittances. Experiments such as ultrafast electron diffraction, experiments at the Terahertz scale, and energy recovery linac applications require such properties. However, optimizing the beam properties is challenging due to the high number of possible machine parameter combinations. This article shows the successful automated optimization of beam properties utilizing an already existing simulation model. To reduce the required computation time, we replace the costly simulation with a faster approximation with a neural network. For optimization, we propose a reinforcement learning approach leveraging the simple computation of the derivative of the approximation. We prove that our approach outperforms standard optimization methods for the required function evaluations given a defined minimum accuracy.
On the Extension of the Weisfeiler-Lehman Hierarchy by WL Tests for Arbitrary Graphs. Beddar-Wiesing, Silvia; D’Inverno, Giuseppe Alessio; Graziani, Caterina; Lachi, Veronica; Moallemy-Oureh, Alice; Scarselli, Franco. In Workshp on Mining and Learning on Graphs (MLG), ECML PKDD, bll 1–13. 2022.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Graph isomorphism (GI) has occupied both theoreticians and applied scientists since the early 1950s. Over the years, several approaches and algorithms with which an isomorphism between two graphs can be tested have been developed. A general approach is the Weisfeiler–Lehman (WL) test, which is based on a coloring algorithm and provides a necessary criterion for graph isomorphism. However, the WL test is restricted to examining graphs with only node attributes. Therefore, this paper presents two extensions of the WL algorithm to allow for testing on arbitrary graphs. One considers edge attributes, and the other tests the isomorphism on dynamic graphs. Additionally, we extend the WL-hierarchy by the attributed and dynamic WL tests and show that it is a partial order, which induces a lattice. In the future, this may allow for practical implications coming from lattice theory.
@inproceedings{beddarwiesing2022extension, abstract = {Graph isomorphism (GI) has occupied both theoreticians and applied scientists since the early 1950s. Over the years, several approaches and algorithms with which an isomorphism between two graphs can be tested have been developed. A general approach is the Weisfeiler–Lehman (WL) test, which is based on a coloring algorithm and provides a necessary criterion for graph isomorphism. However, the WL test is restricted to examining graphs with only node attributes. Therefore, this paper presents two extensions of the WL algorithm to allow for testing on arbitrary graphs. One considers edge attributes, and the other tests the isomorphism on dynamic graphs. Additionally, we extend the WL-hierarchy by the attributed and dynamic WL tests and show that it is a partial order, which induces a lattice. In the future, this may allow for practical implications coming from lattice theory.}, author = {Beddar-Wiesing, Silvia and D'Inverno, Giuseppe Alessio and Graziani, Caterina and Lachi, Veronica and Moallemy-Oureh, Alice and Scarselli, Franco}, booktitle = {Workshp on Mining and Learning on Graphs (MLG), ECML PKDD}, keywords = {itegpub}, pages = {1–13}, title = {On the Extension of the {W}eisfeiler-{L}ehman Hierarchy by WL Tests for Arbitrary Graphs}, year = 2022 }
%0 Conference Paper %1 beddarwiesing2022extension %A Beddar-Wiesing, Silvia %A D'Inverno, Giuseppe Alessio %A Graziani, Caterina %A Lachi, Veronica %A Moallemy-Oureh, Alice %A Scarselli, Franco %B Workshp on Mining and Learning on Graphs (MLG), ECML PKDD %D 2022 %P 1--13 %T On the Extension of the Weisfeiler-Lehman Hierarchy by WL Tests for Arbitrary Graphs %U https://openreview.net/forum?id=Qt6GrgDz2y5 %X Graph isomorphism (GI) has occupied both theoreticians and applied scientists since the early 1950s. Over the years, several approaches and algorithms with which an isomorphism between two graphs can be tested have been developed. A general approach is the Weisfeiler–Lehman (WL) test, which is based on a coloring algorithm and provides a necessary criterion for graph isomorphism. However, the WL test is restricted to examining graphs with only node attributes. Therefore, this paper presents two extensions of the WL algorithm to allow for testing on arbitrary graphs. One considers edge attributes, and the other tests the isomorphism on dynamic graphs. Additionally, we extend the WL-hierarchy by the attributed and dynamic WL tests and show that it is a partial order, which induces a lattice. In the future, this may allow for practical implications coming from lattice theory.
NDNET: A Unified Framework for Anomaly and Novelty Detection. Decke, Jens; Schmeißing, Jörn; Botache, Diego; Bieshaar, Maarten; Sick, Bernhard; Gruhl, Christian. In International Conference on Architecture of Computing Systems (ARCS), bll 197–210. Springer, 2022.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
We introduce NDNET (https://novelty-detection.net/p/ndnet), an anomaly and novelty detection library that implements various detection algorithms adjusted for online processing of data streams. The intention of this library is threefold: 1) Make experimentation with different anomaly and novelty detection algorithms simple. 2) Support the development of new novelty detection approaches by providing the mCANDIES framework. 3) Provide fundamentals to analyze and evaluate novelty detection algorithms on data streams. The library is freely available and developed as open-source software.
@inproceedings{decke2022ndnet, abstract = {We introduce NDNET (https://novelty-detection.net/p/ndnet), an anomaly and novelty detection library that implements various detection algorithms adjusted for online processing of data streams. The intention of this library is threefold: 1) Make experimentation with different anomaly and novelty detection algorithms simple. 2) Support the development of new novelty detection approaches by providing the mCANDIES framework. 3) Provide fundamentals to analyze and evaluate novelty detection algorithms on data streams. The library is freely available and developed as open-source software.}, author = {Decke, Jens and Schmeißing, Jörn and Botache, Diego and Bieshaar, Maarten and Sick, Bernhard and Gruhl, Christian}, booktitle = {International Conference on Architecture of Computing Systems (ARCS)}, keywords = {itegpub}, pages = {197–210}, publisher = {Springer}, title = {{NDNET}: {A} Unified Framework for Anomaly and Novelty Detection}, year = 2022 }
%0 Conference Paper %1 decke2022ndnet %A Decke, Jens %A Schmeißing, Jörn %A Botache, Diego %A Bieshaar, Maarten %A Sick, Bernhard %A Gruhl, Christian %B International Conference on Architecture of Computing Systems (ARCS) %D 2022 %I Springer %P 197--210 %R 10.1007/978-3-031-21867-5_13 %T NDNET: A Unified Framework for Anomaly and Novelty Detection %X We introduce NDNET (https://novelty-detection.net/p/ndnet), an anomaly and novelty detection library that implements various detection algorithms adjusted for online processing of data streams. The intention of this library is threefold: 1) Make experimentation with different anomaly and novelty detection algorithms simple. 2) Support the development of new novelty detection approaches by providing the mCANDIES framework. 3) Provide fundamentals to analyze and evaluate novelty detection algorithms on data streams. The library is freely available and developed as open-source software.
Multi-Task Autoencoders and Transfer Learning for Day-Ahead Wind and Photovoltaic Power Forecasts. Schreiber, Jens; Sick, Bernhard. In Energies, 15(21), bl 8062. MDPI, 2022.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
Integrating new renewable energy resources requires robust and reliable forecasts to ensure a stable electrical grid and avoid blackouts. Sophisticated representation learning techniques, such as autoencoders, play an essential role, as they allow for the extraction of latent features to forecast the expected generated wind and photovoltaic power for the next seconds up to days. Thereby, autoencoders reduce the required training time and the time spent in manual feature engineering and often improve the forecast error. However, most current renewable energy forecasting research on autoencoders focuses on smaller forecast horizons for the following seconds and hours based on meteorological measurements. At the same time, larger forecast horizons, such as day-ahead power forecasts based on numerical weather predictions, are crucial for planning loads and demands within the electrical grid to prevent power failures. There is little evidence on the ability of autoencoders and their respective forecasting models to improve through multi-task learning and time series autoencoders for day-ahead power forecasts. We can close these gaps by proposing a multi-task learning autoencoder based on the recently introduced temporal convolution network. This approach reduces the number of trainable parameters by 38 for photovoltaic data and 202 for wind data while having the best reconstruction error compared to nine other representation learning techniques. At the same time, this model decreases the day-ahead forecast error up to 18.3% for photovoltaic parks and 1.5% for wind parks. We round off these results by analyzing the influences of the latent size and the number of layers to fine-tune the encoder for wind and photovoltaic power forecasts.
@article{schreiber2022multi, abstract = {Integrating new renewable energy resources requires robust and reliable forecasts to ensure a stable electrical grid and avoid blackouts. Sophisticated representation learning techniques, such as autoencoders, play an essential role, as they allow for the extraction of latent features to forecast the expected generated wind and photovoltaic power for the next seconds up to days. Thereby, autoencoders reduce the required training time and the time spent in manual feature engineering and often improve the forecast error. However, most current renewable energy forecasting research on autoencoders focuses on smaller forecast horizons for the following seconds and hours based on meteorological measurements. At the same time, larger forecast horizons, such as day-ahead power forecasts based on numerical weather predictions, are crucial for planning loads and demands within the electrical grid to prevent power failures. There is little evidence on the ability of autoencoders and their respective forecasting models to improve through multi-task learning and time series autoencoders for day-ahead power forecasts. We can close these gaps by proposing a multi-task learning autoencoder based on the recently introduced temporal convolution network. This approach reduces the number of trainable parameters by 38 for photovoltaic data and 202 for wind data while having the best reconstruction error compared to nine other representation learning techniques. At the same time, this model decreases the day-ahead forecast error up to 18.3% for photovoltaic parks and 1.5% for wind parks. We round off these results by analyzing the influences of the latent size and the number of layers to fine-tune the encoder for wind and photovoltaic power forecasts.}, author = {Schreiber, Jens and Sick, Bernhard}, journal = {Energies}, keywords = {itegpub}, number = 21, pages = 8062, publisher = {MDPI}, title = {Multi-Task Autoencoders and Transfer Learning for Day-Ahead Wind and Photovoltaic Power Forecasts}, volume = 15, year = 2022 }
%0 Journal Article %1 schreiber2022multi %A Schreiber, Jens %A Sick, Bernhard %D 2022 %I MDPI %J Energies %N 21 %P 8062 %R 10.3390/en15218062 %T Multi-Task Autoencoders and Transfer Learning for Day-Ahead Wind and Photovoltaic Power Forecasts %V 15 %X Integrating new renewable energy resources requires robust and reliable forecasts to ensure a stable electrical grid and avoid blackouts. Sophisticated representation learning techniques, such as autoencoders, play an essential role, as they allow for the extraction of latent features to forecast the expected generated wind and photovoltaic power for the next seconds up to days. Thereby, autoencoders reduce the required training time and the time spent in manual feature engineering and often improve the forecast error. However, most current renewable energy forecasting research on autoencoders focuses on smaller forecast horizons for the following seconds and hours based on meteorological measurements. At the same time, larger forecast horizons, such as day-ahead power forecasts based on numerical weather predictions, are crucial for planning loads and demands within the electrical grid to prevent power failures. There is little evidence on the ability of autoencoders and their respective forecasting models to improve through multi-task learning and time series autoencoders for day-ahead power forecasts. We can close these gaps by proposing a multi-task learning autoencoder based on the recently introduced temporal convolution network. This approach reduces the number of trainable parameters by 38 for photovoltaic data and 202 for wind data while having the best reconstruction error compared to nine other representation learning techniques. At the same time, this model decreases the day-ahead forecast error up to 18.3% for photovoltaic parks and 1.5% for wind parks. We round off these results by analyzing the influences of the latent size and the number of layers to fine-tune the encoder for wind and photovoltaic power forecasts.
Heterogeneous Multi-Source Deep Adaptive Knowledge-Aware Learning for E-Mobility. Ali, Mohammad Wazed. In IEEE International Conference on Autonomic Computing and Self-Organizing Systems Companion (ACSOS-C), bll 57–60. IEEE, 2022.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Electromobility (e-mobility) reduces global fossil fuel-based energy demand and promotes the usage of renewable energy sources. Different types of electric vehicle (EVs) production have increased recently due to their need. However, there is no fixed charging behavior, and demand exists. Uncontrolled EV charging may lead to a harmful impact on the power grid. Besides, most renewable energy sources depend highly on the weather and location. Thus, analyzing, forecasting, and adapting EV charging demand is essential to prevent power outages. Deep Learning (DL) models are a de facto standard technology for energy forecasting in many scenarios. Still, there is a lack of real-world data in the e-mobility domain to train a DL model from scratch. Besides, DL models have explainability issues, which can hinder decision-making. This article proposes a novel framework for addressing data scarcity issues, enabling continuous adaptation to change, and improving explainability.
@inproceedings{ali2022heterogeneous, abstract = {Electromobility (e-mobility) reduces global fossil fuel-based energy demand and promotes the usage of renewable energy sources. Different types of electric vehicle (EVs) production have increased recently due to their need. However, there is no fixed charging behavior, and demand exists. Uncontrolled EV charging may lead to a harmful impact on the power grid. Besides, most renewable energy sources depend highly on the weather and location. Thus, analyzing, forecasting, and adapting EV charging demand is essential to prevent power outages. Deep Learning (DL) models are a de facto standard technology for energy forecasting in many scenarios. Still, there is a lack of real-world data in the e-mobility domain to train a DL model from scratch. Besides, DL models have explainability issues, which can hinder decision-making. This article proposes a novel framework for addressing data scarcity issues, enabling continuous adaptation to change, and improving explainability.}, author = {Ali, Mohammad Wazed}, booktitle = {IEEE International Conference on Autonomic Computing and Self-Organizing Systems Companion (ACSOS-C)}, keywords = {itegpub}, pages = {57–60}, publisher = {IEEE}, title = {Heterogeneous Multi-Source Deep Adaptive Knowledge-Aware Learning for E-Mobility}, year = 2022 }
%0 Conference Paper %1 ali2022heterogeneous %A Ali, Mohammad Wazed %B IEEE International Conference on Autonomic Computing and Self-Organizing Systems Companion (ACSOS-C) %D 2022 %I IEEE %P 57--60 %R 10.1109/ACSOSC56246.2022.00030 %T Heterogeneous Multi-Source Deep Adaptive Knowledge-Aware Learning for E-Mobility %U https://ieeexplore.ieee.org/document/9935088 %X Electromobility (e-mobility) reduces global fossil fuel-based energy demand and promotes the usage of renewable energy sources. Different types of electric vehicle (EVs) production have increased recently due to their need. However, there is no fixed charging behavior, and demand exists. Uncontrolled EV charging may lead to a harmful impact on the power grid. Besides, most renewable energy sources depend highly on the weather and location. Thus, analyzing, forecasting, and adapting EV charging demand is essential to prevent power outages. Deep Learning (DL) models are a de facto standard technology for energy forecasting in many scenarios. Still, there is a lack of real-world data in the e-mobility domain to train a DL model from scratch. Besides, DL models have explainability issues, which can hinder decision-making. This article proposes a novel framework for addressing data scarcity issues, enabling continuous adaptation to change, and improving explainability.
Graph Neural Networks Designed for Different Graph Types: A Survey. Thomas, Josephine M.; Moallemy-Oureh, Alice; Beddar-Wiesing, Silvia; Holzhüter, Clara. In arXiv e-prints, bl arXiv:2204.03080. 2022.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Graphs are ubiquitous in nature and can therefore serve as models for many practical but also theoretical problems. Based on this, the young research field of Graph Neural Networks (GNNs) has emerged. Despite the youth of the field and the speed in which new models are developed, many good surveys have been published in the last years. Nevertheless, an overview on which graph types can be modeled by GNNs is missing. In this survey, we give a detailed overview of already existing GNNs and, unlike previous surveys, categorize them according to their ability to handle different graph types and properties. We consider GNNs operating on static as well as on dynamic graphs of different structural constitutions, with or without node or edge attributes. Moreover in the dynamic case, we separate the models in discrete-time and continuous-time dynamic graphs based on their architecture. While ordering the existing GNN models, we find, that there are still graph types, that are not or only rarely covered by existing GNN models. We point out where models are missing and give potential reasons for their absence.
@article{thomas2022graph, abstract = {Graphs are ubiquitous in nature and can therefore serve as models for many practical but also theoretical problems. Based on this, the young research field of Graph Neural Networks (GNNs) has emerged. Despite the youth of the field and the speed in which new models are developed, many good surveys have been published in the last years. Nevertheless, an overview on which graph types can be modeled by GNNs is missing. In this survey, we give a detailed overview of already existing GNNs and, unlike previous surveys, categorize them according to their ability to handle different graph types and properties. We consider GNNs operating on static as well as on dynamic graphs of different structural constitutions, with or without node or edge attributes. Moreover in the dynamic case, we separate the models in discrete-time and continuous-time dynamic graphs based on their architecture. While ordering the existing GNN models, we find, that there are still graph types, that are not or only rarely covered by existing GNN models. We point out where models are missing and give potential reasons for their absence.}, author = {Thomas, Josephine M. and Moallemy-Oureh, Alice and Beddar-Wiesing, Silvia and Holzhüter, Clara}, journal = {arXiv e-prints}, keywords = {itegpub}, pages = {arXiv:2204.03080}, title = {Graph Neural Networks Designed for Different Graph Types: A Survey}, year = 2022 }
%0 Journal Article %1 thomas2022graph %A Thomas, Josephine M. %A Moallemy-Oureh, Alice %A Beddar-Wiesing, Silvia %A Holzhüter, Clara %D 2022 %J arXiv e-prints %P arXiv:2204.03080 %T Graph Neural Networks Designed for Different Graph Types: A Survey %U https://arxiv.org/abs/2204.03080 %X Graphs are ubiquitous in nature and can therefore serve as models for many practical but also theoretical problems. Based on this, the young research field of Graph Neural Networks (GNNs) has emerged. Despite the youth of the field and the speed in which new models are developed, many good surveys have been published in the last years. Nevertheless, an overview on which graph types can be modeled by GNNs is missing. In this survey, we give a detailed overview of already existing GNNs and, unlike previous surveys, categorize them according to their ability to handle different graph types and properties. We consider GNNs operating on static as well as on dynamic graphs of different structural constitutions, with or without node or edge attributes. Moreover in the dynamic case, we separate the models in discrete-time and continuous-time dynamic graphs based on their architecture. While ordering the existing GNN models, we find, that there are still graph types, that are not or only rarely covered by existing GNN models. We point out where models are missing and give potential reasons for their absence.
Generating Synthetic Time Series for Machine-Learning-Empowered Monitoring of Electric Motor Test Benches. Westmeier, Tobias; Botache, Diego; Bieshaar, Maarten; Sick, Bernhard. In IEEE International Conference on Data Science and Advanced Analytics (DSAA), bll 513–522. IEEE, 2022.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
The development of new electric traction machines is a time-consuming process as it involves intensive testing on motor test benches. Machine-Learning-empowered monitoring offers the opportunity to anticipate costly failures early and hence reducing development time. However, machine learning (ML) for process monitoring requires large amounts of training data, especially as the targeted fault states are scarce and yet diverse in their appearances. Therefore, we propose to use synthetic time series data to leverage the high cost of acquiring training data from experiments in real test benches. In this article, we present a novel scheme to generate synthetic data based on a sub-dimensional time series representation. We introduce a highly flexible model by mapping the data to a latent representation and approximating the latent data distribution by a Gaussian Mixture Model. In addition, we propose the Frechet InceptionTime Distance (FITD) as a new distance measure to evaluate the generated data. It allows extracting characteristics at different scales by using multiple kernel sizes. In this way, we ensure that the synthesized data contains characteristics similar to those present in the real data. In our experiment, we train two types of fault detectors, one based on real data of a motor test bench and the other based on synthetic data. We also consider employing fault-aware conditional architectures to generate training data for different fault types explicitly. Our final results show that using synthesized data in the training process increases the performance in terms of classification accuracy score (CAS) up to 29%.
@inproceedings{westmeier2022generating, abstract = {The development of new electric traction machines is a time-consuming process as it involves intensive testing on motor test benches. Machine-Learning-empowered monitoring offers the opportunity to anticipate costly failures early and hence reducing development time. However, machine learning (ML) for process monitoring requires large amounts of training data, especially as the targeted fault states are scarce and yet diverse in their appearances. Therefore, we propose to use synthetic time series data to leverage the high cost of acquiring training data from experiments in real test benches. In this article, we present a novel scheme to generate synthetic data based on a sub-dimensional time series representation. We introduce a highly flexible model by mapping the data to a latent representation and approximating the latent data distribution by a Gaussian Mixture Model. In addition, we propose the Frechet InceptionTime Distance (FITD) as a new distance measure to evaluate the generated data. It allows extracting characteristics at different scales by using multiple kernel sizes. In this way, we ensure that the synthesized data contains characteristics similar to those present in the real data. In our experiment, we train two types of fault detectors, one based on real data of a motor test bench and the other based on synthetic data. We also consider employing fault-aware conditional architectures to generate training data for different fault types explicitly. Our final results show that using synthesized data in the training process increases the performance in terms of classification accuracy score (CAS) up to 29%.}, author = {Westmeier, Tobias and Botache, Diego and Bieshaar, Maarten and Sick, Bernhard}, booktitle = {IEEE International Conference on Data Science and Advanced Analytics (DSAA)}, keywords = {Variational-Autoencoder}, pages = {513–522}, publisher = {IEEE}, title = {Generating Synthetic Time Series for Machine-Learning-Empowered Monitoring of Electric Motor Test Benches}, year = 2022 }
%0 Conference Paper %1 westmeier2022generating %A Westmeier, Tobias %A Botache, Diego %A Bieshaar, Maarten %A Sick, Bernhard %B IEEE International Conference on Data Science and Advanced Analytics (DSAA) %D 2022 %I IEEE %P 513--522 %R 10.1109/DSAA54385.2022.10032385 %T Generating Synthetic Time Series for Machine-Learning-Empowered Monitoring of Electric Motor Test Benches %U https://ieeexplore.ieee.org/document/10032385 %X The development of new electric traction machines is a time-consuming process as it involves intensive testing on motor test benches. Machine-Learning-empowered monitoring offers the opportunity to anticipate costly failures early and hence reducing development time. However, machine learning (ML) for process monitoring requires large amounts of training data, especially as the targeted fault states are scarce and yet diverse in their appearances. Therefore, we propose to use synthetic time series data to leverage the high cost of acquiring training data from experiments in real test benches. In this article, we present a novel scheme to generate synthetic data based on a sub-dimensional time series representation. We introduce a highly flexible model by mapping the data to a latent representation and approximating the latent data distribution by a Gaussian Mixture Model. In addition, we propose the Frechet InceptionTime Distance (FITD) as a new distance measure to evaluate the generated data. It allows extracting characteristics at different scales by using multiple kernel sizes. In this way, we ensure that the synthesized data contains characteristics similar to those present in the real data. In our experiment, we train two types of fault detectors, one based on real data of a motor test bench and the other based on synthetic data. We also consider employing fault-aware conditional architectures to generate training data for different fault types explicitly. Our final results show that using synthesized data in the training process increases the performance in terms of classification accuracy score (CAS) up to 29%.
FDGNN: Fully Dynamic Graph Neural Network. Moallemy-Oureh, Alice; Beddar-Wiesing, Silcia; Nather, Rüdiger; Thomas, Josephine M. In arXiv e-prints, bl arXiv:2206.03469. 2022.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Dynamic Graph Neural Networks recently became more and more important as graphs from many scientific fields, ranging from mathematics, biology, social sciences, and physics to computer science, are dynamic by nature. While temporal changes (dynamics) play an essential role in many real-world applications, most of the models in the literature on Graph Neural Networks (GNN) process static graphs. The few GNN models on dynamic graphs only consider exceptional cases of dynamics, e.g., node attribute-dynamic graphs or structure-dynamic graphs limited to additions or changes to the graph's edges, etc. Therefore, we present a novel Fully Dynamic Graph Neural Network (FDGNN) that can handle fully-dynamic graphs in continuous time. The proposed method provides a node and an edge embedding that includes their activity to address added and deleted nodes or edges, and possible attributes. Furthermore, the embeddings specify Temporal Point Processes for each event to encode the distributions of the structure- and attribute-related incoming graph events. In addition, our model can be updated efficiently by considering single events for local retraining.
@article{moallemyoureh2022fdgnn, abstract = {Dynamic Graph Neural Networks recently became more and more important as graphs from many scientific fields, ranging from mathematics, biology, social sciences, and physics to computer science, are dynamic by nature. While temporal changes (dynamics) play an essential role in many real-world applications, most of the models in the literature on Graph Neural Networks (GNN) process static graphs. The few GNN models on dynamic graphs only consider exceptional cases of dynamics, e.g., node attribute-dynamic graphs or structure-dynamic graphs limited to additions or changes to the graph's edges, etc. Therefore, we present a novel Fully Dynamic Graph Neural Network (FDGNN) that can handle fully-dynamic graphs in continuous time. The proposed method provides a node and an edge embedding that includes their activity to address added and deleted nodes or edges, and possible attributes. Furthermore, the embeddings specify Temporal Point Processes for each event to encode the distributions of the structure- and attribute-related incoming graph events. In addition, our model can be updated efficiently by considering single events for local retraining.}, author = {Moallemy-Oureh, Alice and Beddar-Wiesing, Silcia and Nather, Rüdiger and Thomas, Josephine M.}, journal = {arXiv e-prints}, keywords = {itegpub}, pages = {arXiv:2206.03469}, title = {FDGNN: Fully Dynamic Graph Neural Network}, year = 2022 }
%0 Journal Article %1 moallemyoureh2022fdgnn %A Moallemy-Oureh, Alice %A Beddar-Wiesing, Silcia %A Nather, Rüdiger %A Thomas, Josephine M. %D 2022 %J arXiv e-prints %P arXiv:2206.03469 %T FDGNN: Fully Dynamic Graph Neural Network %U https://arxiv.org/abs/2206.03469 %X Dynamic Graph Neural Networks recently became more and more important as graphs from many scientific fields, ranging from mathematics, biology, social sciences, and physics to computer science, are dynamic by nature. While temporal changes (dynamics) play an essential role in many real-world applications, most of the models in the literature on Graph Neural Networks (GNN) process static graphs. The few GNN models on dynamic graphs only consider exceptional cases of dynamics, e.g., node attribute-dynamic graphs or structure-dynamic graphs limited to additions or changes to the graph's edges, etc. Therefore, we present a novel Fully Dynamic Graph Neural Network (FDGNN) that can handle fully-dynamic graphs in continuous time. The proposed method provides a node and an edge embedding that includes their activity to address added and deleted nodes or edges, and possible attributes. Furthermore, the embeddings specify Temporal Point Processes for each event to encode the distributions of the structure- and attribute-related incoming graph events. In addition, our model can be updated efficiently by considering single events for local retraining.
Fast Bayesian Updates for Deep Learning with a Use Case in Active Learning. Herde, Marek; Huang, Zhixin; Huseljic, Denis; Kottke, Daniel; Vogt, Stephan; Sick, Bernhard. In arXiv e-prints, bl arXiv:2210.06112. 2022.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Retraining deep neural networks when new data arrives is typically computationally expensive. Moreover, certain applications do not allow such costly retraining due to time or computational constraints. Fast Bayesian updates are a possible solution to this issue. Therefore, we propose a Bayesian update based on Monte-Carlo samples and a last-layer Laplace approximation for different Bayesian neural network types, i.e., Dropout, Ensemble, and Spectral Normalized Neural Gaussian Process (SNGP). In a large-scale evaluation study, we show that our updates combined with SNGP represent a fast and competitive alternative to costly retraining. As a use case, we combine the Bayesian updates for SNGP with different sequential query strategies to exemplarily demonstrate their improved selection performance in active learning.
@article{herde2022fast, abstract = {Retraining deep neural networks when new data arrives is typically computationally expensive. Moreover, certain applications do not allow such costly retraining due to time or computational constraints. Fast Bayesian updates are a possible solution to this issue. Therefore, we propose a Bayesian update based on Monte-Carlo samples and a last-layer Laplace approximation for different Bayesian neural network types, i.e., Dropout, Ensemble, and Spectral Normalized Neural Gaussian Process (SNGP). In a large-scale evaluation study, we show that our updates combined with SNGP represent a fast and competitive alternative to costly retraining. As a use case, we combine the Bayesian updates for SNGP with different sequential query strategies to exemplarily demonstrate their improved selection performance in active learning.}, author = {Herde, Marek and Huang, Zhixin and Huseljic, Denis and Kottke, Daniel and Vogt, Stephan and Sick, Bernhard}, journal = {arXiv e-prints}, keywords = {itegpub}, pages = {arXiv:2210.06112}, title = {Fast Bayesian Updates for Deep Learning with a Use Case in Active Learning}, year = 2022 }
%0 Journal Article %1 herde2022fast %A Herde, Marek %A Huang, Zhixin %A Huseljic, Denis %A Kottke, Daniel %A Vogt, Stephan %A Sick, Bernhard %D 2022 %J arXiv e-prints %P arXiv:2210.06112 %T Fast Bayesian Updates for Deep Learning with a Use Case in Active Learning %U https://arxiv.org/abs/2210.06112 %X Retraining deep neural networks when new data arrives is typically computationally expensive. Moreover, certain applications do not allow such costly retraining due to time or computational constraints. Fast Bayesian updates are a possible solution to this issue. Therefore, we propose a Bayesian update based on Monte-Carlo samples and a last-layer Laplace approximation for different Bayesian neural network types, i.e., Dropout, Ensemble, and Spectral Normalized Neural Gaussian Process (SNGP). In a large-scale evaluation study, we show that our updates combined with SNGP represent a fast and competitive alternative to costly retraining. As a use case, we combine the Bayesian updates for SNGP with different sequential query strategies to exemplarily demonstrate their improved selection performance in active learning.
