Prof. Dr. rer. nat. Bernhard Sick

Group Leader; Team Leader: Collaborative Interactive Learning (CIL); Team Leader: AI for Computationally Intelligent Systems (AI4CIS)

Telephone: +49 561 804-6020
Email: bsick[at]uni-kassel[dot]de

Location: Wilhelmshöher Allee 73
34121 Kassel

Room: WA-altes Gebäude (WA 73), ohne Raumangabe

Publications

[ 2025 ]
[ 2024 ]
[ 2023 ]
[ 2022 ]
[ 2021 ]
[ 2020 ]
[ 2019 ]
[ 2018 ]
[ 2017 ]
[ 2016 ]
[ 2015 ]
[ 2014 ]
[ 2013 ]
[ 2012 ]
[ 2011 ]
[ 2010 ]
[ 2006 ]

2025[ to top ]

Unify: Uncertainty incorporated Federated Learning for Object Detection. Gao, Shang; Sick, Bernhard; Götz-Hahn, Franz. In International Conference on Architecture of Computing Systems (ARCS). Springer, 2025.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
Federated Learning (FL) has demonstrated promise for collaborative training on decentralized data while preserving privacy. However, applying FL to object detection remains challenging due to non-IID data distributions and domain shifts that can degrade performance with standard aggregation methods. To address these issues, we propose the Uncertainty Incorporated Federated Learning for Object Detection (Unify) framework, a novel FL framework that leverages Evidential Learning (EL) to estimate both epistemic and aleatoric uncertainties. By integrating these uncertainty estimates into the aggregation process, Unify down-weights unreliable client updates, leading to improved cross-domain generalization and enhanced stability. Built upon a lightweight YOLOX detector, our approach achieves detection performance that closely approaches centralized training while significantly outperforming conventional FedAvg under heterogeneous conditions. Evaluations on the KITTI and nuImages datasets demonstrate that Unify improves mean Average Precision (mAP) and yields uncertainties. The findings highlight the potential of uncertainty-incorporated FL in developing resilient, adaptive, and self-organizing computing systems.
@inproceedings{gao2025unify, abstract = {Federated Learning (FL) has demonstrated promise for collaborative training on decentralized data while preserving privacy. However, applying FL to object detection remains challenging due to non-IID data distributions and domain shifts that can degrade performance with standard aggregation methods. To address these issues, we propose the Uncertainty Incorporated Federated Learning for Object Detection (Unify) framework, a novel FL framework that leverages Evidential Learning (EL) to estimate both epistemic and aleatoric uncertainties. By integrating these uncertainty estimates into the aggregation process, Unify down-weights unreliable client updates, leading to improved cross-domain generalization and enhanced stability. Built upon a lightweight YOLOX detector, our approach achieves detection performance that closely approaches centralized training while significantly outperforming conventional FedAvg under heterogeneous conditions. Evaluations on the KITTI and nuImages datasets demonstrate that Unify improves mean Average Precision (mAP) and yields uncertainties. The findings highlight the potential of uncertainty-incorporated FL in developing resilient, adaptive, and self-organizing computing systems.}, author = {Gao, Shang and Sick, Bernhard and Götz-Hahn, Franz}, booktitle = {International Conference on Architecture of Computing Systems (ARCS)}, keywords = {itegpub}, note = {(accepted)}, publisher = {Springer}, title = {Unify: Uncertainty incorporated Federated Learning for Object Detection}, year = 2025 }
%0 Conference Paper %1 gao2025unify %A Gao, Shang %A Sick, Bernhard %A Götz-Hahn, Franz %B International Conference on Architecture of Computing Systems (ARCS) %D 2025 %I Springer %T Unify: Uncertainty incorporated Federated Learning for Object Detection %X Federated Learning (FL) has demonstrated promise for collaborative training on decentralized data while preserving privacy. However, applying FL to object detection remains challenging due to non-IID data distributions and domain shifts that can degrade performance with standard aggregation methods. To address these issues, we propose the Uncertainty Incorporated Federated Learning for Object Detection (Unify) framework, a novel FL framework that leverages Evidential Learning (EL) to estimate both epistemic and aleatoric uncertainties. By integrating these uncertainty estimates into the aggregation process, Unify down-weights unreliable client updates, leading to improved cross-domain generalization and enhanced stability. Built upon a lightweight YOLOX detector, our approach achieves detection performance that closely approaches centralized training while significantly outperforming conventional FedAvg under heterogeneous conditions. Evaluations on the KITTI and nuImages datasets demonstrate that Unify improves mean Average Precision (mAP) and yields uncertainties. The findings highlight the potential of uncertainty-incorporated FL in developing resilient, adaptive, and self-organizing computing systems.
Towards Cognitive Situational Awareness in Maritime Traffic Using Federated Evidential Learning. Gao, Shang; Huang, Zhixin; Al-Falouji, Ghassan; Sick, Bernhard; Tomforde, Sven. In IEEE Conference on Cognitive and Computational Aspects of Situation Management (CogSIMA). IEEE, 2025.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
The increasing complexity of maritime navigation and the shift towards (semi)autonomous systems necessitate enhanced situational awareness (SA) to ensure maritime safety. This transition introduces new requirements for situation mod- elling and SA, particularly in busy waterways. To address these challenges, we present the Federated Evidential Learning for Anomaly Detection of Ship Trajectories (FEAST) framework, which integrates Federated Learning and Evidential Learning to provide a privacy-preserving, collaborative, and uncertainty- aware approach to out-of-distribution (OOD) anomaly detection in maritime traffic. FEAST uses data from the Automatic Identification System from the Kiel region, Germany, which exhibits unique characteristics of dynamic and heterogeneous maritime activity due to its connection with the traffic-dense Kiel Canal. Our extensive evaluations demonstrate that FEAST improves OOD anomaly detection by leveraging epistemic and aleatoric uncertainty estimates, outperforming baseline methods such as Denoise AutoEncoders and Variational AutoEncoders. Consequently, FEAST forms a solution to reliable and inter- pretable maritime traffic anomaly detection, supporting enhanced SA in maritime operations.
@inproceedings{gao2025towards, abstract = {The increasing complexity of maritime navigation and the shift towards (semi)autonomous systems necessitate enhanced situational awareness (SA) to ensure maritime safety. This transition introduces new requirements for situation mod- elling and SA, particularly in busy waterways. To address these challenges, we present the Federated Evidential Learning for Anomaly Detection of Ship Trajectories (FEAST) framework, which integrates Federated Learning and Evidential Learning to provide a privacy-preserving, collaborative, and uncertainty- aware approach to out-of-distribution (OOD) anomaly detection in maritime traffic. FEAST uses data from the Automatic Identification System from the Kiel region, Germany, which exhibits unique characteristics of dynamic and heterogeneous maritime activity due to its connection with the traffic-dense Kiel Canal. Our extensive evaluations demonstrate that FEAST improves OOD anomaly detection by leveraging epistemic and aleatoric uncertainty estimates, outperforming baseline methods such as Denoise AutoEncoders and Variational AutoEncoders. Consequently, FEAST forms a solution to reliable and inter- pretable maritime traffic anomaly detection, supporting enhanced SA in maritime operations.}, author = {Gao, Shang and Huang, Zhixin and Al-Falouji, Ghassan and Sick, Bernhard and Tomforde, Sven}, booktitle = {IEEE Conference on Cognitive and Computational Aspects of Situation Management (CogSIMA)}, keywords = {itegpub}, note = {(accepted)}, publisher = {IEEE}, title = {Towards Cognitive Situational Awareness in Maritime Traffic Using Federated Evidential Learning}, year = 2025 }
%0 Conference Paper %1 gao2025towards %A Gao, Shang %A Huang, Zhixin %A Al-Falouji, Ghassan %A Sick, Bernhard %A Tomforde, Sven %B IEEE Conference on Cognitive and Computational Aspects of Situation Management (CogSIMA) %D 2025 %I IEEE %T Towards Cognitive Situational Awareness in Maritime Traffic Using Federated Evidential Learning %X The increasing complexity of maritime navigation and the shift towards (semi)autonomous systems necessitate enhanced situational awareness (SA) to ensure maritime safety. This transition introduces new requirements for situation mod- elling and SA, particularly in busy waterways. To address these challenges, we present the Federated Evidential Learning for Anomaly Detection of Ship Trajectories (FEAST) framework, which integrates Federated Learning and Evidential Learning to provide a privacy-preserving, collaborative, and uncertainty- aware approach to out-of-distribution (OOD) anomaly detection in maritime traffic. FEAST uses data from the Automatic Identification System from the Kiel region, Germany, which exhibits unique characteristics of dynamic and heterogeneous maritime activity due to its connection with the traffic-dense Kiel Canal. Our extensive evaluations demonstrate that FEAST improves OOD anomaly detection by leveraging epistemic and aleatoric uncertainty estimates, outperforming baseline methods such as Denoise AutoEncoders and Variational AutoEncoders. Consequently, FEAST forms a solution to reliable and inter- pretable maritime traffic anomaly detection, supporting enhanced SA in maritime operations.
AudioProtoPNet: An interpretable deep learning model for bird sound classification. Heinrich, René; Rauch, Lukas; Sick, Bernhard; Scholz, Christoph. In Ecological Informatics, 87, bl 103081. Elsevier, 2025.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Deep learning models have significantly advanced acoustic bird monitoring by recognizing numerous bird species based on their vocalizations. However, traditional deep learning models are black boxes that provide no insight into their underlying computations, limiting their usefulness to ornithologists and machine learning engineers. Explainable models could facilitate debugging, knowledge discovery, trust, and interdisciplinary collaboration. We introduce AudioProtoPNet, an adaptation of the Prototypical Part Network (ProtoPNet) for multi-label bird sound classification. It is inherently interpretable, leveraging a ConvNeXt backbone to extract embeddings and a prototype learning classifier trained on these embeddings. The classifier learns prototypical patterns of each bird species’ vocalizations from spectrograms of instances in the training data. During inference, recordings are classified by comparing them to learned prototypes in the embedding space, providing explanations for the model’s decisions and insights into the most informative embeddings of each bird species. The model was trained on the BirdSet training dataset, which consists of 9734 bird species and over 6800 h of recordings. Its performance was evaluated on the seven BirdSet test datasets, covering different geographical regions. AudioProtoPNet outperformed the state-of-the-art bird sound classification model Perch, which is superior to the more popular BirdNet, achieving an average AUROC of 0.90 and a cmAP of 0.42, with relative improvements of 7.1% and 16.7% over Perch, respectively. These results demonstrate that even for the challenging task of multi-label bird sound classification, it is possible to develop powerful yet interpretable deep learning models that provide valuable insights for professionals in ornithology and machine learning.
@article{heinrich2025audioprotopnet, abstract = {Deep learning models have significantly advanced acoustic bird monitoring by recognizing numerous bird species based on their vocalizations. However, traditional deep learning models are black boxes that provide no insight into their underlying computations, limiting their usefulness to ornithologists and machine learning engineers. Explainable models could facilitate debugging, knowledge discovery, trust, and interdisciplinary collaboration. We introduce AudioProtoPNet, an adaptation of the Prototypical Part Network (ProtoPNet) for multi-label bird sound classification. It is inherently interpretable, leveraging a ConvNeXt backbone to extract embeddings and a prototype learning classifier trained on these embeddings. The classifier learns prototypical patterns of each bird species’ vocalizations from spectrograms of instances in the training data. During inference, recordings are classified by comparing them to learned prototypes in the embedding space, providing explanations for the model’s decisions and insights into the most informative embeddings of each bird species. The model was trained on the BirdSet training dataset, which consists of 9734 bird species and over 6800 h of recordings. Its performance was evaluated on the seven BirdSet test datasets, covering different geographical regions. AudioProtoPNet outperformed the state-of-the-art bird sound classification model Perch, which is superior to the more popular BirdNet, achieving an average AUROC of 0.90 and a cmAP of 0.42, with relative improvements of 7.1% and 16.7% over Perch, respectively. These results demonstrate that even for the challenging task of multi-label bird sound classification, it is possible to develop powerful yet interpretable deep learning models that provide valuable insights for professionals in ornithology and machine learning.}, author = {Heinrich, René and Rauch, Lukas and Sick, Bernhard and Scholz, Christoph}, journal = {Ecological Informatics}, keywords = {itegpub}, pages = 103081, publisher = {Elsevier}, title = {AudioProtoPNet: An interpretable deep learning model for bird sound classification}, volume = 87, year = 2025 }
%0 Journal Article %1 heinrich2025audioprotopnet %A Heinrich, René %A Rauch, Lukas %A Sick, Bernhard %A Scholz, Christoph %D 2025 %I Elsevier %J Ecological Informatics %P 103081 %R 10.1016/j.ecoinf.2025.103081 %T AudioProtoPNet: An interpretable deep learning model for bird sound classification %U https://www.sciencedirect.com/science/article/pii/S1574954125000901 %V 87 %X Deep learning models have significantly advanced acoustic bird monitoring by recognizing numerous bird species based on their vocalizations. However, traditional deep learning models are black boxes that provide no insight into their underlying computations, limiting their usefulness to ornithologists and machine learning engineers. Explainable models could facilitate debugging, knowledge discovery, trust, and interdisciplinary collaboration. We introduce AudioProtoPNet, an adaptation of the Prototypical Part Network (ProtoPNet) for multi-label bird sound classification. It is inherently interpretable, leveraging a ConvNeXt backbone to extract embeddings and a prototype learning classifier trained on these embeddings. The classifier learns prototypical patterns of each bird species’ vocalizations from spectrograms of instances in the training data. During inference, recordings are classified by comparing them to learned prototypes in the embedding space, providing explanations for the model’s decisions and insights into the most informative embeddings of each bird species. The model was trained on the BirdSet training dataset, which consists of 9734 bird species and over 6800 h of recordings. Its performance was evaluated on the seven BirdSet test datasets, covering different geographical regions. AudioProtoPNet outperformed the state-of-the-art bird sound classification model Perch, which is superior to the more popular BirdNet, achieving an average AUROC of 0.90 and a cmAP of 0.42, with relative improvements of 7.1% and 16.7% over Perch, respectively. These results demonstrate that even for the challenging task of multi-label bird sound classification, it is possible to develop powerful yet interpretable deep learning models that provide valuable insights for professionals in ornithology and machine learning.

2024[ to top ]

Tutorial: Interactive Adaptive Learning. Herde, Marek; Pham, Minh Tuan; Tharwat, Alaa; Sick, Bernhard. In Workshop on Interactive Adapative Learning (IAL), ECML PKDD, bll 1–6. 2024.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
We summarize the contents of the tutorial we present as a part of the 8th Interactive Adaptive Learning workshop. This workshop is co-located with the ECML-PKDD conference, where it takes place on September 9th, 2024 in Vilnius, Lithuania.
@inproceedings{herde2024tutorial, abstract = {We summarize the contents of the tutorial we present as a part of the 8th Interactive Adaptive Learning workshop. This workshop is co-located with the ECML-PKDD conference, where it takes place on September 9th, 2024 in Vilnius, Lithuania.}, author = {Herde, Marek and Pham, Minh Tuan and Tharwat, Alaa and Sick, Bernhard}, booktitle = {Workshop on Interactive Adapative Learning (IAL), ECML PKDD}, keywords = {itegpub}, pages = {1–6}, title = {Tutorial: Interactive Adaptive Learning}, year = 2024 }
%0 Conference Paper %1 herde2024tutorial %A Herde, Marek %A Pham, Minh Tuan %A Tharwat, Alaa %A Sick, Bernhard %B Workshop on Interactive Adapative Learning (IAL), ECML PKDD %D 2024 %P 1--6 %T Tutorial: Interactive Adaptive Learning %U https://ceur-ws.org/Vol-3770/paper1.pdf %X We summarize the contents of the tutorial we present as a part of the 8th Interactive Adaptive Learning workshop. This workshop is co-located with the ECML-PKDD conference, where it takes place on September 9th, 2024 in Vilnius, Lithuania.
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), bll 1–21. Springer, 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}, pages = {1–21}, publisher = {Springer}, 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 %I Springer %P 1--21 %R 10.1007/978-3-031-78398-2_1 %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.
Systematic Evaluation of Uncertainty Calibration in Pretrained Object Detectors. Huseljic, Denis; Herde, Marek; Hahn, Paul; Müjde, Mehmet; Sick, Bernhard. In International Journal of Computer Vision, 133(3), bll 1033–1047. Springer, 2024.
- [ 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{huseljic2024systematic, 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 Hahn, Paul and Müjde, Mehmet and Sick, Bernhard}, journal = {International Journal of Computer Vision}, keywords = {itegpub}, number = 3, pages = {1033–1047}, publisher = {Springer}, title = {Systematic Evaluation of Uncertainty Calibration in Pretrained Object Detectors}, volume = 133, year = 2024 }
%0 Journal Article %1 huseljic2024systematic %A Huseljic, Denis %A Herde, Marek %A Hahn, Paul %A Müjde, Mehmet %A Sick, Bernhard %D 2024 %I Springer %J International Journal of Computer Vision %N 3 %P 1033--1047 %R 10.1007/s11263-024-02219-z %T Systematic Evaluation of Uncertainty Calibration in Pretrained Object Detectors %U https://link.springer.com/article/10.1007/s11263-024-02219-z %V 133 %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.
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.
Sensor Equivariance: A Framework for Semantic Segmentation with Diverse Camera Models. Reichert, Hannes; Hetzel, Manuel; Hubert, Andreas; Doll, Konrad; Sick, Bernhard. In Workshop on Omnidirectional Computer Vision (OmniCV), ICVPR, bll 1254–1261. IEEE, 2024.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
Objects are represented differently in projection-based sensors such as cameras depending on sensor resolution, field of view, and distortion, leading to distorted physical and geometric properties. As a result, sensor data process- ing depend on these properties. With the large variations of sensors on the market, an equivariant representation and suitable processing are necessary to become independent of the sensor used. In this work, we propose an extension of conventional image data by an additional channel in which the associated projection properties are encoded. Further- more, we introduce a SensorConv layer as an extension to the conventional convolution layer. SensorConv enable us- ing projection properties in convolutional neural networks. To that end, we propose an architecture for using the Sen- sorConv layer in the Detectron2 [21] framework. We col- lected a dataset of equirectangular images for our experi- ments with the CARLA [3] simulator. To analyze multiple sensor models (i.e., sensor intrinsic), we created an aug- mentation method to emulate a high variability of sensors from the collected equirectangular panoramas. In our ex- periment, we show that our method can generalize better across different camera sensors.
@inproceedings{reichert2024sensor, abstract = {Objects are represented differently in projection-based sensors such as cameras depending on sensor resolution, field of view, and distortion, leading to distorted physical and geometric properties. As a result, sensor data process- ing depend on these properties. With the large variations of sensors on the market, an equivariant representation and suitable processing are necessary to become independent of the sensor used. In this work, we propose an extension of conventional image data by an additional channel in which the associated projection properties are encoded. Further- more, we introduce a SensorConv layer as an extension to the conventional convolution layer. SensorConv enable us- ing projection properties in convolutional neural networks. To that end, we propose an architecture for using the Sen- sorConv layer in the Detectron2 [21] framework. We col- lected a dataset of equirectangular images for our experi- ments with the CARLA [3] simulator. To analyze multiple sensor models (i.e., sensor intrinsic), we created an aug- mentation method to emulate a high variability of sensors from the collected equirectangular panoramas. In our ex- periment, we show that our method can generalize better across different camera sensors.}, author = {Reichert, Hannes and Hetzel, Manuel and Hubert, Andreas and Doll, Konrad and Sick, Bernhard}, booktitle = {Workshop on Omnidirectional Computer Vision (OmniCV), ICVPR}, keywords = {itegpub}, pages = {1254–1261}, publisher = {IEEE}, title = {Sensor Equivariance: A Framework for Semantic Segmentation with Diverse Camera Models}, year = 2024 }
%0 Conference Paper %1 reichert2024sensor %A Reichert, Hannes %A Hetzel, Manuel %A Hubert, Andreas %A Doll, Konrad %A Sick, Bernhard %B Workshop on Omnidirectional Computer Vision (OmniCV), ICVPR %D 2024 %I IEEE %P 1254--1261 %R 10.1109/CVPRW63382.2024.00132 %T Sensor Equivariance: A Framework for Semantic Segmentation with Diverse Camera Models %X Objects are represented differently in projection-based sensors such as cameras depending on sensor resolution, field of view, and distortion, leading to distorted physical and geometric properties. As a result, sensor data process- ing depend on these properties. With the large variations of sensors on the market, an equivariant representation and suitable processing are necessary to become independent of the sensor used. In this work, we propose an extension of conventional image data by an additional channel in which the associated projection properties are encoded. Further- more, we introduce a SensorConv layer as an extension to the conventional convolution layer. SensorConv enable us- ing projection properties in convolutional neural networks. To that end, we propose an architecture for using the Sen- sorConv layer in the Detectron2 [21] framework. We col- lected a dataset of equirectangular images for our experi- ments with the CARLA [3] simulator. To analyze multiple sensor models (i.e., sensor intrinsic), we created an aug- mentation method to emulate a high variability of sensors from the collected equirectangular panoramas. In our ex- periment, we show that our method can generalize better across different camera sensors.
Self-Aware Control for Autonomous Underwater Vehicles. Decke, Jens; Gerland, Florian; Schomberg, Thomas; Wünsch, Olaf; Sick, Bernhard; Gruhl, Christian. In Workshop on self-improving system integration (SISSY), ACSOS, bll 13–14. IEEE, 2024.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
We present a concept to research the implementation of a self-aware control system for underwater cleaning robots. Multiple robots cooperate as a swarm to clean the hull of large container ships while in transit. We utilise physics-informed neural networks to implement an autonomous steering system and combine it with a deep reinforcement learning-based decision and scheduling system. This approach ensures efficient navigation and cleaning operations, adapting to dynamic environmental conditions in real-time. The proposed control system allows the cleaner robots, to enhance fuel efficiency, reduce CO2 emissions, and minimize the environmental impact of maritime transportation.
@inproceedings{decke2024self, abstract = {We present a concept to research the implementation of a self-aware control system for underwater cleaning robots. Multiple robots cooperate as a swarm to clean the hull of large container ships while in transit. We utilise physics-informed neural networks to implement an autonomous steering system and combine it with a deep reinforcement learning-based decision and scheduling system. This approach ensures efficient navigation and cleaning operations, adapting to dynamic environmental conditions in real-time. The proposed control system allows the cleaner robots, to enhance fuel efficiency, reduce CO2 emissions, and minimize the environmental impact of maritime transportation.}, author = {Decke, Jens and Gerland, Florian and Schomberg, Thomas and Wünsch, Olaf and Sick, Bernhard and Gruhl, Christian}, booktitle = {Workshop on self-improving system integration (SISSY), ACSOS}, keywords = {itegpub}, pages = {13–14}, publisher = {IEEE}, title = {Self-Aware Control for Autonomous Underwater Vehicles}, year = 2024 }
%0 Conference Paper %1 decke2024self %A Decke, Jens %A Gerland, Florian %A Schomberg, Thomas %A Wünsch, Olaf %A Sick, Bernhard %A Gruhl, Christian %B Workshop on self-improving system integration (SISSY), ACSOS %D 2024 %I IEEE %P 13--14 %R 10.1109/ACSOS-C63493.2024.00022 %T Self-Aware Control for Autonomous Underwater Vehicles %X We present a concept to research the implementation of a self-aware control system for underwater cleaning robots. Multiple robots cooperate as a swarm to clean the hull of large container ships while in transit. We utilise physics-informed neural networks to implement an autonomous steering system and combine it with a deep reinforcement learning-based decision and scheduling system. This approach ensures efficient navigation and cleaning operations, adapting to dynamic environmental conditions in real-time. The proposed control system allows the cleaner robots, to enhance fuel efficiency, reduce CO2 emissions, and minimize the environmental impact of maritime transportation.
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.
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), bll 1–7. 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}, pages = {1–7}, 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 %P 1--7 %R 10.1109/ICIEA61579.2024.10665236 %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.
General Reusability: Ensuring Long-Term Benefits of Deep Active Learning. Hahn, Paul; Huseljic, Denis; Herde, Marek; Sick, Bernhard. In Workshop on Interactive Adapative Learning (IAL), ECML PKDD, bll 33–46. 2024.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Deep active learning (DAL) provides a promising framework for reducing labeling costs for data-hungry deep neural networks. In DAL research, experiments are evaluated based on the performance of the model that is responsible for querying data, which can be interpreted as a model-centric evaluation. However, the data queried by DAL should be model agnostic so that new models can be effectively trained on it. An example can be derived from the rapid progress in deep learning, where new architectures are proposed in quick succession. Naturally, we want to employ these new and more effective models while still using the queried data from DAL. This results in the need to ensure high performance for both current and future models, which we refer to as reusability. In line with this topic, we propose general reusability, a novel, data-centric evaluation metric that measures the long-term value of queried data. Our experiments demonstrate that the current evaluation protocol in DAL research does not assess the reusability of data and that GR can fill this gap.
@inproceedings{hahn2024general, abstract = {Deep active learning (DAL) provides a promising framework for reducing labeling costs for data-hungry deep neural networks. In DAL research, experiments are evaluated based on the performance of the model that is responsible for querying data, which can be interpreted as a model-centric evaluation. However, the data queried by DAL should be model agnostic so that new models can be effectively trained on it. An example can be derived from the rapid progress in deep learning, where new architectures are proposed in quick succession. Naturally, we want to employ these new and more effective models while still using the queried data from DAL. This results in the need to ensure high performance for both current and future models, which we refer to as reusability. In line with this topic, we propose general reusability, a novel, data-centric evaluation metric that measures the long-term value of queried data. Our experiments demonstrate that the current evaluation protocol in DAL research does not assess the reusability of data and that GR can fill this gap.}, author = {Hahn, Paul and Huseljic, Denis and Herde, Marek and Sick, Bernhard}, booktitle = {Workshop on Interactive Adapative Learning (IAL), ECML PKDD}, keywords = {itegpub}, pages = {33–46}, title = {General Reusability: Ensuring Long-Term Benefits of Deep Active Learning}, year = 2024 }
%0 Conference Paper %1 hahn2024general %A Hahn, Paul %A Huseljic, Denis %A Herde, Marek %A Sick, Bernhard %B Workshop on Interactive Adapative Learning (IAL), ECML PKDD %D 2024 %P 33--46 %T General Reusability: Ensuring Long-Term Benefits of Deep Active Learning %U https://ceur-ws.org/Vol-3770/paper5.pdf %X Deep active learning (DAL) provides a promising framework for reducing labeling costs for data-hungry deep neural networks. In DAL research, experiments are evaluated based on the performance of the model that is responsible for querying data, which can be interpreted as a model-centric evaluation. However, the data queried by DAL should be model agnostic so that new models can be effectively trained on it. An example can be derived from the rapid progress in deep learning, where new architectures are proposed in quick succession. Naturally, we want to employ these new and more effective models while still using the queried data from DAL. This results in the need to ensure high performance for both current and future models, which we refer to as reusability. In line with this topic, we propose general reusability, a novel, data-centric evaluation metric that measures the long-term value of queried data. Our experiments demonstrate that the current evaluation protocol in DAL research does not assess the reusability of data and that GR can fill this gap.
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.
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.
Exploring 3D Object Detection for Autonomous Factory Driving: Advanced Research on Handling Limited Annotations with Ground Truth Sampling Augmentation. Reuse, Matthias; Amende, Karl; Simon, Martin; Sick, Bernhard. In Computer Sciences & Mathematics Forum, 9(1), bl 5. MDPI, 2024.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
Autonomously driving vehicles in car factories and parking spaces can represent a competitive advantage in the logistics industry. However, the real-world application is challenging in many ways. First of all, there are no publicly available datasets for this specific task. Therefore, we equipped two industrial production sites with up to 11 LiDAR sensors to collect and annotate our own data for infrastructural 3D object detection. These form the basis for extensive experiments. Due to the still limited amount of labeled data, the commonly used ground truth sampling augmentation is the core of research in this work. Several variations of this augmentation method are explored, revealing that in our case, the most commonly used is not necessarily the best. We show that an easy-to-create polygon can noticeably improve the detection results in this application scenario. By using these augmentation methods, it is even possible to achieve moderate detection results when only empty frames without any objects and a database with only a few labeled objects are used.
@article{reuse2024exploring, abstract = {Autonomously driving vehicles in car factories and parking spaces can represent a competitive advantage in the logistics industry. However, the real-world application is challenging in many ways. First of all, there are no publicly available datasets for this specific task. Therefore, we equipped two industrial production sites with up to 11 LiDAR sensors to collect and annotate our own data for infrastructural 3D object detection. These form the basis for extensive experiments. Due to the still limited amount of labeled data, the commonly used ground truth sampling augmentation is the core of research in this work. Several variations of this augmentation method are explored, revealing that in our case, the most commonly used is not necessarily the best. We show that an easy-to-create polygon can noticeably improve the detection results in this application scenario. By using these augmentation methods, it is even possible to achieve moderate detection results when only empty frames without any objects and a database with only a few labeled objects are used.}, author = {Reuse, Matthias and Amende, Karl and Simon, Martin and Sick, Bernhard}, journal = {Computer Sciences \& Mathematics Forum}, keywords = {itegpub}, number = 1, pages = 5, publisher = {MDPI}, title = {Exploring 3D Object Detection for Autonomous Factory Driving: Advanced Research on Handling Limited Annotations with Ground Truth Sampling Augmentation}, volume = 9, year = 2024 }
%0 Journal Article %1 reuse2024exploring %A Reuse, Matthias %A Amende, Karl %A Simon, Martin %A Sick, Bernhard %D 2024 %I MDPI %J Computer Sciences & Mathematics Forum %N 1 %P 5 %R 10.3390/cmsf2024009005 %T Exploring 3D Object Detection for Autonomous Factory Driving: Advanced Research on Handling Limited Annotations with Ground Truth Sampling Augmentation %V 9 %X Autonomously driving vehicles in car factories and parking spaces can represent a competitive advantage in the logistics industry. However, the real-world application is challenging in many ways. First of all, there are no publicly available datasets for this specific task. Therefore, we equipped two industrial production sites with up to 11 LiDAR sensors to collect and annotate our own data for infrastructural 3D object detection. These form the basis for extensive experiments. Due to the still limited amount of labeled data, the commonly used ground truth sampling augmentation is the core of research in this work. Several variations of this augmentation method are explored, revealing that in our case, the most commonly used is not necessarily the best. We show that an easy-to-create polygon can noticeably improve the detection results in this application scenario. By using these augmentation methods, it is even possible to achieve moderate detection results when only empty frames without any objects and a database with only a few labeled objects are used.
dopanim: A Dataset of Doppelganger Animals with Noisy Annotations from Multiple Humans. Herde, Marek; Huseljic, Denis; Rauch, Lukas; Sick, Bernhard. In Conference on Neural Information Processing Systems (NeurIPS 2024) Track on Datasets and Benchmarks, bll 1–16. 2024.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Human annotators typically provide annotated data for training machine learning models, such as neural networks. Yet, human annotations are subject to noise, impairing generalization performances. Methodological research on approaches counteracting noisy annotations requires corresponding datasets for a meaningful empirical evaluation. Consequently, we introduce a novel benchmark dataset, dopanim, consisting of about 15,750 animal images of 15 classes with ground truth labels. For approximately 10,500 of these images, 20 humans provided over 52,000 annotations with an accuracy of circa 67%. Its key attributes include (1) the challenging task of classifying doppelganger animals, (2) human-estimated likelihoods as annotations, and (3) annotator metadata. We benchmark well-known multi-annotator learning approaches using seven variants of this dataset and outline further evaluation use cases such as learning beyond hard class labels and active learning. Our dataset and a comprehensive codebase are publicly available to emulate the data collection process and to reproduce all empirical results.
@inproceedings{herde2024dopanim, abstract = {Human annotators typically provide annotated data for training machine learning models, such as neural networks. Yet, human annotations are subject to noise, impairing generalization performances. Methodological research on approaches counteracting noisy annotations requires corresponding datasets for a meaningful empirical evaluation. Consequently, we introduce a novel benchmark dataset, dopanim, consisting of about 15,750 animal images of 15 classes with ground truth labels. For approximately 10,500 of these images, 20 humans provided over 52,000 annotations with an accuracy of circa 67%. Its key attributes include (1) the challenging task of classifying doppelganger animals, (2) human-estimated likelihoods as annotations, and (3) annotator metadata. We benchmark well-known multi-annotator learning approaches using seven variants of this dataset and outline further evaluation use cases such as learning beyond hard class labels and active learning. Our dataset and a comprehensive codebase are publicly available to emulate the data collection process and to reproduce all empirical results.}, author = {Herde, Marek and Huseljic, Denis and Rauch, Lukas and Sick, Bernhard}, booktitle = {Conference on Neural Information Processing Systems (NeurIPS 2024) Track on Datasets and Benchmarks}, keywords = {itegpub}, pages = {1–16}, title = {dopanim: A Dataset of Doppelganger Animals with Noisy Annotations from Multiple Humans}, year = 2024 }
%0 Conference Paper %1 herde2024dopanim %A Herde, Marek %A Huseljic, Denis %A Rauch, Lukas %A Sick, Bernhard %B Conference on Neural Information Processing Systems (NeurIPS 2024) Track on Datasets and Benchmarks %D 2024 %P 1--16 %T dopanim: A Dataset of Doppelganger Animals with Noisy Annotations from Multiple Humans %U https://openreview.net/forum?id=XOGosbxLrz %X Human annotators typically provide annotated data for training machine learning models, such as neural networks. Yet, human annotations are subject to noise, impairing generalization performances. Methodological research on approaches counteracting noisy annotations requires corresponding datasets for a meaningful empirical evaluation. Consequently, we introduce a novel benchmark dataset, dopanim, consisting of about 15,750 animal images of 15 classes with ground truth labels. For approximately 10,500 of these images, 20 humans provided over 52,000 annotations with an accuracy of circa 67%. Its key attributes include (1) the challenging task of classifying doppelganger animals, (2) human-estimated likelihoods as annotations, and (3) annotator metadata. We benchmark well-known multi-annotator learning approaches using seven variants of this dataset and outline further evaluation use cases such as learning beyond hard class labels and active learning. Our dataset and a comprehensive codebase are publicly available to emulate the data collection process and to reproduce all empirical results.
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.
Annot-Mix: Learning with Noisy Class Labels from Multiple Annotators via a Mixup Extension. Herde, Marek; Lührs, Lukas; Huseljic, Denis; Sick, Bernhard. In European Conference on Artificial Intelligence (ECAI), bll 2910–2918. IOS Press, 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 multiple annotators, e.g., crowdworkers, typically 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 eleven (mostly state-of-the-art) approaches in an evaluation study with eleven datasets comprising noisy class labels from either human or simulated annotators. Our code is publicly available through our GitHub repository at https://github.com/ies-research/multi-annotator-machine-learning/tree/annot-mix.
@inproceedings{herde2024annota, 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 multiple annotators, e.g., crowdworkers, typically 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 eleven (mostly state-of-the-art) approaches in an evaluation study with eleven datasets comprising noisy class labels from either human or simulated annotators. Our code is publicly available through our GitHub repository at https://github.com/ies-research/multi-annotator-machine-learning/tree/annot-mix.}, author = {Herde, Marek and Lührs, Lukas and Huseljic, Denis and Sick, Bernhard}, booktitle = {European Conference on Artificial Intelligence (ECAI)}, keywords = {itegpub}, pages = {2910–2918}, publisher = {IOS Press}, title = {Annot-Mix: Learning with Noisy Class Labels from Multiple Annotators via a Mixup Extension}, year = 2024 }
%0 Conference Paper %1 herde2024annota %A Herde, Marek %A Lührs, Lukas %A Huseljic, Denis %A Sick, Bernhard %B European Conference on Artificial Intelligence (ECAI) %D 2024 %I IOS Press %P 2910--2918 %R 10.3233/FAIA240829 %T Annot-Mix: Learning with Noisy Class Labels from Multiple Annotators via a Mixup Extension %U https://ebooks.iospress.nl/doi/10.3233/FAIA240829 %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 multiple annotators, e.g., crowdworkers, typically 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 eleven (mostly state-of-the-art) approaches in an evaluation study with eleven datasets comprising noisy class labels from either human or simulated annotators. Our code is publicly available through our GitHub repository at https://github.com/ies-research/multi-annotator-machine-learning/tree/annot-mix.
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.
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.
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
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.
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.
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.
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.
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.
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.
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 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 ]

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.
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.
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.
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.
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.
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.
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.
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.
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%.
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.
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.
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
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
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
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
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
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
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
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
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 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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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 ]