Enhancing Active Learning with Weak Supervision and Transfer Learning by Leveraging Information and Knowledge Sources. Rauch, Lukas; Huseljic, Denis; Sick, Bernhard. In Workshop on Interactive Adaptive Learning (IAL), ECML PKDD, bll 27–42. 2022.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
One of the major limitations of deploying a machine learning model is the availability of labeled training data and the resulting expensive annotation process. Although active learning (AL) methods may reduce the annotation cost by actively selecting the most-useful instances, a costly human annotator usually provides the labels. Therefore, even with AL, we still consider the annotation process to be time-consuming and expensive. Besides human annotators, though, companies often have a vast amount of information and knowledge sources available that can generate low-cost labels (e.g., a black-box model) or improve the learning process (e.g., a pre-trained model). We present a novel approach that enhances AL with weak supervision (WS) and transfer learning (TL) to reduce the annotation cost by leveraging these sources. Specifically, we consider a black-box model like a rule-based system as an error-prone and weakly-supervised annotator that inexpensively provides labels. We estimate its performance with an annotator model to decide whether a human annotation is required. Additionally, we utilize unlabeled internal and external data by transferring knowledge from a pre-trained model to the AL cycle. We sequentially investigate the impact of WS and TL on annotation cost and model performance in an AL cycle through a use case. Our evaluation shows that our approach can reduce annotation cost by 51% while achieving nearly identical model performance compared to a traditional AL approach.
@inproceedings{rauch2022enhancing, abstract = {One of the major limitations of deploying a machine learning model is the availability of labeled training data and the resulting expensive annotation process. Although active learning (AL) methods may reduce the annotation cost by actively selecting the most-useful instances, a costly human annotator usually provides the labels. Therefore, even with AL, we still consider the annotation process to be time-consuming and expensive. Besides human annotators, though, companies often have a vast amount of information and knowledge sources available that can generate low-cost labels (e.g., a black-box model) or improve the learning process (e.g., a pre-trained model). We present a novel approach that enhances AL with weak supervision (WS) and transfer learning (TL) to reduce the annotation cost by leveraging these sources. Specifically, we consider a black-box model like a rule-based system as an error-prone and weakly-supervised annotator that inexpensively provides labels. We estimate its performance with an annotator model to decide whether a human annotation is required. Additionally, we utilize unlabeled internal and external data by transferring knowledge from a pre-trained model to the AL cycle. We sequentially investigate the impact of WS and TL on annotation cost and model performance in an AL cycle through a use case. Our evaluation shows that our approach can reduce annotation cost by 51% while achieving nearly identical model performance compared to a traditional AL approach.}, author = {Rauch, Lukas and Huseljic, Denis and Sick, Bernhard}, booktitle = {Workshop on Interactive Adaptive Learning (IAL), ECML PKDD}, keywords = {itegpub}, pages = {27–42}, title = {Enhancing Active Learning with Weak Supervision and Transfer Learning by Leveraging Information and Knowledge Sources}, year = 2022 }
%0 Conference Paper %1 rauch2022enhancing %A Rauch, Lukas %A Huseljic, Denis %A Sick, Bernhard %B Workshop on Interactive Adaptive Learning (IAL), ECML PKDD %D 2022 %P 27--42 %T Enhancing Active Learning with Weak Supervision and Transfer Learning by Leveraging Information and Knowledge Sources %U http://ceur-ws.org/Vol-3259/ialatecml_paper3.pdf %X One of the major limitations of deploying a machine learning model is the availability of labeled training data and the resulting expensive annotation process. Although active learning (AL) methods may reduce the annotation cost by actively selecting the most-useful instances, a costly human annotator usually provides the labels. Therefore, even with AL, we still consider the annotation process to be time-consuming and expensive. Besides human annotators, though, companies often have a vast amount of information and knowledge sources available that can generate low-cost labels (e.g., a black-box model) or improve the learning process (e.g., a pre-trained model). We present a novel approach that enhances AL with weak supervision (WS) and transfer learning (TL) to reduce the annotation cost by leveraging these sources. Specifically, we consider a black-box model like a rule-based system as an error-prone and weakly-supervised annotator that inexpensively provides labels. We estimate its performance with an annotator model to decide whether a human annotation is required. Additionally, we utilize unlabeled internal and external data by transferring knowledge from a pre-trained model to the AL cycle. We sequentially investigate the impact of WS and TL on annotation cost and model performance in an AL cycle through a use case. Our evaluation shows that our approach can reduce annotation cost by 51% while achieving nearly identical model performance compared to a traditional AL approach.
Efficient SVDD sampling with approximation guarantees for the decision boundary. Englhardt, Adrian; Trittenbach, Holger; Kottke, Daniel; Sick, Bernhard; Böhm, Klemens. In Machine Learning, 111(4), bll 1349–1375. Springer, 2022.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Support Vector Data Description (SVDD) is a popular one-class classifier for anomaly and novelty detection. But despite its effectiveness, SVDD does not scale well with data size. To avoid prohibitive training times, sampling methods select small subsets of the training data on which SVDD trains a decision boundary hopefully equivalent to the one obtained on the full data set. According to the literature, a good sample should therefore contain so-called boundary observations that SVDD would select as support vectors on the full data set. However, non-boundary observations also are essential to not fragment contiguous inlier regions and avoid poor classification accuracy. Other aspects, such as selecting a sufficiently representative sample, are important as well. But existing sampling methods largely overlook them, resulting in poor classification accuracy. In this article, we study how to select a sample considering these points. Our approach is to frame SVDD sampling as an optimization problem, where constraints guarantee that sampling indeed approximates the original decision boundary. We then propose RAPID, an efficient algorithm to solve this optimization problem. RAPID does not require any tuning of parameters, is easy to implement and scales well to large data sets. We evaluate our approach on real-world and synthetic data. Our evaluation is the most comprehensive one for SVDD sampling so far. Our results show that RAPID outperforms its competitors in classification accuracy, in sample size, and in runtime.
@article{englhardt2022efficient, abstract = {Support Vector Data Description (SVDD) is a popular one-class classifier for anomaly and novelty detection. But despite its effectiveness, SVDD does not scale well with data size. To avoid prohibitive training times, sampling methods select small subsets of the training data on which SVDD trains a decision boundary hopefully equivalent to the one obtained on the full data set. According to the literature, a good sample should therefore contain so-called boundary observations that SVDD would select as support vectors on the full data set. However, non-boundary observations also are essential to not fragment contiguous inlier regions and avoid poor classification accuracy. Other aspects, such as selecting a sufficiently representative sample, are important as well. But existing sampling methods largely overlook them, resulting in poor classification accuracy. In this article, we study how to select a sample considering these points. Our approach is to frame SVDD sampling as an optimization problem, where constraints guarantee that sampling indeed approximates the original decision boundary. We then propose RAPID, an efficient algorithm to solve this optimization problem. RAPID does not require any tuning of parameters, is easy to implement and scales well to large data sets. We evaluate our approach on real-world and synthetic data. Our evaluation is the most comprehensive one for SVDD sampling so far. Our results show that RAPID outperforms its competitors in classification accuracy, in sample size, and in runtime.}, author = {Englhardt, Adrian and Trittenbach, Holger and Kottke, Daniel and Sick, Bernhard and Böhm, Klemens}, journal = {Machine Learning}, keywords = {itegpub}, number = 4, pages = {1349–1375}, publisher = {Springer}, title = {Efficient {SVDD} sampling with approximation guarantees for the decision boundary}, volume = 111, year = 2022 }
%0 Journal Article %1 englhardt2022efficient %A Englhardt, Adrian %A Trittenbach, Holger %A Kottke, Daniel %A Sick, Bernhard %A Böhm, Klemens %D 2022 %I Springer %J Machine Learning %N 4 %P 1349--1375 %R 10.1007/s10994-022-06149-0 %T Efficient SVDD sampling with approximation guarantees for the decision boundary %U https://link.springer.com/article/10.1007/s10994-022-06149-0 %V 111 %X Support Vector Data Description (SVDD) is a popular one-class classifier for anomaly and novelty detection. But despite its effectiveness, SVDD does not scale well with data size. To avoid prohibitive training times, sampling methods select small subsets of the training data on which SVDD trains a decision boundary hopefully equivalent to the one obtained on the full data set. According to the literature, a good sample should therefore contain so-called boundary observations that SVDD would select as support vectors on the full data set. However, non-boundary observations also are essential to not fragment contiguous inlier regions and avoid poor classification accuracy. Other aspects, such as selecting a sufficiently representative sample, are important as well. But existing sampling methods largely overlook them, resulting in poor classification accuracy. In this article, we study how to select a sample considering these points. Our approach is to frame SVDD sampling as an optimization problem, where constraints guarantee that sampling indeed approximates the original decision boundary. We then propose RAPID, an efficient algorithm to solve this optimization problem. RAPID does not require any tuning of parameters, is easy to implement and scales well to large data sets. We evaluate our approach on real-world and synthetic data. Our evaluation is the most comprehensive one for SVDD sampling so far. Our results show that RAPID outperforms its competitors in classification accuracy, in sample size, and in runtime.
Detecting Corner Case in the Context of Highly Automated Driving. Heidecker, Florian. In Organic Computing -- Doctoral Dissertation Colloquium 2021, S. Tomforde, C. Krupitzer (reds.), bll 60–73. kassel university press, 2022.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
This article introduces a research proposal that aims to deﬁne, detect, and evaluate corner cases in the context of machine learning (ML) systems and highly automated driving. Corner cases are scenarios or data in a dataset that are recorded only very rarely and therefore only available in small quantities or not at all in the dataset. However, corner cases are very important for model training, as they are needed to improve the model performance in these rare scenarios. On the other hand, in safety- and security-critical applications, such as highly automated driving, corner case data is extremely important for testing and verifying the ML system. The research proposal addresses these challenges and focuses on the deﬁnition and categorization of corner cases. Based on this, ML methods for corner case detection are developed, focusing on object detection for automated driving and trajectory data for intention detection of pedestrians and cyclists. Finally, the research proposal addresses corner case metrics and the evaluation of the developed detection models.
@incollection{florianheidecker2022detecting, abstract = {This article introduces a research proposal that aims to deﬁne, detect, and evaluate corner cases in the context of machine learning (ML) systems and highly automated driving. Corner cases are scenarios or data in a dataset that are recorded only very rarely and therefore only available in small quantities or not at all in the dataset. However, corner cases are very important for model training, as they are needed to improve the model performance in these rare scenarios. On the other hand, in safety- and security-critical applications, such as highly automated driving, corner case data is extremely important for testing and verifying the ML system. The research proposal addresses these challenges and focuses on the deﬁnition and categorization of corner cases. Based on this, ML methods for corner case detection are developed, focusing on object detection for automated driving and trajectory data for intention detection of pedestrians and cyclists. Finally, the research proposal addresses corner case metrics and the evaluation of the developed detection models.}, author = {Heidecker, Florian}, booktitle = {Organic Computing – Doctoral Dissertation Colloquium 2021}, editor = {Tomforde, Sven and Krupitzer, Christian}, keywords = {itegpub}, pages = {60–73}, publisher = {kassel university press}, title = {Detecting Corner Case in the Context of Highly Automated Driving}, year = 2022 }
%0 Book Section %1 florianheidecker2022detecting %A Heidecker, Florian %B Organic Computing -- Doctoral Dissertation Colloquium 2021 %D 2022 %E Tomforde, Sven %E Krupitzer, Christian %I kassel university press %P 60--73 %T Detecting Corner Case in the Context of Highly Automated Driving %X This article introduces a research proposal that aims to deﬁne, detect, and evaluate corner cases in the context of machine learning (ML) systems and highly automated driving. Corner cases are scenarios or data in a dataset that are recorded only very rarely and therefore only available in small quantities or not at all in the dataset. However, corner cases are very important for model training, as they are needed to improve the model performance in these rare scenarios. On the other hand, in safety- and security-critical applications, such as highly automated driving, corner case data is extremely important for testing and verifying the ML system. The research proposal addresses these challenges and focuses on the deﬁnition and categorization of corner cases. Based on this, ML methods for corner case detection are developed, focusing on object detection for automated driving and trajectory data for intention detection of pedestrians and cyclists. Finally, the research proposal addresses corner case metrics and the evaluation of the developed detection models.
Design of Explainability Module with Experts in the Loop for Visualization and Dynamic Adjustment of Continual Learning. He, Yujiang; Huang, Zhixin; Sick, Bernhard. In Workshop on Interactive Machine Learning Workshop (IMLW), AAAI, bll 1–6. 2022.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Continual learning can enable neural networks to evolve by learning new tasks sequentially in task-changing scenarios. However, two general challenges should be overcome in further research before we apply this technique to real-world applications. Firstly, newly collected novelties from the data stream in applications could contain anomalies that are meaningless for continual learning. Instead of viewing them as a new task for updating, we have to filter out such anomalies to reduce the disturbance of extremely high-entropy data for the progression of convergence. Secondly, fewer efforts have been put into research regarding the explainability of continual learning, which leads to a lack of transparency and credibility of the updated neural networks. Elaborated explanations about the process and result of continual learning can help experts in judgment and making decisions. Therefore, we propose the conceptual design of an explainability module with experts in the loop based on techniques, such as dimension reduction, visualization, and evaluation strategies. This work aims to overcome the mentioned challenges by sufficiently explaining and visualizing the identified anomalies and the updated neural network. With the help of this module, experts can be more confident in decision-making regarding anomaly filtering, dynamic adjustment of hyperparameters, data backup, etc.
@inproceedings{he2022design, abstract = {Continual learning can enable neural networks to evolve by learning new tasks sequentially in task-changing scenarios. However, two general challenges should be overcome in further research before we apply this technique to real-world applications. Firstly, newly collected novelties from the data stream in applications could contain anomalies that are meaningless for continual learning. Instead of viewing them as a new task for updating, we have to filter out such anomalies to reduce the disturbance of extremely high-entropy data for the progression of convergence. Secondly, fewer efforts have been put into research regarding the explainability of continual learning, which leads to a lack of transparency and credibility of the updated neural networks. Elaborated explanations about the process and result of continual learning can help experts in judgment and making decisions. Therefore, we propose the conceptual design of an explainability module with experts in the loop based on techniques, such as dimension reduction, visualization, and evaluation strategies. This work aims to overcome the mentioned challenges by sufficiently explaining and visualizing the identified anomalies and the updated neural network. With the help of this module, experts can be more confident in decision-making regarding anomaly filtering, dynamic adjustment of hyperparameters, data backup, etc.}, author = {He, Yujiang and Huang, Zhixin and Sick, Bernhard}, booktitle = {Workshop on Interactive Machine Learning Workshop (IMLW), AAAI}, keywords = {itegpub}, pages = {1–6}, title = {Design of Explainability Module with Experts in the Loop for Visualization and Dynamic Adjustment of Continual Learning}, year = 2022 }
%0 Conference Paper %1 he2022design %A He, Yujiang %A Huang, Zhixin %A Sick, Bernhard %B Workshop on Interactive Machine Learning Workshop (IMLW), AAAI %D 2022 %P 1--6 %T Design of Explainability Module with Experts in the Loop for Visualization and Dynamic Adjustment of Continual Learning %U https://arxiv.org/abs/2202.06781 %X Continual learning can enable neural networks to evolve by learning new tasks sequentially in task-changing scenarios. However, two general challenges should be overcome in further research before we apply this technique to real-world applications. Firstly, newly collected novelties from the data stream in applications could contain anomalies that are meaningless for continual learning. Instead of viewing them as a new task for updating, we have to filter out such anomalies to reduce the disturbance of extremely high-entropy data for the progression of convergence. Secondly, fewer efforts have been put into research regarding the explainability of continual learning, which leads to a lack of transparency and credibility of the updated neural networks. Elaborated explanations about the process and result of continual learning can help experts in judgment and making decisions. Therefore, we propose the conceptual design of an explainability module with experts in the loop based on techniques, such as dimension reduction, visualization, and evaluation strategies. This work aims to overcome the mentioned challenges by sufficiently explaining and visualizing the identified anomalies and the updated neural network. With the help of this module, experts can be more confident in decision-making regarding anomaly filtering, dynamic adjustment of hyperparameters, data backup, etc.
Deep Adaptive Knowledge-Aware Learning for E-Mobility. Ali, Mohammad Wazed. In Organic Computing - Doctoral Dissertation Colloquium 2022, S. Tomforde, C. Krupitzer (reds.), bll 139–155. kassel university press, 2022.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
Electromobility can reduce global energy demand by reducing the dependence on fossil fuels. Many different types of electric vehicles (EVs) have been produced recently and EV usage is also rising. However, there is no fixed charging behavior of these EV users. Moreover, most renewable energy sources are stochastic in nature. Thus, it is essential that EV charging demand is controlled and adapted in advance to prevent catastrophic failures such as blackouts. Deep learning models are standard technology for power forecasting in many scenarios. However, there is a lack of real-world heterogeneous multi-source data in the e-mobility domain to train a deep learning model from scratch. Moreover, deep learning (DL) models lack model explainability. Therefore, EV stakeholders can benefit from a framework that coordinates deep transfer learning, interactive machine learning, and heterogeneous graph representation learning (to ensure self-explainability). This work aims to develop a novel framework to solve e-mobility-related tasks such as forecasting EV loads efficiently in a resource-constrained environment (data, computing power, etc.). It also describe various research challenges and potential approaches to build the proposed framework. This work also present a deep generative model to synthesize EV charging session data.
@incollection{ali2022deep, abstract = {Electromobility can reduce global energy demand by reducing the dependence on fossil fuels. Many different types of electric vehicles (EVs) have been produced recently and EV usage is also rising. However, there is no fixed charging behavior of these EV users. Moreover, most renewable energy sources are stochastic in nature. Thus, it is essential that EV charging demand is controlled and adapted in advance to prevent catastrophic failures such as blackouts. Deep learning models are standard technology for power forecasting in many scenarios. However, there is a lack of real-world heterogeneous multi-source data in the e-mobility domain to train a deep learning model from scratch. Moreover, deep learning (DL) models lack model explainability. Therefore, EV stakeholders can benefit from a framework that coordinates deep transfer learning, interactive machine learning, and heterogeneous graph representation learning (to ensure self-explainability). This work aims to develop a novel framework to solve e-mobility-related tasks such as forecasting EV loads efficiently in a resource-constrained environment (data, computing power, etc.). It also describe various research challenges and potential approaches to build the proposed framework. This work also present a deep generative model to synthesize EV charging session data.}, author = {Ali, Mohammad Wazed}, booktitle = {Organic Computing - Doctoral Dissertation Colloquium 2022}, editor = {Tomforde, Sven and Krupitzer, Christian}, keywords = {itegpub}, pages = {139–155}, publisher = {kassel university press}, title = {Deep Adaptive Knowledge-Aware Learning for E-Mobility}, year = 2022 }
%0 Book Section %1 ali2022deep %A Ali, Mohammad Wazed %B Organic Computing - Doctoral Dissertation Colloquium 2022 %D 2022 %E Tomforde, Sven %E Krupitzer, Christian %I kassel university press %P 139--155 %T Deep Adaptive Knowledge-Aware Learning for E-Mobility %X Electromobility can reduce global energy demand by reducing the dependence on fossil fuels. Many different types of electric vehicles (EVs) have been produced recently and EV usage is also rising. However, there is no fixed charging behavior of these EV users. Moreover, most renewable energy sources are stochastic in nature. Thus, it is essential that EV charging demand is controlled and adapted in advance to prevent catastrophic failures such as blackouts. Deep learning models are standard technology for power forecasting in many scenarios. However, there is a lack of real-world heterogeneous multi-source data in the e-mobility domain to train a deep learning model from scratch. Moreover, deep learning (DL) models lack model explainability. Therefore, EV stakeholders can benefit from a framework that coordinates deep transfer learning, interactive machine learning, and heterogeneous graph representation learning (to ensure self-explainability). This work aims to develop a novel framework to solve e-mobility-related tasks such as forecasting EV loads efficiently in a resource-constrained environment (data, computing power, etc.). It also describe various research challenges and potential approaches to build the proposed framework. This work also present a deep generative model to synthesize EV charging session data.
Artificial intelligence for online characterization of ultrashort X‑ray free‑electron laser pulses. Dingel, Kristina; Otto, Thorsten; Marder, Lutz; Funke, Lars; Held, Arne; Savio, Sara; Hans, Andreas; Hartmann, Gregor; Meier, David; Viefhaus, Jens; Sick, Bernhard; Ehresmann, Arno; Ilchen, Markus; Helml, Wolfram. In Scientific Reports, 12(1), bll 1–14. Nature Publishing Group, 2022.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
X-ray free-electron lasers (XFELs) as the world’s brightest light sources provide ultrashort X-ray pulses with a duration typically in the order of femtoseconds. Recently, they have approached and entered the attosecond regime, which holds new promises for single-molecule imaging and studying nonlinear and ultrafast phenomena such as localized electron dynamics. The technological evolution of XFELs toward well-controllable light sources for precise metrology of ultrafast processes has been, however, hampered by the diagnostic capabilities for characterizing X-ray pulses at the attosecond frontier. In this regard, the spectroscopic technique of photoelectron angular streaking has successfully proven how to non-destructively retrieve the exact time–energy structure of XFEL pulses on a single-shot basis. By using artificial intelligence techniques, in particular convolutional neural networks, we here show how this technique can be leveraged from its proof-of-principle stage toward routine diagnostics even at high-repetition-rate XFELs, thus enhancing and refining their scientific accessibility in all related disciplines.
@article{dingel2022artificial, abstract = {X-ray free-electron lasers (XFELs) as the world’s brightest light sources provide ultrashort X-ray pulses with a duration typically in the order of femtoseconds. Recently, they have approached and entered the attosecond regime, which holds new promises for single-molecule imaging and studying nonlinear and ultrafast phenomena such as localized electron dynamics. The technological evolution of XFELs toward well-controllable light sources for precise metrology of ultrafast processes has been, however, hampered by the diagnostic capabilities for characterizing X-ray pulses at the attosecond frontier. In this regard, the spectroscopic technique of photoelectron angular streaking has successfully proven how to non-destructively retrieve the exact time–energy structure of XFEL pulses on a single-shot basis. By using artificial intelligence techniques, in particular convolutional neural networks, we here show how this technique can be leveraged from its proof-of-principle stage toward routine diagnostics even at high-repetition-rate XFELs, thus enhancing and refining their scientific accessibility in all related disciplines.}, author = {Dingel, Kristina and Otto, Thorsten and Marder, Lutz and Funke, Lars and Held, Arne and Savio, Sara and Hans, Andreas and Hartmann, Gregor and Meier, David and Viefhaus, Jens and Sick, Bernhard and Ehresmann, Arno and Ilchen, Markus and Helml, Wolfram}, journal = {Scientific Reports}, keywords = {itegpub}, number = 1, pages = {1–14}, publisher = {Nature Publishing Group}, title = {Artificial intelligence for online characterization of ultrashort X‑ray free‑electron laser pulses}, volume = 12, year = 2022 }
%0 Journal Article %1 dingel2022artificial %A Dingel, Kristina %A Otto, Thorsten %A Marder, Lutz %A Funke, Lars %A Held, Arne %A Savio, Sara %A Hans, Andreas %A Hartmann, Gregor %A Meier, David %A Viefhaus, Jens %A Sick, Bernhard %A Ehresmann, Arno %A Ilchen, Markus %A Helml, Wolfram %D 2022 %I Nature Publishing Group %J Scientific Reports %N 1 %P 1--14 %R 10.1038/s41598-022-21646-x %T Artificial intelligence for online characterization of ultrashort X‑ray free‑electron laser pulses %U https://www.nature.com/articles/s41598-022-21646-x %V 12 %X X-ray free-electron lasers (XFELs) as the world’s brightest light sources provide ultrashort X-ray pulses with a duration typically in the order of femtoseconds. Recently, they have approached and entered the attosecond regime, which holds new promises for single-molecule imaging and studying nonlinear and ultrafast phenomena such as localized electron dynamics. The technological evolution of XFELs toward well-controllable light sources for precise metrology of ultrafast processes has been, however, hampered by the diagnostic capabilities for characterizing X-ray pulses at the attosecond frontier. In this regard, the spectroscopic technique of photoelectron angular streaking has successfully proven how to non-destructively retrieve the exact time–energy structure of XFEL pulses on a single-shot basis. By using artificial intelligence techniques, in particular convolutional neural networks, we here show how this technique can be leveraged from its proof-of-principle stage toward routine diagnostics even at high-repetition-rate XFELs, thus enhancing and refining their scientific accessibility in all related disciplines.
Adaptive Explainable Continual Learning Framework for Regression Problems with Focus on Power Forecasts. He, Yujiang. In Organic Computing -- Doctoral Dissertation Colloquium 2021, S. Tomforde, C. Krupitzer (reds.), bll 125–140. kassel university press, 2022.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
Compared with traditional deep learning techniques, continual learning enables deep neural networks to learn continually and adaptively. Deep neural networks have to learn unseen tasks and overcome forgetting the knowledge obtained from previously learned tasks as the amount of data keeps increasing in applications. This article proposes two continual learning application scenarios, i.e., the target-domain incremental scenario and the data-domain incremental scenario, to describe the potential challenges in this context. Based on our previous work regarding the CLeaR framework, which is short for continual learning for regression tasks, models will be enabled to extend themselves and to learn data successively. Research topics are related, but not limited, to developing continual deep learning algorithms, strategies for non-stationarity detection in data streams, explainable and visualizable artificial intelligence, etc. Moreover, the framework- and algorithm-related hyperparameters should be dynamically updated in applications. Forecasting experiments will be conducted based on power generation and consumption data collected from real-world applications. A series of comprehensive evaluation metrics and visualization tools are applied to access the experimental results. The proposed framework is expected to be generally applied to other constantly changing scenarios.
@incollection{he2022adaptive, abstract = {Compared with traditional deep learning techniques, continual learning enables deep neural networks to learn continually and adaptively. Deep neural networks have to learn unseen tasks and overcome forgetting the knowledge obtained from previously learned tasks as the amount of data keeps increasing in applications. This article proposes two continual learning application scenarios, i.e., the target-domain incremental scenario and the data-domain incremental scenario, to describe the potential challenges in this context. Based on our previous work regarding the CLeaR framework, which is short for continual learning for regression tasks, models will be enabled to extend themselves and to learn data successively. Research topics are related, but not limited, to developing continual deep learning algorithms, strategies for non-stationarity detection in data streams, explainable and visualizable artificial intelligence, etc. Moreover, the framework- and algorithm-related hyperparameters should be dynamically updated in applications. Forecasting experiments will be conducted based on power generation and consumption data collected from real-world applications. A series of comprehensive evaluation metrics and visualization tools are applied to access the experimental results. The proposed framework is expected to be generally applied to other constantly changing scenarios.}, author = {He, Yujiang}, booktitle = {Organic Computing – Doctoral Dissertation Colloquium 2021}, editor = {Tomforde, Sven and Krupitzer, Christian}, keywords = {itegpub}, pages = {125–140}, publisher = {kassel university press}, title = {Adaptive Explainable Continual Learning Framework for Regression Problems with Focus on Power Forecasts}, year = 2022 }
%0 Book Section %1 he2022adaptive %A He, Yujiang %B Organic Computing -- Doctoral Dissertation Colloquium 2021 %D 2022 %E Tomforde, Sven %E Krupitzer, Christian %I kassel university press %P 125--140 %T Adaptive Explainable Continual Learning Framework for Regression Problems with Focus on Power Forecasts %X Compared with traditional deep learning techniques, continual learning enables deep neural networks to learn continually and adaptively. Deep neural networks have to learn unseen tasks and overcome forgetting the knowledge obtained from previously learned tasks as the amount of data keeps increasing in applications. This article proposes two continual learning application scenarios, i.e., the target-domain incremental scenario and the data-domain incremental scenario, to describe the potential challenges in this context. Based on our previous work regarding the CLeaR framework, which is short for continual learning for regression tasks, models will be enabled to extend themselves and to learn data successively. Research topics are related, but not limited, to developing continual deep learning algorithms, strategies for non-stationarity detection in data streams, explainable and visualizable artificial intelligence, etc. Moreover, the framework- and algorithm-related hyperparameters should be dynamically updated in applications. Forecasting experiments will be conducted based on power generation and consumption data collected from real-world applications. A series of comprehensive evaluation metrics and visualization tools are applied to access the experimental results. The proposed framework is expected to be generally applied to other constantly changing scenarios.
Actively Controlling and Redesigning Experiments using the Application Case of Free-Electron Laser Pulse Characterization. Dingel, Kristina. In Organic Computing -- Doctoral Dissertation Colloquium 2021, S. Tomforde, C. Krupitzer (reds.), bll 86–98. kassel university press, 2022.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
Experiments are the elective tool for developing new technologies, testing hypotheses, and designing new materials in many scientific fields. Thereby, it is state-of-the-art to create experiments traditionally, starting with a hypothesis leading to the product or relevant data after several experiment cycles. There are some techniques such as automation, parallelization, or inverse design to accelerate experiments. Particularly interesting, however, is the approach to integrate immediate data analysis into the experiment cycle. By analyzing experiment output data on-site using, e.g., neural networks, one can make inferences regarding the experiment's current settings at run-time and furthermore improve them. In the following research project, the goal is to develop and incorporate a data analysis stage into an experimental setup, which can be actively adapted and designed on-site. To demonstrate the developed method, the experimental design of a self-amplification of spontaneous emission pulse characterization experiment at a free-electron laser will be used to show to what extent the experiment can be adapted and optimized.