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
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 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.}, author = {Schreiber, Jens and Sick, Bernhard}, booktitle = {International Conference on Power and Renewable Energy (ICPRE)}, keywords = {imported}, pages = {1–6}, title = {Quantifying the Influences on Probabilistic Wind Power Forecasts}, year = 2018 }
%0 Conference Paper %1 schreiber2018quantifying %A Schreiber, Jens %A Sick, Bernhard %B International Conference on Power and Renewable Energy (ICPRE) %D 2018 %P 1--6 %R 10.1051/e3sconf/20186406002 %T Quantifying the Influences on Probabilistic Wind Power Forecasts %X 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.
Organic Computing -- Doctoral Dissertation Colloquium 2017. Tomforde, S.; Sick, B. In Vol. 11Intelligent Embedded Systems. kassel university press, 2018.
- [ BibTeX ]
- [ EndNote ]
@book{tomforde2018organic, editor = {Tomforde, S. and Sick, B.}, keywords = {itegpub}, publisher = {kassel university press}, series = {Intelligent Embedded Systems}, title = {Organic Computing – Doctoral Dissertation Colloquium 2017}, volume = 11, year = 2018 }
%0 Book %1 tomforde2018organic %B Intelligent Embedded Systems %D 2018 %E Tomforde, S. %E Sick, B. %I kassel university press %R 10.19211/KUP9783737605151 %T Organic Computing -- Doctoral Dissertation Colloquium 2017 %V 11
Novelty detection with CANDIES: a holistic technique based on probabilistic models. Gruhl, Christian; Sick, Bernhard. In International Journal of Machine Learning and Cybernetics, 9(6), bll 927–945. Springer, 2018.
- [ BibTeX ]
- [ EndNote ]
@article{gruhl2018novelty, author = {Gruhl, Christian and Sick, Bernhard}, journal = {International Journal of Machine Learning and Cybernetics}, keywords = {imported}, number = 6, pages = {927–945}, publisher = {Springer}, title = {Novelty detection with {CANDIES:} a holistic technique based on probabilistic models}, volume = 9, year = 2018 }
%0 Journal Article %1 gruhl2018novelty %A Gruhl, Christian %A Sick, Bernhard %D 2018 %I Springer %J International Journal of Machine Learning and Cybernetics %N 6 %P 927--945 %R 10.1007/s13042-016-0618-8 %T Novelty detection with CANDIES: a holistic technique based on probabilistic models %V 9
Leveraging the Potentials of Dedicated Collaborative Interactive Learning: Conceptual Foundations to Overcome Uncertainty by Human-Machine Collaboration. Calma, Adrian; Oeste-Reiß, Sarah; Sick, Bernhard; Leimeister, Jan Marco. In Hawaii International Conference on System Sciences (HICSS). 2018.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{calma2018leveraging, author = {Calma, Adrian and Oeste-Rei{\ss}, Sarah and Sick, Bernhard and Leimeister, Jan Marco}, booktitle = {Hawaii International Conference on System Sciences (HICSS)}, keywords = {imported}, title = {Leveraging the Potentials of Dedicated Collaborative Interactive Learning: Conceptual Foundations to Overcome Uncertainty by Human-Machine Collaboration}, year = 2018 }
%0 Conference Paper %1 calma2018leveraging %A Calma, Adrian %A Oeste-Reiß, Sarah %A Sick, Bernhard %A Leimeister, Jan Marco %B Hawaii International Conference on System Sciences (HICSS) %D 2018 %R 10.24251/hicss.2018.120 %T Leveraging the Potentials of Dedicated Collaborative Interactive Learning: Conceptual Foundations to Overcome Uncertainty by Human-Machine Collaboration
Human Pose Estimation in Real Traffic Scenes. Kress, V.; Jung, J.; Zernetsch, S.; Doll, K.; Sick, B. In IEEE Symposium Series on Computational Intelligence (SSCI). IEEE, Bangalore, India, 2018.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{kress2018human, address = {Bangalore, India}, author = {Kress, V. and Jung, J. and Zernetsch, S. and Doll, K. and Sick, B.}, booktitle = {IEEE Symposium Series on Computational Intelligence (SSCI)}, keywords = {imported}, publisher = {IEEE}, title = {Human Pose Estimation in Real Traffic Scenes}, year = 2018 }
%0 Conference Paper %1 kress2018human %A Kress, V. %A Jung, J. %A Zernetsch, S. %A Doll, K. %A Sick, B. %B IEEE Symposium Series on Computational Intelligence (SSCI) %C Bangalore, India %D 2018 %I IEEE %R 10.1109/ssci.2018.8628660 %T Human Pose Estimation in Real Traffic Scenes
Hosting capacity of low-voltage grids for distributed generation: Classification by means of machine learning techniques. Breker, Sebastian; Rentmeister, Jan; Sick, Bernhard; Braun, Martin. In Applied Soft Computing, 70, bll 195–207. Elsevier, 2018.
- [ BibTeX ]
- [ EndNote ]
@article{breker2018hosting, author = {Breker, Sebastian and Rentmeister, Jan and Sick, Bernhard and Braun, Martin}, journal = {Applied Soft Computing}, keywords = {imported}, pages = {195–207}, publisher = {Elsevier}, title = {Hosting capacity of low-voltage grids for distributed generation: Classification by means of machine learning techniques}, volume = 70, year = 2018 }
%0 Journal Article %1 breker2018hosting %A Breker, Sebastian %A Rentmeister, Jan %A Sick, Bernhard %A Braun, Martin %D 2018 %I Elsevier %J Applied Soft Computing %P 195--207 %R 10.1016/j.asoc.2018.05.007 %T Hosting capacity of low-voltage grids for distributed generation: Classification by means of machine learning techniques %V 70
Hijacked Smart Devices -- Methodical Foundations for Autonomous Theft Awareness based on Activity Recognition and Novelty Detection. Jänicke, Martin; Schmidt, Viktor; Sick, Bernhard; Tomforde, Sven; Lukowicz, Paul. In International Conference on Agents and Artificial Intelligence (ICAART). 2018.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{jaenicke2018hijacked, author = {J{\"a}nicke, Martin and Schmidt, Viktor and Sick, Bernhard and Tomforde, Sven and Lukowicz, Paul}, booktitle = {International Conference on Agents and Artificial Intelligence (ICAART)}, keywords = {imported}, title = {Hijacked Smart Devices – Methodical Foundations for Autonomous Theft Awareness based on Activity Recognition and Novelty Detection}, year = 2018 }
%0 Conference Paper %1 jaenicke2018hijacked %A Jänicke, Martin %A Schmidt, Viktor %A Sick, Bernhard %A Tomforde, Sven %A Lukowicz, Paul %B International Conference on Agents and Artificial Intelligence (ICAART) %D 2018 %R 10.5220/0006594901310142 %T Hijacked Smart Devices -- Methodical Foundations for Autonomous Theft Awareness based on Activity Recognition and Novelty Detection
Generalizing Application Agnostic Remaining Useful Life Estimation Using Data-Driven Open Source Algorithms. Schlegel, B.; Mrowca, A.; Wolf, P.; Sick, B.; Steinhorst, S. In IEEE International Conference on Big Data Analysis (ICBDA). IEEE, Shanghai, China, 2018.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{schlegel2018generalizing, address = {Shanghai, China}, author = {Schlegel, B. and Mrowca, A. and Wolf, P. and Sick, B. and Steinhorst, S.}, booktitle = {IEEE International Conference on Big Data Analysis (ICBDA)}, keywords = {imported}, publisher = {IEEE}, title = {Generalizing Application Agnostic Remaining Useful Life Estimation Using Data-Driven Open Source Algorithms}, year = 2018 }
%0 Conference Paper %1 schlegel2018generalizing %A Schlegel, B. %A Mrowca, A. %A Wolf, P. %A Sick, B. %A Steinhorst, S. %B IEEE International Conference on Big Data Analysis (ICBDA) %C Shanghai, China %D 2018 %I IEEE %R 10.1109/icbda.2018.8367659 %T Generalizing Application Agnostic Remaining Useful Life Estimation Using Data-Driven Open Source Algorithms
Early Start Intention Detection of Cyclists Using Motion History Images and a Deep Residual Network. Zernetsch, Stefan; Kress, Viktor; Sick, Bernhard; Doll, Konrad. In IEEE Intelligent Vehicles Symposium (IV), bll 1–6. IEEE, 2018.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{zernetsch2018early, author = {Zernetsch, Stefan and Kress, Viktor and Sick, Bernhard and Doll, Konrad}, booktitle = {{IEEE} Intelligent Vehicles Symposium (IV)}, keywords = {imported}, pages = {1–6}, publisher = {IEEE}, title = {Early Start Intention Detection of Cyclists Using Motion History Images and a Deep Residual Network}, year = 2018 }
%0 Conference Paper %1 zernetsch2018early %A Zernetsch, Stefan %A Kress, Viktor %A Sick, Bernhard %A Doll, Konrad %B IEEE Intelligent Vehicles Symposium (IV) %D 2018 %I IEEE %P 1--6 %R 10.1109/ivs.2018.8500428 %T Early Start Intention Detection of Cyclists Using Motion History Images and a Deep Residual Network
Coopetitive Soft Gating Ensemble. Schreiber, J.; Bieshaar, M.; Gensler, A.; Sick, B.; Deist, S. In Workshop on Self-Improving System Integration (SISSY), FAS*W. IEEE, Trento, Italy, 2018.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{schreiber2018coopetitive, address = {Trento, Italy}, author = {Schreiber, J. and Bieshaar, M. and Gensler, A. and Sick, B. and Deist, S.}, booktitle = {Workshop on Self-Improving System Integration (SISSY), FAS*W}, keywords = {imported}, publisher = {IEEE}, title = {Coopetitive Soft Gating Ensemble}, year = 2018 }
%0 Conference Paper %1 schreiber2018coopetitive %A Schreiber, J. %A Bieshaar, M. %A Gensler, A. %A Sick, B. %A Deist, S. %B Workshop on Self-Improving System Integration (SISSY), FAS*W %C Trento, Italy %D 2018 %I IEEE %R 10.1109/fas-w.2018.00046 %T Coopetitive Soft Gating Ensemble
Cooperative Tracking of Cyclists Based on Smart Devices and Infrastructure. Reitberger, G.; Zernetsch, S.; Bieshaar, M.; Sick, B.; Doll, K.; Fuchs, E. In IEEE International Conference on Intelligent Transportation Systems (ITSC). IEEE, Maui, HI, 2018.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{reitberger2018cooperative, address = {Maui, HI}, author = {Reitberger, G. and Zernetsch, S. and Bieshaar, M. and Sick, B. and Doll, K. and Fuchs, E.}, booktitle = {IEEE International Conference on Intelligent Transportation Systems (ITSC)}, keywords = {imported}, publisher = {IEEE}, title = {Cooperative Tracking of Cyclists Based on Smart Devices and Infrastructure}, year = 2018 }
%0 Conference Paper %1 reitberger2018cooperative %A Reitberger, G. %A Zernetsch, S. %A Bieshaar, M. %A Sick, B. %A Doll, K. %A Fuchs, E. %B IEEE International Conference on Intelligent Transportation Systems (ITSC) %C Maui, HI %D 2018 %I IEEE %R 10.1109/itsc.2018.8569267 %T Cooperative Tracking of Cyclists Based on Smart Devices and Infrastructure
Cooperative Starting Movement Detection of Cyclists Using Convolutional Neural Networks and a Boosted Stacking Ensemble. Bieshaar, M.; Zernetsch, S.; Hubert, A.; Sick, B.; Doll, K. In IEEE Transactions on Intelligent Vehicles, 3(4), bll 534–544. IEEE, 2018.
- [ BibTeX ]
- [ EndNote ]
@article{bieshaar2018cooperative, author = {Bieshaar, M. and Zernetsch, S. and Hubert, A. and Sick, B. and Doll, K.}, journal = {IEEE Transactions on Intelligent Vehicles}, keywords = {imported}, number = 4, pages = {534–544}, publisher = {IEEE}, title = {Cooperative Starting Movement Detection of Cyclists Using Convolutional Neural Networks and a Boosted Stacking Ensemble}, volume = 3, year = 2018 }
%0 Journal Article %1 bieshaar2018cooperative %A Bieshaar, M. %A Zernetsch, S. %A Hubert, A. %A Sick, B. %A Doll, K. %D 2018 %I IEEE %J IEEE Transactions on Intelligent Vehicles %N 4 %P 534--544 %R 10.1109/tiv.2018.2873900 %T Cooperative Starting Movement Detection of Cyclists Using Convolutional Neural Networks and a Boosted Stacking Ensemble %V 3
Automated Active Learning with a Robot. Scharei, Kristina; Herde, Marek; Bieshaar, Maarten; Calma, Adrian; Kottke, Daniel; Sick, Bernhard. In Archives of Data Science, Series A (Online First), 5(1), bl 16. KIT, 2018.
- [ BibTeX ]
- [ EndNote ]
@article{scharei2018automated, author = {Scharei, Kristina and Herde, Marek and Bieshaar, Maarten and Calma, Adrian and Kottke, Daniel and Sick, Bernhard}, journal = {Archives of Data Science, Series A (Online First)}, keywords = {imported}, number = 1, pages = 16, publisher = {KIT}, title = {Automated Active Learning with a Robot}, volume = 5, year = 2018 }
%0 Journal Article %1 scharei2018automated %A Scharei, Kristina %A Herde, Marek %A Bieshaar, Maarten %A Calma, Adrian %A Kottke, Daniel %A Sick, Bernhard %D 2018 %I KIT %J Archives of Data Science, Series A (Online First) %N 1 %P 16 %R 10.5445/KSP/1000087327/16 %T Automated Active Learning with a Robot %V 5
Aspects of Measuring and Evaluating the Integration Status of a (Sub-)System at Runtime. Gruhl, Christian; Tomforde, Sven; Sick, Bernhard. In Workshop on Self-Improving System Integration (SISSY), FAS*W, bll 198–203. IEEE, 2018.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{gruhl2018aspects, author = {Gruhl, Christian and Tomforde, Sven and Sick, Bernhard}, booktitle = {Workshop on Self-Improving System Integration (SISSY), FAS*W}, keywords = {imported}, pages = {198–203}, publisher = {IEEE}, title = {Aspects of Measuring and Evaluating the Integration Status of a (Sub-)System at Runtime}, year = 2018 }
%0 Conference Paper %1 gruhl2018aspects %A Gruhl, Christian %A Tomforde, Sven %A Sick, Bernhard %B Workshop on Self-Improving System Integration (SISSY), FAS*W %D 2018 %I IEEE %P 198--203 %R 10.1109/fas-w.2018.00047 %T Aspects of Measuring and Evaluating the Integration Status of a (Sub-)System at Runtime
Active Sorting -- An Efficient Training of a Sorting Robot with Active Learning Techniques. Herde, Marek; Kottke, Daniel; Calma, Adrian; Bieshaar, Maarten; Deist, Stephan; Sick, Bernhard. In International Joint Conference on Neural Networks (IJCNN). IEEE, Rio de Janiero, Brazil, 2018.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{herde2018active, address = {Rio de Janiero, Brazil}, author = {Herde, Marek and Kottke, Daniel and Calma, Adrian and Bieshaar, Maarten and Deist, Stephan and Sick, Bernhard}, booktitle = {International Joint Conference on Neural Networks (IJCNN)}, keywords = {imported}, publisher = {IEEE}, title = {Active Sorting – An Efficient Training of a Sorting Robot with Active Learning Techniques}, year = 2018 }
%0 Conference Paper %1 herde2018active %A Herde, Marek %A Kottke, Daniel %A Calma, Adrian %A Bieshaar, Maarten %A Deist, Stephan %A Sick, Bernhard %B International Joint Conference on Neural Networks (IJCNN) %C Rio de Janiero, Brazil %D 2018 %I IEEE %R 10.1109/ijcnn.2018.8489161 %T Active Sorting -- An Efficient Training of a Sorting Robot with Active Learning Techniques
Active Learning with Realistic Data -- A Case Study. Calma, Adrian; Stolz, Moritz; Kottke, Daniel; Tomforde, Sven; Sick, Bernhard. In International Joint Conference on Neural Networks (IJCNN). IEEE, Rio de Janiero, Brazil, 2018.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{calma2018active, address = {Rio de Janiero, Brazil}, author = {Calma, Adrian and Stolz, Moritz and Kottke, Daniel and Tomforde, Sven and Sick, Bernhard}, booktitle = {International Joint Conference on Neural Networks (IJCNN)}, keywords = {imported}, publisher = {IEEE}, title = {Active Learning with Realistic Data – A Case Study}, year = 2018 }
%0 Conference Paper %1 calma2018active %A Calma, Adrian %A Stolz, Moritz %A Kottke, Daniel %A Tomforde, Sven %A Sick, Bernhard %B International Joint Conference on Neural Networks (IJCNN) %C Rio de Janiero, Brazil %D 2018 %I IEEE %R 10.1109/ijcnn.2018.8489394 %T Active Learning with Realistic Data -- A Case Study
A review of uncertainty representations and metaverification of uncertainty assessment techniques for renewable energies. Gensler, André; Sick, Bernhard; Vogt, Stephan. In Renewable and Sustainable Energy Reviews, 96, bll 352–379. Elsevier, 2018.
- [ BibTeX ]
- [ EndNote ]
@article{gensler2018review, author = {Gensler, Andr{\'e} and Sick, Bernhard and Vogt, Stephan}, journal = {Renewable and Sustainable Energy Reviews}, keywords = {imported}, pages = {352–379}, publisher = {Elsevier}, title = {A review of uncertainty representations and metaverification of uncertainty assessment techniques for renewable energies}, volume = 96, year = 2018 }
%0 Journal Article %1 gensler2018review %A Gensler, André %A Sick, Bernhard %A Vogt, Stephan %D 2018 %I Elsevier %J Renewable and Sustainable Energy Reviews %P 352--379 %R 10.1016/j.rser.2018.07.042 %T A review of uncertainty representations and metaverification of uncertainty assessment techniques for renewable energies %V 96
A Multi-Scheme Ensemble Using Coopetitive Soft-Gating With Application to Power Forecasting for Renewable Energy Generation. Gensler, André; Sick, Bernhard. In arXiv e-prints, bl arXiv:1803.06344. 2018.
- [ BibTeX ]
- [ EndNote ]
@article{gensler2018multi, author = {Gensler, Andr{\'e} and Sick, Bernhard}, journal = {arXiv e-prints}, keywords = {Machine}, pages = {arXiv:1803.06344}, title = {{A Multi-Scheme Ensemble Using Coopetitive Soft-Gating With Application to Power Forecasting for Renewable Energy Generation}}, year = 2018 }
%0 Journal Article %1 gensler2018multi %A Gensler, André %A Sick, Bernhard %D 2018 %J arXiv e-prints %P arXiv:1803.06344 %T A Multi-Scheme Ensemble Using Coopetitive Soft-Gating With Application to Power Forecasting for Renewable Energy Generation

2017[ to top ]