@incollection{dingel2022actively, abstract = {Experiments are the elective tool for developing new technologies, testing hypotheses, and designing new materials in many scientific fields. Thereby, it is state-of-the-art to create experiments traditionally, starting with a hypothesis leading to the product or relevant data after several experiment cycles. There are some techniques such as automation, parallelization, or inverse design to accelerate experiments. Particularly interesting, however, is the approach to integrate immediate data analysis into the experiment cycle. By analyzing experiment output data on-site using, e.g., neural networks, one can make inferences regarding the experiment's current settings at run-time and furthermore improve them. In the following research project, the goal is to develop and incorporate a data analysis stage into an experimental setup, which can be actively adapted and designed on-site. To demonstrate the developed method, the experimental design of a self-amplification of spontaneous emission pulse characterization experiment at a free-electron laser will be used to show to what extent the experiment can be adapted and optimized.}, author = {Dingel, Kristina}, booktitle = {Organic Computing – Doctoral Dissertation Colloquium 2021}, editor = {Tomforde, Sven and Krupitzer, Christian}, keywords = {itegpub}, pages = {86–98}, publisher = {kassel university press}, title = {Actively Controlling and Redesigning Experiments using the Application Case of Free-Electron Laser Pulse Characterization}, year = 2022 }
%0 Book Section %1 dingel2022actively %A Dingel, Kristina %B Organic Computing -- Doctoral Dissertation Colloquium 2021 %D 2022 %E Tomforde, Sven %E Krupitzer, Christian %I kassel university press %P 86--98 %T Actively Controlling and Redesigning Experiments using the Application Case of Free-Electron Laser Pulse Characterization %X Experiments are the elective tool for developing new technologies, testing hypotheses, and designing new materials in many scientific fields. Thereby, it is state-of-the-art to create experiments traditionally, starting with a hypothesis leading to the product or relevant data after several experiment cycles. There are some techniques such as automation, parallelization, or inverse design to accelerate experiments. Particularly interesting, however, is the approach to integrate immediate data analysis into the experiment cycle. By analyzing experiment output data on-site using, e.g., neural networks, one can make inferences regarding the experiment's current settings at run-time and furthermore improve them. In the following research project, the goal is to develop and incorporate a data analysis stage into an experimental setup, which can be actively adapted and designed on-site. To demonstrate the developed method, the experimental design of a self-amplification of spontaneous emission pulse characterization experiment at a free-electron laser will be used to show to what extent the experiment can be adapted and optimized.
Active Learning in Multivariate Time Series Anomaly Detection. Huang, Zhixin. In Organic Computing -- Doctoral Dissertation Colloquium 2021, S. Tomforde, C. Krupitzer (reds.), bll 113–124. kassel university press, 2022.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
Multivariate time series anomaly detection is an important research field of industry, science, and finances. In practical applications, unlabeled data is abundant, and labeled data is rare. Experts’ experience plays a key role in data labeling, while experts often have limited time, are expensive, and are concerned primarily with finding the potential anomalies. Active learning, which has been widely used to select the most informative data for labeling through experts, can improve training with less labeling effort. However, most active learning algorithms have not been evaluated on datasets with imbalanced class frequencies, such as anomaly detection. Although some semi-supervised and active learning methods were proposed to handle univariate time series data, not much work has been done on multivariate time series classification. Therefore, this article identifies critical challenges and proposes potential solutions for active learning in multivariate time series anomaly detection. We combine all possible solutions into a framework that conforms to the scope of the observation/control system in organic computing.
@incollection{huang2022active, abstract = {Multivariate time series anomaly detection is an important research field of industry, science, and finances. In practical applications, unlabeled data is abundant, and labeled data is rare. Experts’ experience plays a key role in data labeling, while experts often have limited time, are expensive, and are concerned primarily with finding the potential anomalies. Active learning, which has been widely used to select the most informative data for labeling through experts, can improve training with less labeling effort. However, most active learning algorithms have not been evaluated on datasets with imbalanced class frequencies, such as anomaly detection. Although some semi-supervised and active learning methods were proposed to handle univariate time series data, not much work has been done on multivariate time series classification. Therefore, this article identifies critical challenges and proposes potential solutions for active learning in multivariate time series anomaly detection. We combine all possible solutions into a framework that conforms to the scope of the observation/control system in organic computing.}, author = {Huang, Zhixin}, booktitle = {Organic Computing – Doctoral Dissertation Colloquium 2021}, editor = {Tomforde, Sven and Krupitzer, Christian}, keywords = {itegpub}, pages = {113–124}, publisher = {kassel university press}, title = {Active Learning in Multivariate Time Series Anomaly Detection}, year = 2022 }
%0 Book Section %1 huang2022active %A Huang, Zhixin %B Organic Computing -- Doctoral Dissertation Colloquium 2021 %D 2022 %E Tomforde, Sven %E Krupitzer, Christian %I kassel university press %P 113--124 %T Active Learning in Multivariate Time Series Anomaly Detection %X Multivariate time series anomaly detection is an important research field of industry, science, and finances. In practical applications, unlabeled data is abundant, and labeled data is rare. Experts’ experience plays a key role in data labeling, while experts often have limited time, are expensive, and are concerned primarily with finding the potential anomalies. Active learning, which has been widely used to select the most informative data for labeling through experts, can improve training with less labeling effort. However, most active learning algorithms have not been evaluated on datasets with imbalanced class frequencies, such as anomaly detection. Although some semi-supervised and active learning methods were proposed to handle univariate time series data, not much work has been done on multivariate time series classification. Therefore, this article identifies critical challenges and proposes potential solutions for active learning in multivariate time series anomaly detection. We combine all possible solutions into a framework that conforms to the scope of the observation/control system in organic computing.
A Stopping Criterion for Transductive Active Learning. Kottke, Daniel; Sandrock, Christoph; Krempl, Georg; Sick, Bernhard. In European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECMLPKDD), bll 468–484. Springer, 2022.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
In transductive active learning, the goal is to determine the correct labels for an unlabeled, known dataset. Therefore, we can either ask an oracle to provide the right label at some cost or use the prediction of a classifier which we train on the labels acquired so far. In contrast, the commonly used (inductive) active learning aims to select instances for labeling out of the unlabeled set to create a generalized classifier, which will be deployed on unknown data. This article formally defines the transductive setting and shows that it requires new solutions. Additionally, we formalize the theoretically cost-optimal stopping point for the transductive scenario. Building upon the probabilistic active learning framework, we propose a new transductive selection strategy that includes a stopping criterion and show its superiority.
@inproceedings{kottke2022stopping, abstract = {In transductive active learning, the goal is to determine the correct labels for an unlabeled, known dataset. Therefore, we can either ask an oracle to provide the right label at some cost or use the prediction of a classifier which we train on the labels acquired so far. In contrast, the commonly used (inductive) active learning aims to select instances for labeling out of the unlabeled set to create a generalized classifier, which will be deployed on unknown data. This article formally defines the transductive setting and shows that it requires new solutions. Additionally, we formalize the theoretically cost-optimal stopping point for the transductive scenario. Building upon the probabilistic active learning framework, we propose a new transductive selection strategy that includes a stopping criterion and show its superiority.}, author = {Kottke, Daniel and Sandrock, Christoph and Krempl, Georg and Sick, Bernhard}, booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECMLPKDD)}, keywords = {itegpub}, pages = {468–484}, publisher = {Springer}, title = {A Stopping Criterion for Transductive Active Learning}, year = 2022 }
%0 Conference Paper %1 kottke2022stopping %A Kottke, Daniel %A Sandrock, Christoph %A Krempl, Georg %A Sick, Bernhard %B European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECMLPKDD) %D 2022 %I Springer %P 468--484 %R 10.1007/978-3-031-26412-2_29 %T A Stopping Criterion for Transductive Active Learning %U https://link.springer.com/chapter/10.1007/978-3-031-26412-2_29 %X In transductive active learning, the goal is to determine the correct labels for an unlabeled, known dataset. Therefore, we can either ask an oracle to provide the right label at some cost or use the prediction of a classifier which we train on the labels acquired so far. In contrast, the commonly used (inductive) active learning aims to select instances for labeling out of the unlabeled set to create a generalized classifier, which will be deployed on unknown data. This article formally defines the transductive setting and shows that it requires new solutions. Additionally, we formalize the theoretically cost-optimal stopping point for the transductive scenario. Building upon the probabilistic active learning framework, we propose a new transductive selection strategy that includes a stopping criterion and show its superiority.
A Review of Uncertainty Calibration in Pretrained Object Detectors. Huseljic, Denis; Herde, Marek; Muejde, Mehmet; Sick, Bernhard. In arXiv e-prints, bl arXiv:2210.02935. 2022.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
In the field of deep learning based computer vision, the development of deep object detection has led to unique paradigms (e.g., two-stage or set-based) and architectures (e.g., Faster-RCNN or DETR) which enable outstanding performance on challenging benchmark datasets. Despite this, the trained object detectors typically do not reliably assess uncertainty regarding their own knowledge, and the quality of their probabilistic predictions is usually poor. As these are often used to make subsequent decisions, such inaccurate probabilistic predictions must be avoided. In this work, we investigate the uncertainty calibration properties of different pretrained object detection architectures in a multi-class setting. We propose a framework to ensure a fair, unbiased, and repeatable evaluation and conduct detailed analyses assessing the calibration under distributional changes (e.g., distributional shift and application to out-of-distribution data). Furthermore, by investigating the influence of different detector paradigms, post-processing steps, and suitable choices of metrics, we deliver novel insights into why poor detector calibration emerges. Based on these insights, we are able to improve the calibration of a detector by simply finetuning its last layer.
@article{huseljic2022review, abstract = {In the field of deep learning based computer vision, the development of deep object detection has led to unique paradigms (e.g., two-stage or set-based) and architectures (e.g., Faster-RCNN or DETR) which enable outstanding performance on challenging benchmark datasets. Despite this, the trained object detectors typically do not reliably assess uncertainty regarding their own knowledge, and the quality of their probabilistic predictions is usually poor. As these are often used to make subsequent decisions, such inaccurate probabilistic predictions must be avoided. In this work, we investigate the uncertainty calibration properties of different pretrained object detection architectures in a multi-class setting. We propose a framework to ensure a fair, unbiased, and repeatable evaluation and conduct detailed analyses assessing the calibration under distributional changes (e.g., distributional shift and application to out-of-distribution data). Furthermore, by investigating the influence of different detector paradigms, post-processing steps, and suitable choices of metrics, we deliver novel insights into why poor detector calibration emerges. Based on these insights, we are able to improve the calibration of a detector by simply finetuning its last layer.}, author = {Huseljic, Denis and Herde, Marek and Muejde, Mehmet and Sick, Bernhard}, journal = {arXiv e-prints}, keywords = {itegpub}, pages = {arXiv:2210.02935}, title = {A Review of Uncertainty Calibration in Pretrained Object Detectors}, year = 2022 }
%0 Journal Article %1 huseljic2022review %A Huseljic, Denis %A Herde, Marek %A Muejde, Mehmet %A Sick, Bernhard %D 2022 %J arXiv e-prints %P arXiv:2210.02935 %T A Review of Uncertainty Calibration in Pretrained Object Detectors %U https://arxiv.org/abs/2210.02935 %X In the field of deep learning based computer vision, the development of deep object detection has led to unique paradigms (e.g., two-stage or set-based) and architectures (e.g., Faster-RCNN or DETR) which enable outstanding performance on challenging benchmark datasets. Despite this, the trained object detectors typically do not reliably assess uncertainty regarding their own knowledge, and the quality of their probabilistic predictions is usually poor. As these are often used to make subsequent decisions, such inaccurate probabilistic predictions must be avoided. In this work, we investigate the uncertainty calibration properties of different pretrained object detection architectures in a multi-class setting. We propose a framework to ensure a fair, unbiased, and repeatable evaluation and conduct detailed analyses assessing the calibration under distributional changes (e.g., distributional shift and application to out-of-distribution data). Furthermore, by investigating the influence of different detector paradigms, post-processing steps, and suitable choices of metrics, we deliver novel insights into why poor detector calibration emerges. Based on these insights, we are able to improve the calibration of a detector by simply finetuning its last layer.
A Practical Evaluation of Active Learning Approaches for Object Detection. Schneegans, Jan; Bieshaar, Maarten; Sick, Bernhard. In Workshop on Interactive Adaptive Learning (IAL), ECML PKDD, bll 49–67. 2022.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Deep learning models are trained most successfully in a supervised manner, which requires vast amounts of annotated data. With active learning, the annotation process can be made much more efficient by intelligently selecting the most valuable batches of samples to annotate and train on. Those samples are selected based on their utility regarding the training algorithm. In this work, we examine a wide range of such selection criteria for the task of object detection as performed by the widely applied Faster R-CNN model. We focus on the large and diverse BDD100K autonomous driving dataset, paying special attention to the model’s sub-tasks and the dataset’s meta information. Furthermore, we distinguish between approaches that select samples based on aleatoric or epistemic uncertainty. A selection of evaluation measures that cover specific error sources and the overall model performance suggests that there is little difference between the individual active learning approaches, even in regards to their specialized focus on different model parts and sub-tasks. We conclude with a detailed discussion of the implied mechanisms regarding the active learning approaches that seem to affect model performances.
@inproceedings{schneegans2022practical, abstract = {Deep learning models are trained most successfully in a supervised manner, which requires vast amounts of annotated data. With active learning, the annotation process can be made much more efficient by intelligently selecting the most valuable batches of samples to annotate and train on. Those samples are selected based on their utility regarding the training algorithm. In this work, we examine a wide range of such selection criteria for the task of object detection as performed by the widely applied Faster R-CNN model. We focus on the large and diverse BDD100K autonomous driving dataset, paying special attention to the model’s sub-tasks and the dataset’s meta information. Furthermore, we distinguish between approaches that select samples based on aleatoric or epistemic uncertainty. A selection of evaluation measures that cover specific error sources and the overall model performance suggests that there is little difference between the individual active learning approaches, even in regards to their specialized focus on different model parts and sub-tasks. We conclude with a detailed discussion of the implied mechanisms regarding the active learning approaches that seem to affect model performances.}, author = {Schneegans, Jan and Bieshaar, Maarten and Sick, Bernhard}, booktitle = {Workshop on Interactive Adaptive Learning (IAL), ECML PKDD}, keywords = {itegpub}, pages = {49–67}, title = {A Practical Evaluation of Active Learning Approaches for Object Detection}, year = 2022 }
%0 Conference Paper %1 schneegans2022practical %A Schneegans, Jan %A Bieshaar, Maarten %A Sick, Bernhard %B Workshop on Interactive Adaptive Learning (IAL), ECML PKDD %D 2022 %P 49--67 %T A Practical Evaluation of Active Learning Approaches for Object Detection %U http://ceur-ws.org/Vol-3259/ialatecml_paper5.pdf %X Deep learning models are trained most successfully in a supervised manner, which requires vast amounts of annotated data. With active learning, the annotation process can be made much more efficient by intelligently selecting the most valuable batches of samples to annotate and train on. Those samples are selected based on their utility regarding the training algorithm. In this work, we examine a wide range of such selection criteria for the task of object detection as performed by the widely applied Faster R-CNN model. We focus on the large and diverse BDD100K autonomous driving dataset, paying special attention to the model’s sub-tasks and the dataset’s meta information. Furthermore, we distinguish between approaches that select samples based on aleatoric or epistemic uncertainty. A selection of evaluation measures that cover specific error sources and the overall model performance suggests that there is little difference between the individual active learning approaches, even in regards to their specialized focus on different model parts and sub-tasks. We conclude with a detailed discussion of the implied mechanisms regarding the active learning approaches that seem to affect model performances.
A Holistic View on Probabilistic Trajectory Forecasting -- Case Study: Cyclist Intention Detection. Zernetsch, Stefan; Reichert, Hannes; Kress, Viktor; Doll, Konrad; Sick, Bernhard. In IEEE Intelligent Vehicles Symposium (IV), bll 265–272. IEEE, 2022.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
This article presents a holistic approach for probabilistic cyclist intention detection. By combining probabilities for the current cyclist motion states with a probabilistic ensemble trajectory forecast, we are able to generate reliable estimates of cyclists’ future positions. The probabilities are used as weights in the probabilistic ensemble trajectory forecast. The ensemble consists of specialized models, which produce individual forecasts in the form of Gaussian distributions under the assumption of a certain motion state of the cyclist (e.g. cyclist is starting). By weighting the specialized models, we create forecasts in the form of Gaussian mixtures that define regions within which the cyclists will reside with a certain probability. To evaluate our method, we rate the reliability, sharpness, and positional accuracy of our forecasted distributions. We compare our method to a widely used unimodal approach which produces forecasts in the form of Gaussian distributions and show that our method is able to produce more reliable and sharper outputs while retaining comparable positional accuracy. By comparing two different methods for basic movement detection, one based on the past cyclist trajectory and one using past image sequences, we demonstrate that the results can be further improved by incorporating video information. Our methods are evaluated using a dataset created at a public intersection. The code and the dataset are publicly available.
@inproceedings{zernetsch2022holistic, abstract = {This article presents a holistic approach for probabilistic cyclist intention detection. By combining probabilities for the current cyclist motion states with a probabilistic ensemble trajectory forecast, we are able to generate reliable estimates of cyclists’ future positions. The probabilities are used as weights in the probabilistic ensemble trajectory forecast. The ensemble consists of specialized models, which produce individual forecasts in the form of Gaussian distributions under the assumption of a certain motion state of the cyclist (e.g. cyclist is starting). By weighting the specialized models, we create forecasts in the form of Gaussian mixtures that define regions within which the cyclists will reside with a certain probability. To evaluate our method, we rate the reliability, sharpness, and positional accuracy of our forecasted distributions. We compare our method to a widely used unimodal approach which produces forecasts in the form of Gaussian distributions and show that our method is able to produce more reliable and sharper outputs while retaining comparable positional accuracy. By comparing two different methods for basic movement detection, one based on the past cyclist trajectory and one using past image sequences, we demonstrate that the results can be further improved by incorporating video information. Our methods are evaluated using a dataset created at a public intersection. The code and the dataset are publicly available.}, author = {Zernetsch, Stefan and Reichert, Hannes and Kress, Viktor and Doll, Konrad and Sick, Bernhard}, booktitle = {IEEE Intelligent Vehicles Symposium (IV)}, keywords = {itegpub}, pages = {265–272}, publisher = {IEEE}, title = {A Holistic View on Probabilistic Trajectory Forecasting – Case Study: Cyclist Intention Detection}, year = 2022 }
%0 Conference Paper %1 zernetsch2022holistic %A Zernetsch, Stefan %A Reichert, Hannes %A Kress, Viktor %A Doll, Konrad %A Sick, Bernhard %B IEEE Intelligent Vehicles Symposium (IV) %D 2022 %I IEEE %P 265--272 %R 10.1109/IV51971.2022.9827220 %T A Holistic View on Probabilistic Trajectory Forecasting -- Case Study: Cyclist Intention Detection %U https://ieeexplore.ieee.org/document/9827220 %X This article presents a holistic approach for probabilistic cyclist intention detection. By combining probabilities for the current cyclist motion states with a probabilistic ensemble trajectory forecast, we are able to generate reliable estimates of cyclists’ future positions. The probabilities are used as weights in the probabilistic ensemble trajectory forecast. The ensemble consists of specialized models, which produce individual forecasts in the form of Gaussian distributions under the assumption of a certain motion state of the cyclist (e.g. cyclist is starting). By weighting the specialized models, we create forecasts in the form of Gaussian mixtures that define regions within which the cyclists will reside with a certain probability. To evaluate our method, we rate the reliability, sharpness, and positional accuracy of our forecasted distributions. We compare our method to a widely used unimodal approach which produces forecasts in the form of Gaussian distributions and show that our method is able to produce more reliable and sharper outputs while retaining comparable positional accuracy. By comparing two different methods for basic movement detection, one based on the past cyclist trajectory and one using past image sequences, we demonstrate that the results can be further improved by incorporating video information. Our methods are evaluated using a dataset created at a public intersection. The code and the dataset are publicly available.
A Concept for Automated Polarized Web Content Annotation based on Multimodal Active Learning. Herde, Marek; Huseljic, Denis; Mitrovic, Jelena; Granitzer, Michael; Sick, Bernhard. In Workshop on Interactive Adaptive Learning (IAL), ECML PKDD, bll 1–6. 2022.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Active learning (AL) techniques hardly cope with complex annotations tasks, where, for example, annotations might express relationships across data modalities. As a use case, we consider the task of automatically detecting and reporting multimodal, polarized web content (PWC). Samples of this content type emerge dynamically, covering a broad spectrum of topics. Thus, training machine learning systems for detecting PWC is challenging, particularly if it needs to be done with minimum annotation cost. In this article, we propose the concept of multimodal AL for complex annotations in the context of PWC detection and formulate the resulting challenges as questions for future research.
@inproceedings{herde2022concept, abstract = {Active learning (AL) techniques hardly cope with complex annotations tasks, where, for example, annotations might express relationships across data modalities. As a use case, we consider the task of automatically detecting and reporting multimodal, polarized web content (PWC). Samples of this content type emerge dynamically, covering a broad spectrum of topics. Thus, training machine learning systems for detecting PWC is challenging, particularly if it needs to be done with minimum annotation cost. In this article, we propose the concept of multimodal AL for complex annotations in the context of PWC detection and formulate the resulting challenges as questions for future research.}, author = {Herde, Marek and Huseljic, Denis and Mitrovic, Jelena and Granitzer, Michael and Sick, Bernhard}, booktitle = {Workshop on Interactive Adaptive Learning (IAL), ECML PKDD}, keywords = {itegpub}, pages = {1–6}, title = {A Concept for Automated Polarized Web Content Annotation based on Multimodal Active Learning}, year = 2022 }
%0 Conference Paper %1 herde2022concept %A Herde, Marek %A Huseljic, Denis %A Mitrovic, Jelena %A Granitzer, Michael %A Sick, Bernhard %B Workshop on Interactive Adaptive Learning (IAL), ECML PKDD %D 2022 %P 1--6 %T A Concept for Automated Polarized Web Content Annotation based on Multimodal Active Learning %U http://ceur-ws.org/Vol-3259/ialatecml_paper1.pdf %X Active learning (AL) techniques hardly cope with complex annotations tasks, where, for example, annotations might express relationships across data modalities. As a use case, we consider the task of automatically detecting and reporting multimodal, polarized web content (PWC). Samples of this content type emerge dynamically, covering a broad spectrum of topics. Thus, training machine learning systems for detecting PWC is challenging, particularly if it needs to be done with minimum annotation cost. In this article, we propose the concept of multimodal AL for complex annotations in the context of PWC detection and formulate the resulting challenges as questions for future research.

2021[ to top ]

Uncertainty and Utility Sampling with Pre-Clustering. Huang, Zhixin; He, Yujiang; Vogt, Stephan; Sick, Bernhard. In Workshop on Interactive Adaptive Learning (IAL), ECML PKDD. 2021.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{huang2021uncertainty, author = {Huang, Zhixin and He, Yujiang and Vogt, Stephan and Sick, Bernhard}, booktitle = {Workshop on Interactive Adaptive Learning (IAL), ECML PKDD}, keywords = {itegpub}, note = {(accepted)}, title = {Uncertainty and Utility Sampling with Pre-Clustering}, year = 2021 }
%0 Conference Paper %1 huang2021uncertainty %A Huang, Zhixin %A He, Yujiang %A Vogt, Stephan %A Sick, Bernhard %B Workshop on Interactive Adaptive Learning (IAL), ECML PKDD %D 2021 %T Uncertainty and Utility Sampling with Pre-Clustering
Transport efficiency of biofunctionalized magnetic particles tailored by surfactant concentration. Reginka, Meike; Hoang, Hai; Efendi, Özge; Merkel, Maximilan; Huhnstock, Rico; Holzinger, Dennis; Dingel, Kristina; Sick, Bernhard; Bertinetti, Daniela; Herberg, Friedrich; Ehresmann, Arno. In Langmuir, 37(28), bll 8498–8507. ACS, 2021.
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
@article{reginka2021transport, author = {{Reginka}, Meike and {Hoang}, Hai and {Efendi}, {\"O}zge and {Merkel}, Maximilan and {Huhnstock}, Rico and {Holzinger}, Dennis and {Dingel}, Kristina and {Sick}, Bernhard and {Bertinetti}, Daniela and {Herberg}, Friedrich and {Ehresmann}, Arno}, journal = {Langmuir}, keywords = {itegpub}, number = 28, pages = {8498–8507}, publisher = {ACS}, title = {Transport efficiency of biofunctionalized magnetic particles tailored by surfactant concentration}, volume = 37, year = 2021 }
%0 Journal Article %1 reginka2021transport %A Reginka, Meike %A Hoang, Hai %A Efendi, Özge %A Merkel, Maximilan %A Huhnstock, Rico %A Holzinger, Dennis %A Dingel, Kristina %A Sick, Bernhard %A Bertinetti, Daniela %A Herberg, Friedrich %A Ehresmann, Arno %D 2021 %I ACS %J Langmuir %N 28 %P 8498--8507 %R 10.1021/acs.langmuir.1c00900 %T Transport efficiency of biofunctionalized magnetic particles tailored by surfactant concentration %U https://pubs.acs.org/doi/abs/10.1021/acs.langmuir.1c00900 %V 37
Translatory and rotatory motion of exchange-bias capped Janus particles controlled by dynamic magnetic field landscapes. Huhnstock, Rico; Reginka, Meike; Tomita, Andreea; Merkel, Maximilian; Dingel, Kristina; Holzinger, Dennis; Sick, Bernhard; Vogel, Michael; Ehresmann, Arno. In Scientific Reports, 11(1), bl 21794. Nature Publishing Group, 2021.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Magnetic Janus particles (MJPs), fabricated by covering a non-magnetic spherical particle with a hemispherical magnetic in-plane exchange-bias layer system cap, display an onion magnetization state for comparably large diameters of a few microns. In this work, the motion characteristics of these MJPs will be investigated when they are steered by a magnetic field landscape over prototypical parallel-stripe domains, dynamically varied by superposed external magnetic field pulse sequences, in an aqueous medium. We demonstrate, that due to the engineered magnetization state in the hemispherical cap, a comparably fast, directed particle transport and particle rotation can be induced. Additionally, by modifying the frequency of the applied pulse sequence and the strengths of the individual field components, we observe a possible separation between a combined or an individual occurrence of these two types of motion. Our findings bear importance for lab-on-a-chip systems, where particle immobilization on a surface via analyte bridges shall be used for low concentration analyte detection and a particle rotation over a defined position of a substrate may dramatically increase the immobilization (and therefore analyte detection) probability.
@article{huhnstock2021translatory, abstract = {Magnetic Janus particles (MJPs), fabricated by covering a non-magnetic spherical particle with a hemispherical magnetic in-plane exchange-bias layer system cap, display an onion magnetization state for comparably large diameters of a few microns. In this work, the motion characteristics of these MJPs will be investigated when they are steered by a magnetic field landscape over prototypical parallel-stripe domains, dynamically varied by superposed external magnetic field pulse sequences, in an aqueous medium. We demonstrate, that due to the engineered magnetization state in the hemispherical cap, a comparably fast, directed particle transport and particle rotation can be induced. Additionally, by modifying the frequency of the applied pulse sequence and the strengths of the individual field components, we observe a possible separation between a combined or an individual occurrence of these two types of motion. Our findings bear importance for lab-on-a-chip systems, where particle immobilization on a surface via analyte bridges shall be used for low concentration analyte detection and a particle rotation over a defined position of a substrate may dramatically increase the immobilization (and therefore analyte detection) probability.}, author = {Huhnstock, Rico and Reginka, Meike and Tomita, Andreea and Merkel, Maximilian and Dingel, Kristina and Holzinger, Dennis and Sick, Bernhard and Vogel, Michael and Ehresmann, Arno}, journal = {Scientific Reports}, keywords = {itegpub}, number = 1, pages = 21794, publisher = {Nature Publishing Group}, title = {Translatory and rotatory motion of exchange-bias capped Janus particles controlled by dynamic magnetic field landscapes}, volume = 11, year = 2021 }
%0 Journal Article %1 huhnstock2021translatory %A Huhnstock, Rico %A Reginka, Meike %A Tomita, Andreea %A Merkel, Maximilian %A Dingel, Kristina %A Holzinger, Dennis %A Sick, Bernhard %A Vogel, Michael %A Ehresmann, Arno %D 2021 %I Nature Publishing Group %J Scientific Reports %N 1 %P 21794 %R 10.1038/s41598-021-01351-x %T Translatory and rotatory motion of exchange-bias capped Janus particles controlled by dynamic magnetic field landscapes %U https://www.nature.com/articles/s41598-021-01351-x %V 11 %X Magnetic Janus particles (MJPs), fabricated by covering a non-magnetic spherical particle with a hemispherical magnetic in-plane exchange-bias layer system cap, display an onion magnetization state for comparably large diameters of a few microns. In this work, the motion characteristics of these MJPs will be investigated when they are steered by a magnetic field landscape over prototypical parallel-stripe domains, dynamically varied by superposed external magnetic field pulse sequences, in an aqueous medium. We demonstrate, that due to the engineered magnetization state in the hemispherical cap, a comparably fast, directed particle transport and particle rotation can be induced. Additionally, by modifying the frequency of the applied pulse sequence and the strengths of the individual field components, we observe a possible separation between a combined or an individual occurrence of these two types of motion. Our findings bear importance for lab-on-a-chip systems, where particle immobilization on a surface via analyte bridges shall be used for low concentration analyte detection and a particle rotation over a defined position of a substrate may dramatically increase the immobilization (and therefore analyte detection) probability. %@ 0123456789
Traffic Safety in Future Cities by Using a Safety Approach Based on AI and Wireless Communications. König, I.; Bachmann, M.; Bieshaar, M.; Schindler, S.; Lambrecht, F.; David, K.; Sick, B.; Hornung, G.; Sommer, C. In ITG-Symposium on Mobile Communication - Technologies and Applications, bll 1–6. Osnabrück, Germany, 2021.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{koenig2021traffic, address = {Osnabrück, Germany}, author = {K\"onig, I. and Bachmann, M. and Bieshaar, M. and Schindler, S. and Lambrecht, F. and David, K. and Sick, B. and Hornung, G. and Sommer, C.}, booktitle = {ITG-Symposium on Mobile Communication - Technologies and Applications}, keywords = {itegpub}, pages = {1–6}, title = {Traffic Safety in Future Cities by Using a Safety Approach Based on AI and Wireless Communications}, year = 2021 }
%0 Conference Paper %1 koenig2021traffic %A König, I. %A Bachmann, M. %A Bieshaar, M. %A Schindler, S. %A Lambrecht, F. %A David, K. %A Sick, B. %A Hornung, G. %A Sommer, C. %B ITG-Symposium on Mobile Communication - Technologies and Applications %C Osnabrück, Germany %D 2021 %P 1--6 %T Traffic Safety in Future Cities by Using a Safety Approach Based on AI and Wireless Communications
Towards Sensor Data Abstraction of Autonomous Vehicle Perception Systems. Reichert, Hannes; Lang, Lukas; Rösch, Kevin; Bogdoll, Daniel; Doll, Konrad; Sick, Bernhard; Reuss, Hans-Christian; Stiller, Christoph; Zöllner, J. Marius. In IEEE International Smart Cities Conference (ISC2), bll 1–4. IEEE, 2021.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{reichert2021towards, author = {Reichert, Hannes and Lang, Lukas and Rösch, Kevin and Bogdoll, Daniel and Doll, Konrad and Sick, Bernhard and Reuss, Hans-Christian and Stiller, Christoph and Zöllner, J. Marius}, booktitle = {IEEE International Smart Cities Conference (ISC2)}, keywords = {itegpub}, pages = {1–4}, publisher = {IEEE}, title = {Towards Sensor Data Abstraction of Autonomous Vehicle Perception Systems}, year = 2021 }
%0 Conference Paper %1 reichert2021towards %A Reichert, Hannes %A Lang, Lukas %A Rösch, Kevin %A Bogdoll, Daniel %A Doll, Konrad %A Sick, Bernhard %A Reuss, Hans-Christian %A Stiller, Christoph %A Zöllner, J. Marius %B IEEE International Smart Cities Conference (ISC2) %D 2021 %I IEEE %P 1--4 %R 10.1109/isc253183.2021.9562912 %T Towards Sensor Data Abstraction of Autonomous Vehicle Perception Systems
Towards Highly Automated Machine-Learning-Empowered Monitoring of Motor Test Stands. Botache, Diego; Bethke, Florian; Hardieck, Martin; Bieshaar, Maarten; Brabetz, Ludwig; Ayeb, Mohamed; Zipf, Peter; Sick, Bernhard. In IEEE International Conference on Autonomic Computing and Self-Organizing Systems (ACSOS), bll 120–130. IEEE, Washington, DC, USA, 2021.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{botache2021towards, address = {Washington, DC, USA}, author = {Botache, Diego and Bethke, Florian and Hardieck, Martin and Bieshaar, Maarten and Brabetz, Ludwig and Ayeb, Mohamed and Zipf, Peter and Sick, Bernhard}, booktitle = {IEEE International Conference on Autonomic Computing and Self-Organizing Systems (ACSOS)}, keywords = {itegpub}, pages = {120–130}, publisher = {IEEE}, title = {Towards Highly Automated Machine-Learning-Empowered Monitoring of Motor Test Stands}, year = 2021 }
%0 Conference Paper %1 botache2021towards %A Botache, Diego %A Bethke, Florian %A Hardieck, Martin %A Bieshaar, Maarten %A Brabetz, Ludwig %A Ayeb, Mohamed %A Zipf, Peter %A Sick, Bernhard %B IEEE International Conference on Autonomic Computing and Self-Organizing Systems (ACSOS) %C Washington, DC, USA %D 2021 %I IEEE %P 120--130 %R 10.1109/acsos52086.2021.00031 %T Towards Highly Automated Machine-Learning-Empowered Monitoring of Motor Test Stands
Towards Corner Case Detection by Modeling the Uncertainty of Instance Segmentation Networks. Heidecker, Florian; Hannan, Abdul; Bieshaar, Maarten; Sick, Bernhard. In Workshop on Integrated Artificial Intelligence in Data Science, ICPR, bll 361–374. IEEE, Milan, Italy, 2021.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{heidecker2021towards, address = {Milan, Italy}, author = {Heidecker, Florian and Hannan, Abdul and Bieshaar, Maarten and Sick, Bernhard}, booktitle = {Workshop on Integrated Artificial Intelligence in Data Science, ICPR}, keywords = {itegpub}, pages = {361–374}, publisher = {IEEE}, title = {Towards Corner Case Detection by Modeling the Uncertainty of Instance Segmentation Networks}, year = 2021 }
%0 Conference Paper %1 heidecker2021towards %A Heidecker, Florian %A Hannan, Abdul %A Bieshaar, Maarten %A Sick, Bernhard %B Workshop on Integrated Artificial Intelligence in Data Science, ICPR %C Milan, Italy %D 2021 %I IEEE %P 361--374 %R 10.1007/978-3-030-68799-1_26 %T Towards Corner Case Detection by Modeling the Uncertainty of Instance Segmentation Networks
Toward optimal probabilistic active learning using a Bayesian approach. Kottke, Daniel; Herde, Marek; Sandrock, Christoph; Huseljic, Denis; Krempl, Georg; Sick, Bernhard. In Machine Learning, 110(6), bll 1199–1231. Springer, 2021.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
Gathering labeled data to train well-performing machine learning models is one of the critical challenges in many applications. Active learning aims at reducing the labeling costs by an efficient and effective allocation of costly labeling resources. In this article, we propose a decision-theoretic selection strategy that (1) directly optimizes the gain in misclassification error, and (2) uses a Bayesian approach by introducing a conjugate prior distribution to determine the class posterior to deal with uncertainties. By reformulating existing selection strategies within our proposed model, we can explain which aspects are not covered in current state-of-the-art and why this leads to the superior performance of our approach. Extensive experiments on a large variety of datasets and different kernels validate our claims.
@article{kottke2021optimal, abstract = {Gathering labeled data to train well-performing machine learning models is one of the critical challenges in many applications. Active learning aims at reducing the labeling costs by an efficient and effective allocation of costly labeling resources. In this article, we propose a decision-theoretic selection strategy that (1) directly optimizes the gain in misclassification error, and (2) uses a Bayesian approach by introducing a conjugate prior distribution to determine the class posterior to deal with uncertainties. By reformulating existing selection strategies within our proposed model, we can explain which aspects are not covered in current state-of-the-art and why this leads to the superior performance of our approach. Extensive experiments on a large variety of datasets and different kernels validate our claims.}, author = {Kottke, Daniel and Herde, Marek and Sandrock, Christoph and Huseljic, Denis and Krempl, Georg and Sick, Bernhard}, journal = {Machine Learning}, keywords = {itegpub}, number = 6, pages = {1199–1231}, publisher = {Springer}, title = {Toward optimal probabilistic active learning using a Bayesian approach}, volume = 110, year = 2021 }
%0 Journal Article %1 kottke2021optimal %A Kottke, Daniel %A Herde, Marek %A Sandrock, Christoph %A Huseljic, Denis %A Krempl, Georg %A Sick, Bernhard %D 2021 %I Springer %J Machine Learning %N 6 %P 1199--1231 %R 10.1007/s10994-021-05986-9 %T Toward optimal probabilistic active learning using a Bayesian approach %V 110 %X Gathering labeled data to train well-performing machine learning models is one of the critical challenges in many applications. Active learning aims at reducing the labeling costs by an efficient and effective allocation of costly labeling resources. In this article, we propose a decision-theoretic selection strategy that (1) directly optimizes the gain in misclassification error, and (2) uses a Bayesian approach by introducing a conjugate prior distribution to determine the class posterior to deal with uncertainties. By reformulating existing selection strategies within our proposed model, we can explain which aspects are not covered in current state-of-the-art and why this leads to the superior performance of our approach. Extensive experiments on a large variety of datasets and different kernels validate our claims.
Toward Application of Continuous Power Forecasts in a Regional Flexibility Market. He, Yujiang; Huang, Zhixin; Sick, Bernhard. In International Joint Conference on Neural Networks (IJCNN), bll 1–8. IEEE, 2021.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{he2021application, author = {He, Yujiang and Huang, Zhixin and Sick, Bernhard}, booktitle = {International Joint Conference on Neural Networks (IJCNN)}, keywords = {itegpub}, pages = {1–8}, publisher = {IEEE}, title = {Toward Application of Continuous Power Forecasts in a Regional Flexibility Market}, year = 2021 }
%0 Conference Paper %1 he2021application %A He, Yujiang %A Huang, Zhixin %A Sick, Bernhard %B International Joint Conference on Neural Networks (IJCNN) %D 2021 %I IEEE %P 1--8 %R 10.1109/ijcnn52387.2021.9533626 %T Toward Application of Continuous Power Forecasts in a Regional Flexibility Market
Toward AI-enhanced online-characterization and shaping of ultrashort X-ray free-electron laser pulses. Dingel, Kristina; Otto, Thorsten; Marder, Lutz; Funke, Lars; Held, Arne; Savio, Sara; Hans, Andreas; Hartmann, Gregor; Meier, David; Viefhaus, Jens; Sick, Bernhard; Ehresmann, Arno; Ilchen, Markus; Helml, Wolfram. In arXiv e-prints, bl arXiv:2108.13979. 2021.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
X-ray free-electron lasers (XFELs) as the world`s most brilliant light sources provide ultrashort X-ray pulses with durations typically on the order of femtoseconds. Recently, they have approached and entered the attosecond regime, which holds new promises for single-molecule imaging and studying nonlinear and ultrafast phenomena like localized electron dynamics. The technological evolution of XFELs toward well-controllable light sources for precise metrology of ultrafast processes was, however, hampered by the diagnostic capabilities for characterizing X-ray pulses at the attosecond frontier. In this regard, the spectroscopic technique of photoelectron angular streaking has successfully proven how to non-destructively retrieve the exact time-energy structure of XFEL pulses on a single-shot basis. By using artificial intelligence algorithms, in particular convolutional neural networks, we here show how this technique can be leveraged from its proof-of-principle stage toward routine diagnostics at XFELs, thus enhancing and refining their scientific access in all related disciplines.
@article{dingel2021ai, abstract = {X-ray free-electron lasers (XFELs) as the world`s most brilliant light sources provide ultrashort X-ray pulses with durations typically on the order of femtoseconds. Recently, they have approached and entered the attosecond regime, which holds new promises for single-molecule imaging and studying nonlinear and ultrafast phenomena like localized electron dynamics. The technological evolution of XFELs toward well-controllable light sources for precise metrology of ultrafast processes was, however, hampered by the diagnostic capabilities for characterizing X-ray pulses at the attosecond frontier. In this regard, the spectroscopic technique of photoelectron angular streaking has successfully proven how to non-destructively retrieve the exact time-energy structure of XFEL pulses on a single-shot basis. By using artificial intelligence algorithms, in particular convolutional neural networks, we here show how this technique can be leveraged from its proof-of-principle stage toward routine diagnostics at XFELs, thus enhancing and refining their scientific access in all related disciplines.}, author = {{Dingel}, Kristina and {Otto}, Thorsten and {Marder}, Lutz and {Funke}, Lars and {Held}, Arne and {Savio}, Sara and {Hans}, Andreas and {Hartmann}, Gregor and {Meier}, David and {Viefhaus}, Jens and {Sick}, Bernhard and {Ehresmann}, Arno and {Ilchen}, Markus and {Helml}, Wolfram}, journal = {arXiv e-prints}, keywords = {Accelerator}, pages = {arXiv:2108.13979}, title = {{Toward AI-enhanced online-characterization and shaping of ultrashort X-ray free-electron laser pulses}}, year = 2021 }
%0 Journal Article %1 dingel2021ai %A Dingel, Kristina %A Otto, Thorsten %A Marder, Lutz %A Funke, Lars %A Held, Arne %A Savio, Sara %A Hans, Andreas %A Hartmann, Gregor %A Meier, David %A Viefhaus, Jens %A Sick, Bernhard %A Ehresmann, Arno %A Ilchen, Markus %A Helml, Wolfram %D 2021 %J arXiv e-prints %P arXiv:2108.13979 %T Toward AI-enhanced online-characterization and shaping of ultrashort X-ray free-electron laser pulses %X X-ray free-electron lasers (XFELs) as the world`s most brilliant light sources provide ultrashort X-ray pulses with durations typically on the order of femtoseconds. Recently, they have approached and entered the attosecond regime, which holds new promises for single-molecule imaging and studying nonlinear and ultrafast phenomena like localized electron dynamics. The technological evolution of XFELs toward well-controllable light sources for precise metrology of ultrafast processes was, however, hampered by the diagnostic capabilities for characterizing X-ray pulses at the attosecond frontier. In this regard, the spectroscopic technique of photoelectron angular streaking has successfully proven how to non-destructively retrieve the exact time-energy structure of XFEL pulses on a single-shot basis. By using artificial intelligence algorithms, in particular convolutional neural networks, we here show how this technique can be leveraged from its proof-of-principle stage toward routine diagnostics at XFELs, thus enhancing and refining their scientific access in all related disciplines.
The Problem with Real-World Novelty Detection -- Issues in Multivariate Probabilistic Models. Gruhl, Christian; Hannan, Abdul; Huang, Zhixin; Nivarthi, Chandana; Vogt, Stephan. In Workshop on Self-Improving System Integration (SISSY), ACSOS, bll 204–209. IEEE, 2021.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{gruhl2021problem, author = {Gruhl, Christian and Hannan, Abdul and Huang, Zhixin and Nivarthi, Chandana and Vogt, Stephan}, booktitle = {Workshop on Self-Improving System Integration (SISSY), ACSOS}, keywords = {itegpub}, pages = {204–209}, publisher = {IEEE}, title = {The Problem with Real-World Novelty Detection – Issues in Multivariate Probabilistic Models}, year = 2021 }
%0 Conference Paper %1 gruhl2021problem %A Gruhl, Christian %A Hannan, Abdul %A Huang, Zhixin %A Nivarthi, Chandana %A Vogt, Stephan %B Workshop on Self-Improving System Integration (SISSY), ACSOS %D 2021 %I IEEE %P 204--209 %R 10.1109/acsos-c52956.2021.00055 %T The Problem with Real-World Novelty Detection -- Issues in Multivariate Probabilistic Models
Task Embedding Temporal Convolution Networks for Transfer Learning Problems in Renewable Power Time Series Forecast. Schreiber, Jens; Vogt, Stephan; Sick, Bernhard. In European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD): Applied Data Science Track, bll 118–134. Springer, 2021.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{schreiber2021task, author = {Schreiber, Jens and Vogt, Stephan and Sick, Bernhard}, booktitle = {European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD): Applied Data Science Track}, keywords = {itegpub}, pages = {118–134}, publisher = {Springer}, title = {Task Embedding Temporal Convolution Networks for Transfer Learning Problems in Renewable Power Time Series Forecast}, year = 2021 }
%0 Conference Paper %1 schreiber2021task %A Schreiber, Jens %A Vogt, Stephan %A Sick, Bernhard %B European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD): Applied Data Science Track %D 2021 %I Springer %P 118--134 %R 10.1007/978-3-030-86514-6_8 %T Task Embedding Temporal Convolution Networks for Transfer Learning Problems in Renewable Power Time Series Forecast
Statistical Analysis of Pairwise Connectivity. Krempl, Georg; Kottke, Daniel; Pham, Tuan. In International Conference on Discovery Science (DS), Lecture Notes in Computer Science, bll 138–148. Springer, 2021.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{krempl2021statistical, author = {Krempl, Georg and Kottke, Daniel and Pham, Tuan}, booktitle = {International Conference on Discovery Science (DS)}, keywords = {itegpub}, pages = {138–148}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, title = {Statistical Analysis of Pairwise Connectivity}, year = 2021 }
%0 Conference Paper %1 krempl2021statistical %A Krempl, Georg %A Kottke, Daniel %A Pham, Tuan %B International Conference on Discovery Science (DS) %D 2021 %I Springer %P 138--148 %R 10.1007/978-3-030-88942-5_11 %T Statistical Analysis of Pairwise Connectivity
Smart Infrastructure: A Research Junction. Hetzel, Manuel; Reichert, Hannes; Doll, Konrad; Sick, Bernhard. In IEEE International Smart Cities Conference (ISC2). IEEE, 2021.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{hetzel2021smart, author = {Hetzel, Manuel and Reichert, Hannes and Doll, Konrad and Sick, Bernhard}, booktitle = {IEEE International Smart Cities Conference (ISC2)}, keywords = {itegpub}, note = 1, publisher = {IEEE}, title = {Smart Infrastructure: A Research Junction}, year = 2021 }
%0 Conference Paper %1 hetzel2021smart %A Hetzel, Manuel %A Reichert, Hannes %A Doll, Konrad %A Sick, Bernhard %B IEEE International Smart Cities Conference (ISC2) %D 2021 %I IEEE %R 10.1109/isc253183.2021.9562809 %T Smart Infrastructure: A Research Junction
Separation of Aleatoric and Epistemic Uncertainty in Deterministic Deep Neural Networks. Huseljic, Denis; Sick, Bernhard; Herde, Marek; Kottke, Daniel. In International Conference on Pattern Recognition (ICPR), bll 9172–9179. IEEE, 2021.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{huseljic2021separation, author = {Huseljic, Denis and Sick, Bernhard and Herde, Marek and Kottke, Daniel}, booktitle = {International Conference on Pattern Recognition (ICPR)}, keywords = {itegpub}, pages = {9172–9179}, publisher = {IEEE}, title = {Separation of Aleatoric and Epistemic Uncertainty in Deterministic Deep Neural Networks}, year = 2021 }
%0 Conference Paper %1 huseljic2021separation %A Huseljic, Denis %A Sick, Bernhard %A Herde, Marek %A Kottke, Daniel %B International Conference on Pattern Recognition (ICPR) %D 2021 %I IEEE %P 9172--9179 %R 10.1109/icpr48806.2021.9412616 %T Separation of Aleatoric and Epistemic Uncertainty in Deterministic Deep Neural Networks
Self-improving system integration: Mastering continuous change. Bellman, Kirstie; Botev, Jean; Diaconescu, Ada; Esterle, Lukas; Gruhl, Christian; Landauer, Christopher; Lewis, Peter R.; Nelson, Phyllis R.; Pournaras, Evangelos; Stein, Anthony; Tomforde, Sven. In Future Generation Computer Systems, 117, bll 29–46. Elsevier, 2021.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
The research initiative “self-improving system integration” (SISSY) was established with the goal to master the ever-changing demands of system organisation in the presence of autonomous subsystems, evolving architectures, and highly-dynamic open environments. It aims to move integration-related decisions from design-time to run-time, implying a further shift of expertise and responsibility from human engineers to autonomous systems. This introduces a qualitative shift from existing self-adaptive and self-organising systems, moving from self-adaptation based on predefined variation types, towards more open contexts involving novel autonomous subsystems, collaborative behaviours, and emerging goals. In this article, we revisit existing SISSY research efforts and establish a corresponding terminology focusing on how SISSY relates to the broad field of integration sciences. We then investigate SISSY-related research efforts and derive a taxonomy of SISSY technology. This is concluded by establishing a research road-map for developing operational self-improving self-integrating systems.
@article{bellman2021self, abstract = {The research initiative “self-improving system integration” (SISSY) was established with the goal to master the ever-changing demands of system organisation in the presence of autonomous subsystems, evolving architectures, and highly-dynamic open environments. It aims to move integration-related decisions from design-time to run-time, implying a further shift of expertise and responsibility from human engineers to autonomous systems. This introduces a qualitative shift from existing self-adaptive and self-organising systems, moving from self-adaptation based on predefined variation types, towards more open contexts involving novel autonomous subsystems, collaborative behaviours, and emerging goals. In this article, we revisit existing SISSY research efforts and establish a corresponding terminology focusing on how SISSY relates to the broad field of integration sciences. We then investigate SISSY-related research efforts and derive a taxonomy of SISSY technology. This is concluded by establishing a research road-map for developing operational self-improving self-integrating systems.}, author = {Bellman, Kirstie and Botev, Jean and Diaconescu, Ada and Esterle, Lukas and Gruhl, Christian and Landauer, Christopher and Lewis, Peter R. and Nelson, Phyllis R. and Pournaras, Evangelos and Stein, Anthony and Tomforde, Sven}, journal = {Future Generation Computer Systems}, keywords = {System}, pages = {29–46}, publisher = {Elsevier}, title = {Self-improving system integration: Mastering continuous change}, volume = 117, year = 2021 }
%0 Journal Article %1 bellman2021self %A Bellman, Kirstie %A Botev, Jean %A Diaconescu, Ada %A Esterle, Lukas %A Gruhl, Christian %A Landauer, Christopher %A Lewis, Peter R. %A Nelson, Phyllis R. %A Pournaras, Evangelos %A Stein, Anthony %A Tomforde, Sven %D 2021 %I Elsevier %J Future Generation Computer Systems %P 29--46 %R 10.1016/j.future.2020.11.019 %T Self-improving system integration: Mastering continuous change %U http://www.sciencedirect.com/science/article/pii/S0167739X20330430 %V 117 %X The research initiative “self-improving system integration” (SISSY) was established with the goal to master the ever-changing demands of system organisation in the presence of autonomous subsystems, evolving architectures, and highly-dynamic open environments. It aims to move integration-related decisions from design-time to run-time, implying a further shift of expertise and responsibility from human engineers to autonomous systems. This introduces a qualitative shift from existing self-adaptive and self-organising systems, moving from self-adaptation based on predefined variation types, towards more open contexts involving novel autonomous subsystems, collaborative behaviours, and emerging goals. In this article, we revisit existing SISSY research efforts and establish a corresponding terminology focusing on how SISSY relates to the broad field of integration sciences. We then investigate SISSY-related research efforts and derive a taxonomy of SISSY technology. This is concluded by establishing a research road-map for developing operational self-improving self-integrating systems.
scikit-activeml: A Library and Toolbox for Active Learning Algorithms. Kottke, Daniel; Herde, Marek; Minh, Tuan Pham; Benz, Alexander; Mergard, Pascal; Roghman, Atal; Sandrock, Christoph; Sick, Bernhard. In Preprints, bl 2021030194. 2021.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Machine learning applications often need large amounts of training data to perform well. Whereas unlabeled data can be easily gathered, the labeling process is difficult, time-consuming, or expensive in most applications. Active learning can help solve this problem by querying labels for those data points that will improve the performance the most. Thereby, the goal is that the learning algorithm performs sufficiently well with fewer labels. We provide a library called scikit-activeml that covers the most relevant query strategies and implements tools to work with partially labeled data. It is programmed in Python and builds on top of scikit-learn.
@article{kottke2021scikit, abstract = {Machine learning applications often need large amounts of training data to perform well. Whereas unlabeled data can be easily gathered, the labeling process is difficult, time-consuming, or expensive in most applications. Active learning can help solve this problem by querying labels for those data points that will improve the performance the most. Thereby, the goal is that the learning algorithm performs sufficiently well with fewer labels. We provide a library called scikit-activeml that covers the most relevant query strategies and implements tools to work with partially labeled data. It is programmed in Python and builds on top of scikit-learn.}, author = {Kottke, Daniel and Herde, Marek and Minh, Tuan Pham and Benz, Alexander and Mergard, Pascal and Roghman, Atal and Sandrock, Christoph and Sick, Bernhard}, journal = {Preprints}, keywords = {itegpub}, pages = 2021030194, title = {{scikit-activeml}: {A} Library and Toolbox for Active Learning Algorithms}, year = 2021 }
%0 Journal Article %1 kottke2021scikit %A Kottke, Daniel %A Herde, Marek %A Minh, Tuan Pham %A Benz, Alexander %A Mergard, Pascal %A Roghman, Atal %A Sandrock, Christoph %A Sick, Bernhard %D 2021 %J Preprints %P 2021030194 %T scikit-activeml: A Library and Toolbox for Active Learning Algorithms %U https://www.preprints.org/manuscript/202103.0194/ %X Machine learning applications often need large amounts of training data to perform well. Whereas unlabeled data can be easily gathered, the labeling process is difficult, time-consuming, or expensive in most applications. Active learning can help solve this problem by querying labels for those data points that will improve the performance the most. Thereby, the goal is that the learning algorithm performs sufficiently well with fewer labels. We provide a library called scikit-activeml that covers the most relevant query strategies and implements tools to work with partially labeled data. It is programmed in Python and builds on top of scikit-learn.
Probabilistic VRU Trajectory Forecasting for Model-Predictive Planning -- A Case Study: Overtaking Cyclists. Schneegans, Jan; Eilbrecht, Jan; Zernetsch, Stefan; Bieshaar, Maarten; Doll, Konrad; Stursberg, Olaf; Sick, Bernhard. In Workshop From Benchmarking Behavior Prediction to Socially Compatible Behavior Generation in Autonomous Driving, IV. 2021.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
This work considers (deep) artiﬁcial feed-forward neural networks as parametric approximators in optimal control of discrete-time switched linear systems with controlled switching. The proposed approach is based on approximate dynamic programming and allows the fast computation of (sub-)optimal discrete and continuous control inputs, either by approximating the optimal cost-to-go functions or by approximating the optimal discrete and continuous input policies. An important property of the approach is the satisfaction of polytopic state and input constraints, which is crucial for ensuring safety, as required in many control applications. A numeric example is provided for illustration and evaluation of the approaches.
@inproceedings{schneegans2021probabilistic, abstract = {This work considers (deep) artiﬁcial feed-forward neural networks as parametric approximators in optimal control of discrete-time switched linear systems with controlled switching. The proposed approach is based on approximate dynamic programming and allows the fast computation of (sub-)optimal discrete and continuous control inputs, either by approximating the optimal cost-to-go functions or by approximating the optimal discrete and continuous input policies. An important property of the approach is the satisfaction of polytopic state and input constraints, which is crucial for ensuring safety, as required in many control applications. A numeric example is provided for illustration and evaluation of the approaches.}, author = {Schneegans, Jan and Eilbrecht, Jan and Zernetsch, Stefan and Bieshaar, Maarten and Doll, Konrad and Stursberg, Olaf and Sick, Bernhard}, booktitle = {Workshop From Benchmarking Behavior Prediction to Socially Compatible Behavior Generation in Autonomous Driving, IV}, keywords = {itegpub}, note = {(accepted)}, title = {Probabilistic VRU Trajectory Forecasting for Model-Predictive Planning – A Case Study: Overtaking Cyclists}, year = 2021 }
%0 Conference Paper %1 schneegans2021probabilistic %A Schneegans, Jan %A Eilbrecht, Jan %A Zernetsch, Stefan %A Bieshaar, Maarten %A Doll, Konrad %A Stursberg, Olaf %A Sick, Bernhard %B Workshop From Benchmarking Behavior Prediction to Socially Compatible Behavior Generation in Autonomous Driving, IV %D 2021 %T Probabilistic VRU Trajectory Forecasting for Model-Predictive Planning -- A Case Study: Overtaking Cyclists %X This work considers (deep) artiﬁcial feed-forward neural networks as parametric approximators in optimal control of discrete-time switched linear systems with controlled switching. The proposed approach is based on approximate dynamic programming and allows the fast computation of (sub-)optimal discrete and continuous control inputs, either by approximating the optimal cost-to-go functions or by approximating the optimal discrete and continuous input policies. An important property of the approach is the satisfaction of polytopic state and input constraints, which is crucial for ensuring safety, as required in many control applications. A numeric example is provided for illustration and evaluation of the approaches.
Pose Based Trajectory Forecast of Vulnerable Road Users Using Recurrent Neural Networks. Kress, Viktor; Zernetsch, Stefan; Doll, Konrad; Sick, Bernhard. In Workshop on Integrated Artificial Intelligence in Data Science, ICPR, bll 57–71. Springer, 2021.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{kress2021pose, author = {Kress, Viktor and Zernetsch, Stefan and Doll, Konrad and Sick, Bernhard}, booktitle = {Workshop on Integrated Artificial Intelligence in Data Science, ICPR}, keywords = {itegpub}, pages = {57–71}, publisher = {Springer}, title = {Pose Based Trajectory Forecast of Vulnerable Road Users Using Recurrent Neural Networks}, year = 2021 }
%0 Conference Paper %1 kress2021pose %A Kress, Viktor %A Zernetsch, Stefan %A Doll, Konrad %A Sick, Bernhard %B Workshop on Integrated Artificial Intelligence in Data Science, ICPR %D 2021 %I Springer %P 57--71 %R 10.1007/978-3-030-68763-2_5 %T Pose Based Trajectory Forecast of Vulnerable Road Users Using Recurrent Neural Networks
Out-of-distribution Detection and Generation using Soft Brownian Offset Sampling and Autoencoders. Möller, Felix; Botache, Diego; Huseljic, Denis; Heidecker, Florian; Bieshaar, Maarten; Sick, Bernhard. In Workshop on Safe Artificial Intelligence for Automated Driving (SAIAD), CVPR, bll 1–10. 2021.
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
@inproceedings{moeller2021out, author = {Möller, Felix and Botache, Diego and Huseljic, Denis and Heidecker, Florian and Bieshaar, Maarten and Sick, Bernhard}, booktitle = {Workshop on Safe Artificial Intelligence for Automated Driving (SAIAD), CVPR}, keywords = {itegpub}, pages = {1–10}, title = {{Out-of-distribution Detection and Generation using Soft Brownian Offset Sampling and Autoencoders}}, year = 2021 }
%0 Conference Paper %1 moeller2021out %A Möller, Felix %A Botache, Diego %A Huseljic, Denis %A Heidecker, Florian %A Bieshaar, Maarten %A Sick, Bernhard %B Workshop on Safe Artificial Intelligence for Automated Driving (SAIAD), CVPR %D 2021 %P 1--10 %T Out-of-distribution Detection and Generation using Soft Brownian Offset Sampling and Autoencoders %U https://openaccess.thecvf.com/content/CVPR2021W/SAIAD/papers/Moller_Out-of-Distribution_Detection_and_Generation_Using_Soft_Brownian_Offset_Sampling_and_CVPRW_2021_paper.pdf
OHODIN -- Online Anomaly Detection for Data Streams. Gruhl, Christian; Tomforde, Sven. In Workshop on Self-Improving System Integration (SISSY), ACSOS, bll 193–197. IEEE, 2021.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{gruhl2021ohodin, author = {Gruhl, Christian and Tomforde, Sven}, booktitle = {Workshop on Self-Improving System Integration (SISSY), ACSOS}, keywords = {itegpub}, pages = {193–197}, publisher = {IEEE}, title = {OHODIN – Online Anomaly Detection for Data Streams}, year = 2021 }
%0 Conference Paper %1 gruhl2021ohodin %A Gruhl, Christian %A Tomforde, Sven %B Workshop on Self-Improving System Integration (SISSY), ACSOS %D 2021 %I IEEE %P 193--197 %R 10.1109/acsos-c52956.2021.00046 %T OHODIN -- Online Anomaly Detection for Data Streams
Object Detection For Automotive Radar Point Clouds -- A Comparison. Scheiner, Nicolas; Kraus, Florian; Appenrodt, Nils; Dickmann, Jürgen; Sick, Bernhard. In AI Perspectives, 3(1), bl 6. Springer, 2021.