Where is my Device? Detecting the Smart Device’s Wearing Position in the Context of Active Safety for Vulnerable Road Users. Bieshaar, M. In Organic Computing -- Doctoral Dissertation Colloquium 2017, S. Tomforde, B. Sick (reds.), bll 27–37. kassel university press, Kassel, Germany, 2017.
- [ BibTeX ]
- [ EndNote ]
@incollection{bieshaar2017where, address = {Kassel, Germany}, author = {Bieshaar, M.}, booktitle = {Organic Computing – Doctoral Dissertation Colloquium 2017}, editor = {Tomforde, S. and Sick, B.}, keywords = {imported}, pages = {27–37}, publisher = {kassel university press}, title = {Where is my Device? Detecting the Smart Device's Wearing Position in the Context of Active Safety for Vulnerable Road Users}, year = 2017 }
%0 Book Section %1 bieshaar2017where %A Bieshaar, M. %B Organic Computing -- Doctoral Dissertation Colloquium 2017 %C Kassel, Germany %D 2017 %E Tomforde, S. %E Sick, B. %I kassel university press %P 27--37 %T Where is my Device? Detecting the Smart Device's Wearing Position in the Context of Active Safety for Vulnerable Road Users
Simulation of Annotators for Active Learning: Uncertain Oracles. Calma, Adrian; Sick, Bernhard. In Workshop on Interactive Adaptive Learning (IAL), ECML PKDD, CEUR Workshop Proceedings, bll 49–58. 2017.
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
@inproceedings{calma2017simulation, author = {Calma, Adrian and Sick, Bernhard}, booktitle = {Workshop on Interactive Adaptive Learning (IAL), ECML PKDD}, keywords = {imported}, pages = {49–58}, series = {CEUR Workshop Proceedings}, title = {Simulation of Annotators for Active Learning: Uncertain Oracles}, year = 2017 }
%0 Conference Paper %1 calma2017simulation %A Calma, Adrian %A Sick, Bernhard %B Workshop on Interactive Adaptive Learning (IAL), ECML PKDD %D 2017 %P 49--58 %T Simulation of Annotators for Active Learning: Uncertain Oracles %U http://ceur-ws.org/Vol-1924/ialatecml_paper4.pdf
Probabilistic wind power forecasting: A multi-scheme ensemble technique with gradual coopetitive soft gating. Gensler, A.; Sick, B. In IEEE Symposium Series on Computational Intelligence (SSCI), bll 1–10. IEEE, 2017.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{gensler2017probabilistic, author = {{Gensler}, A. and {Sick}, B.}, booktitle = {IEEE Symposium Series on Computational Intelligence (SSCI)}, keywords = {itegpub}, pages = {1–10}, publisher = {IEEE}, title = {Probabilistic wind power forecasting: A multi-scheme ensemble technique with gradual coopetitive soft gating}, year = 2017 }
%0 Conference Paper %1 gensler2017probabilistic %A Gensler, A. %A Sick, B. %B IEEE Symposium Series on Computational Intelligence (SSCI) %D 2017 %I IEEE %P 1--10 %R 10.1109/SSCI.2017.8285344 %T Probabilistic wind power forecasting: A multi-scheme ensemble technique with gradual coopetitive soft gating
Probabilistic Active Learning with Structure-Sensitive Kernels. Lang, Dominik; Kottke, Daniel; Krempl, Georg; Sick, Bernhard. In Workshop on Interactive Adaptive Learning (IAL), ECML PKDD, CEUR Workshop Proceedings, bll 37–48. 2017.
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
@inproceedings{lang2017probabilistic, author = {Lang, Dominik and Kottke, Daniel and Krempl, Georg and Sick, Bernhard}, booktitle = {Workshop on Interactive Adaptive Learning (IAL), ECML PKDD}, keywords = {imported}, pages = {37–48}, series = {CEUR Workshop Proceedings}, title = {Probabilistic Active Learning with Structure-Sensitive Kernels}, year = 2017 }
%0 Conference Paper %1 lang2017probabilistic %A Lang, Dominik %A Kottke, Daniel %A Krempl, Georg %A Sick, Bernhard %B Workshop on Interactive Adaptive Learning (IAL), ECML PKDD %D 2017 %P 37--48 %T Probabilistic Active Learning with Structure-Sensitive Kernels %U http://ceur-ws.org/Vol-1924/ialatecml_paper3.pdf
Performing event detection in time series with SwiftEvent: an algorithm with supervised learning of detection criteria. Gensler, A.; Sick, B. In Pattern Analysis and Applications, 21(2), bll 543–562. Springer, 2017.
- [ BibTeX ]
- [ EndNote ]
@article{gensler2017performing, author = {Gensler, A. and Sick, B.}, journal = {Pattern Analysis and Applications}, keywords = {imported}, number = 2, pages = {543–562}, publisher = {Springer}, title = {Performing event detection in time series with {SwiftEvent}: an algorithm with supervised learning of detection criteria}, volume = 21, year = 2017 }
%0 Journal Article %1 gensler2017performing %A Gensler, A. %A Sick, B. %D 2017 %I Springer %J Pattern Analysis and Applications %N 2 %P 543--562 %R 10.1007/s10044-017-0657-0 %T Performing event detection in time series with SwiftEvent: an algorithm with supervised learning of detection criteria %V 21
Organic Computing in the Spotlight. Tomforde, Sven; Sick, Bernhard; Müller-Schloer, Christian. In arXiv e-prints, bl arXiv:1701.08125. 2017.
- [ BibTeX ]
- [ EndNote ]
@article{tomforde2017organic, author = {{Tomforde}, Sven and {Sick}, Bernhard and {M{\"u}ller-Schloer}, Christian}, journal = {arXiv e-prints}, keywords = {Science}, pages = {arXiv:1701.08125}, title = {{Organic Computing in the Spotlight}}, year = 2017 }
%0 Journal Article %1 tomforde2017organic %A Tomforde, Sven %A Sick, Bernhard %A Müller-Schloer, Christian %D 2017 %J arXiv e-prints %P arXiv:1701.08125 %T Organic Computing in the Spotlight
Organic Computing -- Doctoral Dissertation Colloquium 2016. Tomforde, S.; Sick, B. In Vol. 10Intelligent Embedded Systems. kassel university press, 2017.
- [ BibTeX ]
- [ EndNote ]
@book{tomforde2017organica, editor = {Tomforde, S. and Sick, B.}, keywords = {imported}, publisher = {kassel university press}, series = {Intelligent Embedded Systems}, title = {Organic Computing – Doctoral Dissertation Colloquium 2016}, volume = 10, year = 2017 }
%0 Book %1 tomforde2017organica %B Intelligent Embedded Systems %D 2017 %E Tomforde, S. %E Sick, B. %I kassel university press %R 10.19211/KUP9783737603010 %T Organic Computing -- Doctoral Dissertation Colloquium 2016 %V 10
On Methodological and Technological Challenges for Proactive Health Management in Smart Homes. Wolf, J.-H.; Dehling, T.; Haux, R.; Sick, B.; Sunyaev, A.; Tomforde, S. In International Conference on Informatics, Management, and Technology in Healthcare (ICIMTH), bll 209–212. Athens, Greece, 2017.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{wolf2017methodological, address = {Athens, Greece}, author = {Wolf, J.-H. and Dehling, T. and Haux, R. and Sick, B. and Sunyaev, A. and Tomforde, S.}, booktitle = {International Conference on Informatics, Management, and Technology in Healthcare (ICIMTH)}, keywords = {imported}, pages = {209–212}, title = {On Methodological and Technological Challenges for Proactive Health Management in Smart Homes}, year = 2017 }
%0 Conference Paper %1 wolf2017methodological %A Wolf, J.-H. %A Dehling, T. %A Haux, R. %A Sick, B. %A Sunyaev, A. %A Tomforde, S. %B International Conference on Informatics, Management, and Technology in Healthcare (ICIMTH) %C Athens, Greece %D 2017 %P 209--212 %T On Methodological and Technological Challenges for Proactive Health Management in Smart Homes
Measuring Self Organisation at Runtime -- A Quantification Method based on Divergence Measures. Tomforde, S.; Kantert, J.; Sick, B. In International Conference on Agents and Artificial Intelligence (ICAART), bll 96–106. Porto, Portugal, 2017.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{tomforde2017measuring, address = {Porto, Portugal}, author = {Tomforde, S. and Kantert, J. and Sick, B.}, booktitle = {International Conference on Agents and Artificial Intelligence (ICAART)}, keywords = {imported}, pages = {96–106}, title = {Measuring Self Organisation at Runtime – A Quantification Method based on Divergence Measures}, year = 2017 }
%0 Conference Paper %1 tomforde2017measuring %A Tomforde, S. %A Kantert, J. %A Sick, B. %B International Conference on Agents and Artificial Intelligence (ICAART) %C Porto, Portugal %D 2017 %P 96--106 %R 10.5220/0006240400960106 %T Measuring Self Organisation at Runtime -- A Quantification Method based on Divergence Measures
Learning Without Ground Truth. Beyer, C.; Bieshaar, M.; Calma, A.; Heck, H.; Kottke, D.; Würtz, R. In Organic Computing -- Doctoral Dissertation Colloquium 2017, S. Tomforde, B. Sick (reds.). kassel university press, Bochum, Germany, 2017.
- [ BibTeX ]
- [ EndNote ]
@incollection{beyer2017learning, address = {Bochum, Germany}, author = {Beyer, C. and Bieshaar, M. and Calma, A. and Heck, H. and Kottke, D. and W{\"u}rtz, R.}, booktitle = {Organic Computing – Doctoral Dissertation Colloquium 2017}, editor = {Tomforde, S. and Sick, B.}, keywords = {imported}, publisher = {kassel university press}, title = {Learning Without Ground Truth}, year = 2017 }
%0 Book Section %1 beyer2017learning %A Beyer, C. %A Bieshaar, M. %A Calma, A. %A Heck, H. %A Kottke, D. %A Würtz, R. %B Organic Computing -- Doctoral Dissertation Colloquium 2017 %C Bochum, Germany %D 2017 %E Tomforde, S. %E Sick, B. %I kassel university press %T Learning Without Ground Truth
Learning to Learn: Dynamic Runtime Exploitation of Various Knowledge Sources and Machine Learning Paradigms. Calma, A.; Kottke, D.; Sick, B.; Tomforde, S. In Workshop on Self-Improving System Integration (SISSY), FAS*W, bll 109–116. IEEE, Tucson, AZ, 2017.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{calma2017learning, address = {Tucson, AZ}, author = {Calma, A. and Kottke, D. and Sick, B. and Tomforde, S.}, booktitle = {Workshop on Self-Improving System Integration (SISSY), FAS*W}, keywords = {imported}, pages = {109–116}, publisher = {IEEE}, title = {Learning to Learn: Dynamic Runtime Exploitation of Various Knowledge Sources and Machine Learning Paradigms}, year = 2017 }
%0 Conference Paper %1 calma2017learning %A Calma, A. %A Kottke, D. %A Sick, B. %A Tomforde, S. %B Workshop on Self-Improving System Integration (SISSY), FAS*W %C Tucson, AZ %D 2017 %I IEEE %P 109--116 %R 10.1109/fas-w.2017.129 %T Learning to Learn: Dynamic Runtime Exploitation of Various Knowledge Sources and Machine Learning Paradigms
Interactive Learning Without Ground Truth. Würtz, Rolf P.; Tomforde, Sven; Calma, Adrian; Kottke, Daniel; Sick, Bernhard. In Organic Computing -- Doctoral Dissertation Colloquium 2017, S. Tomforde, B. Sick (reds.), bll 1–4. kassel university press, Kassel, Germany, 2017.
- [ BibTeX ]
- [ EndNote ]
@incollection{wuertz2017interactive, address = {Kassel, Germany}, author = {Würtz, Rolf P. and Tomforde, Sven and Calma, Adrian and Kottke, Daniel and Sick, Bernhard}, booktitle = {Organic Computing – Doctoral Dissertation Colloquium 2017}, editor = {Tomforde, S. and Sick, B.}, keywords = {imported}, pages = {1–4}, publisher = {kassel university press}, title = {Interactive Learning Without Ground Truth}, year = 2017 }
%0 Book Section %1 wuertz2017interactive %A Würtz, Rolf P. %A Tomforde, Sven %A Calma, Adrian %A Kottke, Daniel %A Sick, Bernhard %B Organic Computing -- Doctoral Dissertation Colloquium 2017 %C Kassel, Germany %D 2017 %E Tomforde, S. %E Sick, B. %I kassel university press %P 1--4 %T Interactive Learning Without Ground Truth
Identifying Representative Load Time Series for Load Flow Calculations. Henze, Janosch; Kneiske, Tanja; Braun, Martin; Sick, Bernhard. In Workshop on Data Analytics for Renewable Energy Integration (DARE), ECML PKDD, bll 83–93. Springer, Cham, Switzerland, 2017.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
Power system analyses increasingly use annual time series for temporal and spatial assessment of operational and also planning aspects. These analyses are often limited due to the computational time of the large amount of load flow calculation. By introducing algorithms which are capable of generating shorter and representative time series of measured load or power generation time series, the calculation time for load flow calculations can be reduced. We present a method which is capable of extracting features from the time series and use those features to create a representative time series. Furthermore, we show that our method is capable of maintaining the most important statistical features of the original time series by applying a Fisher-Pitman Permutation test.
@inproceedings{henze2017identifying, abstract = {Power system analyses increasingly use annual time series for temporal and spatial assessment of operational and also planning aspects. These analyses are often limited due to the computational time of the large amount of load flow calculation. By introducing algorithms which are capable of generating shorter and representative time series of measured load or power generation time series, the calculation time for load flow calculations can be reduced. We present a method which is capable of extracting features from the time series and use those features to create a representative time series. Furthermore, we show that our method is capable of maintaining the most important statistical features of the original time series by applying a Fisher-Pitman Permutation test.}, address = {Cham, Switzerland}, author = {Henze, Janosch and Kneiske, Tanja and Braun, Martin and Sick, Bernhard}, booktitle = {Workshop on Data Analytics for Renewable Energy Integration (DARE), ECML PKDD}, keywords = {imported}, pages = {83–93}, publisher = {Springer}, title = {Identifying Representative Load Time Series for Load Flow Calculations}, year = 2017 }
%0 Conference Paper %1 henze2017identifying %A Henze, Janosch %A Kneiske, Tanja %A Braun, Martin %A Sick, Bernhard %B Workshop on Data Analytics for Renewable Energy Integration (DARE), ECML PKDD %C Cham, Switzerland %D 2017 %I Springer %P 83--93 %R 10.1007/978-3-319-71643-5_8 %T Identifying Representative Load Time Series for Load Flow Calculations %X Power system analyses increasingly use annual time series for temporal and spatial assessment of operational and also planning aspects. These analyses are often limited due to the computational time of the large amount of load flow calculation. By introducing algorithms which are capable of generating shorter and representative time series of measured load or power generation time series, the calculation time for load flow calculations can be reduced. We present a method which is capable of extracting features from the time series and use those features to create a representative time series. Furthermore, we show that our method is capable of maintaining the most important statistical features of the original time series by applying a Fisher-Pitman Permutation test.
Highly Autonomous Learning in Collaborative, Technical Systems. Gruhl, C. In Organic Computing -- Doctoral Dissertation Colloquium 2017, S. Tomforde, B. Sick (reds.). kassel university press, Kassel, Germany, 2017.
- [ BibTeX ]
- [ EndNote ]
@incollection{gruhl2017highly, address = {Kassel, Germany}, author = {Gruhl, C.}, booktitle = {Organic Computing – Doctoral Dissertation Colloquium 2017}, editor = {Tomforde, S. and Sick, B.}, keywords = {imported}, publisher = {kassel university press}, series = {Intelligent Embedded Systems}, title = {Highly Autonomous Learning in Collaborative, Technical Systems}, year = 2017 }
%0 Book Section %1 gruhl2017highly %A Gruhl, C. %B Organic Computing -- Doctoral Dissertation Colloquium 2017 %C Kassel, Germany %D 2017 %E Tomforde, S. %E Sick, B. %I kassel university press %T Highly Autonomous Learning in Collaborative, Technical Systems
Enhanced Probabilistic Active Learning: Cost-sensitive, Unbalanced, Time-variant, Self-optimising, and Parameter-free. Kottke, Daniel. In Organic Computing -- Doctoral Dissertation Colloquium 2017, S. Tomforde, B. Sick (reds.), bll 67–78. kassel university press, Kassel, Germany, 2017.
- [ BibTeX ]
- [ EndNote ]
@incollection{kottke2017enhanced, address = {Kassel, Germany}, author = {Kottke, Daniel}, booktitle = {Organic Computing – Doctoral Dissertation Colloquium 2017}, editor = {Tomforde, S. and Sick, B.}, keywords = {imported}, pages = {67–78}, publisher = {kassel university press}, title = {Enhanced Probabilistic Active Learning: Cost-sensitive, Unbalanced, Time-variant, Self-optimising, and Parameter-free}, year = 2017 }
%0 Book Section %1 kottke2017enhanced %A Kottke, Daniel %B Organic Computing -- Doctoral Dissertation Colloquium 2017 %C Kassel, Germany %D 2017 %E Tomforde, S. %E Sick, B. %I kassel university press %P 67--78 %T Enhanced Probabilistic Active Learning: Cost-sensitive, Unbalanced, Time-variant, Self-optimising, and Parameter-free
Detecting Intentions of Vulnerable Road Users Based on Collective Intelligence. Bieshaar, M.; Reitberger, G.; Zernetsch, S.; Sick, B.; Fuchs, E.; Doll, K. In Automatisiertes und vernetztes Fahren Symposium (AAET), bll 67–87. Braunschweig, Germany, 2017.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{bieshaar2017detecting, address = {Braunschweig, Germany}, author = {Bieshaar, M. and Reitberger, G. and Zernetsch, S. and Sick, B. and Fuchs, E. and Doll, K.}, booktitle = {Automatisiertes und vernetztes Fahren Symposium (AAET)}, keywords = {imported}, pages = {67–87}, title = {Detecting Intentions of Vulnerable Road Users Based on Collective Intelligence}, year = 2017 }
%0 Conference Paper %1 bieshaar2017detecting %A Bieshaar, M. %A Reitberger, G. %A Zernetsch, S. %A Sick, B. %A Fuchs, E. %A Doll, K. %B Automatisiertes und vernetztes Fahren Symposium (AAET) %C Braunschweig, Germany %D 2017 %P 67--87 %T Detecting Intentions of Vulnerable Road Users Based on Collective Intelligence
Dealing with class imbalance the scalable way: Evaluation of various techniques based on classification grade and computational complexity. Schlegel, Bernhard; Sick, Bernhard. In Workshop on Data Science and Big Data Analytics (DSBDA), ICDM, bll 69–78. IEEE, 2017.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{schlegel2017dealing, author = {Schlegel, Bernhard and Sick, Bernhard}, booktitle = {Workshop on Data Science and Big Data Analytics (DSBDA), ICDM}, keywords = {imported}, pages = {69–78}, publisher = {IEEE}, title = {Dealing with class imbalance the scalable way: Evaluation of various techniques based on classification grade and computational complexity}, year = 2017 }
%0 Conference Paper %1 schlegel2017dealing %A Schlegel, Bernhard %A Sick, Bernhard %B Workshop on Data Science and Big Data Analytics (DSBDA), ICDM %D 2017 %I IEEE %P 69--78 %R 10.1109/icdmw.2017.16 %T Dealing with class imbalance the scalable way: Evaluation of various techniques based on classification grade and computational complexity
Cooperative Starting Intention Detection of Cyclists Based on Smart Devices and Infrastructure. Bieshaar, M.; Zernetsch, S.; Depping, M.; Sick, B.; Doll, K. In IEEE International Conference on Intelligent Transportation Systems (ITSC). IEEE, Yokohama, Japan, 2017.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{bieshaar2017cooperative, address = {Yokohama, Japan}, author = {Bieshaar, M. and Zernetsch, S. and Depping, M. and Sick, B. and Doll, K.}, booktitle = {IEEE International Conference on Intelligent Transportation Systems (ITSC)}, keywords = {imported}, publisher = {IEEE}, title = {Cooperative Starting Intention Detection of Cyclists Based on Smart Devices and Infrastructure}, year = 2017 }
%0 Conference Paper %1 bieshaar2017cooperative %A Bieshaar, M. %A Zernetsch, S. %A Depping, M. %A Sick, B. %A Doll, K. %B IEEE International Conference on Intelligent Transportation Systems (ITSC) %C Yokohama, Japan %D 2017 %I IEEE %R 10.1109/itsc.2017.8317691 %T Cooperative Starting Intention Detection of Cyclists Based on Smart Devices and Infrastructure
Challenges of Reliable, Realistic and Comparable Active Learning Evaluation. Kottke, Daniel; Calma, Adrian; Huseljic, Denis; Krempl, Georg; Sick, Bernhard. In Workshop on Interactive Adaptive Learning (IAL), ECML PKDD, CEUR Workshop Proceedings, bll 2–14. 2017.
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
@inproceedings{kottke2017challenges, author = {Kottke, Daniel and Calma, Adrian and Huseljic, Denis and Krempl, Georg and Sick, Bernhard}, booktitle = {Workshop on Interactive Adaptive Learning (IAL), ECML PKDD}, keywords = {imported}, pages = {2–14}, series = {CEUR Workshop Proceedings}, title = {Challenges of Reliable, Realistic and Comparable Active Learning Evaluation}, year = 2017 }
%0 Conference Paper %1 kottke2017challenges %A Kottke, Daniel %A Calma, Adrian %A Huseljic, Denis %A Krempl, Georg %A Sick, Bernhard %B Workshop on Interactive Adaptive Learning (IAL), ECML PKDD %D 2017 %P 2--14 %T Challenges of Reliable, Realistic and Comparable Active Learning Evaluation %U http://ceur-ws.org/Vol-1924/ialatecml_paper0.pdf
Case Study on Pool-based Active Learning with Human Oracles. Calma, A. In Organic Computing -- Doctoral Dissertation Colloquium 2017, S. Tomforde, B. Sick (reds.), bll 39–49. kassel university press, Kassel, Germany, 2017.
- [ BibTeX ]
- [ EndNote ]
@incollection{calma2017case, address = {Kassel, Germany}, author = {Calma, A.}, booktitle = {Organic Computing – Doctoral Dissertation Colloquium 2017}, editor = {Tomforde, S. and Sick, B.}, keywords = {imported}, pages = {39–49}, publisher = {kassel university press}, title = {Case Study on Pool-based Active Learning with Human Oracles}, year = 2017 }
%0 Book Section %1 calma2017case %A Calma, A. %B Organic Computing -- Doctoral Dissertation Colloquium 2017 %C Kassel, Germany %D 2017 %E Tomforde, S. %E Sick, B. %I kassel university press %P 39--49 %T Case Study on Pool-based Active Learning with Human Oracles

2016[ to top ]

Trajectory Prediction of Cyclists Using a Physical Model and an Artificial Neural Network. Zernetsch, S.; Kohnen, S.; Goldhammer, M.; Doll, K.; Sick, B. In IEEE Intelligent Vehicles Symposium (IV), bll 833–838. IEEE, Gothenburg, Sweden, 2016.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{zernetsch2016trajectory, address = {Gothenburg, Sweden}, author = {Zernetsch, S. and Kohnen, S. and Goldhammer, M. and Doll, K. and Sick, B.}, booktitle = {IEEE Intelligent Vehicles Symposium (IV)}, keywords = {imported}, pages = {833–838}, publisher = {IEEE}, title = {Trajectory Prediction of Cyclists Using a Physical Model and an {Artificial Neural Network}}, year = 2016 }
%0 Conference Paper %1 zernetsch2016trajectory %A Zernetsch, S. %A Kohnen, S. %A Goldhammer, M. %A Doll, K. %A Sick, B. %B IEEE Intelligent Vehicles Symposium (IV) %C Gothenburg, Sweden %D 2016 %I IEEE %P 833--838 %R 10.1109/ivs.2016.7535484 %T Trajectory Prediction of Cyclists Using a Physical Model and an Artificial Neural Network
Towards Self-Improving Activity Recognition Systems based on Probabilistic, Generative Models. Jänicke, M.; Tomforde, S.; Sick, B. In Workshop on Self-Improving System Integration (SISSY), ICAC, bll 285–291. IEEE, Würzburg, Germany, 2016.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{jaenicke2016towards, address = {W{\"u}rzburg, Germany}, author = {J{\"a}nicke, M. and Tomforde, S. and Sick, B.}, booktitle = {Workshop on Self-Improving System Integration (SISSY), ICAC}, keywords = {imported}, pages = {285–291}, publisher = {IEEE}, title = {Towards Self-Improving Activity Recognition Systems based on Probabilistic, Generative Models}, year = 2016 }
%0 Conference Paper %1 jaenicke2016towards %A Jänicke, M. %A Tomforde, S. %A Sick, B. %B Workshop on Self-Improving System Integration (SISSY), ICAC %C Würzburg, Germany %D 2016 %I IEEE %P 285--291 %R 10.1109/icac.2016.22 %T Towards Self-Improving Activity Recognition Systems based on Probabilistic, Generative Models
Towards Autonomous Self-tests at Runtime. Heck, H.; Wacker, A.; Rudolph, S.; Gruhl, C.; Sick, B.; Tomforde, S. In IEEE International Workshop on Quality Assurance for Self-Adaptive, Self-Organising Systems (QA4SASO), FAS*W, bll 98–99. IEEE, 2016.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{heck2016towards, author = {Heck, H. and Wacker, A. and Rudolph, S. and Gruhl, C. and Sick, B. and Tomforde, S.}, booktitle = {IEEE International Workshop on Quality Assurance for Self-Adaptive, Self-Organising Systems (QA4SASO), FAS*W}, keywords = {imported}, pages = {98–99}, publisher = {IEEE}, title = {Towards Autonomous Self-tests at Runtime}, year = 2016 }
%0 Conference Paper %1 heck2016towards %A Heck, H. %A Wacker, A. %A Rudolph, S. %A Gruhl, C. %A Sick, B. %A Tomforde, S. %B IEEE International Workshop on Quality Assurance for Self-Adaptive, Self-Organising Systems (QA4SASO), FAS*W %D 2016 %I IEEE %P 98--99 %R 10.1109/fas-w.2016.32 %T Towards Autonomous Self-tests at Runtime
Towards Automation of Knowledge Understanding: An Approach for Probabilistic Generative Classifiers. Fisch, D.; Gruhl, C.; Kalkowski, E.; Sick, B.; Ovaska, S. J. In Information Sciences, 370--371, bll 476–496. Elsevier, 2016.
- [ BibTeX ]
- [ EndNote ]
@article{fisch2016towards, author = {Fisch, D. and Gruhl, C. and Kalkowski, E. and Sick, B. and Ovaska, S. J.}, journal = {Information Sciences}, keywords = {imported}, pages = {476–496}, publisher = {Elsevier}, title = {Towards Automation of Knowledge Understanding: An Approach for Probabilistic Generative Classifiers}, volume = {370–371}, year = 2016 }
%0 Journal Article %1 fisch2016towards %A Fisch, D. %A Gruhl, C. %A Kalkowski, E. %A Sick, B. %A Ovaska, S. J. %D 2016 %I Elsevier %J Information Sciences %P 476--496 %R 10.1016/j.ins.2016.08.016 %T Towards Automation of Knowledge Understanding: An Approach for Probabilistic Generative Classifiers %V 370--371
Semi-Supervised Active Learning for Support Vector Machines: A Novel Approach that Exploits Structure Information in Data. Reitmaier, Tobias; Calma, Adrian; Sick, Bernhard. In arXiv e-prints, bl arXiv:1610.03995. 2016.
- [ BibTeX ]
- [ EndNote ]
@article{reitmaier2016semi, author = {{Reitmaier}, Tobias and {Calma}, Adrian and {Sick}, Bernhard}, journal = {arXiv e-prints}, keywords = {Machine}, pages = {arXiv:1610.03995}, title = {{Semi-Supervised Active Learning for Support Vector Machines: A Novel Approach that Exploits Structure Information in Data}}, year = 2016 }
%0 Journal Article %1 reitmaier2016semi %A Reitmaier, Tobias %A Calma, Adrian %A Sick, Bernhard %D 2016 %J arXiv e-prints %P arXiv:1610.03995 %T Semi-Supervised Active Learning for Support Vector Machines: A Novel Approach that Exploits Structure Information in Data
Resp-kNN: A probabilistic k-nearest neighbor classifier for sparsely labeled data. Calma, A.; Reitmaier, T.; Sick, B. In International Joint Conference on Neural Networks (IJCNN), bll 4040–4047. IEEE, Vancouver, BC, 2016.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{calma2016resp, address = {Vancouver, BC}, author = {Calma, A. and Reitmaier, T. and Sick, B.}, booktitle = {International Joint Conference on Neural Networks (IJCNN)}, keywords = {imported}, pages = {4040–4047}, publisher = {IEEE}, title = {{Resp-kNN}: A probabilistic k-nearest neighbor classifier for sparsely labeled data}, year = 2016 }
%0 Conference Paper %1 calma2016resp %A Calma, A. %A Reitmaier, T. %A Sick, B. %B International Joint Conference on Neural Networks (IJCNN) %C Vancouver, BC %D 2016 %I IEEE %P 4040--4047 %R 10.1109/ijcnn.2016.7727725 %T Resp-kNN: A probabilistic k-nearest neighbor classifier for sparsely labeled data
Probabilistic Obsoleteness Detection for Gaussian Mixture Models. Gruhl, C. In Organic Computing -- Doctoral Dissertation Colloquium 2016, S. Tomforde, B. Sick (reds.), bll 45–56. kassel university press, Kassel, Germany, 2016.
- [ BibTeX ]
- [ EndNote ]
@incollection{gruhl2016probabilistic, address = {Kassel, Germany}, author = {Gruhl, C.}, booktitle = {Organic Computing – Doctoral Dissertation Colloquium 2016}, editor = {Tomforde, S. and Sick, B.}, keywords = {imported}, pages = {45–56}, publisher = {kassel university press}, title = {Probabilistic Obsoleteness Detection for Gaussian Mixture Models}, year = 2016 }
%0 Book Section %1 gruhl2016probabilistic %A Gruhl, C. %B Organic Computing -- Doctoral Dissertation Colloquium 2016 %C Kassel, Germany %D 2016 %E Tomforde, S. %E Sick, B. %I kassel university press %P 45--56 %T Probabilistic Obsoleteness Detection for Gaussian Mixture Models
Pals: Interactive Pool-based Active Learning System with Uncertain Oracles. Calma, A. In Organic Computing -- Doctoral Dissertation Colloquium 2016, B. Sick, S. Tomforde (reds.), bll 35–44. kassel university press, Kassel, Germany, 2016.
- [ BibTeX ]
- [ EndNote ]
@incollection{calma2016pals, address = {Kassel, Germany}, author = {Calma, A.}, booktitle = {Organic Computing – Doctoral Dissertation Colloquium 2016}, editor = {Sick, B. and Tomforde, S.}, keywords = {imported}, pages = {35–44}, publisher = {kassel university press}, title = {Pals: Interactive Pool-based Active Learning System with Uncertain Oracles}, year = 2016 }
%0 Book Section %1 calma2016pals %A Calma, A. %B Organic Computing -- Doctoral Dissertation Colloquium 2016 %C Kassel, Germany %D 2016 %E Sick, B. %E Tomforde, S. %I kassel university press %P 35--44 %T Pals: Interactive Pool-based Active Learning System with Uncertain Oracles
Generative Exponential Smoothing and Generative ARMA Models to Forecast Time-Variant Rates or Probabilities. Kalkowski, E.; Sick, B. In International Work-Conference on Time Series (ITISE): Selected Contributions, bll 75–88. Springer, Cham, Switzerland, 2016.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{kalkowski2016generative, address = {Cham, Switzerland}, author = {Kalkowski, E. and Sick, B.}, booktitle = {International Work-Conference on Time Series (ITISE): Selected Contributions}, keywords = {imported}, pages = {75–88}, publisher = {Springer}, title = {Generative Exponential Smoothing and Generative {ARMA} Models to Forecast Time-Variant Rates or Probabilities}, year = 2016 }
%0 Conference Paper %1 kalkowski2016generative %A Kalkowski, E. %A Sick, B. %B International Work-Conference on Time Series (ITISE): Selected Contributions %C Cham, Switzerland %D 2016 %I Springer %P 75--88 %R 10.1007/978-3-319-28725-6_6 %T Generative Exponential Smoothing and Generative ARMA Models to Forecast Time-Variant Rates or Probabilities
Forecasting Wind Power -- An Ensemble Technique With Gradual Coopetitive Weighting Based on Weather Situation. Gensler, A.; Sick, B. In International Joint Conference on Neural Networks (IJCNN), bll 4976–4984. IEEE, Vancouver, BC, 2016.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{gensler2016forecasting, address = {Vancouver, BC}, author = {Gensler, A. and Sick, B.}, booktitle = {International Joint Conference on Neural Networks (IJCNN)}, keywords = {imported}, pages = {4976–4984}, publisher = {IEEE}, title = {Forecasting Wind Power – An Ensemble Technique With Gradual Coopetitive Weighting Based on Weather Situation}, year = 2016 }
%0 Conference Paper %1 gensler2016forecasting %A Gensler, A. %A Sick, B. %B International Joint Conference on Neural Networks (IJCNN) %C Vancouver, BC %D 2016 %I IEEE %P 4976--4984 %R 10.1109/ijcnn.2016.7727855 %T Forecasting Wind Power -- An Ensemble Technique With Gradual Coopetitive Weighting Based on Weather Situation
Exploit the Potential of the Group: Putting Humans in the Dedicated Collaborative Interactive Learning Loop. Calma, A. In Organic Computing -- Doctoral Dissertation Colloquium 2016, B. Sick, S. Tomforde (reds.). kassel university press, Kassel, Germany, 2016.
- [ BibTeX ]
- [ EndNote ]
@incollection{calma2016exploit, address = {Kassel, Germany}, author = {Calma, A.}, booktitle = {Organic Computing – Doctoral Dissertation Colloquium 2016}, editor = {Sick, B. and Tomforde, S.}, keywords = {imported}, publisher = {kassel university press}, title = {Exploit the Potential of the Group: Putting Humans in the Dedicated Collaborative Interactive Learning Loop}, year = 2016 }
%0 Book Section %1 calma2016exploit %A Calma, A. %B Organic Computing -- Doctoral Dissertation Colloquium 2016 %C Kassel, Germany %D 2016 %E Sick, B. %E Tomforde, S. %I kassel university press %T Exploit the Potential of the Group: Putting Humans in the Dedicated Collaborative Interactive Learning Loop
Design and optimization of an autonomous feature selection pipeline for high dimensional, heterogeneous feature spaces. Schlegel, B.; Sick, B. In IEEE Symposium Series on Computational Intelligence (SSCI), bll 1–9. IEEE, Athens, Greece, 2016.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{schlegel2016design, address = {Athens, Greece}, author = {Schlegel, B. and Sick, B.}, booktitle = {IEEE Symposium Series on Computational Intelligence (SSCI)}, keywords = {imported}, pages = {1–9}, publisher = {IEEE}, title = {Design and optimization of an autonomous feature selection pipeline for high dimensional, heterogeneous feature spaces}, year = 2016 }
%0 Conference Paper %1 schlegel2016design %A Schlegel, B. %A Sick, B. %B IEEE Symposium Series on Computational Intelligence (SSCI) %C Athens, Greece %D 2016 %I IEEE %P 1--9 %R 10.1109/ssci.2016.7850092 %T Design and optimization of an autonomous feature selection pipeline for high dimensional, heterogeneous feature spaces
Deep Learning for Solar Power Forecasting -- An Approach using Autoencoder and LSTM Neural Networks. Gensler, A.; Henze, J.; Sick, B.; Raabe, N. In IEEE International Conference on Systems, Man and Cybernetics (SMC), bll 2858–2865. IEEE, Budapest, Hungary, 2016.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{gensler2016deep, address = {Budapest, Hungary}, author = {Gensler, A. and Henze, J. and Sick, B. and Raabe, N.}, booktitle = {IEEE International Conference on Systems, Man and Cybernetics (SMC)}, keywords = {imported}, pages = {2858–2865}, publisher = {IEEE}, title = {Deep Learning for Solar Power Forecasting – An Approach using Autoencoder and {LSTM} Neural Networks}, year = 2016 }
%0 Conference Paper %1 gensler2016deep %A Gensler, A. %A Henze, J. %A Sick, B. %A Raabe, N. %B IEEE International Conference on Systems, Man and Cybernetics (SMC) %C Budapest, Hungary %D 2016 %I IEEE %P 2858--2865 %R 10.1109/smc.2016.7844673 %T Deep Learning for Solar Power Forecasting -- An Approach using Autoencoder and LSTM Neural Networks
Correlation of Ontology-Based Semantic Similarity and Human Judgement for a Domain Specific Fashion Ontology. Kalkowski, E.; Sick, B. In International Conference on Web Engineering (ICWE), bll 207–224. Springer, 2016.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{kalkowski2016correlation, author = {Kalkowski, E. and Sick, B.}, booktitle = {International Conference on Web Engineering (ICWE)}, keywords = {imported}, pages = {207–224}, publisher = {Springer}, title = {Correlation of Ontology-Based Semantic Similarity and Human Judgement for a Domain Specific Fashion Ontology}, year = 2016 }
%0 Conference Paper %1 kalkowski2016correlation %A Kalkowski, E. %A Sick, B. %B International Conference on Web Engineering (ICWE) %D 2016 %I Springer %P 207--224 %R 10.1007/978-3-319-38791-8_12 %T Correlation of Ontology-Based Semantic Similarity and Human Judgement for a Domain Specific Fashion Ontology
Coping with variability in motion based activity recognition. Kreil, M.; Sick, B.; Lukowicz, P. In International Workshop on Sensor-based Activity Recognition and Interaction (iWOAR), bll 1–8. Rostock, Germany, 2016.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{kreil2016coping, address = {Rostock, Germany}, author = {Kreil, M. and Sick, B. and Lukowicz, P.}, booktitle = {International Workshop on Sensor-based Activity Recognition and Interaction (iWOAR)}, keywords = {imported}, pages = {1–8}, title = {Coping with variability in motion based activity recognition}, year = 2016 }
%0 Conference Paper %1 kreil2016coping %A Kreil, M. %A Sick, B. %A Lukowicz, P. %B International Workshop on Sensor-based Activity Recognition and Interaction (iWOAR) %C Rostock, Germany %D 2016 %P 1--8 %R 10.1145/2948963.2948967 %T Coping with variability in motion based activity recognition
Combinations of uncertain ordinal expert statements: The combination rule EIDMR and its application to low-voltage grid classification with SVM. Breker, S.; Sick, B. In International Joint Conference on Neural Networks (IJCNN), bll 2164–2173. IEEE, Vancouver, BC, 2016.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{breker2016combinations, address = {Vancouver, BC}, author = {Breker, S. and Sick, B.}, booktitle = {International Joint Conference on Neural Networks (IJCNN)}, keywords = {imported}, pages = {2164–2173}, publisher = {IEEE}, title = {Combinations of uncertain ordinal expert statements: The combination rule {EIDMR} and its application to low-voltage grid classification with {SVM}}, year = 2016 }
%0 Conference Paper %1 breker2016combinations %A Breker, S. %A Sick, B. %B International Joint Conference on Neural Networks (IJCNN) %C Vancouver, BC %D 2016 %I IEEE %P 2164--2173 %R 10.1109/ijcnn.2016.7727467 %T Combinations of uncertain ordinal expert statements: The combination rule EIDMR and its application to low-voltage grid classification with SVM
An Analog Ensemble-Based Similarity Search Technique for Solar Power Forecasting. Gensler, A.; Sick, B.; Pankraz, V. In IEEE International Conference on Systems, Man and Cybernetics (SMC), bll 2850–2857. IEEE, 2016.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{gensler2016analog, author = {Gensler, A. and Sick, B. and Pankraz, V.}, booktitle = {IEEE International Conference on Systems, Man and Cybernetics (SMC)}, keywords = {imported}, pages = {2850–2857}, publisher = {IEEE}, title = {An Analog Ensemble-Based Similarity Search Technique for Solar Power Forecasting}, year = 2016 }
%0 Conference Paper %1 gensler2016analog %A Gensler, A. %A Sick, B. %A Pankraz, V. %B IEEE International Conference on Systems, Man and Cybernetics (SMC) %D 2016 %I IEEE %P 2850--2857 %R 10.1109/SMC.2016.7844672 %T An Analog Ensemble-Based Similarity Search Technique for Solar Power Forecasting
A Review of Deterministic Error Scores and Normalization Techniques for Power Forecasting Algorithms. Gensler, A.; Sick, B.; Vogt, S. In IEEE Symposium Series on Computational Intelligence (SSCI), bll 1–9. IEEE, Athens, Greece, 2016.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{gensler2016review, address = {Athens, Greece}, author = {Gensler, A. and Sick, B. and Vogt, S.}, booktitle = {IEEE Symposium Series on Computational Intelligence (SSCI)}, keywords = {imported}, pages = {1–9}, publisher = {IEEE}, title = {A Review of Deterministic Error Scores and Normalization Techniques for Power Forecasting Algorithms}, year = 2016 }
%0 Conference Paper %1 gensler2016review %A Gensler, A. %A Sick, B. %A Vogt, S. %B IEEE Symposium Series on Computational Intelligence (SSCI) %C Athens, Greece %D 2016 %I IEEE %P 1--9 %R 10.1109/ssci.2016.7849848 %T A Review of Deterministic Error Scores and Normalization Techniques for Power Forecasting Algorithms

2015[ to top ]