- [ BibTeX ]
- [ EndNote ]
@article{scheiner2021object, author = {Scheiner, Nicolas and Kraus, Florian and Appenrodt, Nils and Dickmann, Jürgen and Sick, Bernhard}, journal = {AI Perspectives}, keywords = {itegpub}, number = 1, pages = 6, publisher = {Springer}, title = {Object Detection For Automotive Radar Point Clouds – A Comparison}, volume = 3, year = 2021 }
%0 Journal Article %1 scheiner2021object %A Scheiner, Nicolas %A Kraus, Florian %A Appenrodt, Nils %A Dickmann, Jürgen %A Sick, Bernhard %D 2021 %I Springer %J AI Perspectives %N 1 %P 6 %R 10.1186/s42467-021-00012-z %T Object Detection For Automotive Radar Point Clouds -- A Comparison %V 3
Novelty detection in continuously changing environments. Gruhl, Christian; Sick, Bernhard; Tomforde, Sven. In Future Generation Computer Systems, 114, bll 138–154. Elsevier, 2021.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
Self-improving system integration (SISSY) aims at mastering the challenges of system organisation decisions for subsystems with highly dynamic behaviours. This is achieved by increased decision freedom of these subsystems, i.e., by moving the corresponding design decisions from design-time to run-time and from engineers to the systems themselves. As a result, a more robust and efficient constellation of the overall system organisation is maintained even under the presence of continuous change and disturbed conditions. Appropriate integration decisions require a solid foundation of assessing the current conditions and their dynamics using identifying triggers for a necessary evaluation of their own integration status. With this article, we present mCANDIES, a modular novelty detection technique especially suited for SISSY systems that fulfils exactly these identification tasks. mCANDIES tackles an anomaly or novelty detection problem in a modular way by combining the advantages of different detection approaches by exploiting locality in different regions of the input space — depending on, e.g. the density or location of expected observations. This is augmented with information about changes in the underlying model of the observations, i.e., mCANDIES identifies concept drifts. The corresponding information can then be used to trigger online learning behaviour. We analyse the behaviour of mCANDIES on artificial and real-world data sets and compare it to other techniques from the state of the art.
@article{gruhl2021novelty, abstract = {Self-improving system integration (SISSY) aims at mastering the challenges of system organisation decisions for subsystems with highly dynamic behaviours. This is achieved by increased decision freedom of these subsystems, i.e., by moving the corresponding design decisions from design-time to run-time and from engineers to the systems themselves. As a result, a more robust and efficient constellation of the overall system organisation is maintained even under the presence of continuous change and disturbed conditions. Appropriate integration decisions require a solid foundation of assessing the current conditions and their dynamics using identifying triggers for a necessary evaluation of their own integration status. With this article, we present mCANDIES, a modular novelty detection technique especially suited for SISSY systems that fulfils exactly these identification tasks. mCANDIES tackles an anomaly or novelty detection problem in a modular way by combining the advantages of different detection approaches by exploiting locality in different regions of the input space — depending on, e.g. the density or location of expected observations. This is augmented with information about changes in the underlying model of the observations, i.e., mCANDIES identifies concept drifts. The corresponding information can then be used to trigger online learning behaviour. We analyse the behaviour of mCANDIES on artificial and real-world data sets and compare it to other techniques from the state of the art.}, author = {Gruhl, Christian and Sick, Bernhard and Tomforde, Sven}, journal = {Future Generation Computer Systems}, keywords = {itegpub}, pages = {138–154}, publisher = {Elsevier}, title = {Novelty detection in continuously changing environments}, volume = 114, year = 2021 }
%0 Journal Article %1 gruhl2021novelty %A Gruhl, Christian %A Sick, Bernhard %A Tomforde, Sven %D 2021 %I Elsevier %J Future Generation Computer Systems %P 138--154 %R 10.1016/j.future.2020.07.037 %T Novelty detection in continuously changing environments %V 114 %X Self-improving system integration (SISSY) aims at mastering the challenges of system organisation decisions for subsystems with highly dynamic behaviours. This is achieved by increased decision freedom of these subsystems, i.e., by moving the corresponding design decisions from design-time to run-time and from engineers to the systems themselves. As a result, a more robust and efficient constellation of the overall system organisation is maintained even under the presence of continuous change and disturbed conditions. Appropriate integration decisions require a solid foundation of assessing the current conditions and their dynamics using identifying triggers for a necessary evaluation of their own integration status. With this article, we present mCANDIES, a modular novelty detection technique especially suited for SISSY systems that fulfils exactly these identification tasks. mCANDIES tackles an anomaly or novelty detection problem in a modular way by combining the advantages of different detection approaches by exploiting locality in different regions of the input space — depending on, e.g. the density or location of expected observations. This is augmented with information about changes in the underlying model of the observations, i.e., mCANDIES identifies concept drifts. The corresponding information can then be used to trigger online learning behaviour. We analyse the behaviour of mCANDIES on artificial and real-world data sets and compare it to other techniques from the state of the art.
Novelty based Driver Identification on RR Intervals from ECG Data. Heidecker, Florian; Gruhl, Christian; Sick, Bernhard. In Workshop on Integrated Artificial Intelligence in Data Science, ICPR, bll 407–421. IEEE, Milan, Italy, 2021.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{heidecker2021novelty, address = {Milan, Italy}, author = {Heidecker, Florian and Gruhl, Christian and Sick, Bernhard}, booktitle = {Workshop on Integrated Artificial Intelligence in Data Science, ICPR}, keywords = {itegpub}, pages = {407–421}, publisher = {IEEE}, title = {Novelty based Driver Identification on RR Intervals from ECG Data}, year = 2021 }
%0 Conference Paper %1 heidecker2021novelty %A Heidecker, Florian %A Gruhl, Christian %A Sick, Bernhard %B Workshop on Integrated Artificial Intelligence in Data Science, ICPR %C Milan, Italy %D 2021 %I IEEE %P 407--421 %R 10.1007/978-3-030-68799-1_29 %T Novelty based Driver Identification on RR Intervals from ECG Data
Multi-annotator Probabilistic Active Learning. Herde, Marek; Kottke, Daniel; Huseljic, Denis; Sick, Bernhard. In International Conference on Pattern Recognition (ICPR), bll 10281–10288. IEEE, 2021.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{herde2021multi, author = {Herde, Marek and Kottke, Daniel and Huseljic, Denis and Sick, Bernhard}, booktitle = {International Conference on Pattern Recognition (ICPR)}, keywords = {itegpub}, pages = {10281–10288}, publisher = {IEEE}, title = {Multi-annotator Probabilistic Active Learning}, year = 2021 }
%0 Conference Paper %1 herde2021multi %A Herde, Marek %A Kottke, Daniel %A Huseljic, Denis %A Sick, Bernhard %B International Conference on Pattern Recognition (ICPR) %D 2021 %I IEEE %P 10281--10288 %R 10.1109/icpr48806.2021.9412298 %T Multi-annotator Probabilistic Active Learning
Iterative Label Improvement: Robust Training by Confidence Based Filtering and Dataset Partitioning. Haase-Schütz, Christian; Stal, Rainer; Hertlein, Heinz; Sick, Bernhard. In International Conference on Pattern Recognition (ICPR), bll 9483–9490. IEEE, 2021.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{haaseschuetz2021iterative, author = {Haase-Schütz, Christian and Stal, Rainer and Hertlein, Heinz and Sick, Bernhard}, booktitle = {International Conference on Pattern Recognition (ICPR)}, keywords = {itegpub}, pages = {9483–9490}, publisher = {IEEE}, title = {Iterative Label Improvement: Robust Training by Confidence Based Filtering and Dataset Partitioning}, year = 2021 }
%0 Conference Paper %1 haaseschuetz2021iterative %A Haase-Schütz, Christian %A Stal, Rainer %A Hertlein, Heinz %A Sick, Bernhard %B International Conference on Pattern Recognition (ICPR) %D 2021 %I IEEE %P 9483--9490 %R 10.1109/icpr48806.2021.9411918 %T Iterative Label Improvement: Robust Training by Confidence Based Filtering and Dataset Partitioning
Intelligent and Interactive Video Annotation for Instance Segmentation using Siamese Neural Networks. Schneegans, Jan; Bieshaar, Maarten; Heidecker, Florian; Sick, Bernhard. In Workshop on Integrated Artificial Intelligence in Data Science, ICPR, bll 375–389. IEEE, Milan, Italy, 2021.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{schneegans2021intelligent, address = {Milan, Italy}, author = {Schneegans, Jan and Bieshaar, Maarten and Heidecker, Florian and Sick, Bernhard}, booktitle = {Workshop on Integrated Artificial Intelligence in Data Science, ICPR}, keywords = {itegpub}, pages = {375–389}, publisher = {IEEE}, title = {Intelligent and Interactive Video Annotation for Instance Segmentation using Siamese Neural Networks}, year = 2021 }
%0 Conference Paper %1 schneegans2021intelligent %A Schneegans, Jan %A Bieshaar, Maarten %A Heidecker, Florian %A Sick, Bernhard %B Workshop on Integrated Artificial Intelligence in Data Science, ICPR %C Milan, Italy %D 2021 %I IEEE %P 375--389 %R 10.1007/978-3-030-68799-1_27 %T Intelligent and Interactive Video Annotation for Instance Segmentation using Siamese Neural Networks
Image Sequence Based Cyclist Action Recognition Using Multi-Stream 3D Convolution. Zernetsch, Stefan; Schreck, Steven; Kress, Viktor; Doll, Konrad; Sick, Bernhard. In International Conference on Pattern Recognition (ICPR), bll 2620–2626. IEEE, 2021.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{zernetsch2021image, author = {Zernetsch, Stefan and Schreck, Steven and Kress, Viktor and Doll, Konrad and Sick, Bernhard}, booktitle = {International Conference on Pattern Recognition (ICPR)}, keywords = {itegpub}, pages = {2620–2626}, publisher = {IEEE}, title = {Image Sequence Based Cyclist Action Recognition Using Multi-Stream 3D Convolution}, year = 2021 }
%0 Conference Paper %1 zernetsch2021image %A Zernetsch, Stefan %A Schreck, Steven %A Kress, Viktor %A Doll, Konrad %A Sick, Bernhard %B International Conference on Pattern Recognition (ICPR) %D 2021 %I IEEE %P 2620--2626 %R 10.1109/icpr48806.2021.9413233 %T Image Sequence Based Cyclist Action Recognition Using Multi-Stream 3D Convolution
Emerging Relation Network and Task Embedding for Multi-Task Regression Problems. Schreiber, Jens; Sick, Bernhard. In International Conference on Pattern Recognition (ICPR), bll 2663–2670. IEEE, 2021.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{schreiber2021emerging, author = {Schreiber, Jens and Sick, Bernhard}, booktitle = {International Conference on Pattern Recognition (ICPR)}, keywords = {itegpub}, pages = {2663–2670}, publisher = {IEEE}, title = {Emerging Relation Network and Task Embedding for Multi-Task Regression Problems}, year = 2021 }
%0 Conference Paper %1 schreiber2021emerging %A Schreiber, Jens %A Sick, Bernhard %B International Conference on Pattern Recognition (ICPR) %D 2021 %I IEEE %P 2663--2670 %R 10.1109/icpr48806.2021.9412476 %T Emerging Relation Network and Task Embedding for Multi-Task Regression Problems
Digital Shadows in Self-Improving System Integration: A Concept Using Generative Modelling. Al-Falouji, Ghassan; Gruhl, Christian; Tomforde, Sven. In Workshop on Self-Improving System Integration (SISSY), ACSOS, bll 166–171. IEEE, 2021.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{alfalouji2021digital, author = {Al-Falouji, Ghassan and Gruhl, Christian and Tomforde, Sven}, booktitle = {Workshop on Self-Improving System Integration (SISSY), ACSOS}, keywords = {itegpub}, pages = {166–171}, publisher = {IEEE}, title = {Digital Shadows in Self-Improving System Integration: A Concept Using Generative Modelling}, year = 2021 }
%0 Conference Paper %1 alfalouji2021digital %A Al-Falouji, Ghassan %A Gruhl, Christian %A Tomforde, Sven %B Workshop on Self-Improving System Integration (SISSY), ACSOS %D 2021 %I IEEE %P 166--171 %R 10.1109/acsos-c52956.2021.00047 %T Digital Shadows in Self-Improving System Integration: A Concept Using Generative Modelling
Description of Corner Cases in Automated Driving: Goals and Challenges. Bogdoll, Daniel; Breitenstein, Jasmin; Heidecker, Florian; Bieshaar, Maarten; Sick, Bernhard; Fingscheidt, Tim; Zöllner, J. Marius. In Embedded and Real-World Computer Vision in Autonomous Driving (ERCVAD), ICCV, bll 1023–1028. IEEE, 2021.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{bogdoll2021description, author = {Bogdoll, Daniel and Breitenstein, Jasmin and Heidecker, Florian and Bieshaar, Maarten and Sick, Bernhard and Fingscheidt, Tim and Zöllner, J. Marius}, booktitle = {Embedded and Real-World Computer Vision in Autonomous Driving (ERCVAD), ICCV}, keywords = {itegpub}, pages = {1023–1028,}, publisher = {IEEE}, title = {Description of Corner Cases in Automated Driving: Goals and Challenges}, year = 2021 }
%0 Conference Paper %1 bogdoll2021description %A Bogdoll, Daniel %A Breitenstein, Jasmin %A Heidecker, Florian %A Bieshaar, Maarten %A Sick, Bernhard %A Fingscheidt, Tim %A Zöllner, J. Marius %B Embedded and Real-World Computer Vision in Autonomous Driving (ERCVAD), ICCV %D 2021 %I IEEE %P 1023--1028, %R 10.1109/iccvw54120.2021.00119 %T Description of Corner Cases in Automated Driving: Goals and Challenges
Cyclist Trajectory Forecasts by Incorporation of Multi-View Video Information. Zernetsch, Stefan; Trupp, Oliver; Kress, Viktor; Doll, Konrad; Sick, Bernhard. In IEEE International Smart Cities Conference (ISC2), bll 1–7. IEEE, 2021.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{zernetsch2021cyclist, author = {Zernetsch, Stefan and Trupp, Oliver and Kress, Viktor and Doll, Konrad and Sick, Bernhard}, booktitle = {IEEE International Smart Cities Conference (ISC2)}, keywords = {itegpub}, pages = {1–7}, publisher = {IEEE}, title = {Cyclist Trajectory Forecasts by Incorporation of Multi-View Video Information}, year = 2021 }
%0 Conference Paper %1 zernetsch2021cyclist %A Zernetsch, Stefan %A Trupp, Oliver %A Kress, Viktor %A Doll, Konrad %A Sick, Bernhard %B IEEE International Smart Cities Conference (ISC2) %D 2021 %I IEEE %P 1--7 %R 10.1109/isc253183.2021.9562857 %T Cyclist Trajectory Forecasts by Incorporation of Multi-View Video Information
Cyclist Motion State Forecasting -- Going beyond Detection. Bieshaar, M.; Zernetsch, S.; Riepe, K.; Doll, K.; Sick, B. In IEEE Symposium Series on Computational Intelligence (SSCI). IEEE, Orlando, FL, USA, 2021.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{bieshaar2021cyclist, address = {Orlando, FL, USA}, author = {Bieshaar, M. and Zernetsch, S. and Riepe, K. and Doll, K. and Sick, B.}, booktitle = {IEEE Symposium Series on Computational Intelligence (SSCI)}, keywords = {itegpub}, note = {(accepted)}, publisher = {IEEE}, title = {Cyclist Motion State Forecasting – Going beyond Detection}, year = 2021 }
%0 Conference Paper %1 bieshaar2021cyclist %A Bieshaar, M. %A Zernetsch, S. %A Riepe, K. %A Doll, K. %A Sick, B. %B IEEE Symposium Series on Computational Intelligence (SSCI) %C Orlando, FL, USA %D 2021 %I IEEE %T Cyclist Motion State Forecasting -- Going beyond Detection
Cooperative intention detection using machine learning. Advanced cyclist protection in the context of automated driving. Bieshaar, Maarten. kassel university press, 2021.
- [ BibTeX ]
- [ EndNote ]
@phdthesis{bieshaar2021cooperative, author = {Bieshaar, Maarten}, keywords = {imported}, publisher = {kassel university press}, school = {University of Kassel}, title = {Cooperative intention detection using machine learning. Advanced cyclist protection in the context of automated driving}, year = 2021 }
%0 Thesis %1 bieshaar2021cooperative %A Bieshaar, Maarten %D 2021 %I kassel university press %R 10.17170/kobra-202101263056 %T Cooperative intention detection using machine learning. Advanced cyclist protection in the context of automated driving
CLeaR: An adaptive continual learning framework for regression tasks. He, Yujiang; Sick, Bernhard. In AI Perspectives, 3(1), bl 2. Springer, 2020.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Catastrophic forgetting means that a trained neural network model gradually forgets the previously learned tasks when being retrained on new tasks. Overcoming the forgetting problem is a major problem in machine learning. Numerous continual learning algorithms are very successful in incremental learning of classification tasks, where new samples with their labels appear frequently. However, there is currently no research that addresses the catastrophic forgetting problem in regression tasks as far as we know. This problem has emerged as one of the primary constraints in some applications, such as renewable energy forecasts. This article clarifies problem-related definitions and proposes a new methodological framework that can forecast targets and update itself by means of continual learning. The framework consists of forecasting neural networks and buffers, which store newly collected data from a non-stationary data stream in an application. The changed probability distribution of the data stream, which the framework has identified, will be learned sequentially. The framework is called CLeaR (Continual Learning for Regression Tasks), where components can be flexibly customized for a specific application scenario. We design two sets of experiments to evaluate the CLeaR framework concerning fitting error (training), prediction error (test), and forgetting ratio. The first one is based on an artificial time series to explore how hyperparameters affect the CLeaR framework. The second one is designed with data collected from European wind farms to evaluate the CLeaR framework's performance in a real-world application. The experimental results demonstrate that the CLeaR framework can continually acquire knowledge in the data stream and improve the prediction accuracy. The article concludes with further research issues arising from requirements to extend the framework.
@article{he2021clear, abstract = {Catastrophic forgetting means that a trained neural network model gradually forgets the previously learned tasks when being retrained on new tasks. Overcoming the forgetting problem is a major problem in machine learning. Numerous continual learning algorithms are very successful in incremental learning of classification tasks, where new samples with their labels appear frequently. However, there is currently no research that addresses the catastrophic forgetting problem in regression tasks as far as we know. This problem has emerged as one of the primary constraints in some applications, such as renewable energy forecasts. This article clarifies problem-related definitions and proposes a new methodological framework that can forecast targets and update itself by means of continual learning. The framework consists of forecasting neural networks and buffers, which store newly collected data from a non-stationary data stream in an application. The changed probability distribution of the data stream, which the framework has identified, will be learned sequentially. The framework is called CLeaR (Continual Learning for Regression Tasks), where components can be flexibly customized for a specific application scenario. We design two sets of experiments to evaluate the CLeaR framework concerning fitting error (training), prediction error (test), and forgetting ratio. The first one is based on an artificial time series to explore how hyperparameters affect the CLeaR framework. The second one is designed with data collected from European wind farms to evaluate the CLeaR framework's performance in a real-world application. The experimental results demonstrate that the CLeaR framework can continually acquire knowledge in the data stream and improve the prediction accuracy. The article concludes with further research issues arising from requirements to extend the framework.}, author = {He, Yujiang and Sick, Bernhard}, journal = {AI Perspectives}, keywords = {itegpub}, number = 1, pages = 2, publisher = {Springer}, title = {CLeaR: An adaptive continual learning framework for regression tasks}, volume = 3, year = 2021 }
%0 Journal Article %1 he2021clear %A He, Yujiang %A Sick, Bernhard %D 2021 %I Springer %J AI Perspectives %N 1 %P 2 %R 10.1186/s42467-021-00009-8 %T CLeaR: An adaptive continual learning framework for regression tasks %U https://doi.org/10.1186/s42467-021-00009-8 %V 3 %X Catastrophic forgetting means that a trained neural network model gradually forgets the previously learned tasks when being retrained on new tasks. Overcoming the forgetting problem is a major problem in machine learning. Numerous continual learning algorithms are very successful in incremental learning of classification tasks, where new samples with their labels appear frequently. However, there is currently no research that addresses the catastrophic forgetting problem in regression tasks as far as we know. This problem has emerged as one of the primary constraints in some applications, such as renewable energy forecasts. This article clarifies problem-related definitions and proposes a new methodological framework that can forecast targets and update itself by means of continual learning. The framework consists of forecasting neural networks and buffers, which store newly collected data from a non-stationary data stream in an application. The changed probability distribution of the data stream, which the framework has identified, will be learned sequentially. The framework is called CLeaR (Continual Learning for Regression Tasks), where components can be flexibly customized for a specific application scenario. We design two sets of experiments to evaluate the CLeaR framework concerning fitting error (training), prediction error (test), and forgetting ratio. The first one is based on an artificial time series to explore how hyperparameters affect the CLeaR framework. The second one is designed with data collected from European wind farms to evaluate the CLeaR framework's performance in a real-world application. The experimental results demonstrate that the CLeaR framework can continually acquire knowledge in the data stream and improve the prediction accuracy. The article concludes with further research issues arising from requirements to extend the framework.
Anomaly based Resilient Network Intrusion Detection using Inferential Autoencoders. Hannan, Abdul; Gruhl, Christian; Sick, Bernhard. In IEEE International Conference on Cyber Security and Resilience (CSR), bll 1–7. IEEE, 2021.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{hannan2021anomaly, author = {Hannan, Abdul and Gruhl, Christian and Sick, Bernhard}, booktitle = {IEEE International Conference on Cyber Security and Resilience (CSR)}, keywords = {itegpub}, pages = {1–7}, publisher = {IEEE}, title = {{Anomaly based Resilient Network Intrusion Detection using Inferential Autoencoders}}, year = 2021 }
%0 Conference Paper %1 hannan2021anomaly %A Hannan, Abdul %A Gruhl, Christian %A Sick, Bernhard %B IEEE International Conference on Cyber Security and Resilience (CSR) %D 2021 %I IEEE %P 1--7 %R 10.1109/csr51186.2021.9527980 %T Anomaly based Resilient Network Intrusion Detection using Inferential Autoencoders
An Application-Driven Conceptualization of Corner Cases for Perception in Highly Automated Driving. Heidecker, Florian; Breitenstein, Jasmin; Rösch, Kevin; Löhdefink, Jonas; Bieshaar, Maarten; Stiller, Christoph; Fingscheidt, Tim; Sick, Bernhard. In IEEE Intelligent Vehicles Symposium (IV), bll 644–651. IEEE, Nagoya, Japan, 2021.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{heidecker2021application, address = {Nagoya, Japan}, author = {Heidecker, Florian and Breitenstein, Jasmin and Rösch, Kevin and Löhdefink, Jonas and Bieshaar, Maarten and Stiller, Christoph and Fingscheidt, Tim and Sick, Bernhard}, booktitle = {IEEE Intelligent Vehicles Symposium (IV)}, keywords = {itegpub}, pages = {644–651}, publisher = {IEEE}, title = {{An Application-Driven Conceptualization of Corner Cases for Perception in Highly Automated Driving}}, year = 2021 }
%0 Conference Paper %1 heidecker2021application %A Heidecker, Florian %A Breitenstein, Jasmin %A Rösch, Kevin %A Löhdefink, Jonas %A Bieshaar, Maarten %A Stiller, Christoph %A Fingscheidt, Tim %A Sick, Bernhard %B IEEE Intelligent Vehicles Symposium (IV) %C Nagoya, Japan %D 2021 %I IEEE %P 644--651 %R 10.1109/iv48863.2021.9575933 %T An Application-Driven Conceptualization of Corner Cases for Perception in Highly Automated Driving
AI - Based On The Fly Design of Experiments in Physics and Engineering. Dingel, Kristina; Liehr, Alexander; Vogel, Michael; Degener, Sebastian; Meier, David; Niendorf, Thomas; Ehresmann, Arno; Sick, Bernhard. In Workshop on Self-Improving System Integration (SISSY), ACSOS, bll 150–153. IEEE, 2021.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{dingel2021aia, author = {Dingel, Kristina and Liehr, Alexander and Vogel, Michael and Degener, Sebastian and Meier, David and Niendorf, Thomas and Ehresmann, Arno and Sick, Bernhard}, booktitle = {Workshop on Self-Improving System Integration (SISSY), ACSOS}, keywords = {itegpub}, pages = {150–153}, publisher = {IEEE}, title = {AI - Based On The Fly Design of Experiments in Physics and Engineering}, year = 2021 }
%0 Conference Paper %1 dingel2021aia %A Dingel, Kristina %A Liehr, Alexander %A Vogel, Michael %A Degener, Sebastian %A Meier, David %A Niendorf, Thomas %A Ehresmann, Arno %A Sick, Bernhard %B Workshop on Self-Improving System Integration (SISSY), ACSOS %D 2021 %I IEEE %P 150--153 %R 10.1109/ACSOS-C52956.2021.00048 %T AI - Based On The Fly Design of Experiments in Physics and Engineering
AdaPT: Adaptable particle tracking for spherical microparticles in lab on chip systems. Dingel, Kristina; Huhnstock, Rico; Knie, André; Ehresmann, Arno; Sick, Bernhard. In Computer Physics Communications, 262, bl 107859. Elsevier, 2021.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
Due to its rising importance in science and technology in recent years, particle tracking in videos presents itself as a tool for successfully acquiring new knowledge in the field of life sciences and physics. Accordingly, different particle tracking methods for various scenarios have been developed. In this article, we present a particle tracking application implemented in Python for, in particular, spherical magnetic particles, including superparamagnetic beads and Janus particles. In the following, we distinguish between two sub-steps in particle tracking, namely the localization of particles in single images and the linking of the extracted particle positions of the subsequent frames into trajectories. We provide an intensity-based localization technique to detect particles and two linking algorithms, which apply either frame-by-frame linking or linear assignment problem solving. Beyond that, we offer helpful tools to preprocess images automatically as well as estimate parameters required for the localization algorithm by utilizing machine learning. As an extra, we have implemented a technique to estimate the current spatial orientation of Janus particles within the x-y-plane. Our framework is readily extendable and easy-to-use as we offer a graphical user interface and a command-line tool. Various output options, such as data frames and videos, ensure further analysis that can be automated.
@article{dingel2021adapt, abstract = {Due to its rising importance in science and technology in recent years, particle tracking in videos presents itself as a tool for successfully acquiring new knowledge in the field of life sciences and physics. Accordingly, different particle tracking methods for various scenarios have been developed. In this article, we present a particle tracking application implemented in Python for, in particular, spherical magnetic particles, including superparamagnetic beads and Janus particles. In the following, we distinguish between two sub-steps in particle tracking, namely the localization of particles in single images and the linking of the extracted particle positions of the subsequent frames into trajectories. We provide an intensity-based localization technique to detect particles and two linking algorithms, which apply either frame-by-frame linking or linear assignment problem solving. Beyond that, we offer helpful tools to preprocess images automatically as well as estimate parameters required for the localization algorithm by utilizing machine learning. As an extra, we have implemented a technique to estimate the current spatial orientation of Janus particles within the x-y-plane. Our framework is readily extendable and easy-to-use as we offer a graphical user interface and a command-line tool. Various output options, such as data frames and videos, ensure further analysis that can be automated.}, author = {Dingel, Kristina and Huhnstock, Rico and Knie, Andr{\'{e}} and Ehresmann, Arno and Sick, Bernhard}, journal = {Computer Physics Communications}, keywords = {itegpub}, pages = 107859, publisher = {Elsevier}, title = {{AdaPT: Adaptable particle tracking for spherical microparticles in lab on chip systems}}, volume = 262, year = 2021 }
%0 Journal Article %1 dingel2021adapt %A Dingel, Kristina %A Huhnstock, Rico %A Knie, André %A Ehresmann, Arno %A Sick, Bernhard %D 2021 %I Elsevier %J Computer Physics Communications %P 107859 %R 10.1016/j.cpc.2021.107859 %T AdaPT: Adaptable particle tracking for spherical microparticles in lab on chip systems %V 262 %X Due to its rising importance in science and technology in recent years, particle tracking in videos presents itself as a tool for successfully acquiring new knowledge in the field of life sciences and physics. Accordingly, different particle tracking methods for various scenarios have been developed. In this article, we present a particle tracking application implemented in Python for, in particular, spherical magnetic particles, including superparamagnetic beads and Janus particles. In the following, we distinguish between two sub-steps in particle tracking, namely the localization of particles in single images and the linking of the extracted particle positions of the subsequent frames into trajectories. We provide an intensity-based localization technique to detect particles and two linking algorithms, which apply either frame-by-frame linking or linear assignment problem solving. Beyond that, we offer helpful tools to preprocess images automatically as well as estimate parameters required for the localization algorithm by utilizing machine learning. As an extra, we have implemented a technique to estimate the current spatial orientation of Janus particles within the x-y-plane. Our framework is readily extendable and easy-to-use as we offer a graphical user interface and a command-line tool. Various output options, such as data frames and videos, ensure further analysis that can be automated.
About the Ambiguity of Data Augmentation for 3D Object Detection in Autonomous Driving. Reuse, Matthias; Simon, Martin; Sick, Bernhard. In Embedded and Real-World Computer Vision in Autonomous Driving (ERCVAD), ICCV, bll 979–987. IEEE, 2021.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{reuse2021ambiguity, author = {Reuse, Matthias and Simon, Martin and Sick, Bernhard}, booktitle = {Embedded and Real-World Computer Vision in Autonomous Driving (ERCVAD), ICCV}, keywords = {itegpub}, pages = {979–987}, publisher = {IEEE}, title = {About the Ambiguity of Data Augmentation for 3D Object Detection in Autonomous Driving}, year = 2021 }
%0 Conference Paper %1 reuse2021ambiguity %A Reuse, Matthias %A Simon, Martin %A Sick, Bernhard %B Embedded and Real-World Computer Vision in Autonomous Driving (ERCVAD), ICCV %D 2021 %I IEEE %P 979--987 %R 10.1109/ICCVW54120.2021.00114 %T About the Ambiguity of Data Augmentation for 3D Object Detection in Autonomous Driving
A Survey on Cost Types, Interaction Schemes, and Annotator Performance Models in Selection Algorithms for Active Learning in Classification. Herde, Marek; Huseljic, Denis; Sick, Bernhard; Calma, Adrian. In IEEE Access, 9, bll 166970–166989. IEEE, 2021.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Pool-based active learning (AL) aims to optimize the annotation process (i.e., labeling) as the acquisition of annotations is often time-consuming and therefore expensive. For this purpose, an AL strategy queries annotations intelligently from annotators to train a high-performance classification model at a low annotation cost. Traditional AL strategies operate in an idealized framework. They assume a single, omniscient annotator who never gets tired and charges uniformly regardless of query difficulty. However, in real-world applications, we often face human annotators, e.g., crowd or in-house workers, who make annotation mistakes and can be reluctant to respond if tired or faced with complex queries. Recently, many novel AL strategies have been proposed to address these issues. They differ in at least one of the following three central aspects from traditional AL: 1) modeling of (multiple) human annotators whose performances can be affected by various factors, such as missing expertise; 2) generalization of the interaction with human annotators through different query and annotation types, such as asking an annotator for feedback on an inferred classification rule; 3) consideration of complex cost schemes regarding annotations and misclassification. This survey provides an overview of these AL strategies and refers to them as real-world AL. Therefore, we introduce a general real-world AL strategy as part of a learning cycle and use its elements, e.g., the query and annotator selection algorithm, to categorize about 60 real-world AL strategies. Finally, we outline possible directions for future research in the field of AL.
@article{herde2021survey, abstract = {Pool-based active learning (AL) aims to optimize the annotation process (i.e., labeling) as the acquisition of annotations is often time-consuming and therefore expensive. For this purpose, an AL strategy queries annotations intelligently from annotators to train a high-performance classification model at a low annotation cost. Traditional AL strategies operate in an idealized framework. They assume a single, omniscient annotator who never gets tired and charges uniformly regardless of query difficulty. However, in real-world applications, we often face human annotators, e.g., crowd or in-house workers, who make annotation mistakes and can be reluctant to respond if tired or faced with complex queries. Recently, many novel AL strategies have been proposed to address these issues. They differ in at least one of the following three central aspects from traditional AL: 1) modeling of (multiple) human annotators whose performances can be affected by various factors, such as missing expertise; 2) generalization of the interaction with human annotators through different query and annotation types, such as asking an annotator for feedback on an inferred classification rule; 3) consideration of complex cost schemes regarding annotations and misclassification. This survey provides an overview of these AL strategies and refers to them as real-world AL. Therefore, we introduce a general real-world AL strategy as part of a learning cycle and use its elements, e.g., the query and annotator selection algorithm, to categorize about 60 real-world AL strategies. Finally, we outline possible directions for future research in the field of AL.}, author = {Herde, Marek and Huseljic, Denis and Sick, Bernhard and Calma, Adrian}, journal = {IEEE Access}, keywords = {classification}, pages = {166970–166989}, publisher = {IEEE}, title = {A Survey on Cost Types, Interaction Schemes, and Annotator Performance Models in Selection Algorithms for Active Learning in Classification}, volume = 9, year = 2021 }
%0 Journal Article %1 herde2021survey %A Herde, Marek %A Huseljic, Denis %A Sick, Bernhard %A Calma, Adrian %D 2021 %I IEEE %J IEEE Access %P 166970--166989 %R 10.1109/ACCESS.2021.3135514 %T A Survey on Cost Types, Interaction Schemes, and Annotator Performance Models in Selection Algorithms for Active Learning in Classification %U https://ieeexplore.ieee.org/abstract/document/9650877 %V 9 %X Pool-based active learning (AL) aims to optimize the annotation process (i.e., labeling) as the acquisition of annotations is often time-consuming and therefore expensive. For this purpose, an AL strategy queries annotations intelligently from annotators to train a high-performance classification model at a low annotation cost. Traditional AL strategies operate in an idealized framework. They assume a single, omniscient annotator who never gets tired and charges uniformly regardless of query difficulty. However, in real-world applications, we often face human annotators, e.g., crowd or in-house workers, who make annotation mistakes and can be reluctant to respond if tired or faced with complex queries. Recently, many novel AL strategies have been proposed to address these issues. They differ in at least one of the following three central aspects from traditional AL: 1) modeling of (multiple) human annotators whose performances can be affected by various factors, such as missing expertise; 2) generalization of the interaction with human annotators through different query and annotation types, such as asking an annotator for feedback on an inferred classification rule; 3) consideration of complex cost schemes regarding annotations and misclassification. This survey provides an overview of these AL strategies and refers to them as real-world AL. Therefore, we introduce a general real-world AL strategy as part of a learning cycle and use its elements, e.g., the query and annotator selection algorithm, to categorize about 60 real-world AL strategies. Finally, we outline possible directions for future research in the field of AL.
A Note on the Modeling Power of Different Graph Types. Thomas, Josephine M.; Beddar-Wiesing, Silvia; Moallemy-Oureh, Alice; Nather, Rüdiger. In arXiv e-prints, bl arXiv:2109.10708. 2021.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Graphs can have different properties that lead to several graph types and may allow for a varying representation of diverse information. In order to clarify the modeling power of graphs, we introduce a partial order on the most common graph types based on an expressivity relation. The expressivity relation quantifies how many properties a graph type can encode compared to another type. Additionally, we show that all attributed graph types are equally expressive and have the same modeling power.
@article{thomas2021note, abstract = {Graphs can have different properties that lead to several graph types and may allow for a varying representation of diverse information. In order to clarify the modeling power of graphs, we introduce a partial order on the most common graph types based on an expressivity relation. The expressivity relation quantifies how many properties a graph type can encode compared to another type. Additionally, we show that all attributed graph types are equally expressive and have the same modeling power.}, author = {Thomas, Josephine M. and Beddar-Wiesing, Silvia and Moallemy-Oureh, Alice and Nather, Rüdiger}, journal = {arXiv e-prints}, keywords = {itegpub}, pages = {arXiv:2109.10708}, title = {A Note on the Modeling Power of Different Graph Types}, year = 2021 }
%0 Journal Article %1 thomas2021note %A Thomas, Josephine M. %A Beddar-Wiesing, Silvia %A Moallemy-Oureh, Alice %A Nather, Rüdiger %D 2021 %J arXiv e-prints %P arXiv:2109.10708 %T A Note on the Modeling Power of Different Graph Types %U https://arxiv.org/abs/2109.10708 %X Graphs can have different properties that lead to several graph types and may allow for a varying representation of diverse information. In order to clarify the modeling power of graphs, we introduce a partial order on the most common graph types based on an expressivity relation. The expressivity relation quantifies how many properties a graph type can encode compared to another type. Additionally, we show that all attributed graph types are equally expressive and have the same modeling power.
A Holistic, Decision-Theoretic Framework for Pool-Based Active Learning. Kottke, Daniel. kassel university press, 2021.
- [ BibTeX ]
- [ EndNote ]
@phdthesis{kottke2021holistic, author = {Kottke, Daniel}, keywords = {imported}, publisher = {kassel university press}, school = {University of Kassel}, title = {A Holistic, Decision-Theoretic Framework for Pool-Based Active Learning}, year = 2021 }
%0 Thesis %1 kottke2021holistic %A Kottke, Daniel %D 2021 %I kassel university press %R 10.17170/kobra-202109244802 %T A Holistic, Decision-Theoretic Framework for Pool-Based Active Learning
A Concept for Highly Automated Pre-Labeling via Cross-Domain Label Transfer for Perception in Autonomous Driving. Bieshaar, Maarten; Herde, Marek; Huselijc, Denis; Sick, Bernhard. In Workshop on Interactive Adaptive Learning (IAL), ECML PKDD. 2021.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{bieshaar2021concept, author = {Bieshaar, Maarten and Herde, Marek and Huselijc, Denis and Sick, Bernhard}, booktitle = {Workshop on Interactive Adaptive Learning (IAL), ECML PKDD}, keywords = {itegpub}, note = {(accepted)}, title = {A Concept for Highly Automated Pre-Labeling via Cross-Domain Label Transfer for Perception in Autonomous Driving}, year = 2021 }
%0 Conference Paper %1 bieshaar2021concept %A Bieshaar, Maarten %A Herde, Marek %A Huselijc, Denis %A Sick, Bernhard %B Workshop on Interactive Adaptive Learning (IAL), ECML PKDD %D 2021 %T A Concept for Highly Automated Pre-Labeling via Cross-Domain Label Transfer for Perception in Autonomous Driving

2020[ to top ]

Toward Optimal Probabilistic Active Learning Using a Bayesian Approach. Kottke, Daniel; Herde, Marek; Sandrock, Christoph; Huseljic, Denis; Krempl, Georg; Sick, Bernhard. In arXiv e-prints, bl arXiv:2006.01732. 2020.
- [ BibTeX ]
- [ EndNote ]
@article{kottke2020optimal, author = {Kottke, Daniel and Herde, Marek and Sandrock, Christoph and Huseljic, Denis and Krempl, Georg and Sick, Bernhard}, journal = {arXiv e-prints}, keywords = {Machine}, pages = {arXiv:2006.01732}, title = {{Toward Optimal Probabilistic Active Learning Using a Bayesian Approach}}, year = 2020 }
%0 Journal Article %1 kottke2020optimal %A Kottke, Daniel %A Herde, Marek %A Sandrock, Christoph %A Huseljic, Denis %A Krempl, Georg %A Sick, Bernhard %D 2020 %J arXiv e-prints %P arXiv:2006.01732 %T Toward Optimal Probabilistic Active Learning Using a Bayesian Approach
Seeing Around Street Corners: Non-Line-of-Sight Detection and Tracking In-the-Wild Using Doppler Radar. Scheiner, Nicolas; Kraus, Florian; Wei, Fangyin; Phan, Buu; Mannan, Fahim; Appenrodt, Nils; Ritter, Werner; Dickmann, Jurgen; Dietmayer, Klaus; Sick, Bernhard; Heide, Felix. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2020.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{scheiner2020seeing, author = {Scheiner, Nicolas and Kraus, Florian and Wei, Fangyin and Phan, Buu and Mannan, Fahim and Appenrodt, Nils and Ritter, Werner and Dickmann, Jurgen and Dietmayer, Klaus and Sick, Bernhard and Heide, Felix}, booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, keywords = {itegpub}, publisher = {IEEE}, title = {Seeing Around Street Corners: Non-Line-of-Sight Detection and Tracking In-the-Wild Using Doppler Radar}, year = 2020 }
%0 Conference Paper %1 scheiner2020seeing %A Scheiner, Nicolas %A Kraus, Florian %A Wei, Fangyin %A Phan, Buu %A Mannan, Fahim %A Appenrodt, Nils %A Ritter, Werner %A Dickmann, Jurgen %A Dietmayer, Klaus %A Sick, Bernhard %A Heide, Felix %B IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) %D 2020 %I IEEE %R 10.1109/cvpr42600.2020.00214 %T Seeing Around Street Corners: Non-Line-of-Sight Detection and Tracking In-the-Wild Using Doppler Radar
Representation Learning in Power Time Series Forecasting. Henze, Janosch; Schreiber, Jens; Sick, Bernhard. In Deep Learning: Algorithms and Applications, W. Pedrycz, S.-M. Chen (reds.), bll 67–101. Springer, 2020.
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
@incollection{henze2020representation, author = {Henze, Janosch and Schreiber, Jens and Sick, Bernhard}, booktitle = {Deep Learning: Algorithms and Applications}, editor = {Pedrycz, Witold and Chen, Shyi-Ming}, keywords = {imported}, pages = {67–101}, publisher = {Springer}, title = {Representation Learning in Power Time Series Forecasting}, year = 2020 }
%0 Book Section %1 henze2020representation %A Henze, Janosch %A Schreiber, Jens %A Sick, Bernhard %B Deep Learning: Algorithms and Applications %D 2020 %E Pedrycz, Witold %E Chen, Shyi-Ming %I Springer %P 67--101 %R 10.1007/978-3-030-31760-7_3 %T Representation Learning in Power Time Series Forecasting %U https://doi.org/10.1007/978-3-030-31760-7_3 %@ 978-3-030-31760-7
Reconstruction of offsets of an electron gun using deep learning and an optimization algorithm. Meier, David; Hartmann, Gregor; Völker, Jens; Viefhaus, Jens; Sick, Bernhard. In Advances in Computational Methods for X-Ray Optics V, bll 71–77. SPIE, 2020.
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
@inproceedings{meier2020reconstruction, author = {Meier, David and Hartmann, Gregor and Völker, Jens and Viefhaus, Jens and Sick, Bernhard}, booktitle = {Advances in Computational Methods for X-Ray Optics V}, keywords = {itegpub}, pages = {71–77}, publisher = {SPIE}, title = {Reconstruction of offsets of an electron gun using deep learning and an optimization algorithm}, year = 2020 }
%0 Conference Paper %1 meier2020reconstruction %A Meier, David %A Hartmann, Gregor %A Völker, Jens %A Viefhaus, Jens %A Sick, Bernhard %B Advances in Computational Methods for X-Ray Optics V %D 2020 %I SPIE %P 71--77 %R 10.1117/12.2568001 %T Reconstruction of offsets of an electron gun using deep learning and an optimization algorithm %U https://doi.org/10.1117/12.2568001
Quantile Surfaces -- Generalizing Quantile Regression to Multivariate Targets. Bieshaar, Maarten; Schreiber, Jens; Vogt, Stephan; Gensler, André; Sick, Bernhard. In arXiv e-prints, bl arXiv:2010.05898. 2020.
- [ BibTeX ]
- [ EndNote ]
@article{bieshaar2020quantile, author = {{Bieshaar}, Maarten and {Schreiber}, Jens and {Vogt}, Stephan and {Gensler}, Andr{\'e} and {Sick}, Bernhard}, journal = {arXiv e-prints}, keywords = {Applications,}, pages = {arXiv:2010.05898}, title = {{Quantile Surfaces – Generalizing Quantile Regression to Multivariate Targets}}, year = 2020 }
%0 Journal Article %1 bieshaar2020quantile %A Bieshaar, Maarten %A Schreiber, Jens %A Vogt, Stephan %A Gensler, André %A Sick, Bernhard %D 2020 %J arXiv e-prints %P arXiv:2010.05898 %T Quantile Surfaces -- Generalizing Quantile Regression to Multivariate Targets
Probabilistic upscaling and aggregation of wind power forecasts. Henze, Janosch; Siefert, Malte; Bremicker-Trübelhorn, Sascha; Asanalieva, Nazgul; Sick, Bernhard. In Energy, Sustainability and Society, 10(1), bl 15. BMC, 2020.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Wind power forecasts of the expected wind feed-in for the next hours or days are necessary to integrate the generated volatile wind energy into power systems. Most forecasting models predict in some sense the best value, but they ignore the other possible outcomes which may arise because of forecasting uncertainties. Probabilistic forecasts, on the other hand, also predict a distribution of possible outcomes with their respective probabilities that specific power values will occur and therefore have higher information content. In this work, we address two problems that hinder the introduction of probabilistic forecasts in practice: (1) no measurement data are available for some wind farms and (2) the flexible aggregation of probabilistic forecasts for changing wind farm portfolios.
@article{henze2020probabilistic, abstract = {Wind power forecasts of the expected wind feed-in for the next hours or days are necessary to integrate the generated volatile wind energy into power systems. Most forecasting models predict in some sense the best value, but they ignore the other possible outcomes which may arise because of forecasting uncertainties. Probabilistic forecasts, on the other hand, also predict a distribution of possible outcomes with their respective probabilities that specific power values will occur and therefore have higher information content. In this work, we address two problems that hinder the introduction of probabilistic forecasts in practice: (1) no measurement data are available for some wind farms and (2) the flexible aggregation of probabilistic forecasts for changing wind farm portfolios.}, author = {Henze, Janosch and Siefert, Malte and Bremicker-Tr{\"u}belhorn, Sascha and Asanalieva, Nazgul and Sick, Bernhard}, journal = {Energy, Sustainability and Society}, keywords = {imported}, number = 1, pages = 15, publisher = {BMC}, title = {Probabilistic upscaling and aggregation of wind power forecasts}, volume = 10, year = 2020 }
%0 Journal Article %1 henze2020probabilistic %A Henze, Janosch %A Siefert, Malte %A Bremicker-Trübelhorn, Sascha %A Asanalieva, Nazgul %A Sick, Bernhard %D 2020 %I BMC %J Energy, Sustainability and Society %N 1 %P 15 %R 10.1186/s13705-020-00247-4 %T Probabilistic upscaling and aggregation of wind power forecasts %U https://doi.org/10.1186/s13705-020-00247-4 %V 10 %X Wind power forecasts of the expected wind feed-in for the next hours or days are necessary to integrate the generated volatile wind energy into power systems. Most forecasting models predict in some sense the best value, but they ignore the other possible outcomes which may arise because of forecasting uncertainties. Probabilistic forecasts, on the other hand, also predict a distribution of possible outcomes with their respective probabilities that specific power values will occur and therefore have higher information content. In this work, we address two problems that hinder the introduction of probabilistic forecasts in practice: (1) no measurement data are available for some wind farms and (2) the flexible aggregation of probabilistic forecasts for changing wind farm portfolios.
Pose Based Action Recognition of Vulnerable Road Users Using Recurrent Neural Networks. Kress, V.; Schreck, S.; Zernetsch, S.; Doll, K.; Sick, B. In IEEE Symposium Series on Computational Intelligence (SSCI), bll 2723–2730. IEEE, 2020.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{kress2020pose, author = {{Kress}, V. and {Schreck}, S. and {Zernetsch}, S. and {Doll}, K. and {Sick}, B.}, booktitle = {IEEE Symposium Series on Computational Intelligence (SSCI)}, keywords = {itegpub}, pages = {2723–2730}, publisher = {IEEE}, title = {Pose Based Action Recognition of Vulnerable Road Users Using Recurrent Neural Networks}, year = 2020 }
%0 Conference Paper %1 kress2020pose %A Kress, V. %A Schreck, S. %A Zernetsch, S. %A Doll, K. %A Sick, B. %B IEEE Symposium Series on Computational Intelligence (SSCI) %D 2020 %I IEEE %P 2723--2730 %R 10.1109/ssci47803.2020.9308462 %T Pose Based Action Recognition of Vulnerable Road Users Using Recurrent Neural Networks
Off-the-shelf sensor vs. experimental radar - How much resolution is necessary in automotive radar classification?. Scheiner, Nicolas; Schumann, Ole; Kraus, Florian; Appenrodt, Nils; Dickmann, Jürgen; Sick, Bernhard. In IEEE International Conference on Information Fusion (FUSION), bll 1–8. IEEE, 2020.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{scheiner2020shelf, author = {Scheiner, Nicolas and Schumann, Ole and Kraus, Florian and Appenrodt, Nils and Dickmann, J{\"{u}}rgen and Sick, Bernhard}, booktitle = {{IEEE} International Conference on Information Fusion (FUSION)}, keywords = {itegpub}, pages = {1–8}, publisher = {IEEE}, title = {Off-the-shelf sensor vs. experimental radar - How much resolution is necessary in automotive radar classification?}, year = 2020 }
%0 Conference Paper %1 scheiner2020shelf %A Scheiner, Nicolas %A Schumann, Ole %A Kraus, Florian %A Appenrodt, Nils %A Dickmann, Jürgen %A Sick, Bernhard %B IEEE International Conference on Information Fusion (FUSION) %D 2020 %I IEEE %P 1--8 %R 10.23919/fusion45008.2020.9190338 %T Off-the-shelf sensor vs. experimental radar - How much resolution is necessary in automotive radar classification?
Normal-Wishart clustering for novelty detection. Gruhl, Christian; Schmeißing, Jörn; Tomforde, Sven; Sick, Bernhard. In Workshop on Self-Improving System Integration (SISSY), ACSOS, bll 64–69. IEEE, 2020.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{gruhl2020normal, author = {Gruhl, Christian and Schmei{\ss}ing, J{\"o}rn and Tomforde, Sven and Sick, Bernhard}, booktitle = {Workshop on Self-Improving System Integration (SISSY), ACSOS}, keywords = {itegpub}, pages = {64–69}, publisher = {IEEE}, title = {{Normal-Wishart} clustering for novelty detection}, year = 2020 }
%0 Conference Paper %1 gruhl2020normal %A Gruhl, Christian %A Schmeißing, Jörn %A Tomforde, Sven %A Sick, Bernhard %B Workshop on Self-Improving System Integration (SISSY), ACSOS %D 2020 %I IEEE %P 64--69 %R 10.1109/acsos-c51401.2020.00032 %T Normal-Wishart clustering for novelty detection
Knowledge Representations in Technical Systems -- A Taxonomy. Scharei, Kristina; Heidecker, Florian; Bieshaar, Maarten. In arXiv e-prints, bl arXiv:2001.04835. 2020.
- [ BibTeX ]
- [ EndNote ]
@article{scharei2020knowledge, author = {Scharei, Kristina and Heidecker, Florian and Bieshaar, Maarten}, journal = {arXiv e-prints}, keywords = {Robotics}, pages = {arXiv:2001.04835}, title = {{Knowledge Representations in Technical Systems – A Taxonomy}}, year = 2020 }
%0 Journal Article %1 scharei2020knowledge %A Scharei, Kristina %A Heidecker, Florian %A Bieshaar, Maarten %D 2020 %J arXiv e-prints %P arXiv:2001.04835 %T Knowledge Representations in Technical Systems -- A Taxonomy
Iterative Label Improvement: Robust Training by Confidence Based Filtering and Dataset Partitioning. Haase-Schütz, Christian; Stal, Rainer; Hertlein, Heinz; Sick, Bernhard. In arXiv e-prints, bl arXiv:2002.02705. 2020.
- [ BibTeX ]
- [ EndNote ]
@article{haaseschuetz2020iterative, author = {{Haase-Sch{\"u}tz}, Christian and {Stal}, Rainer and {Hertlein}, Heinz and {Sick}, Bernhard}, journal = {arXiv e-prints}, keywords = {Recognition,}, pages = {arXiv:2002.02705}, title = {{Iterative Label Improvement: Robust Training by Confidence Based Filtering and Dataset Partitioning}}, year = 2020 }
%0 Journal Article %1 haaseschuetz2020iterative %A Haase-Schütz, Christian %A Stal, Rainer %A Hertlein, Heinz %A Sick, Bernhard %D 2020 %J arXiv e-prints %P arXiv:2002.02705 %T Iterative Label Improvement: Robust Training by Confidence Based Filtering and Dataset Partitioning
Improving Self-Adaptation For Multi-Sensor Activity Recognition with Active Learning. Pham Minh, T.; Kottke, D.; Tsarenko, A.; Gruhl, C.; Sick, B. In International Joint Conference on Neural Networks (IJCNN). IEEE, 2020.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{phamminh2020improving, author = {{Pham Minh}, T. and {Kottke}, D. and {Tsarenko}, A. and {Gruhl}, C. and {Sick}, B.}, booktitle = {International Joint Conference on Neural Networks (IJCNN)}, keywords = {itegpub}, publisher = {IEEE}, title = {Improving Self-Adaptation For Multi-Sensor Activity Recognition with Active Learning}, year = 2020 }
%0 Conference Paper %1 phamminh2020improving %A Pham Minh, T. %A Kottke, D. %A Tsarenko, A. %A Gruhl, C. %A Sick, B. %B International Joint Conference on Neural Networks (IJCNN) %D 2020 %I IEEE %R 10.1109/ijcnn48605.2020.9206873 %T Improving Self-Adaptation For Multi-Sensor Activity Recognition with Active Learning
Forecasting Power Grid States for Regional Energy Markets with Deep Neural Networks. He, Y.; Henze, J.; Sick, B. In International Joint Conference on Neural Networks (IJCNN). IEEE, 2020.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{he2020forecasting, author = {{He}, Y. and {Henze}, J. and {Sick}, B.}, booktitle = {International Joint Conference on Neural Networks (IJCNN)}, keywords = {itegpub}, publisher = {IEEE}, title = {Forecasting Power Grid States for Regional Energy Markets with Deep Neural Networks}, year = 2020 }
%0 Conference Paper %1 he2020forecasting %A He, Y. %A Henze, J. %A Sick, B. %B International Joint Conference on Neural Networks (IJCNN) %D 2020 %I IEEE %R 10.1109/ijcnn48605.2020.9207536 %T Forecasting Power Grid States for Regional Energy Markets with Deep Neural Networks
Fairness, performance, and robustness: is there a cap theorem for self-adaptive and self-organising systems?. Tomforde, Sven; Gruhl, Christian. In Workshop on Self-Improving System Integration (SISSY), ACSOS, bll 54–59. IEEE, 2020.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{tomforde2020fairness, author = {Tomforde, Sven and Gruhl, Christian}, booktitle = {Workshop on Self-Improving System Integration (SISSY), ACSOS}, keywords = {itegpub}, pages = {54–59}, publisher = {IEEE}, title = {Fairness, performance, and robustness: is there a cap theorem for self-adaptive and self-organising systems?}, year = 2020 }
%0 Conference Paper %1 tomforde2020fairness %A Tomforde, Sven %A Gruhl, Christian %B Workshop on Self-Improving System Integration (SISSY), ACSOS %D 2020 %I IEEE %P 54--59 %R 10.1109/acsos-c51401.2020.00029 %T Fairness, performance, and robustness: is there a cap theorem for self-adaptive and self-organising systems?
Extended Coopetitive Soft Gating Ensemble. Deist, Stephan; Schreiber, Jens; Bieshaar, Maarten; Sick, Bernhard. In arXiv e-prints, bl arXiv:2004.14026. 2020.
- [ BibTeX ]
- [ EndNote ]
@article{deist2020extended, author = {Deist, Stephan and Schreiber, Jens and Bieshaar, Maarten and Sick, Bernhard}, journal = {arXiv e-prints}, keywords = {Machine}, pages = {arXiv:2004.14026}, title = {{Extended Coopetitive Soft Gating Ensemble}}, year = 2020 }
%0 Journal Article %1 deist2020extended %A Deist, Stephan %A Schreiber, Jens %A Bieshaar, Maarten %A Sick, Bernhard %D 2020 %J arXiv e-prints %P arXiv:2004.14026 %T Extended Coopetitive Soft Gating Ensemble
Efficient SVDD Sampling with Approximation Guarantees for the Decision Boundary. Englhardt, Adrian; Trittenbach, Holger; Kottke, Daniel; Sick, Bernhard; Böhm, Klemens. In arXiv e-prints, bl arXiv:2009.13853. 2020.
- [ BibTeX ]
- [ EndNote ]
@article{englhardt2020efficient, author = {{Englhardt}, Adrian and {Trittenbach}, Holger and {Kottke}, Daniel and {Sick}, Bernhard and {B{\"o}hm}, Klemens}, journal = {arXiv e-prints}, keywords = {Machine}, pages = {arXiv:2009.13853}, title = {{Efficient SVDD Sampling with Approximation Guarantees for the Decision Boundary}}, year = 2020 }
%0 Journal Article %1 englhardt2020efficient %A Englhardt, Adrian %A Trittenbach, Holger %A Kottke, Daniel %A Sick, Bernhard %A Böhm, Klemens %D 2020 %J arXiv e-prints %P arXiv:2009.13853 %T Efficient SVDD Sampling with Approximation Guarantees for the Decision Boundary
Continuous Learning of Deep Neural Networks to Improve Forecasts for Regional Energy Markets. He, Yujiang; Henze, Janosch; Sick, Bernhard. In International Federation of Automatic Control (IFAC) World Congress, bll 12175–12182. Elsevier, 2020.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{he2020continuous, author = {He, Yujiang and Henze, Janosch and Sick, Bernhard}, booktitle = {{International Federation of Automatic Control (IFAC) World Congress}}, keywords = {itegpub}, pages = {12175–12182}, publisher = {Elsevier}, title = {Continuous Learning of Deep Neural Networks to Improve Forecasts for Regional Energy Markets}, year = 2020 }
%0 Conference Paper %1 he2020continuous %A He, Yujiang %A Henze, Janosch %A Sick, Bernhard %B International Federation of Automatic Control (IFAC) World Congress %D 2020 %I Elsevier %P 12175--12182 %R 10.1016/j.ifacol.2020.12.1017 %T Continuous Learning of Deep Neural Networks to Improve Forecasts for Regional Energy Markets
Active Learning with Uncertain Annotators. Calma, Adrian. kassel university press, 2020.
- [ BibTeX ]
- [ EndNote ]
@phdthesis{calma2020active, author = {Calma, Adrian}, keywords = {imported}, publisher = {kassel university press}, school = {University of Kassel}, title = {Active Learning with Uncertain Annotators}, year = 2020 }
%0 Thesis %1 calma2020active %A Calma, Adrian %D 2020 %I kassel university press %R 10.17170/kobra-202009171814 %T Active Learning with Uncertain Annotators
A swarm-fleet infrastructure as a scenario for proactive, hybrid adaptation of system behaviour. Tomforde, Sven; Gruhl, Christian; Sick, Bernhard. In Workshop on Self -Aware Computing (SeAC), ACSOS, bll 166–169. IEEE, 2020.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{tomforde2020swarm, author = {Tomforde, Sven and Gruhl, Christian and Sick, Bernhard}, booktitle = {Workshop on Self -Aware Computing (SeAC), ACSOS}, keywords = {itegpub}, pages = {166–169}, publisher = {IEEE}, title = {A swarm-fleet infrastructure as a scenario for proactive, hybrid adaptation of system behaviour}, year = 2020 }
%0 Conference Paper %1 tomforde2020swarm %A Tomforde, Sven %A Gruhl, Christian %A Sick, Bernhard %B Workshop on Self -Aware Computing (SeAC), ACSOS %D 2020 %I IEEE %P 166--169 %R 10.1109/acsos-c51401.2020.00050 %T A swarm-fleet infrastructure as a scenario for proactive, hybrid adaptation of system behaviour

2019[ to top ]

Wind Power Forecasting Based on Deep Neural Networks and Transfer Learning. Vogt, Stephan; Braun, Axel; Dobschinski, Jan; Sick, Bernhard. In Wind Integration Workshop. Dublin, Ireland, 2019.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{vogt2019wind, address = {Dublin, Ireland}, author = {Vogt, Stephan and Braun, Axel and Dobschinski, Jan and Sick, Bernhard}, booktitle = {Wind Integration Workshop}, keywords = {imported}, title = {Wind Power Forecasting Based on Deep Neural Networks and Transfer Learning}, year = 2019 }
%0 Conference Paper %1 vogt2019wind %A Vogt, Stephan %A Braun, Axel %A Dobschinski, Jan %A Sick, Bernhard %B Wind Integration Workshop %C Dublin, Ireland %D 2019 %R 10.24406/publica-fhg-406413 %T Wind Power Forecasting Based on Deep Neural Networks and Transfer Learning
Wind Power Ensemble Forecasting. Gensler, André. kassel university press, 2019.