Using Ontology-Based Similarity Measures to Find Training Data for Problems with Sparse Data. Kalkowski, E.; Sick, B. In IEEE International Conference on Systems, Man and Cybernetics (SMC), bll 1693–1699. IEEE, Hongkong, China, 2015.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{kalkowski2015using, address = {Hongkong, China}, author = {Kalkowski, E. and Sick, B.}, booktitle = {IEEE International Conference on Systems, Man and Cybernetics (SMC)}, keywords = {imported}, pages = {1693–1699}, publisher = {IEEE}, title = {Using Ontology-Based Similarity Measures to Find Training Data for Problems with Sparse Data}, year = 2015 }
%0 Conference Paper %1 kalkowski2015using %A Kalkowski, E. %A Sick, B. %B IEEE International Conference on Systems, Man and Cybernetics (SMC) %C Hongkong, China %D 2015 %I IEEE %P 1693--1699 %R 10.1109/smc.2015.298 %T Using Ontology-Based Similarity Measures to Find Training Data for Problems with Sparse Data
Transductive active learning -- A new semi-supervised learning approach based on iteratively refined generative models to capture structure in data. Reitmaier, T.; Calma, A.; Sick, B. In Information Sciences, 293, bll 275–298. Elsevier, 2015.
- [ BibTeX ]
- [ EndNote ]
@article{reitmaier2015transductive, author = {Reitmaier, T. and Calma, A. and Sick, B.}, journal = {Information Sciences}, keywords = {imported}, pages = {275–298}, publisher = {Elsevier}, title = {Transductive active learning – A new semi-supervised learning approach based on iteratively refined generative models to capture structure in data}, volume = 293, year = 2015 }
%0 Journal Article %1 reitmaier2015transductive %A Reitmaier, T. %A Calma, A. %A Sick, B. %D 2015 %I Elsevier %J Information Sciences %P 275--298 %R 10.1016/j.ins.2014.09.009 %T Transductive active learning -- A new semi-supervised learning approach based on iteratively refined generative models to capture structure in data %V 293
Track-Based Forecasting of Pedestrian Behavior by Polynomial Approximation and Multilayer Perceptions. Goldhammer, M.; Köhler, S.; Doll, K.; Sick, B. In SAI Intelligent Systems Conference (IntelliSys), Studies in Computational Intelligence, bll 259–279. Springer, Cham, Switzerland, 2015.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{goldhammer2015track, address = {Cham, Switzerland}, author = {Goldhammer, M. and K{\"o}hler, S. and Doll, K. and Sick, B.}, booktitle = {SAI Intelligent Systems Conference (IntelliSys)}, keywords = {imported}, pages = {259–279}, publisher = {Springer}, series = {Studies in Computational Intelligence}, title = {Track-Based Forecasting of Pedestrian Behavior by Polynomial Approximation and Multilayer Perceptions}, year = 2015 }
%0 Conference Paper %1 goldhammer2015track %A Goldhammer, M. %A Köhler, S. %A Doll, K. %A Sick, B. %B SAI Intelligent Systems Conference (IntelliSys) %C Cham, Switzerland %D 2015 %I Springer %P 259--279 %R 10.1007/978-3-319-33386-1_13 %T Track-Based Forecasting of Pedestrian Behavior by Polynomial Approximation and Multilayer Perceptions
The Responsibility Weighted Mahalanobis Kernel for Semi-Supervised Training of Support Vector Machines for Classification. Reitmaier, T.; Sick, B. In Information Sciences, 323, bll 179–198. Elsevier, 2015.
- [ BibTeX ]
- [ EndNote ]
@article{reitmaier2015responsibility, author = {Reitmaier, T. and Sick, B.}, journal = {Information Sciences}, keywords = {imported}, pages = {179–198}, publisher = {Elsevier}, title = {The Responsibility Weighted {M}ahalanobis Kernel for Semi-Supervised Training of Support Vector Machines for Classification}, volume = 323, year = 2015 }
%0 Journal Article %1 reitmaier2015responsibility %A Reitmaier, T. %A Sick, B. %D 2015 %I Elsevier %J Information Sciences %P 179--198 %R 10.1016/j.ins.2015.06.027 %T The Responsibility Weighted Mahalanobis Kernel for Semi-Supervised Training of Support Vector Machines for Classification %V 323
Self-adapting Multi-Sensor System Using Classifiers Based on Gaussian Mixture Models. Jänicke, M. In Organic Computing -- Doctoral Dissertation Colloquium 2015, S. Tomforde, B. Sick (reds.), bll 109–120. kassel university press, Kassel, Germany, 2015.
- [ BibTeX ]
- [ EndNote ]
@incollection{jaenicke2015self, address = {Kassel, Germany}, author = {J{\"a}nicke, M.}, booktitle = {Organic Computing – Doctoral Dissertation Colloquium 2015}, editor = {Tomforde, S. and Sick, B.}, keywords = {imported}, pages = {109–120}, publisher = {kassel university press}, title = {Self-adapting Multi-Sensor System Using Classifiers Based on Gaussian Mixture Models}, year = 2015 }
%0 Book Section %1 jaenicke2015self %A Jänicke, M. %B Organic Computing -- Doctoral Dissertation Colloquium 2015 %C Kassel, Germany %D 2015 %E Tomforde, S. %E Sick, B. %I kassel university press %P 109--120 %T Self-adapting Multi-Sensor System Using Classifiers Based on Gaussian Mixture Models
Organic Computing -- Doctoral Dissertation Colloquium 2015. Tomforde, S.; Sick, B. In Vol. 7Intelligent Embedded Systems. kassel university press, 2015.
- [ BibTeX ]
- [ EndNote ]
@book{tomforde2015organic, editor = {Tomforde, S. and Sick, B.}, keywords = {imported}, publisher = {kassel university press}, series = {Intelligent Embedded Systems}, title = {Organic Computing – Doctoral Dissertation Colloquium 2015}, volume = 7, year = 2015 }
%0 Book %1 tomforde2015organic %B Intelligent Embedded Systems %D 2015 %E Tomforde, S. %E Sick, B. %I kassel university press %R 10.19211/KUP9783737600293 %T Organic Computing -- Doctoral Dissertation Colloquium 2015 %V 7
On the Application Possibilities of Organic Computing Principles in Socio-technical Systems. Heck, H.; Edenhofer, S.; Gruhl, C.; Lund, A.; Shuka, R.; Hähner, J. In Organic Computing -- Doctoral Dissertation Colloquium 2015, S. Tomforde, B. Sick (reds.), bll 165–170. kassel university press, Kassel, Germany, 2015.
- [ BibTeX ]
- [ EndNote ]
@incollection{heck2015application, address = {Kassel, Germany}, author = {Heck, H. and Edenhofer, S. and Gruhl, C. and Lund, A. and Shuka, R. and H{\"a}hner, J.}, booktitle = {Organic Computing – Doctoral Dissertation Colloquium 2015}, editor = {Tomforde, S. and Sick, B.}, keywords = {imported}, pages = {165–170}, publisher = {kassel university press}, title = {On the Application Possibilities of Organic Computing Principles in Socio-technical Systems}, year = 2015 }
%0 Book Section %1 heck2015application %A Heck, H. %A Edenhofer, S. %A Gruhl, C. %A Lund, A. %A Shuka, R. %A Hähner, J. %B Organic Computing -- Doctoral Dissertation Colloquium 2015 %C Kassel, Germany %D 2015 %E Tomforde, S. %E Sick, B. %I kassel university press %P 165--170 %T On the Application Possibilities of Organic Computing Principles in Socio-technical Systems
Horizontal Integration of Organic Computing and Control Theory Concepts. Calma, A.; Jänicke, M.; Kantert, J.; Kopal, N.; Siefert, F.; Tomforde, S. In Organic Computing -- Doctoral Dissertation Colloquium 2015, S. Tomforde, B. Sick (reds.), bll 157–164. kassel university press, Kassel, Germany, 2015.
- [ BibTeX ]
- [ EndNote ]
@incollection{calma2015horizontal, address = {Kassel, Germany}, author = {Calma, A. and J{\"a}nicke, M. and Kantert, J. and Kopal, N. and Siefert, F. and Tomforde, S.}, booktitle = {Organic Computing – Doctoral Dissertation Colloquium 2015}, editor = {Tomforde, S. and Sick, B.}, keywords = {imported}, pages = {157–164}, publisher = {kassel university press}, title = {Horizontal Integration of Organic Computing and Control Theory Concepts}, year = 2015 }
%0 Book Section %1 calma2015horizontal %A Calma, A. %A Jänicke, M. %A Kantert, J. %A Kopal, N. %A Siefert, F. %A Tomforde, S. %B Organic Computing -- Doctoral Dissertation Colloquium 2015 %C Kassel, Germany %D 2015 %E Tomforde, S. %E Sick, B. %I kassel university press %P 157--164 %T Horizontal Integration of Organic Computing and Control Theory Concepts
Generative Exponential Smoothing Models for Rate Forecasting with Uncertainty Estimation. Kalkowski, E.; Sick, B. In International Work-Conference on Time Series (ITISE), bll 806–817. Granada, Spain, 2015.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{kalkowski2015generative, address = {Granada, Spain}, author = {Kalkowski, E. and Sick, B.}, booktitle = {International Work-Conference on Time Series (ITISE)}, keywords = {imported}, pages = {806–817}, title = {Generative Exponential Smoothing Models for Rate Forecasting with Uncertainty Estimation}, year = 2015 }
%0 Conference Paper %1 kalkowski2015generative %A Kalkowski, E. %A Sick, B. %B International Work-Conference on Time Series (ITISE) %C Granada, Spain %D 2015 %P 806--817 %T Generative Exponential Smoothing Models for Rate Forecasting with Uncertainty Estimation
Fast Feature Extraction for Time Series Analysis Using Least-squares Approximations with Orthogonal Basis Functions. Gensler, A.; Gruber, T.; Sick, B. In International Symposium on Temporal Representation and Reasoning (TIME), bll 29–37. IEEE, Kassel, Germany, 2015.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{gensler2015fast, address = {Kassel, Germany}, author = {Gensler, A. and Gruber, T. and Sick, B.}, booktitle = {International Symposium on Temporal Representation and Reasoning (TIME)}, keywords = {imported}, pages = {29–37}, publisher = {IEEE}, title = {Fast Feature Extraction for Time Series Analysis Using Least-squares Approximations with Orthogonal Basis Functions}, year = 2015 }
%0 Conference Paper %1 gensler2015fast %A Gensler, A. %A Gruber, T. %A Sick, B. %B International Symposium on Temporal Representation and Reasoning (TIME) %C Kassel, Germany %D 2015 %I IEEE %P 29--37 %R 10.1109/time.2015.21 %T Fast Feature Extraction for Time Series Analysis Using Least-squares Approximations with Orthogonal Basis Functions
Effiziente Bewertung des Anschlu\ss{}potentials von Niederspannungsnetzen für dezentrale Erzeugungsanlagen: Klassifikation mit Methoden der Computational Intelligence. Breker, S.; Sick, B. In Tagung Nachhaltige Energieversorgung und Integration von Speichern (NEIS), bll 51–56. Hamburg, Germany, 2015.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{breker2015effiziente, address = {Hamburg, Germany}, author = {Breker, S. and Sick, B.}, booktitle = {Tagung Nachhaltige Energieversorgung und Integration von Speichern (NEIS)}, keywords = {imported}, pages = {51–56}, title = {{Effiziente Bewertung des Anschlu\ss{}potentials von Niederspannungsnetzen f{\"u}r dezentrale Erzeugungsanlagen: Klassifikation mit Methoden der Computational Intelligence}}, year = 2015 }
%0 Conference Paper %1 breker2015effiziente %A Breker, S. %A Sick, B. %B Tagung Nachhaltige Energieversorgung und Integration von Speichern (NEIS) %C Hamburg, Germany %D 2015 %P 51--56 %R 10.1007/978-3-658-10958-5_8 %T Effiziente Bewertung des Anschlu\ss{}potentials von Niederspannungsnetzen für dezentrale Erzeugungsanlagen: Klassifikation mit Methoden der Computational Intelligence
Car Drive Classification and Context Recognition for Personalized Entertainment Preference Learning. Stone, T. C.; Haas, S.; Breitenstein, S.; Wiesner, K.; Sick, B. In International Journal on Advances in Software, 8(1--2), bll 53–64. IARIA, 2015.
- [ BibTeX ]
- [ EndNote ]
@article{stone2015car, author = {Stone, T. C. and Haas, S. and Breitenstein, S. and Wiesner, K. and Sick, B.}, journal = {International Journal on Advances in Software}, keywords = {imported}, number = {1–2}, pages = {53–64}, publisher = {IARIA}, title = {Car Drive Classification and Context Recognition for Personalized Entertainment Preference Learning}, volume = 8, year = 2015 }
%0 Journal Article %1 stone2015car %A Stone, T. C. %A Haas, S. %A Breitenstein, S. %A Wiesner, K. %A Sick, B. %D 2015 %I IARIA %J International Journal on Advances in Software %N 1--2 %P 53--64 %T Car Drive Classification and Context Recognition for Personalized Entertainment Preference Learning %V 8
Capacity of Low-Voltage Grids for Distributed Generation: Classification by Means of Stochastic Simulations. Breker, S.; Claudi, A.; Sick, B. In IEEE Transactions on Power Systems, 30(2), bll 689–700. IEEE, 2015.
- [ BibTeX ]
- [ EndNote ]
@article{breker2015capacity, author = {Breker, S. and Claudi, A. and Sick, B.}, journal = {IEEE Transactions on Power Systems}, keywords = {imported}, number = 2, pages = {689–700}, publisher = {IEEE}, title = {Capacity of Low-Voltage Grids for Distributed Generation: Classification by Means of Stochastic Simulations}, volume = 30, year = 2015 }
%0 Journal Article %1 breker2015capacity %A Breker, S. %A Claudi, A. %A Sick, B. %D 2015 %I IEEE %J IEEE Transactions on Power Systems %N 2 %P 689--700 %R 10.1109/tpwrs.2014.2332361 %T Capacity of Low-Voltage Grids for Distributed Generation: Classification by Means of Stochastic Simulations %V 30
Camera Based Pedestrian Path Prediction by Means of Polynominal Least-squares Approximation and Multilayer Perceptron Neural Networks. Goldhammer, M.; Köhler, S.; Doll, K.; Sick, B. In SAI Intelligent Systems Conference (IntelliSys), bll 390–399. Springer, London, UK, 2015.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{goldhammer2015camera, address = {London, UK}, author = {Goldhammer, M. and K\"ohler, S. and Doll, K. and Sick, B.}, booktitle = {SAI Intelligent Systems Conference (IntelliSys)}, keywords = {imported}, pages = {390–399}, publisher = {Springer}, title = {Camera Based Pedestrian Path Prediction by Means of Polynominal Least-squares Approximation and Multilayer Perceptron Neural Networks}, year = 2015 }
%0 Conference Paper %1 goldhammer2015camera %A Goldhammer, M. %A Köhler, S. %A Doll, K. %A Sick, B. %B SAI Intelligent Systems Conference (IntelliSys) %C London, UK %D 2015 %I Springer %P 390--399 %R 10.1109/IntelliSys.2015.7361171 %T Camera Based Pedestrian Path Prediction by Means of Polynominal Least-squares Approximation and Multilayer Perceptron Neural Networks
Bewertung verschiedener Spannungsregelungskonzepte in einem einspeisegeprägten Mittelspannungsnetz und Ausblick auf neue Konzepte basierend auf Methoden der Computational Intelligence. Rudolph, J.; Breker, S.; Sick, B. In Tagung Nachhaltige Energieversorgung und Integration von Speichern (NEIS), bll 57–63. Hamburg, Germany, 2015.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{rudolph2015bewertung, address = {Hamburg, Germany}, author = {Rudolph, J. and Breker, S. and Sick, B.}, booktitle = {Tagung Nachhaltige Energieversorgung und Integration von Speichern (NEIS)}, keywords = {imported}, pages = {57–63}, title = {Bewertung verschiedener {Spannungsregelungskonzepte} in einem einspeisegepr{\"a}gten {Mittelspannungsnetz und Ausblick auf neue Konzepte basierend auf Methoden der Computational Intelligence}}, year = 2015 }
%0 Conference Paper %1 rudolph2015bewertung %A Rudolph, J. %A Breker, S. %A Sick, B. %B Tagung Nachhaltige Energieversorgung und Integration von Speichern (NEIS) %C Hamburg, Germany %D 2015 %P 57--63 %R 10.1007/978-3-658-10958-5_9 %T Bewertung verschiedener Spannungsregelungskonzepte in einem einspeisegeprägten Mittelspannungsnetz und Ausblick auf neue Konzepte basierend auf Methoden der Computational Intelligence
Anomalies in Generative Trajectory Models -- Discovering Suspicious Traces with Novelty Detection Methods. Gruhl, C. In Organic Computing -- Doctoral Dissertation Colloquium 2015, S. Tomforde, B. Sick (reds.), bll 95–107. kassel university press, Kassel, Germany, 2015.
- [ BibTeX ]
- [ EndNote ]
@incollection{gruhl2015anomalies, address = {Kassel, Germany}, author = {Gruhl, C.}, booktitle = {Organic Computing – Doctoral Dissertation Colloquium 2015}, editor = {Tomforde, S. and Sick, B.}, keywords = {imported}, pages = {95–107}, publisher = {kassel university press}, title = {Anomalies in Generative Trajectory Models – Discovering Suspicious Traces with Novelty Detection Methods}, year = 2015 }
%0 Book Section %1 gruhl2015anomalies %A Gruhl, C. %B Organic Computing -- Doctoral Dissertation Colloquium 2015 %C Kassel, Germany %D 2015 %E Tomforde, S. %E Sick, B. %I kassel university press %P 95--107 %T Anomalies in Generative Trajectory Models -- Discovering Suspicious Traces with Novelty Detection Methods
Analyse des Fahrerverhaltens zur Entwicklung von intelligenten Komfortfunktionen. Stone, T. C.; Huber, A.; Siwy, R.; Sick, B. In Elektronik automotive, 2(2), bll 32–36. WEKA Fachmedien, Landshut, Germany, 2015.
- [ BibTeX ]
- [ EndNote ]
@article{stone2015analyse, address = {Landshut, Germany}, author = {Stone, T. C. and Huber, A. and Siwy, R. and Sick, B.}, journal = {Elektronik automotive}, keywords = {imported}, number = 2, pages = {32–36}, publisher = {WEKA Fachmedien}, title = {{Analyse des Fahrerverhaltens zur Entwicklung von intelligenten Komfortfunktionen}}, volume = 2, year = 2015 }
%0 Journal Article %1 stone2015analyse %A Stone, T. C. %A Huber, A. %A Siwy, R. %A Sick, B. %C Landshut, Germany %D 2015 %I WEKA Fachmedien %J Elektronik automotive %N 2 %P 32--36 %T Analyse des Fahrerverhaltens zur Entwicklung von intelligenten Komfortfunktionen %V 2
A Tool Chain for Context Detection Automating the Investigation of a Multitude of Parameter Sets. Jahn, A.; Lau, S. L.; David, K.; Sick, B. In International Workshop on Mobile and Context Aware Services (MOCS), VTC, bll 1–5. Boston, MA, 2015.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{jahn2015tool, address = {Boston, MA}, author = {Jahn, A. and Lau, S. L. and David, K. and Sick, B.}, booktitle = {International Workshop on Mobile and Context Aware Services (MOCS), VTC}, keywords = {imported}, pages = {1–5}, title = {A Tool Chain for Context Detection Automating the Investigation of a Multitude of Parameter Sets}, year = 2015 }
%0 Conference Paper %1 jahn2015tool %A Jahn, A. %A Lau, S. L. %A David, K. %A Sick, B. %B International Workshop on Mobile and Context Aware Services (MOCS), VTC %C Boston, MA %D 2015 %P 1--5 %T A Tool Chain for Context Detection Automating the Investigation of a Multitude of Parameter Sets
A New Vision of Collaborative Active Learning. Calma, Adrian; Reitmaier, Tobias; Sick, Bernhard; Lukowicz, Paul; Embrechts, Mark. In arXiv e-prints, bl arXiv:1504.00284. 2015.
- [ BibTeX ]
- [ EndNote ]
@article{calma2015new, author = {Calma, Adrian and Reitmaier, Tobias and Sick, Bernhard and Lukowicz, Paul and Embrechts, Mark}, journal = {arXiv e-prints}, keywords = {Machine}, pages = {arXiv:1504.00284}, title = {{A New Vision of Collaborative Active Learning}}, year = 2015 }
%0 Journal Article %1 calma2015new %A Calma, Adrian %A Reitmaier, Tobias %A Sick, Bernhard %A Lukowicz, Paul %A Embrechts, Mark %D 2015 %J arXiv e-prints %P arXiv:1504.00284 %T A New Vision of Collaborative Active Learning
A Mutual Influence Detection Algorithm for Systems with Local Performance Measurement. Rudolph, S.; Tomforde, S.; Sick, B.; Hähner, J. In IEEE International Conference on Self-Adaptive and Self-Organizing Systems (SASO), bll 144–149. IEEE, Cambridge, MA, 2015.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{rudolph2015mutual, address = {Cambridge, MA}, author = {Rudolph, S. and Tomforde, S. and Sick, B. and H{\"a}hner, J.}, booktitle = {IEEE International Conference on Self-Adaptive and Self-Organizing Systems (SASO)}, keywords = {imported}, pages = {144–149}, publisher = {IEEE}, title = {A Mutual Influence Detection Algorithm for Systems with Local Performance Measurement}, year = 2015 }
%0 Conference Paper %1 rudolph2015mutual %A Rudolph, S. %A Tomforde, S. %A Sick, B. %A Hähner, J. %B IEEE International Conference on Self-Adaptive and Self-Organizing Systems (SASO) %C Cambridge, MA %D 2015 %I IEEE %P 144--149 %R 10.1109/saso.2015.23 %T A Mutual Influence Detection Algorithm for Systems with Local Performance Measurement
A Generalized Hebb (GH) rule based on a cross-entropy error function for deep belief recursive learning. Embrechts, M.; Sick, B. In International Conference on Neural Networks - Fuzzy Systems (NN-FS), bll 21–24. Vienna, Austria, 2015.
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
@inproceedings{embrechts2015generalized, address = {Vienna, Austria}, author = {Embrechts, M. and Sick, B.}, booktitle = {International Conference on Neural Networks - Fuzzy Systems (NN-FS)}, keywords = {imported}, pages = {21–24}, title = {A {Generalized Hebb (GH)} rule based on a cross-entropy error function for deep belief recursive learning}, year = 2015 }
%0 Conference Paper %1 embrechts2015generalized %A Embrechts, M. %A Sick, B. %B International Conference on Neural Networks - Fuzzy Systems (NN-FS) %C Vienna, Austria %D 2015 %P 21--24 %T A Generalized Hebb (GH) rule based on a cross-entropy error function for deep belief recursive learning %U http://www.inase.org/library/2015/vienna/bypaper/APNE/APNE-02.pdf
A building block for awareness in technical systems: Online novelty detection and reaction with an application in intrusion detection. Gruhl, C.; Sick, B.; Wacker, A.; Tomforde, S.; Hähner, J. In IEEE International Conference on Awareness Science and Technology (iCAST), bll 194–200. IEEE, Qinhuangdao, China, 2015.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{gruhl2015building, address = {Qinhuangdao, China}, author = {Gruhl, C. and Sick, B. and Wacker, A. and Tomforde, S. and H{\"a}hner, J.}, booktitle = {IEEE International Conference on Awareness Science and Technology (iCAST)}, keywords = {imported}, pages = {194–200}, publisher = {IEEE}, title = {A building block for awareness in technical systems: Online novelty detection and reaction with an application in intrusion detection}, year = 2015 }
%0 Conference Paper %1 gruhl2015building %A Gruhl, C. %A Sick, B. %A Wacker, A. %A Tomforde, S. %A Hähner, J. %B IEEE International Conference on Awareness Science and Technology (iCAST) %C Qinhuangdao, China %D 2015 %I IEEE %P 194--200 %R 10.1109/icawst.2015.7314046 %T A building block for awareness in technical systems: Online novelty detection and reaction with an application in intrusion detection
4DSPro: A New Selection Strategy for Pool-based Active Learning. Calma, A. In Organic Computing -- Doctoral Dissertation Colloquium 2015, S. Tomforde, B. Sick (reds.), bll 121–133. kassel university press, Kassel, Germany, 2015.
- [ BibTeX ]
- [ EndNote ]
@incollection{calma20154dspro, address = {Kassel, Germany}, author = {Calma, A.}, booktitle = {Organic Computing – Doctoral Dissertation Colloquium 2015}, editor = {Tomforde, S. and Sick, B.}, keywords = {imported}, pages = {121–133}, publisher = {kassel university press}, title = {{4DSPro}: A New Selection Strategy for Pool-based Active Learning}, year = 2015 }
%0 Book Section %1 calma20154dspro %A Calma, A. %B Organic Computing -- Doctoral Dissertation Colloquium 2015 %C Kassel, Germany %D 2015 %E Tomforde, S. %E Sick, B. %I kassel university press %P 121--133 %T 4DSPro: A New Selection Strategy for Pool-based Active Learning

2014[ to top ]

Temporal data analytics based on eigenmotif and shape space representations of time series. Gensler, A.; Sick, B.; Willkomm, J. In IEEE China Summit and International Conference on Signal and Information Processing (ChinaSIP), bll 753–757. IEEE, Xian, China, 2014.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{gensler2014temporal, address = {Xian, China}, author = {Gensler, A. and Sick, B. and Willkomm, J.}, booktitle = {IEEE China Summit and International Conference on Signal and Information Processing (ChinaSIP)}, keywords = {imported}, pages = {753–757}, publisher = {IEEE}, title = {Temporal data analytics based on eigenmotif and shape space representations of time series}, year = 2014 }
%0 Conference Paper %1 gensler2014temporal %A Gensler, A. %A Sick, B. %A Willkomm, J. %B IEEE China Summit and International Conference on Signal and Information Processing (ChinaSIP) %C Xian, China %D 2014 %I IEEE %P 753--757 %R 10.1109/chinasip.2014.6889345 %T Temporal data analytics based on eigenmotif and shape space representations of time series
Self-Extending Training Sets: Using Ontologies to Improve Machine Learning Performance. Kalkowski, E. In Organic Computing -- Doctoral Dissertation Colloquium 2014, S. Tomforde, B. Sick (reds.), bll 111–125. kassel university press, Kassel, Germany, 2014.
- [ BibTeX ]
- [ EndNote ]
@incollection{kalkowski2014self, address = {Kassel, Germany}, author = {Kalkowski, E.}, booktitle = {Organic Computing – Doctoral Dissertation Colloquium 2014}, editor = {Tomforde, S. and Sick, B.}, keywords = {imported}, pages = {111–125}, publisher = {kassel university press}, title = {Self-Extending Training Sets: Using Ontologies to Improve Machine Learning Performance}, year = 2014 }
%0 Book Section %1 kalkowski2014self %A Kalkowski, E. %B Organic Computing -- Doctoral Dissertation Colloquium 2014 %C Kassel, Germany %D 2014 %E Tomforde, S. %E Sick, B. %I kassel university press %P 111--125 %T Self-Extending Training Sets: Using Ontologies to Improve Machine Learning Performance
Self-Adapting Multi-sensor Systems: A Concept for Self-Improvement and Self-Healing Techniques. Jänicke, M.; Sick, B.; Lukowicz, P.; Bannach, D. In Workshop on Self-Improving System Integration (SISSY), SASO, bll 128–136. IEEE, London, UK, 2014.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{jaenicke2014self, address = {London, UK}, author = {J{\"a}nicke, M. and Sick, B. and Lukowicz, P. and Bannach, D.}, booktitle = {Workshop on Self-Improving System Integration (SISSY), SASO}, keywords = {imported}, pages = {128–136}, publisher = {IEEE}, title = {Self-Adapting Multi-sensor Systems: A Concept for Self-Improvement and Self-Healing Techniques}, year = 2014 }
%0 Conference Paper %1 jaenicke2014self %A Jänicke, M. %A Sick, B. %A Lukowicz, P. %A Bannach, D. %B Workshop on Self-Improving System Integration (SISSY), SASO %C London, UK %D 2014 %I IEEE %P 128--136 %R 10.1109/sasow.2014.22 %T Self-Adapting Multi-sensor Systems: A Concept for Self-Improvement and Self-Healing Techniques
Self-Adapting Generative Modeling Techniques -- A Basic Building Block for Many Organic Computing Techniques. Gruhl, C. In Organic Computing -- Doctoral Dissertation Colloquium 2014, S. Tomforde, B. Sick (reds.), bll 99–109. kassel university press, Kassel, Germany, 2014.
- [ BibTeX ]
- [ EndNote ]
@incollection{gruhl2014self, address = {Kassel, Germany}, author = {Gruhl, C.}, booktitle = {Organic Computing – Doctoral Dissertation Colloquium 2014}, editor = {Tomforde, S. and Sick, B.}, keywords = {imported}, pages = {99–109}, publisher = {kassel university press}, title = {Self-Adapting Generative Modeling Techniques – A Basic Building Block for Many Organic Computing Techniques}, year = 2014 }
%0 Book Section %1 gruhl2014self %A Gruhl, C. %B Organic Computing -- Doctoral Dissertation Colloquium 2014 %C Kassel, Germany %D 2014 %E Tomforde, S. %E Sick, B. %I kassel university press %P 99--109 %T Self-Adapting Generative Modeling Techniques -- A Basic Building Block for Many Organic Computing Techniques
Resp-kNN: A Semi-Supervised kNN-Classifier for Sparsely Labeled Data in the Field of Organic Computing. Reitmaier, T.; Calma, A. In Organic Computing -- Doctoral Dissertation Colloquium 2014, S. Tomforde, B. Sick (reds.), bll 85–97. kassel university press, Kassel, Germany, 2014.
- [ BibTeX ]
- [ EndNote ]
@incollection{reitmaier2014resp, address = {Kassel, Germany}, author = {Reitmaier, T. and Calma, A.}, booktitle = {Organic Computing – Doctoral Dissertation Colloquium 2014}, editor = {Tomforde, S. and Sick, B.}, keywords = {imported}, pages = {85–97}, publisher = {kassel university press}, title = {Resp-{kNN}: A Semi-Supervised {kNN}-Classifier for Sparsely Labeled Data in the Field of Organic Computing}, year = 2014 }
%0 Book Section %1 reitmaier2014resp %A Reitmaier, T. %A Calma, A. %B Organic Computing -- Doctoral Dissertation Colloquium 2014 %C Kassel, Germany %D 2014 %E Tomforde, S. %E Sick, B. %I kassel university press %P 85--97 %T Resp-kNN: A Semi-Supervised kNN-Classifier for Sparsely Labeled Data in the Field of Organic Computing
Programmierkompetenz prüfen … am Beispiel der Vorlesung "Einführung in C" an der Universität Kassel. Herwig, B.; Frommann, U.; Gruber, T.; Sick, B. In Neues Handbuch Hochschullehre, bll 71–94. Raabe, 2014.
- [ BibTeX ]
- [ EndNote ]
@incollection{herwig2014programmierkompetenz, author = {Herwig, B. and Frommann, U. and Gruber, T. and Sick, B.}, booktitle = {Neues Handbuch Hochschullehre}, keywords = {imported}, number = 64, pages = {71–94}, publisher = {Raabe}, title = {Programmierkompetenz pr{\"u}fen … am Beispiel der Vorlesung "Einf{\"u}hrung in C" an der Universit{\"a}t Kassel}, year = 2014 }
%0 Book Section %1 herwig2014programmierkompetenz %A Herwig, B. %A Frommann, U. %A Gruber, T. %A Sick, B. %B Neues Handbuch Hochschullehre %D 2014 %I Raabe %N 64 %P 71--94 %T Programmierkompetenz prüfen … am Beispiel der Vorlesung "Einführung in C" an der Universität Kassel
Pedestrian’s Trajectory Forecast in Public Traffic with Artificial Neural Networks. Goldhammer, M.; Doll, K.; Brunsmann, U.; Gensler, A.; Sick, B. In International Conference on Pattern Recognition (ICPR), bll 4110–4115. IEEE, Stockholm, Sweden, 2014.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{goldhammer2014pedestrians, address = {Stockholm, Sweden}, author = {Goldhammer, M. and Doll, K. and Brunsmann, U. and Gensler, A. and Sick, B.}, booktitle = {International Conference on Pattern Recognition (ICPR)}, keywords = {imported}, pages = {4110–4115}, publisher = {IEEE}, title = {Pedestrian's Trajectory Forecast in Public Traffic with Artificial Neural Networks}, year = 2014 }
%0 Conference Paper %1 goldhammer2014pedestrians %A Goldhammer, M. %A Doll, K. %A Brunsmann, U. %A Gensler, A. %A Sick, B. %B International Conference on Pattern Recognition (ICPR) %C Stockholm, Sweden %D 2014 %I IEEE %P 4110--4115 %R 10.1109/icpr.2014.704 %T Pedestrian's Trajectory Forecast in Public Traffic with Artificial Neural Networks
Organic Computing -- Doctoral Dissertation Colloquium 2014. Tomforde, S.; Sick, B. In Vol. 4Intelligent Embedded Systems. kassel university press, 2014.
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
@book{tomforde2014organic, editor = {Tomforde, S. and Sick, B.}, keywords = {imported}, publisher = {kassel university press}, series = {Intelligent Embedded Systems}, title = {Organic Computing – Doctoral Dissertation Colloquium 2014}, volume = 4, year = 2014 }
%0 Book %1 tomforde2014organic %B Intelligent Embedded Systems %D 2014 %E Tomforde, S. %E Sick, B. %I kassel university press %T Organic Computing -- Doctoral Dissertation Colloquium 2014 %U https://www.uni-kassel.de/ub/publizieren/kassel-university-press/verlagsprogramm?h=9783862198320 %V 4
On General Purpose Time Series Similarity Measures and Their Use as Kernel Functions in Support Vector Machines. Pree, H.; Herwig, B.; Gruber, T.; Sick, B.; David, K.; Lukowicz, P. In Information Sciences, 281, bll 478–495. Elsevier, 2014.
- [ BibTeX ]
- [ EndNote ]
@article{pree2014general, author = {Pree, H. and Herwig, B. and Gruber, T. and Sick, B. and David, K. and Lukowicz, P.}, journal = {Information Sciences}, keywords = {imported}, pages = {478–495}, publisher = {Elsevier}, title = {On General Purpose Time Series Similarity Measures and Their Use as Kernel Functions in Support Vector Machines}, volume = 281, year = 2014 }
%0 Journal Article %1 pree2014general %A Pree, H. %A Herwig, B. %A Gruber, T. %A Sick, B. %A David, K. %A Lukowicz, P. %D 2014 %I Elsevier %J Information Sciences %P 478--495 %R 10.1016/j.ins.2014.05.025 %T On General Purpose Time Series Similarity Measures and Their Use as Kernel Functions in Support Vector Machines %V 281
Novel Criteria to Measure Performance of Time Series Segmentation Techniques. Gensler, A.; Sick, B.; Pankraz, V. In Workshop on Knowledge Discovery, Data Mining and Machine Learning (KDML), LWA, bll 192–204. Aachen, Germany, 2014.
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
@inproceedings{gensler2014novel, address = {Aachen, Germany}, author = {Gensler, A. and Sick, B. and Pankraz, V.}, booktitle = {Workshop on Knowledge Discovery, Data Mining and Machine Learning (KDML), LWA}, keywords = {imported}, pages = {192–204}, title = {Novel Criteria to Measure Performance of Time Series Segmentation Techniques}, year = 2014 }
%0 Conference Paper %1 gensler2014novel %A Gensler, A. %A Sick, B. %A Pankraz, V. %B Workshop on Knowledge Discovery, Data Mining and Machine Learning (KDML), LWA %C Aachen, Germany %D 2014 %P 192--204 %T Novel Criteria to Measure Performance of Time Series Segmentation Techniques %U http://ceur-ws.org/Vol-1226/paper31.pdf
Knowledge Fusion for Probabilistic Generative Classifiers with Data Mining Applications. Fisch, D.; Kalkowski, E.; Sick, B. In IEEE Transactions on Knowledge and Data Engineering, 26(3), bll 652–666. IEEE, 2014.
- [ BibTeX ]
- [ EndNote ]
@article{fisch2014knowledge, author = {Fisch, D. and Kalkowski, E. and Sick, B.}, journal = {IEEE Transactions on Knowledge and Data Engineering}, keywords = {imported}, number = 3, pages = {652–666}, publisher = {IEEE}, title = {Knowledge Fusion for Probabilistic Generative Classifiers with Data Mining Applications}, volume = 26, year = 2014 }
%0 Journal Article %1 fisch2014knowledge %A Fisch, D. %A Kalkowski, E. %A Sick, B. %D 2014 %I IEEE %J IEEE Transactions on Knowledge and Data Engineering %N 3 %P 652--666 %R 10.1109/tkde.2013.20 %T Knowledge Fusion for Probabilistic Generative Classifiers with Data Mining Applications %V 26
Interwoven Systems. Tomforde, S.; Hähner, J.; Sick, B. In Informatik Spektrum, 37(5), bll 483–487. Springer, 2014.
- [ BibTeX ]
- [ EndNote ]
@article{tomforde2014interwoven, author = {Tomforde, S. and H{\"a}hner, J. and Sick, B.}, journal = {Informatik Spektrum}, keywords = {imported}, number = 5, pages = {483–487}, publisher = {Springer}, title = {Interwoven Systems}, volume = 37, year = 2014 }
%0 Journal Article %1 tomforde2014interwoven %A Tomforde, S. %A Hähner, J. %A Sick, B. %D 2014 %I Springer %J Informatik Spektrum %N 5 %P 483--487 %R 10.1007/s00287-014-0827-z %T Interwoven Systems %V 37
Dealing with human variability in motion based, wearable activity recognition. Kreil, M.; Sick, B.; Lukowicz, P. In Symposium on Activity and Context Modeling and Recognition (ACOMORE), PerCom, bll 36–40. IEEE, Budapest, Hungary, 2014.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{kreil2014dealing, address = {Budapest, Hungary}, author = {Kreil, M. and Sick, B. and Lukowicz, P.}, booktitle = {Symposium on Activity and Context Modeling and Recognition (ACOMORE), PerCom}, keywords = {imported}, pages = {36–40}, publisher = {IEEE}, title = {Dealing with human variability in motion based, wearable activity recognition}, year = 2014 }
%0 Conference Paper %1 kreil2014dealing %A Kreil, M. %A Sick, B. %A Lukowicz, P. %B Symposium on Activity and Context Modeling and Recognition (ACOMORE), PerCom %C Budapest, Hungary %D 2014 %I IEEE %P 36--40 %R 10.1109/percomw.2014.6815161 %T Dealing with human variability in motion based, wearable activity recognition

2013[ to top ]