- [ BibTeX ]
- [ EndNote ]
@phdthesis{gensler2019wind, author = {Gensler, André}, keywords = {imported}, publisher = {kassel university press}, school = {University of Kassel}, title = {Wind Power Ensemble Forecasting}, year = 2019 }
%0 Thesis %1 gensler2019wind %A Gensler, André %D 2019 %I kassel university press %R 10.17170/kobra-202008181589 %T Wind Power Ensemble Forecasting
Using grid supporting flexibility in electricity distribution networks. König, Immanuel; Heilmann, Erik; Henze, Janosch; David, Klaus; Wetzel, Heike; Sick, Bernhard. In INFORMATIK 2019: 50 Jahre Gesellschaft für Informatik -- Informatik für Gesellschaft, bll 531–544. Gesellschaft für Informatik e.V., Bonn, 2019.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{koenig2019using, address = {Bonn}, author = {König, Immanuel and Heilmann, Erik and Henze, Janosch and David, Klaus and Wetzel, Heike and Sick, Bernhard}, booktitle = {INFORMATIK 2019: 50 Jahre Gesellschaft für Informatik – Informatik für Gesellschaft}, keywords = {imported}, pages = {531–544}, publisher = {Gesellschaft für Informatik e.V.}, title = {Using grid supporting flexibility in electricity distribution networks}, year = 2019 }
%0 Conference Paper %1 koenig2019using %A König, Immanuel %A Heilmann, Erik %A Henze, Janosch %A David, Klaus %A Wetzel, Heike %A Sick, Bernhard %B INFORMATIK 2019: 50 Jahre Gesellschaft für Informatik -- Informatik für Gesellschaft %C Bonn %D 2019 %I Gesellschaft für Informatik e.V. %P 531--544 %R 10.18420/inf2019_70 %T Using grid supporting flexibility in electricity distribution networks
Tree Species Classification Based on Hybrid Ensembles of a Convolutional Neural Network (CNN) and Random Forest Classifiers. Knauer, Uwe; Styp von Rekowski, Cornelius; Stecklina, Marianne; Krokotsch, Tilman; Pham Minh, Tuan; Hauffe, Viola; Kilias, David; Ehrhardt, Ina; Sagischewski, Herbert; Chmara, Sergej; Seiffert, Udo. In Remote Sensing, 11(23), bl 2788. MDPI, 2019.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
In this paper, we evaluate different popular voting strategies for fusion of classifier results. A convolutional neural network (CNN) and different variants of random forest (RF) classifiers were trained to discriminate between 15 tree species based on airborne hyperspectral imaging data. The spectral data was preprocessed with a multi-class linear discriminant analysis (MCLDA) as a means to reduce dimensionality and to obtain spatial–spectral features. The best individual classifier was a CNN with a classification accuracy of 0.73 +/− 0.086. The classification performance increased to an accuracy of 0.78 +/− 0.053 by using precision weighted voting for a hybrid ensemble of the CNN and two RF classifiers. This voting strategy clearly outperformed majority voting (0.74), accuracy weighted voting (0.75), and presidential voting (0.75).
@article{knauer2019tree, abstract = {In this paper, we evaluate different popular voting strategies for fusion of classifier results. A convolutional neural network (CNN) and different variants of random forest (RF) classifiers were trained to discriminate between 15 tree species based on airborne hyperspectral imaging data. The spectral data was preprocessed with a multi-class linear discriminant analysis (MCLDA) as a means to reduce dimensionality and to obtain spatial–spectral features. The best individual classifier was a CNN with a classification accuracy of 0.73 +/− 0.086. The classification performance increased to an accuracy of 0.78 +/− 0.053 by using precision weighted voting for a hybrid ensemble of the CNN and two RF classifiers. This voting strategy clearly outperformed majority voting (0.74), accuracy weighted voting (0.75), and presidential voting (0.75).}, author = {Knauer, Uwe and Styp von Rekowski, Cornelius and Stecklina, Marianne and Krokotsch, Tilman and Pham Minh, Tuan and Hauffe, Viola and Kilias, David and Ehrhardt, Ina and Sagischewski, Herbert and Chmara, Sergej and Seiffert, Udo}, journal = {Remote Sensing}, keywords = {imported}, number = 23, pages = 2788, publisher = {MDPI}, title = {Tree Species Classification Based on Hybrid Ensembles of a Convolutional Neural Network (CNN) and Random Forest Classifiers}, volume = 11, year = 2019 }
%0 Journal Article %1 knauer2019tree %A Knauer, Uwe %A Styp von Rekowski, Cornelius %A Stecklina, Marianne %A Krokotsch, Tilman %A Pham Minh, Tuan %A Hauffe, Viola %A Kilias, David %A Ehrhardt, Ina %A Sagischewski, Herbert %A Chmara, Sergej %A Seiffert, Udo %D 2019 %I MDPI %J Remote Sensing %N 23 %P 2788 %R 10.3390/rs11232788 %T Tree Species Classification Based on Hybrid Ensembles of a Convolutional Neural Network (CNN) and Random Forest Classifiers %U https://www.mdpi.com/2072-4292/11/23/2788 %V 11 %X In this paper, we evaluate different popular voting strategies for fusion of classifier results. A convolutional neural network (CNN) and different variants of random forest (RF) classifiers were trained to discriminate between 15 tree species based on airborne hyperspectral imaging data. The spectral data was preprocessed with a multi-class linear discriminant analysis (MCLDA) as a means to reduce dimensionality and to obtain spatial–spectral features. The best individual classifier was a CNN with a classification accuracy of 0.73 +/− 0.086. The classification performance increased to an accuracy of 0.78 +/− 0.053 by using precision weighted voting for a hybrid ensemble of the CNN and two RF classifiers. This voting strategy clearly outperformed majority voting (0.74), accuracy weighted voting (0.75), and presidential voting (0.75).
Transfer Learning is a Crucial Capability of Intelligent Systems Self-Integrating at Runtime. Stein, A.; Tomforde, S. In Workshop on Self-Improving System Integration (SISSY), FAS*W, bll 32–35. IEEE, 2019.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{stein2019transfer, author = {{Stein}, A. and {Tomforde}, S.}, booktitle = {Workshop on Self-Improving System Integration (SISSY), FAS*W}, keywords = {imported}, pages = {32–35}, publisher = {IEEE}, title = {Transfer Learning is a Crucial Capability of Intelligent Systems Self-Integrating at Runtime}, year = 2019 }
%0 Conference Paper %1 stein2019transfer %A Stein, A. %A Tomforde, S. %B Workshop on Self-Improving System Integration (SISSY), FAS*W %D 2019 %I IEEE %P 32--35 %R 10.1109/FAS-W.2019.00021 %T Transfer Learning is a Crucial Capability of Intelligent Systems Self-Integrating at Runtime
Transfer Learning in the Field of Renewable Energies -- A Transfer Learning Framework Providing Power Forecasts Throughout the Lifecycle of Wind Farms After Initial Connection to the Electrical Grid. Schreiber, Jens. In Organic Computing -- Doctoral Dissertation Colloquium 2018, S. Tomforde, B. Sick (reds.), bll 75–87. kassel university press, Kassel, Germany, 2019.
- [ BibTeX ]
- [ EndNote ]
@incollection{schreiber2019transfer, address = {Kassel, Germany}, author = {Schreiber, Jens}, booktitle = {Organic Computing – Doctoral Dissertation Colloquium 2018}, editor = {Tomforde, S. and Sick, B.}, keywords = {imported}, pages = {75–87}, publisher = {kassel university press}, title = {Transfer Learning in the Field of Renewable Energies – {A} Transfer Learning Framework Providing Power Forecasts Throughout the Lifecycle of Wind Farms After Initial Connection to the Electrical Grid}, year = 2019 }
%0 Book Section %1 schreiber2019transfer %A Schreiber, Jens %B Organic Computing -- Doctoral Dissertation Colloquium 2018 %C Kassel, Germany %D 2019 %E Tomforde, S. %E Sick, B. %I kassel university press %P 75--87 %T Transfer Learning in the Field of Renewable Energies -- A Transfer Learning Framework Providing Power Forecasts Throughout the Lifecycle of Wind Farms After Initial Connection to the Electrical Grid
Trajectory Forecasts with Uncertainties of Vulnerable Road Users by Means of Neural Networks. Zernetsch, S.; Reichert, H.; Kress, V.; Doll, K.; Sick, B. In IEEE Intelligent Vehicles Symposium (IV), bll 810–815. IEEE, 2019.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{zernetsch2019trajectory, author = {{Zernetsch}, S. and {Reichert}, H. and {Kress}, V. and {Doll}, K. and {Sick}, B.}, booktitle = {IEEE Intelligent Vehicles Symposium (IV)}, keywords = {imported}, pages = {810–815}, publisher = {IEEE}, title = {Trajectory Forecasts with Uncertainties of Vulnerable Road Users by Means of Neural Networks}, year = 2019 }
%0 Conference Paper %1 zernetsch2019trajectory %A Zernetsch, S. %A Reichert, H. %A Kress, V. %A Doll, K. %A Sick, B. %B IEEE Intelligent Vehicles Symposium (IV) %D 2019 %I IEEE %P 810--815 %R 10.1109/IVS.2019.8814258 %T Trajectory Forecasts with Uncertainties of Vulnerable Road Users by Means of Neural Networks
Towards Corner Case Identification in Cyclists’ Trajectories. Heidecker, F.; Bieshaar, M.; Sick, B. In ACM Computer Science in Cars Symposium (CSCS). ACM, 2019.
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
@inproceedings{heidecker2019towards, author = {Heidecker, F. and Bieshaar, M. and Sick, B.}, booktitle = {ACM Computer Science in Cars Symposium (CSCS)}, keywords = {imported}, publisher = {ACM}, title = {Towards Corner Case Identification in Cyclists’ Trajectories}, year = 2019 }
%0 Conference Paper %1 heidecker2019towards %A Heidecker, F. %A Bieshaar, M. %A Sick, B. %B ACM Computer Science in Cars Symposium (CSCS) %D 2019 %I ACM %T Towards Corner Case Identification in Cyclists’ Trajectories %U https://cscs19.cispa.saarland/files/cscs19_camera_ready/28_fhmbbs_19_cscs_.pdf
The Organic Computing Doctoral Dissertation Colloquium: Status and Overview in 2019. Krupitzer, Christian; Tomforde, Sven. In INFORMATIK 2019: 50 Jahre Gesellschaft für Informatik -- Informatik für Gesellschaft (Workshop-Beiträge), bll 545–554. Gesellschaft für Informatik e.V., Bonn, 2019.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{krupitzer2019organic, address = {Bonn}, author = {Krupitzer, Christian and Tomforde, Sven}, booktitle = {INFORMATIK 2019: 50 Jahre Gesellschaft für Informatik – Informatik für Gesellschaft (Workshop-Beiträge)}, keywords = {imported}, pages = {545–554}, publisher = {Gesellschaft für Informatik e.V.}, title = {The Organic Computing Doctoral Dissertation Colloquium: Status and Overview in 2019}, year = 2019 }
%0 Conference Paper %1 krupitzer2019organic %A Krupitzer, Christian %A Tomforde, Sven %B INFORMATIK 2019: 50 Jahre Gesellschaft für Informatik -- Informatik für Gesellschaft (Workshop-Beiträge) %C Bonn %D 2019 %I Gesellschaft für Informatik e.V. %P 545--554 %R 10.18420/inf2019_ws57 %T The Organic Computing Doctoral Dissertation Colloquium: Status and Overview in 2019
Start Intention Detection of Cyclists using an LSTM Network. Kress, Viktor; Jung, Janis; Zernetsch, Stefan; Doll, Konrad; Sick, Bernhard. In INFORMATIK 2019: 50 Jahre Gesellschaft für Informatik -- Informatik für Gesellschaft (Workshop-Beiträge), bll 219–228. Gesellschaft für Informatik e.V., Bonn, 2019.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{kress2019start, address = {Bonn}, author = {Kress, Viktor and Jung, Janis and Zernetsch, Stefan and Doll, Konrad and Sick, Bernhard}, booktitle = {INFORMATIK 2019: 50 Jahre Gesellschaft für Informatik – Informatik für Gesellschaft (Workshop-Beiträge)}, keywords = {imported}, pages = {219–228}, publisher = {Gesellschaft für Informatik e.V.}, title = {Start Intention Detection of Cyclists using an {LSTM} Network}, year = 2019 }
%0 Conference Paper %1 kress2019start %A Kress, Viktor %A Jung, Janis %A Zernetsch, Stefan %A Doll, Konrad %A Sick, Bernhard %B INFORMATIK 2019: 50 Jahre Gesellschaft für Informatik -- Informatik für Gesellschaft (Workshop-Beiträge) %C Bonn %D 2019 %I Gesellschaft für Informatik e.V. %P 219--228 %R 10.18420/inf2019_ws25 %T Start Intention Detection of Cyclists using an LSTM Network
Smart Device Based Initial Movement Detection of Cyclists Using Convolutional Neural Networks. Schneegans, Jan; Bieshaar, Maarten. In Organic Computing -- Doctoral Dissertation Colloquium 2018, S. Tomforde, B. Sick (reds.), bll 45–60. kassel university press, Kassel, Germany, 2019.
- [ BibTeX ]
- [ EndNote ]
@incollection{schneegans2019smart, address = {Kassel, Germany}, author = {Schneegans, Jan and Bieshaar, Maarten}, booktitle = {Organic Computing – Doctoral Dissertation Colloquium 2018}, editor = {Tomforde, S. and Sick, B.}, keywords = {imported}, pages = {45–60}, publisher = {kassel university press}, title = {Smart Device Based Initial Movement Detection of Cyclists Using Convolutional Neural Networks}, year = 2019 }
%0 Book Section %1 schneegans2019smart %A Schneegans, Jan %A Bieshaar, Maarten %B Organic Computing -- Doctoral Dissertation Colloquium 2018 %C Kassel, Germany %D 2019 %E Tomforde, S. %E Sick, B. %I kassel university press %P 45--60 %T Smart Device Based Initial Movement Detection of Cyclists Using Convolutional Neural Networks
Self-Improving System Integration -- On a Definition and Characteristics of the Challenge. Bellman, K. L.; Gruhl, C.; Landauer, C.; Tomforde, S. In Workshop on Self-Improving System Integration (SISSY), FAS*W, bll 1–3. IEEE, 2019.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
The self-improving system integration (SISSY) initiative-sometimes also called self-integration-started over six years ago. Recently, we have seen contributions approaching parts of the scope from different directions. In order to provide a better understanding how these attempts support the development of novel SISSY technology, this paper presents a definition of the term. In addition, it discusses the fundamental challenges stemming from the increasingly interconnected character of large-scale distributed and adaptive systems typically referred to as "Interwoven Systems", with these systems describing the basic motivation for SISSY research.
@inproceedings{bellman2019self, abstract = {The self-improving system integration (SISSY) initiative-sometimes also called self-integration-started over six years ago. Recently, we have seen contributions approaching parts of the scope from different directions. In order to provide a better understanding how these attempts support the development of novel SISSY technology, this paper presents a definition of the term. In addition, it discusses the fundamental challenges stemming from the increasingly interconnected character of large-scale distributed and adaptive systems typically referred to as "Interwoven Systems", with these systems describing the basic motivation for SISSY research.}, author = {{Bellman}, K. L. and {Gruhl}, C. and {Landauer}, C. and {Tomforde}, S.}, booktitle = {Workshop on Self-Improving System Integration (SISSY), FAS*W}, keywords = {integration;self}, pages = {1–3}, publisher = {IEEE}, title = {Self-Improving System Integration – {O}n a Definition and Characteristics of the Challenge}, year = 2019 }
%0 Conference Paper %1 bellman2019self %A Bellman, K. L. %A Gruhl, C. %A Landauer, C. %A Tomforde, S. %B Workshop on Self-Improving System Integration (SISSY), FAS*W %D 2019 %I IEEE %P 1--3 %R 10.1109/FAS-W.2019.00014 %T Self-Improving System Integration -- On a Definition and Characteristics of the Challenge %X The self-improving system integration (SISSY) initiative-sometimes also called self-integration-started over six years ago. Recently, we have seen contributions approaching parts of the scope from different directions. In order to provide a better understanding how these attempts support the development of novel SISSY technology, this paper presents a definition of the term. In addition, it discusses the fundamental challenges stemming from the increasingly interconnected character of large-scale distributed and adaptive systems typically referred to as "Interwoven Systems", with these systems describing the basic motivation for SISSY research.
Radar-based Road User Classification and Novelty Detection with Recurrent Neural Network Ensembles. Scheiner, Nicolas; Appenrodt, Nils; Dickmann, Jürgen; Sick, Bernhard. In IEEE Intelligent Vehicles Symposium (IV), bll 642–649. IEEE, Paris, France, 2019.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{scheiner2019radar, address = {Paris, France}, author = {Scheiner, Nicolas and Appenrodt, Nils and Dickmann, J{\"{u}}rgen and Sick, Bernhard}, booktitle = {IEEE Intelligent Vehicles Symposium (IV)}, keywords = {imported}, pages = {642–649}, publisher = {IEEE}, title = {Radar-based Road User Classification and Novelty Detection with Recurrent Neural Network Ensembles}, year = 2019 }
%0 Conference Paper %1 scheiner2019radar %A Scheiner, Nicolas %A Appenrodt, Nils %A Dickmann, Jürgen %A Sick, Bernhard %B IEEE Intelligent Vehicles Symposium (IV) %C Paris, France %D 2019 %I IEEE %P 642--649 %R 10.1109/ivs.2019.8813773 %T Radar-based Road User Classification and Novelty Detection with Recurrent Neural Network Ensembles
Pose Based Trajectory Forecast of Vulnerable Road Users. Kress, V.; Zernetsch, S.; Doll, K.; Sick, B. In IEEE Symposium Series on Computational Intelligence (SSCI). IEEE, Xiamen, 2019.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{kress2019pose, address = {Xiamen}, author = {Kress, V. and Zernetsch, S. and Doll, K. and Sick, B.}, booktitle = {IEEE Symposium Series on Computational Intelligence (SSCI)}, keywords = {imported}, publisher = {IEEE}, title = {Pose Based Trajectory Forecast of Vulnerable Road Users}, year = 2019 }
%0 Conference Paper %1 kress2019pose %A Kress, V. %A Zernetsch, S. %A Doll, K. %A Sick, B. %B IEEE Symposium Series on Computational Intelligence (SSCI) %C Xiamen %D 2019 %I IEEE %R 10.1109/ssci44817.2019.9003023 %T Pose Based Trajectory Forecast of Vulnerable Road Users
Pose Based Start Intention Detection of Cyclists. Kress, V.; Jung, J.; Zernetsch, S.; Doll, K.; Sick, B. In IEEE International Conference on Intelligent Transportation Systems (ITSC), bll 2381–2386. IEEE, 2019.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{kress2019posea, author = {{Kress}, V. and {Jung}, J. and {Zernetsch}, S. and {Doll}, K. and {Sick}, B.}, booktitle = {IEEE International Conference on Intelligent Transportation Systems (ITSC)}, keywords = {displays}, pages = {2381–2386}, publisher = {IEEE}, title = {Pose Based Start Intention Detection of Cyclists}, year = 2019 }
%0 Conference Paper %1 kress2019posea %A Kress, V. %A Jung, J. %A Zernetsch, S. %A Doll, K. %A Sick, B. %B IEEE International Conference on Intelligent Transportation Systems (ITSC) %D 2019 %I IEEE %P 2381--2386 %R 10.1109/ITSC.2019.8917215 %T Pose Based Start Intention Detection of Cyclists
Organic Computing -- Doctoral Dissertation Colloquium 2018. Tomforde, S.; Sick, B. In Vol. 13Intelligent Embedded Systems. kassel university press, 2019.
- [ BibTeX ]
- [ EndNote ]
@book{tomforde2019organic, editor = {Tomforde, S. and Sick, B.}, keywords = {itegpub}, publisher = {kassel university press}, series = {Intelligent Embedded Systems}, title = {Organic Computing – Doctoral Dissertation Colloquium 2018}, volume = 13, year = 2019 }
%0 Book %1 tomforde2019organic %B Intelligent Embedded Systems %D 2019 %E Tomforde, S. %E Sick, B. %I kassel university press %R 10.19211/KUP9783737606974 %T Organic Computing -- Doctoral Dissertation Colloquium 2018 %V 13
On the Detection of Mutual Influences and Their Consideration in Reinforcement Learning Processes. Rudolph, Stefan; Tomforde, Sven; Hähner, Jörg. In arXiv e-prints, bl arXiv:1905.04205. 2019.
- [ BibTeX ]
- [ EndNote ]
@article{rudolph2019detection, author = {{Rudolph}, Stefan and {Tomforde}, Sven and {H{\"a}hner}, J{\"o}rg}, journal = {arXiv e-prints}, keywords = {Science}, pages = {arXiv:1905.04205}, title = {{On the Detection of Mutual Influences and Their Consideration in Reinforcement Learning Processes}}, year = 2019 }
%0 Journal Article %1 rudolph2019detection %A Rudolph, Stefan %A Tomforde, Sven %A Hähner, Jörg %D 2019 %J arXiv e-prints %P arXiv:1905.04205 %T On the Detection of Mutual Influences and Their Consideration in Reinforcement Learning Processes
On Learning in Collective Self-Adaptive Systems: State of Practice and a 3D Framework. D’Angelo, M.; Gerasimou, S.; Ghahremani, S.; Grohmann, J.; Nunes, I.; Pournaras, E.; Tomforde, S. In International Symposium on Software Engineering for Adaptive and Self-Managing Systems (SEAMS), bll 13–24. IEEE/ACM, 2019.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{dangelo2019learning, author = {{D'Angelo}, M. and {Gerasimou}, S. and {Ghahremani}, S. and {Grohmann}, J. and {Nunes}, I. and {Pournaras}, E. and {Tomforde}, S.}, booktitle = {International Symposium on Software Engineering for Adaptive and Self-Managing Systems (SEAMS)}, keywords = {imported}, pages = {13–24}, publisher = {IEEE/ACM}, title = {On Learning in Collective Self-Adaptive Systems: State of Practice and a 3D Framework}, year = 2019 }
%0 Conference Paper %1 dangelo2019learning %A D'Angelo, M. %A Gerasimou, S. %A Ghahremani, S. %A Grohmann, J. %A Nunes, I. %A Pournaras, E. %A Tomforde, S. %B International Symposium on Software Engineering for Adaptive and Self-Managing Systems (SEAMS) %D 2019 %I IEEE/ACM %P 13--24 %R 10.1109/SEAMS.2019.00012 %T On Learning in Collective Self-Adaptive Systems: State of Practice and a 3D Framework
Off-Board Car Diagnostics Based on Heterogeneous, Highly Imbalanced and High-Dimensional Data Using Machine Learning Techniques. Schlegel, Bernhard. kassel university press, 2019.
- [ BibTeX ]
- [ EndNote ]
@phdthesis{schlegel2019board, author = {Schlegel, Bernhard}, keywords = {imported}, publisher = {kassel university press}, school = {University of Kassel}, title = {Off-Board Car Diagnostics Based on Heterogeneous, Highly Imbalanced and High-Dimensional Data Using Machine Learning Techniques}, year = 2019 }
%0 Thesis %1 schlegel2019board %A Schlegel, Bernhard %D 2019 %I kassel university press %R 10.17170/kobra-202008141582 %T Off-Board Car Diagnostics Based on Heterogeneous, Highly Imbalanced and High-Dimensional Data Using Machine Learning Techniques
Mutual Influence-aware Runtime Learning of Self-adaptation Behavior. Rudolph, Stefan; Tomforde, Sven; Hähner, Jörg. In ACM Transactions on Autonomous and Adaptive Systems, 14(1), bl 4. ACM, New York, NY, USA, 2019.
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
@article{rudolph2019mutual, address = {New York, NY, USA}, author = {Rudolph, Stefan and Tomforde, Sven and H\"{a}hner, J\"{o}rg}, journal = {ACM Transactions on Autonomous and Adaptive Systems}, keywords = {imported}, number = 1, pages = 4, publisher = {ACM}, title = {Mutual Influence-aware Runtime Learning of Self-adaptation Behavior}, volume = 14, year = 2019 }
%0 Journal Article %1 rudolph2019mutual %A Rudolph, Stefan %A Tomforde, Sven %A Hähner, Jörg %C New York, NY, USA %D 2019 %I ACM %J ACM Transactions on Autonomous and Adaptive Systems %N 1 %P 4 %R 10.1145/3345319 %T Mutual Influence-aware Runtime Learning of Self-adaptation Behavior %U http://doi.acm.org/10.1145/3345319 %V 14
Multi-objective Optimisation in Hybrid Collaborating Adaptive Systems. Lesch, V.; Krupitzer, C.; Tomforde, S. In International Workshop on Self-optimisation in Organic and Autonomic Computing Systems (SAOS), ARCS, bll 1–8. VDE, 2019.
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
@inproceedings{lesch2019multi, author = {{Lesch}, V. and {Krupitzer}, C. and {Tomforde}, S.}, booktitle = {International Workshop on Self-optimisation in Organic and Autonomic Computing Systems (SAOS), ARCS}, keywords = {imported}, pages = {1–8}, publisher = {VDE}, title = {Multi-objective Optimisation in Hybrid Collaborating Adaptive Systems}, year = 2019 }
%0 Conference Paper %1 lesch2019multi %A Lesch, V. %A Krupitzer, C. %A Tomforde, S. %B International Workshop on Self-optimisation in Organic and Autonomic Computing Systems (SAOS), ARCS %D 2019 %I VDE %P 1--8 %T Multi-objective Optimisation in Hybrid Collaborating Adaptive Systems %U https://ieeexplore.ieee.org/document/8836195
Limitations of Assessing Active Learning Performance at Runtime. Kottke, Daniel; Schellinger, Jim; Huseljic, Denis; Sick, Bernhard. In arXiv e-prints, bl arXiv:1901.10338. 2019.
- [ BibTeX ]
- [ EndNote ]
@article{kottke2019limitations, author = {{Kottke}, Daniel and {Schellinger}, Jim and {Huseljic}, Denis and {Sick}, Bernhard}, journal = {arXiv e-prints}, keywords = {Machine}, pages = {arXiv:1901.10338}, title = {{Limitations of Assessing Active Learning Performance at Runtime}}, year = 2019 }
%0 Journal Article %1 kottke2019limitations %A Kottke, Daniel %A Schellinger, Jim %A Huseljic, Denis %A Sick, Bernhard %D 2019 %J arXiv e-prints %P arXiv:1901.10338 %T Limitations of Assessing Active Learning Performance at Runtime
Intentions of Vulnerable Road Users -- Detection and Forecasting by Means of Machine Learning. Goldhammer, M.; Köhler, S.; Zernetsch, S.; Doll, K.; Sick, B.; Dietmayer, K. In IEEE Transactions on Intelligent Transportation Systems, 21(7), bll 3035–3045. IEEE, 2019.
- [ BibTeX ]
- [ EndNote ]
@article{goldhammer2019intentions, author = {{Goldhammer}, M. and {Köhler}, S. and {Zernetsch}, S. and {Doll}, K. and {Sick}, B. and {Dietmayer}, K.}, journal = {IEEE Transactions on Intelligent Transportation Systems}, keywords = {imported}, number = 7, pages = {3035–3045}, publisher = {IEEE}, title = {Intentions of Vulnerable Road Users – {D}etection and Forecasting by Means of Machine Learning}, volume = 21, year = 2019 }
%0 Journal Article %1 goldhammer2019intentions %A Goldhammer, M. %A Köhler, S. %A Zernetsch, S. %A Doll, K. %A Sick, B. %A Dietmayer, K. %D 2019 %I IEEE %J IEEE Transactions on Intelligent Transportation Systems %N 7 %P 3035--3045 %R 10.1109/TITS.2019.2923319 %T Intentions of Vulnerable Road Users -- Detection and Forecasting by Means of Machine Learning %V 21
INFORMATIK 2019: 50 Jahre Gesellschaft für Informatik -- Informatik für Gesellschaft (Workshop-Beitr{{ä}}ge). Draude, Claude; Lange, Martin; Sick, Bernhard. Vol. P295. Gesellschaft für Informatik e.V., 2019.