Let us know your decision: Pool-based active training of a generative classifier with the selection strategy 4DS. Reitmaier, T.; Sick, B. In Information Sciences, 230, bll 106–131. Elsevier, 2013.
- [ BibTeX ]
- [ EndNote ]
@article{reitmaier2013let, author = {Reitmaier, T. and Sick, B.}, journal = {Information Sciences}, keywords = {imported}, pages = {106–131}, publisher = {Elsevier}, title = {Let us know your decision: Pool-based active training of a generative classifier with the selection strategy {4DS}}, volume = 230, year = 2013 }
%0 Journal Article %1 reitmaier2013let %A Reitmaier, T. %A Sick, B. %D 2013 %I Elsevier %J Information Sciences %P 106--131 %R 10.1016/j.ins.2012.11.015 %T Let us know your decision: Pool-based active training of a generative classifier with the selection strategy 4DS %V 230
Classification of Electromyographic Signals: Comparing Evolvable Hardware to Conventional Classifiers. Kaufmann, P.; Glette, K.; Gruber, T.; Platzner, M.; Torresen, J.; Sick, B. In IEEE Transactions on Evolutionary Computation, 17(1), bll 46–63. IEEE, 2013.
- [ BibTeX ]
- [ EndNote ]
@article{kaufmann2013classification, author = {Kaufmann, P. and Glette, K. and Gruber, T. and Platzner, M. and Torresen, J. and Sick, B.}, journal = {IEEE Transactions on Evolutionary Computation}, keywords = {imported}, number = 1, pages = {46–63}, publisher = {IEEE}, title = {Classification of Electromyographic Signals: Comparing Evolvable Hardware to Conventional Classifiers}, volume = 17, year = 2013 }
%0 Journal Article %1 kaufmann2013classification %A Kaufmann, P. %A Glette, K. %A Gruber, T. %A Platzner, M. %A Torresen, J. %A Sick, B. %D 2013 %I IEEE %J IEEE Transactions on Evolutionary Computation %N 1 %P 46--63 %R 10.1109/tevc.2012.2185845 %T Classification of Electromyographic Signals: Comparing Evolvable Hardware to Conventional Classifiers %V 17
Blazing Fast Time Series Segmentation Based on Update Techniques for Polynomial Approximations. Gensler, A.; Gruber, T.; Sick, B. In International Workshop on Spatial and Spatio-Temporal Data Mining (SSTDM), ICDM, bll 1002–1011. IEEE, Dallas, TX, 2013.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{gensler2013blazing, address = {Dallas, TX}, author = {Gensler, A. and Gruber, T. and Sick, B.}, booktitle = {International Workshop on Spatial and Spatio-Temporal Data Mining (SSTDM), ICDM}, keywords = {imported}, pages = {1002–1011}, publisher = {IEEE}, title = {Blazing Fast Time Series Segmentation Based on Update Techniques for Polynomial Approximations}, year = 2013 }
%0 Conference Paper %1 gensler2013blazing %A Gensler, A. %A Gruber, T. %A Sick, B. %B International Workshop on Spatial and Spatio-Temporal Data Mining (SSTDM), ICDM %C Dallas, TX %D 2013 %I IEEE %P 1002--1011 %R 10.1109/icdmw.2013.90 %T Blazing Fast Time Series Segmentation Based on Update Techniques for Polynomial Approximations

2012[ to top ]

Techniques for knowledge acquisition in dynamically changing environments. Fisch, D.; Jänicke, M.; Kalkowski, E.; Sick, B. In ACM Transactions on Autonomous and Adaptive Systems, 7(1), bl 16. ACM, 2012.
- [ BibTeX ]
- [ EndNote ]
@article{fisch2012techniques, author = {Fisch, D. and J{\"a}nicke, M. and Kalkowski, E. and Sick, B.}, journal = {{ACM} Transactions on Autonomous and Adaptive Systems}, keywords = {imported}, number = 1, pages = 16, publisher = {ACM}, title = {Techniques for knowledge acquisition in dynamically changing environments}, volume = 7, year = 2012 }
%0 Journal Article %1 fisch2012techniques %A Fisch, D. %A Jänicke, M. %A Kalkowski, E. %A Sick, B. %D 2012 %I ACM %J ACM Transactions on Autonomous and Adaptive Systems %N 1 %P 16 %R 10.1145/2168260.2168276 %T Techniques for knowledge acquisition in dynamically changing environments %V 7
Learning from others: Exchange of classification rules in intelligent distributed systems. Fisch, D.; Jänicke, M.; Kalkowski, E.; Sick, B. In Artificial Intelligence, 187--188, bll 90–114. Elsevier, 2012.
- [ BibTeX ]
- [ EndNote ]
@article{fisch2012learning, author = {Fisch, D. and J{\"a}nicke, M. and Kalkowski, E. and Sick, B.}, journal = {Artificial Intelligence}, keywords = {imported}, pages = {90–114}, publisher = {Elsevier}, title = {Learning from others: Exchange of classification rules in intelligent distributed systems}, volume = {187–188}, year = 2012 }
%0 Journal Article %1 fisch2012learning %A Fisch, D. %A Jänicke, M. %A Kalkowski, E. %A Sick, B. %D 2012 %I Elsevier %J Artificial Intelligence %P 90--114 %R 10.1016/j.artint.2012.04.002 %T Learning from others: Exchange of classification rules in intelligent distributed systems %V 187--188
Handedness Tests for Preschool Children: A Novel Approach Based on Graphics Tablets and Support Vector Machines. Gruber, T.; Meixner, B.; Prosser, J.; Sick, B. In Applied Soft Computing, 12(4), bll 1390–1398. Elsevier, 2012.
- [ BibTeX ]
- [ EndNote ]
@article{gruber2012handedness, author = {Gruber, T. and Meixner, B. and Prosser, J. and Sick, B.}, journal = {Applied Soft Computing}, keywords = {imported}, number = 4, pages = {1390–1398}, publisher = {Elsevier}, title = {Handedness Tests for Preschool Children: A Novel Approach Based on Graphics Tablets and Support Vector Machines}, volume = 12, year = 2012 }
%0 Journal Article %1 gruber2012handedness %A Gruber, T. %A Meixner, B. %A Prosser, J. %A Sick, B. %D 2012 %I Elsevier %J Applied Soft Computing %N 4 %P 1390--1398 %R 10.1016/j.asoc.2011.11.022 %T Handedness Tests for Preschool Children: A Novel Approach Based on Graphics Tablets and Support Vector Machines %V 12
Determination of Optimal CT Scan Parameters Using Radial Basis Function Neural Networks. Giedl-Wagner, R.; Miller, T.; Sick, B. In Conference on Industrial Computed Tomography (iCT), bll 221–228. Wels, Austria, 2012.
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
@inproceedings{giedlwagner2012determination, address = {Wels, Austria}, author = {Giedl-Wagner, R. and Miller, T. and Sick, B.}, booktitle = {Conference on Industrial Computed Tomography (iCT)}, keywords = {imported}, pages = {221–228}, title = {Determination of Optimal {CT} Scan Parameters Using Radial Basis Function Neural Networks}, year = 2012 }
%0 Conference Paper %1 giedlwagner2012determination %A Giedl-Wagner, R. %A Miller, T. %A Sick, B. %B Conference on Industrial Computed Tomography (iCT) %C Wels, Austria %D 2012 %P 221--228 %T Determination of Optimal CT Scan Parameters Using Radial Basis Function Neural Networks %U https://www.ndt.net/article/ctc2012/papers/235.pdf

2011[ to top ]

SwiftRule: Mining Comprehensible Classification Rules for Time Series Analysis. Fisch, D.; Gruber, T.; Sick, B. In IEEE Transactions on Knowledge and Data Engineering, 23(5), bll 774–787. IEEE, 2011.
- [ BibTeX ]
- [ EndNote ]
@article{fisch2011swiftrule, author = {Fisch, D. and Gruber, T. and Sick, B.}, journal = {IEEE Transactions on Knowledge and Data Engineering}, keywords = {imported}, number = 5, pages = {774–787}, publisher = {IEEE}, title = {{SwiftRule}: Mining Comprehensible Classification Rules for Time Series Analysis}, volume = 23, year = 2011 }
%0 Journal Article %1 fisch2011swiftrule %A Fisch, D. %A Gruber, T. %A Sick, B. %D 2011 %I IEEE %J IEEE Transactions on Knowledge and Data Engineering %N 5 %P 774--787 %R 10.1109/tkde.2010.161 %T SwiftRule: Mining Comprehensible Classification Rules for Time Series Analysis %V 23
On-Line Intrusion Alert Aggregation With Generative Data Stream Modeling. Hofmann, A.; Sick, B. In IEEE Transactions on Dependable and Secure Computing, 8(2), bll 282–294. IEEE, 2011.
- [ BibTeX ]
- [ EndNote ]
@article{hofmann2011line, author = {Hofmann, A. and Sick, B.}, journal = {IEEE Transactions on Dependable and Secure Computing}, keywords = {imported}, number = 2, pages = {282–294}, publisher = {IEEE}, title = {On-Line Intrusion Alert Aggregation With Generative Data Stream Modeling}, volume = 8, year = 2011 }
%0 Journal Article %1 hofmann2011line %A Hofmann, A. %A Sick, B. %D 2011 %I IEEE %J IEEE Transactions on Dependable and Secure Computing %N 2 %P 282--294 %R 10.1109/tdsc.2009.36 %T On-Line Intrusion Alert Aggregation With Generative Data Stream Modeling %V 8
Learning: Preface. Sick, B. In Organic Computing -- A Paradigm Shift for Complex Systems, C. Müller-Schloer, H. Schmeck, T. Ungerer (reds.), bll 235–236. Springer, 2011.
- [ BibTeX ]
- [ EndNote ]
@inbook{sick2011learning, author = {Sick, B.}, booktitle = {Organic Computing – A Paradigm Shift for Complex Systems}, chapter = 3, editor = {M{\"u}ller-Schloer, C. and Schmeck, H. and Ungerer, T.}, keywords = {imported}, pages = {235–236}, publisher = {Springer}, title = {Learning: Preface}, year = 2011 }
%0 Book Section %1 sick2011learning %A Sick, B. %B Organic Computing -- A Paradigm Shift for Complex Systems %D 2011 %E Müller-Schloer, C. %E Schmeck, H. %E Ungerer, T. %I Springer %P 235--236 %R 10.1007/978-3-0348-0130-0 %T Learning: Preface %& 3
In your interest: Objective interestingness measures for a generative classifier. Fisch, D.; Kalkowski, E.; Sick, B.; Ovaska, S. In International Conference on Agents and Artificial Intelligence (ICAART), bll 414–423. Rome, Italy, 2011.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{fisch2011your, address = {Rome, Italy}, author = {Fisch, D. and Kalkowski, E. and Sick, B. and Ovaska, S.}, booktitle = {International Conference on Agents and Artificial Intelligence (ICAART)}, keywords = {imported}, pages = {414–423}, title = {In your interest: Objective interestingness measures for a generative classifier}, year = 2011 }
%0 Conference Paper %1 fisch2011your %A Fisch, D. %A Kalkowski, E. %A Sick, B. %A Ovaska, S. %B International Conference on Agents and Artificial Intelligence (ICAART) %C Rome, Italy %D 2011 %P 414--423 %R 10.5220/0003186404140423 %T In your interest: Objective interestingness measures for a generative classifier
Divergence Measures as a Generalised Approach to Quantitative Emergence. Fisch, D.; Jänicke, M.; Müller-Schloer, C.; Sick, B. In Organic Computing -- A Paradigm Shift for Complex Systems, C. Müller-Schloer, H. Schmeck, T. Ungerer (reds.), bll 53–66. Springer, 2011.
- [ BibTeX ]
- [ EndNote ]
@inbook{fisch2011divergence, author = {Fisch, D. and J{\"a}nicke, M. and M{\"u}ller-Schloer, C. and Sick, B.}, booktitle = {Organic Computing – A Paradigm Shift for Complex Systems}, chapter = 1, editor = {M{\"u}ller-Schloer, C. and Schmeck, H. and Ungerer, T.}, keywords = {imported}, pages = {53–66}, publisher = {Springer}, title = {Divergence Measures as a Generalised Approach to Quantitative Emergence}, year = 2011 }
%0 Book Section %1 fisch2011divergence %A Fisch, D. %A Jänicke, M. %A Müller-Schloer, C. %A Sick, B. %B Organic Computing -- A Paradigm Shift for Complex Systems %D 2011 %E Müller-Schloer, C. %E Schmeck, H. %E Ungerer, T. %I Springer %P 53--66 %R 10.1007/978-3-0348-0130-0_3 %T Divergence Measures as a Generalised Approach to Quantitative Emergence %& 1
Collaborative Learning by Knowledge Exchange. Fisch, D.; Kalkowski, E.; Sick, B. In Organic Computing -- A Paradigm Shift for Complex Systems, C. Müller-Schloer, H. Schmeck, T. Ungerer (reds.), bll 267–280. Springer, 2011.
- [ BibTeX ]
- [ EndNote ]
@inbook{fisch2011collaborative, author = {Fisch, D. and Kalkowski, E. and Sick, B.}, booktitle = {Organic Computing – A Paradigm Shift for Complex Systems}, chapter = 3, editor = {M{\"u}ller-Schloer, C. and Schmeck, H. and Ungerer, T.}, keywords = {imported}, pages = {267–280}, publisher = {Springer}, title = {Collaborative Learning by Knowledge Exchange}, year = 2011 }
%0 Book Section %1 fisch2011collaborative %A Fisch, D. %A Kalkowski, E. %A Sick, B. %B Organic Computing -- A Paradigm Shift for Complex Systems %D 2011 %E Müller-Schloer, C. %E Schmeck, H. %E Ungerer, T. %I Springer %P 267--280 %R 10.1007/978-3-0348-0130-0_17 %T Collaborative Learning by Knowledge Exchange %& 3
Automatic Adaptation of Mobile Activity Recognition Systems to New Sensors. Bannach, D.; Sick, B.; Lukowicz, P. In Workshop Mobile Sensing: Challenges, Opportunities, and Future Directions, UbiComp, bll 1–5. ACM, Beijing, China, 2011.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{bannach2011automatic, address = {Beijing, China}, author = {Bannach, D. and Sick, B. and Lukowicz, P.}, booktitle = {Workshop Mobile Sensing: Challenges, Opportunities, and Future Directions, UbiComp}, keywords = {imported}, pages = {1–5}, publisher = {ACM}, title = {Automatic Adaptation of Mobile Activity Recognition Systems to New Sensors}, year = 2011 }
%0 Conference Paper %1 bannach2011automatic %A Bannach, D. %A Sick, B. %A Lukowicz, P. %B Workshop Mobile Sensing: Challenges, Opportunities, and Future Directions, UbiComp %C Beijing, China %D 2011 %I ACM %P 1--5 %T Automatic Adaptation of Mobile Activity Recognition Systems to New Sensors
Active classifier training with the 3DS strategy. Reitmaier, T.; Sick, B. In IEEE Symposium on Computational Intelligence and Data Mining (CIDM), bll 88–95. IEEE, Paris, France, 2011.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{reitmaier2011active, address = {Paris, France}, author = {Reitmaier, T. and Sick, B.}, booktitle = {IEEE Symposium on Computational Intelligence and Data Mining (CIDM)}, keywords = {imported}, pages = {88–95}, publisher = {IEEE}, title = {Active classifier training with the {3DS} strategy}, year = 2011 }
%0 Conference Paper %1 reitmaier2011active %A Reitmaier, T. %A Sick, B. %B IEEE Symposium on Computational Intelligence and Data Mining (CIDM) %C Paris, France %D 2011 %I IEEE %P 88--95 %R 10.1109/cidm.2011.5949421 %T Active classifier training with the 3DS strategy

2010[ to top ]

Temporal Data Mining Using Shape Space Representations of Time Series. Fuchs, E.; Gruber, T.; Pree, H.; Sick, B. In Neurocomputing, 74(1--3), bll 379–393. Elsevier, 2010.
- [ BibTeX ]
- [ EndNote ]
@article{fuchs2010temporal, author = {Fuchs, E. and Gruber, T. and Pree, H. and Sick, B.}, journal = {Neurocomputing}, keywords = {imported}, number = {1–3}, pages = {379–393}, publisher = {Elsevier}, title = {Temporal Data Mining Using Shape Space Representations of Time Series}, volume = 74, year = 2010 }
%0 Journal Article %1 fuchs2010temporal %A Fuchs, E. %A Gruber, T. %A Pree, H. %A Sick, B. %D 2010 %I Elsevier %J Neurocomputing %N 1--3 %P 379--393 %R 10.1016/j.neucom.2010.03.022 %T Temporal Data Mining Using Shape Space Representations of Time Series %V 74
Online Signature Verification With Support Vector Machines Based on LCSS Kernel Functions. Gruber, C.; Gruber, T.; Krinninger, S.; Sick, B. In IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 40(4), bll 1088–1100. IEEE, 2010.
- [ BibTeX ]
- [ EndNote ]
@article{gruber2010online, author = {Gruber, C. and Gruber, T. and Krinninger, S. and Sick, B.}, journal = {IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics)}, keywords = {imported}, number = 4, pages = {1088–1100}, publisher = {IEEE}, title = {Online Signature Verification With Support Vector Machines Based on {LCSS} Kernel Functions}, volume = 40, year = 2010 }
%0 Journal Article %1 gruber2010online %A Gruber, C. %A Gruber, T. %A Krinninger, S. %A Sick, B. %D 2010 %I IEEE %J IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics) %N 4 %P 1088--1100 %R 10.1109/tsmcb.2009.2034382 %T Online Signature Verification With Support Vector Machines Based on LCSS Kernel Functions %V 40
Online Segmentation of Time Series Based on Polynomial Least-Squares Approximations. Fuchs, E.; Gruber, T.; Nitschke, J.; Sick, B. In IEEE Transactions on Pattern Analysis and Machine Intelligence, 32(12), bll 2232–2245. IEEE, 2010.
- [ BibTeX ]
- [ EndNote ]
@article{fuchs2010online, author = {Fuchs, E. and Gruber, T. and Nitschke, J. and Sick, B.}, journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence}, keywords = {imported}, number = 12, pages = {2232–2245}, publisher = {IEEE}, title = {Online Segmentation of Time Series Based on Polynomial Least-Squares Approximations}, volume = 32, year = 2010 }
%0 Journal Article %1 fuchs2010online %A Fuchs, E. %A Gruber, T. %A Nitschke, J. %A Sick, B. %D 2010 %I IEEE %J IEEE Transactions on Pattern Analysis and Machine Intelligence %N 12 %P 2232--2245 %R 10.1109/tpami.2010.44 %T Online Segmentation of Time Series Based on Polynomial Least-Squares Approximations %V 32

2006[ to top ]

Biometric Analysis of Handwriting Dynamics Using a Script Generator Model. Hofer, J.; Gruber, C.; Sick, B. In IEEE Mountain Workshop on Adaptive and Learning Systems, bll 36–41. IEEE, Logan, 2006.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{hofer2006biometric, address = {Logan}, author = {Hofer, J. and Gruber, C. and Sick, B.}, booktitle = {IEEE Mountain Workshop on Adaptive and Learning Systems}, keywords = {imported}, pages = {36–41}, publisher = {IEEE}, title = {Biometric Analysis of Handwriting Dynamics Using a Script Generator Model}, year = 2006 }
%0 Conference Paper %1 hofer2006biometric %A Hofer, J. %A Gruber, C. %A Sick, B. %B IEEE Mountain Workshop on Adaptive and Learning Systems %C Logan %D 2006 %I IEEE %P 36--41 %R 10.1109/smcals.2006.250689 %T Biometric Analysis of Handwriting Dynamics Using a Script Generator Model