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
@proceedings{draude2019informatik, editor = {Draude, Claude and Lange, Martin and Sick, Bernhard}, keywords = {imported}, publisher = {Gesellschaft für Informatik e.V.}, title = {INFORMATIK 2019: 50 Jahre Gesellschaft f{\"{u}}r Informatik – Informatik f{\"{u}}r Gesellschaft (Workshop-Beitr{\"{a}}ge)}, volume = {{P295}}, year = 2019 }
%0 Conference Proceedings %1 draude2019informatik %D 2019 %E Draude, Claude %E Lange, Martin %E Sick, Bernhard %I Gesellschaft für Informatik e.V. %T INFORMATIK 2019: 50 Jahre Gesellschaft für Informatik -- Informatik für Gesellschaft (Workshop-Beitr{{ä}}ge) %U https://dl.gi.de/handle/20.500.12116/25040 %V P295 %@ 978-3-88579-689-3
Influences in Forecast Errors for Wind and Photovoltaic Power: A Study on Machine Learning Models. Schreiber, Jens; Buschin, Artjom; Sick, Bernhard. In INFORMATIK 2019: 50 Jahre Gesellschaft für Informatik -- Informatik für Gesellschaft, bll 585–598. Gesellschaft für Informatik e.V., Bonn, 2019.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{schreiber2019influences, address = {Bonn}, author = {Schreiber, Jens and Buschin, Artjom and Sick, Bernhard}, booktitle = {INFORMATIK 2019: 50 Jahre Gesellschaft für Informatik – Informatik für Gesellschaft}, keywords = {imported}, pages = {585–598}, publisher = {Gesellschaft für Informatik e.V.}, title = {Influences in Forecast Errors for Wind and Photovoltaic Power: A Study on Machine Learning Models}, year = 2019 }
%0 Conference Paper %1 schreiber2019influences %A Schreiber, Jens %A Buschin, Artjom %A Sick, Bernhard %B INFORMATIK 2019: 50 Jahre Gesellschaft für Informatik -- Informatik für Gesellschaft %C Bonn %D 2019 %I Gesellschaft für Informatik e.V. %P 585--598 %R 10.18420/inf2019_74 %T Influences in Forecast Errors for Wind and Photovoltaic Power: A Study on Machine Learning Models
Generative Adversarial Networks for Operational Scenario Planning of Renewable Energy Farms: A Study on Wind and Photovoltaic. Schreiber, Jens; Jessulat, Maik; Sick, Bernhard. In International Conference on Artificial Neural Networks and Machine Learning (ICANN): Image Processing, bll 550–564. Springer, Cham, 2019.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{schreiber2019generative, address = {Cham}, author = {Schreiber, Jens and Jessulat, Maik and Sick, Bernhard}, booktitle = {International Conference on Artificial Neural Networks and Machine Learning (ICANN): Image Processing}, keywords = {imported}, pages = {550–564}, publisher = {Springer}, title = {Generative Adversarial Networks for Operational Scenario Planning of Renewable Energy Farms: A Study on Wind and Photovoltaic}, year = 2019 }
%0 Conference Paper %1 schreiber2019generative %A Schreiber, Jens %A Jessulat, Maik %A Sick, Bernhard %B International Conference on Artificial Neural Networks and Machine Learning (ICANN): Image Processing %C Cham %D 2019 %I Springer %P 550--564 %R 10.1007/978-3-030-30508-6_44 %T Generative Adversarial Networks for Operational Scenario Planning of Renewable Energy Farms: A Study on Wind and Photovoltaic %@ 978-3-030-30508-6
From "Normal" to "Abnormal": A Concept for Determining Expected Self-Adaptation Behaviour. Tomforde, Sven. In IEEE International Workshop on Evaluations and Measurements in Self-Aware Computing Systems (EMSAC-SeAC), FAS*W, bll 126–129. IEEE, 2019.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{tomforde2019normal, author = {Tomforde, Sven}, booktitle = {IEEE International Workshop on Evaluations and Measurements in Self-Aware Computing Systems (EMSAC-SeAC), FAS*W}, keywords = {imported}, pages = {126–129}, publisher = {IEEE}, title = {From "Normal" to "Abnormal": A Concept for Determining Expected Self-Adaptation Behaviour}, year = 2019 }
%0 Conference Paper %1 tomforde2019normal %A Tomforde, Sven %B IEEE International Workshop on Evaluations and Measurements in Self-Aware Computing Systems (EMSAC-SeAC), FAS*W %D 2019 %I IEEE %P 126--129 %R 10.1109/fas-w.2019.00041 %T From "Normal" to "Abnormal": A Concept for Determining Expected Self-Adaptation Behaviour
Explicit Consideration of Resilience in Organic Computing Design Processes. Tomforde, S.; Gelhausen, P.; Gruhl, C.; Haering, I.; Sick, B. In International Workshop on Self-optimisation in Organic and Autonomic Computing Systems (SAOS), ARCS, bll 1–6. VDE, 2019.
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
@inproceedings{tomforde2019explicit, author = {{Tomforde}, S. and {Gelhausen}, P. and {Gruhl}, C. and {Haering}, I. and {Sick}, B.}, booktitle = {International Workshop on Self-optimisation in Organic and Autonomic Computing Systems (SAOS), ARCS}, keywords = {imported}, pages = {1–6}, publisher = {VDE}, title = {Explicit Consideration of Resilience in Organic Computing Design Processes}, year = 2019 }
%0 Conference Paper %1 tomforde2019explicit %A Tomforde, S. %A Gelhausen, P. %A Gruhl, C. %A Haering, I. %A Sick, B. %B International Workshop on Self-optimisation in Organic and Autonomic Computing Systems (SAOS), ARCS %D 2019 %I VDE %P 1--6 %T Explicit Consideration of Resilience in Organic Computing Design Processes %U https://ieeexplore.ieee.org/document/8836197
Emerging Self-Integration through Coordination of Autonomous Adaptive Systems. Lesch, V.; Krupitzer, C.; Tomforde, S. In Workshop on Self-Improving System Integration (SISSY), FAS*W, bll 6–9. IEEE, 2019.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{lesch2019emerging, author = {{Lesch}, V. and {Krupitzer}, C. and {Tomforde}, S.}, booktitle = {Workshop on Self-Improving System Integration (SISSY), FAS*W}, keywords = {imported}, pages = {6–9}, publisher = {IEEE}, title = {Emerging Self-Integration through Coordination of Autonomous Adaptive Systems}, year = 2019 }
%0 Conference Paper %1 lesch2019emerging %A Lesch, V. %A Krupitzer, C. %A Tomforde, S. %B Workshop on Self-Improving System Integration (SISSY), FAS*W %D 2019 %I IEEE %P 6--9 %R 10.1109/FAS-W.2019.00016 %T Emerging Self-Integration through Coordination of Autonomous Adaptive Systems
Early Pedestrian Movement Detection Using Smart Devices Based on Human Activity Recognition. Botache, Diego; Dandan, Liu; Bieshaar, Maarten; Sick, Bernhard. In INFORMATIK 2019: 50 Jahre Gesellschaft für Informatik -- Informatik für Gesellschaft (Workshop-Beiträge), bll 229–238. Gesellschaft für Informatik e.V., Bonn, 2019.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{botache2019early, address = {Bonn}, author = {Botache, Diego and Dandan, Liu and Bieshaar, Maarten and Sick, Bernhard}, booktitle = {INFORMATIK 2019: 50 Jahre Gesellschaft für Informatik – Informatik für Gesellschaft (Workshop-Beiträge)}, keywords = {imported}, pages = {229–238}, publisher = {Gesellschaft für Informatik e.V.}, title = {Early Pedestrian Movement Detection Using Smart Devices Based on Human Activity Recognition}, year = 2019 }
%0 Conference Paper %1 botache2019early %A Botache, Diego %A Dandan, Liu %A Bieshaar, Maarten %A Sick, Bernhard %B INFORMATIK 2019: 50 Jahre Gesellschaft für Informatik -- Informatik für Gesellschaft (Workshop-Beiträge) %C Bonn %D 2019 %I Gesellschaft für Informatik e.V. %P 229--238 %R 10.18420/inf2019_ws26 %T Early Pedestrian Movement Detection Using Smart Devices Based on Human Activity Recognition
Decision Support with Hybrid Intelligence. Calma, Adrian; Dellermann, Dominik. In Organic Computing -- Doctoral Dissertation Colloquium 2018, S. Tomforde, B. Sick (reds.), bll 143–153. kassel university press, Kassel, Germany, 2019.
- [ BibTeX ]
- [ EndNote ]
@incollection{calma2019decision, address = {Kassel, Germany}, author = {Calma, Adrian and Dellermann, Dominik}, booktitle = {Organic Computing – Doctoral Dissertation Colloquium 2018}, editor = {Tomforde, S. and Sick, B.}, keywords = {imported}, pages = {143–153}, publisher = {kassel university press}, title = {Decision Support with Hybrid Intelligence}, year = 2019 }
%0 Book Section %1 calma2019decision %A Calma, Adrian %A Dellermann, Dominik %B Organic Computing -- Doctoral Dissertation Colloquium 2018 %C Kassel, Germany %D 2019 %E Tomforde, S. %E Sick, B. %I kassel university press %P 143--153 %T Decision Support with Hybrid Intelligence
Combining Self-reported Confidences from Uncertain Annotators to Improve Label Quality. Sandrock, C.; Herde, M.; Calma, A.; Kottke, D.; Sick, B. In International Joint Conference on Neural Networks (IJCNN), bll 1–8. IEEE, 2019.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{sandrock2019combining, author = {{Sandrock}, C. and {Herde}, M. and {Calma}, A. and {Kottke}, D. and {Sick}, B.}, booktitle = {International Joint Conference on Neural Networks (IJCNN)}, keywords = {annotators;confidence}, pages = {1–8}, publisher = {IEEE}, title = {Combining Self-reported Confidences from Uncertain Annotators to Improve Label Quality}, year = 2019 }
%0 Conference Paper %1 sandrock2019combining %A Sandrock, C. %A Herde, M. %A Calma, A. %A Kottke, D. %A Sick, B. %B International Joint Conference on Neural Networks (IJCNN) %D 2019 %I IEEE %P 1--8 %R 10.1109/IJCNN.2019.8852456 %T Combining Self-reported Confidences from Uncertain Annotators to Improve Label Quality
Collaborative Interactive Learning -- A clarification of terms and a differentiation from other research fields. Hanika, Tom; Herde, Marek; Kuhn, Jochen; Leimeister, Jan Marco; Lukowicz, Paul; Oeste-Reiß, Sarah; Schmidt, Albrecht; Sick, Bernhard; Stumme, Gerd; Tomforde, Sven; Zweig, Katharina Anna. In arXiv e-prints, bl arXiv:1905.07264. 2019.
- [ BibTeX ]
- [ EndNote ]
@article{hanika2019collaborative, author = {{Hanika}, Tom and {Herde}, Marek and {Kuhn}, Jochen and {Leimeister}, Jan Marco and {Lukowicz}, Paul and {Oeste-Rei{\ss}}, Sarah and {Schmidt}, Albrecht and {Sick}, Bernhard and {Stumme}, Gerd and {Tomforde}, Sven and {Zweig}, Katharina Anna}, journal = {arXiv e-prints}, keywords = {Machine}, pages = {arXiv:1905.07264}, title = {{Collaborative Interactive Learning – A clarification of terms and a differentiation from other research fields}}, year = 2019 }
%0 Journal Article %1 hanika2019collaborative %A Hanika, Tom %A Herde, Marek %A Kuhn, Jochen %A Leimeister, Jan Marco %A Lukowicz, Paul %A Oeste-Reiß, Sarah %A Schmidt, Albrecht %A Sick, Bernhard %A Stumme, Gerd %A Tomforde, Sven %A Zweig, Katharina Anna %D 2019 %J arXiv e-prints %P arXiv:1905.07264 %T Collaborative Interactive Learning -- A clarification of terms and a differentiation from other research fields
CHARIOT -- Towards a Continuous High-Level Adaptive Runtime Integration Testbed. Barnes, C. M.; Bellman, K.; Botev, J.; Diaconescu, A.; Esterle, L.; Gruhl, C.; Landauer, C.; Lewis, P. R.; Nelson, P. R.; Stein, A.; Stewart, C.; Tomforde, S. In Workshop on Self-Improving System Integration (SISSY), FAS*W, bll 52–55. IEEE, 2019.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{barnes2019chariot, author = {{Barnes}, C. M. and {Bellman}, K. and {Botev}, J. and {Diaconescu}, A. and {Esterle}, L. and {Gruhl}, C. and {Landauer}, C. and {Lewis}, P. R. and {Nelson}, P. R. and {Stein}, A. and {Stewart}, C. and {Tomforde}, S.}, booktitle = {Workshop on Self-Improving System Integration (SISSY), FAS*W}, keywords = {imported}, pages = {52–55}, publisher = {IEEE}, title = {{CHARIOT} – {T}owards a Continuous High-Level Adaptive Runtime Integration Testbed}, year = 2019 }
%0 Conference Paper %1 barnes2019chariot %A Barnes, C. M. %A Bellman, K. %A Botev, J. %A Diaconescu, A. %A Esterle, L. %A Gruhl, C. %A Landauer, C. %A Lewis, P. R. %A Nelson, P. R. %A Stein, A. %A Stewart, C. %A Tomforde, S. %B Workshop on Self-Improving System Integration (SISSY), FAS*W %D 2019 %I IEEE %P 52--55 %R 10.1109/FAS-W.2019.00026 %T CHARIOT -- Towards a Continuous High-Level Adaptive Runtime Integration Testbed
Automated Ground Truth Estimation of Vulnerable Road Users in Automotive Radar Data Using GNSS. Scheiner, Nicolas; Appenrodt, Nils; Dickmann, Jürgen; Sick, Bernhard. In IEEE MTT-S International Conference on Microwaves for Intelligent Mobility (ICMIM), bll 5–9. IEEE, 2019.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{scheiner2019automated, author = {Scheiner, Nicolas and Appenrodt, Nils and Dickmann, J{\"{u}}rgen and Sick, Bernhard}, booktitle = {IEEE MTT-S International Conference on Microwaves for Intelligent Mobility (ICMIM)}, keywords = {imported}, pages = {5–9}, publisher = {IEEE}, title = {Automated Ground Truth Estimation of Vulnerable Road Users in Automotive Radar Data Using GNSS}, year = 2019 }
%0 Conference Paper %1 scheiner2019automated %A Scheiner, Nicolas %A Appenrodt, Nils %A Dickmann, Jürgen %A Sick, Bernhard %B IEEE MTT-S International Conference on Microwaves for Intelligent Mobility (ICMIM) %D 2019 %I IEEE %P 5--9 %R 10.1109/ICMIM.2019.8726801 %T Automated Ground Truth Estimation of Vulnerable Road Users in Automotive Radar Data Using GNSS
Automated Ground Truth Estimation For Automotive Radar Tracking Applications With Portable GNSS And IMU Devices. Scheiner, Nicolas; Haag, Stefan; Appenrodt, Nils; Duraisamy, Bharanidhar; Dickmann, Jürgen; Fritzsche, Martin; Sick, Bernhard. In International Radar Symposium (IRS), bll 1–10. Ulm, Germany, 2019.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{scheiner2019automateda, address = {Ulm, Germany}, author = {Scheiner, Nicolas and Haag, Stefan and Appenrodt, Nils and Duraisamy, Bharanidhar and Dickmann, J{\"{u}}rgen and Fritzsche, Martin and Sick, Bernhard}, booktitle = {International Radar Symposium (IRS)}, keywords = {imported}, pages = {1–10}, title = {Automated Ground Truth Estimation For Automotive Radar Tracking Applications With Portable GNSS And IMU Devices}, year = 2019 }
%0 Conference Paper %1 scheiner2019automateda %A Scheiner, Nicolas %A Haag, Stefan %A Appenrodt, Nils %A Duraisamy, Bharanidhar %A Dickmann, Jürgen %A Fritzsche, Martin %A Sick, Bernhard %B International Radar Symposium (IRS) %C Ulm, Germany %D 2019 %P 1--10 %R 10.23919/irs.2019.8768169 %T Automated Ground Truth Estimation For Automotive Radar Tracking Applications With Portable GNSS And IMU Devices %@ 9783736998605
A Multi-Stage Clustering Framework for Automotive Radar Data. Scheiner, Nicolas; Appenrodt, Nils; Dickmann, Jürgen; Sick, Bernhard. In IEEE International Conference on Intelligent Transportation Systems (ITSC), bll 2060–2067. IEEE, 2019.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{scheiner2019multi, author = {Scheiner, Nicolas and Appenrodt, Nils and Dickmann, J{\"{u}}rgen and Sick, Bernhard}, booktitle = {IEEE International Conference on Intelligent Transportation Systems (ITSC)}, keywords = {imported}, pages = {2060–2067}, publisher = {IEEE}, title = {A Multi-Stage Clustering Framework for Automotive Radar Data}, year = 2019 }
%0 Conference Paper %1 scheiner2019multi %A Scheiner, Nicolas %A Appenrodt, Nils %A Dickmann, Jürgen %A Sick, Bernhard %B IEEE International Conference on Intelligent Transportation Systems (ITSC) %D 2019 %I IEEE %P 2060--2067 %R 10.1109/itsc.2019.8916873 %T A Multi-Stage Clustering Framework for Automotive Radar Data

2018[ to top ]

Workshop on Interactive Adaptive Learning (IAL), ECML PKDD. Krempl, Georg; Lemaire, Vincent; Kottke, Daniel; Calma, Adrian; Holzinger, Andreas; Polikar, Robi; Sick, Bernhard. In Vol. 2192CEUR Workshop Proceedings. 2018.
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
@proceedings{krempl2018workshop, editor = {Krempl, Georg and Lemaire, Vincent and Kottke, Daniel and Calma, Adrian and Holzinger, Andreas and Polikar, Robi and Sick, Bernhard}, keywords = {imported}, series = {{CEUR} Workshop Proceedings}, title = {Workshop on Interactive Adaptive Learning (IAL), ECML PKDD}, volume = 2192, year = 2018 }
%0 Conference Proceedings %1 krempl2018workshop %B CEUR Workshop Proceedings %D 2018 %E Krempl, Georg %E Lemaire, Vincent %E Kottke, Daniel %E Calma, Adrian %E Holzinger, Andreas %E Polikar, Robi %E Sick, Bernhard %T Workshop on Interactive Adaptive Learning (IAL), ECML PKDD %U http://ceur-ws.org/Vol-2192 %V 2192
Towards Proactive Health-enabling Living Environments: Simulation-based Study and Research Challenges. Tomforde, Sven; Dehling, Tobias; Haux, Reinhold; Huseljic, Denis; Kottke, Daniel; Scheerbaum, Jonas; Sick, Bernhard; Sunyaev, Ali; Wolf, Klaus-Hendrik. In International Workshop on Self-optimisation in Organic and Autonomic Computing Systems (SAOS), ARCS, bll 1–8. VDE, 2018.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{tomforde2018towards, author = {Tomforde, Sven and Dehling, Tobias and Haux, Reinhold and Huseljic, Denis and Kottke, Daniel and Scheerbaum, Jonas and Sick, Bernhard and Sunyaev, Ali and Wolf, Klaus-Hendrik}, booktitle = {International Workshop on Self-optimisation in Organic and Autonomic Computing Systems (SAOS), ARCS}, keywords = {imported}, pages = {1–8}, publisher = {VDE}, title = {Towards Proactive Health-enabling Living Environments: Simulation-based Study and Research Challenges}, year = 2018 }
%0 Conference Paper %1 tomforde2018towards %A Tomforde, Sven %A Dehling, Tobias %A Haux, Reinhold %A Huseljic, Denis %A Kottke, Daniel %A Scheerbaum, Jonas %A Sick, Bernhard %A Sunyaev, Ali %A Wolf, Klaus-Hendrik %B International Workshop on Self-optimisation in Organic and Autonomic Computing Systems (SAOS), ARCS %D 2018 %I VDE %P 1--8 %T Towards Proactive Health-enabling Living Environments: Simulation-based Study and Research Challenges
Towards Cooperative Self-adapting Activity Recognition. Jahn, Andreas; Tomforde, Sven; Morold, Michel; David, Klaus; Sick, Bernhard. In International Joint Conference on Pervasive and Embedded Computing and Communication Systems (PECCS), bll 215–222. 2018.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{jahn2018towards, author = {Jahn, Andreas and Tomforde, Sven and Morold, Michel and David, Klaus and Sick, Bernhard}, booktitle = {International Joint Conference on Pervasive and Embedded Computing and Communication Systems (PECCS)}, keywords = {imported}, pages = {215–222}, title = {Towards Cooperative Self-adapting Activity Recognition}, year = 2018 }
%0 Conference Paper %1 jahn2018towards %A Jahn, Andreas %A Tomforde, Sven %A Morold, Michel %A David, Klaus %A Sick, Bernhard %B International Joint Conference on Pervasive and Embedded Computing and Communication Systems (PECCS) %D 2018 %P 215--222 %R 10.5220/0006856102150222 %T Towards Cooperative Self-adapting Activity Recognition
The Other Human in The Loop -- A Pilot Study to Find Selection Strategies for Active Learning. Kottke, Daniel; Calma, Adrian; Huseljic, Denis; Sandrock, Christoph; Kachergis, George; Sick, Bernhard. In International Joint Conference on Neural Networks (IJCNN). IEEE, Rio de Janiero, Brazil, 2018.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{kottke2018other, address = {Rio de Janiero, Brazil}, author = {Kottke, Daniel and Calma, Adrian and Huseljic, Denis and Sandrock, Christoph and Kachergis, George and Sick, Bernhard}, booktitle = {International Joint Conference on Neural Networks (IJCNN)}, keywords = {imported}, publisher = {IEEE}, title = {The Other Human in The Loop – A Pilot Study to Find Selection Strategies for Active Learning}, year = 2018 }
%0 Conference Paper %1 kottke2018other %A Kottke, Daniel %A Calma, Adrian %A Huseljic, Denis %A Sandrock, Christoph %A Kachergis, George %A Sick, Bernhard %B International Joint Conference on Neural Networks (IJCNN) %C Rio de Janiero, Brazil %D 2018 %I IEEE %R 10.1109/ijcnn.2018.8489637 %T The Other Human in The Loop -- A Pilot Study to Find Selection Strategies for Active Learning
Starting Movement Detection of Cyclists Using Smart Devices. Bieshaar, M.; Depping, M.; Schneegans, J.; Sick, B. In IEEE International Conference on Data Science and Advanced Analytics (DSAA). IEEE, Turin, Italy, 2018.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{bieshaar2018starting, address = {Turin, Italy}, author = {Bieshaar, M. and Depping, M. and Schneegans, J. and Sick, B.}, booktitle = {IEEE International Conference on Data Science and Advanced Analytics (DSAA)}, keywords = {imported}, publisher = {IEEE}, title = {Starting Movement Detection of Cyclists Using Smart Devices}, year = 2018 }
%0 Conference Paper %1 bieshaar2018starting %A Bieshaar, M. %A Depping, M. %A Schneegans, J. %A Sick, B. %B IEEE International Conference on Data Science and Advanced Analytics (DSAA) %C Turin, Italy %D 2018 %I IEEE %R 10.1109/dsaa.2018.00042 %T Starting Movement Detection of Cyclists Using Smart Devices
Smart Device Stealing and CANDIES. Jänicke, Martin; Schmidt, Viktor; Sick, Bernhard; Tomforde, Sven; Lukowicz, Paul; Schmeißing, Jörn. In International Conference on Agents and Artificial Intelligence (ICAART), bll 247–273. Springer, 2018.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{jaenicke2018smart, author = {J{\"{a}}nicke, Martin and Schmidt, Viktor and Sick, Bernhard and Tomforde, Sven and Lukowicz, Paul and Schmei{\ss}ing, J{\"{o}}rn}, booktitle = {International Conference on Agents and Artificial Intelligence (ICAART)}, keywords = {imported}, pages = {247–273}, publisher = {Springer}, title = {Smart Device Stealing and {CANDIES}}, year = 2018 }
%0 Conference Paper %1 jaenicke2018smart %A Jänicke, Martin %A Schmidt, Viktor %A Sick, Bernhard %A Tomforde, Sven %A Lukowicz, Paul %A Schmeißing, Jörn %B International Conference on Agents and Artificial Intelligence (ICAART) %D 2018 %I Springer %P 247--273 %R 10.1007/978-3-030-05453-3_12 %T Smart Device Stealing and CANDIES
Semi-supervised active learning for support vector machines: A novel approach that exploits structure information in data. Calma, A.; Reitmaier, T.; Sick, B. In Information Sciences, 456, bll 13–33. Elsevier, 2018.
- [ BibTeX ]
- [ EndNote ]
@article{calma2018semi, author = {Calma, A. and Reitmaier, T. and Sick, B.}, journal = {Information Sciences}, keywords = {imported}, pages = {13–33}, publisher = {Elsevier}, title = {Semi-supervised active learning for support vector machines: {A} novel approach that exploits structure information in data}, volume = 456, year = 2018 }
%0 Journal Article %1 calma2018semi %A Calma, A. %A Reitmaier, T. %A Sick, B. %D 2018 %I Elsevier %J Information Sciences %P 13--33 %R 10.1016/j.ins.2018.04.063 %T Semi-supervised active learning for support vector machines: A novel approach that exploits structure information in data %V 456
Self-Adaptive Multi-Sensor Activity Recognition Systems Based on Gaussian Mixture Models. Jänicke, Martin; Sick, Bernhard; Tomforde, Sven. In Informatics, 5(3), bl 38. MDPI, 2018.
- [ BibTeX ]
- [ EndNote ]
@article{jaenicke2018self, author = {J{\"{a}}nicke, Martin and Sick, Bernhard and Tomforde, Sven}, journal = {Informatics}, keywords = {imported}, number = 3, pages = 38, publisher = {MDPI}, title = {Self-Adaptive Multi-Sensor Activity Recognition Systems Based on Gaussian Mixture Models}, volume = 5, year = 2018 }
%0 Journal Article %1 jaenicke2018self %A Jänicke, Martin %A Sick, Bernhard %A Tomforde, Sven %D 2018 %I MDPI %J Informatics %N 3 %P 38 %R 10.3390/informatics5030038 %T Self-Adaptive Multi-Sensor Activity Recognition Systems Based on Gaussian Mixture Models %V 5
Security Issues in Self-Improving System Integration - Challenges and Solution Strategies. Heck, Henner; Sick, Bernhard; Tomforde, Sven. In Workshop on Self-Improving System Integration (SISSY), FAS*W, bll 176–181. IEEE, 2018.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{heck2018security, author = {Heck, Henner and Sick, Bernhard and Tomforde, Sven}, booktitle = {Workshop on Self-Improving System Integration (SISSY), FAS*W}, keywords = {imported}, pages = {176–181}, publisher = {IEEE}, title = {Security Issues in Self-Improving System Integration - Challenges and Solution Strategies}, year = 2018 }
%0 Conference Paper %1 heck2018security %A Heck, Henner %A Sick, Bernhard %A Tomforde, Sven %B Workshop on Self-Improving System Integration (SISSY), FAS*W %D 2018 %I IEEE %P 176--181 %R 10.1109/fas-w.2018.00044 %T Security Issues in Self-Improving System Integration - Challenges and Solution Strategies
Sampling Strategies for Representative Time Series in Load Flow Calculations. Henze, Janosch; Kutzner, Stephan; Sick, Bernhard. In Workshop on Data Analytics for Renewable Energy Integration (DARE), ECML PKDD, bll 27–48. Springer, 2018.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{henze2018sampling, author = {Henze, Janosch and Kutzner, Stephan and Sick, Bernhard}, booktitle = {Workshop on Data Analytics for Renewable Energy Integration (DARE), ECML PKDD}, keywords = {imported}, pages = {27–48}, publisher = {Springer}, title = {Sampling Strategies for Representative Time Series in Load Flow Calculations}, year = 2018 }
%0 Conference Paper %1 henze2018sampling %A Henze, Janosch %A Kutzner, Stephan %A Sick, Bernhard %B Workshop on Data Analytics for Renewable Energy Integration (DARE), ECML PKDD %D 2018 %I Springer %P 27--48 %R 10.1007/978-3-030-04303-2_3 %T Sampling Strategies for Representative Time Series in Load Flow Calculations
Radar-based Feature Design and Multiclass Classification for Road User Recognition. Scheiner, Nicolas; Appenrodt, Nils; Dickmann, Jürgen; Sick, Bernhard. In IEEE Intelligent Vehicles Symposium (IV), bll 779–786. IEEE, Changshu, China, 2018.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{scheiner2018radar, address = {Changshu, China}, author = {Scheiner, Nicolas and Appenrodt, Nils and Dickmann, J{\"{u}}rgen and Sick, Bernhard}, booktitle = {IEEE Intelligent Vehicles Symposium (IV)}, keywords = {imported}, pages = {779–786}, publisher = {IEEE}, title = {Radar-based Feature Design and Multiclass Classification for Road User Recognition}, year = 2018 }
%0 Conference Paper %1 scheiner2018radar %A Scheiner, Nicolas %A Appenrodt, Nils %A Dickmann, Jürgen %A Sick, Bernhard %B IEEE Intelligent Vehicles Symposium (IV) %C Changshu, China %D 2018 %I IEEE %P 779--786 %R 10.1109/ivs.2018.8500607 %T Radar-based Feature Design and Multiclass Classification for Road User Recognition
Quantifying the Influences on Probabilistic Wind Power Forecasts. Schreiber, Jens; Sick, Bernhard. In International Conference on Power and Renewable Energy (ICPRE), bll 1–6. 2018.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
In recent years, probabilistic forecasts techniques were proposed in research as well as in applications to integrate volatile renewable energy resources into the electrical grid. These techniques allow decision makers to take the uncertainty of the prediction into account and, therefore, to devise optimal decisions, e.g., related to costs and risks in the electrical grid. However, it was yet not studied how the input, such as numerical weather predictions, affects the model output of forecasting models in detail. Therefore, we examine the potential influences with techniques from the field of sensitivity analysis on three different black-box models to obtain insights into differences and similarities of these probabilistic models. The analysis shows a considerable number of potential influences in those models depending on, e.g., the predicted probability and the type of model. These effects motivate the need to take various influences into account when models are tested, analyzed, or compared. Nevertheless, results of the sensitivity analysis will allow us to select a model with advantages in the practical application.
@inproceedings{schreiber2018quantifying, abstract = {In recent years, probabilistic forecasts techniques were proposed in research as well as in applications to integrate volatile renewable energy resources into the electrical grid. These techniques allow decision makers to take the uncertainty of the prediction into account and, therefore, to devise optimal decisions, e.g., related to costs and risks in the electrical grid. However, it was yet not studied how the input, such as numerical weather predictions, affects the model output of forecasting models in