检索结果-内蒙古大学图书馆

Multi-Channel Time-Series Person and Soft-Biometric Identification 26th

学校读者我要写书评

暂无评论

Multi-Channel Time-Series Person and Soft-Biometric Identif...

26th International Conference on pattern recognition, ICPR 2022

作者： Nair, Nilah Ravi Moya Rueda, Fernando Reining, Christopher Fink, Gernot A. Chair of Material Handling and Warehousing TU Dortmund University Dortmund Germany Pattern Recognition in Embedded Systems Group TU Dortmund University Dortmund Germany

ISBN: (纸本)9783031376597

Multi-channel time-series datasets are popular in the context of human activity recognition (HAR). On-body device (OBD) recordings of human movements are often preferred for HAR applications not only for their reliability but as an approach for identity protection, e.g., in industrial settings. Contradictory, the gait activity is a biometric, as the cyclic movement is distinctive and collectable. In addition, the gait cycle has proven to contain soft-biometric information of human groups, such as age and height. Though general human movements have not been considered a biometric, they might contain identity information. This work investigates person and soft-biometrics identification from OBD recordings of humans performing different activities using deep architectures. Furthermore, we propose the use of attribute representation for soft-biometric identification. We evaluate the method on four datasets of multi-channel time-series HAR, measuring the performance of a person and soft-biometrics identification and its relation concerning performed activities. We find that person identification is not limited to gait activity. The impact of activities on the identification performance was found to be training and dataset specific. Soft-biometric based attribute representation shows promising results and emphasis the necessity of larger datasets. © 2023, Springer Nature Switzerland AG.

关键词： Deep neural networks

A Tutorial on Dataset Creation for Sensor-based Human Activity recognition

学校读者我要写书评

暂无评论

A Tutorial on Dataset Creation for Sensor-based Human Activi...

IEEE Annual Conference on Pervasive Computing and Communications Workshops (PerCom)

作者： Christopher Reining Nilah Ravi Nair Friedrich Niemann Fernando Moya Rueda Gernot A. Fink Chair of Material Handling and Warehousing Pattern Recognition in Embedded Systems Group

关键词：

Video-based Pose-Estimation Data as Source for Transfer Learning in Human Activity recognition

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Awasthi, Shrutarv Rueda, Fernando Moya Fink, Gernot A. Pattern Recognition in Embedded Systems Group TU Dortmund University Dortmund Germany

Human Activity recognition (HAR) using on-body devices identifies specific human actions in unconstrained environments. HAR is challenging due to the inter and intra-variance of human movements;moreover, annotated datasets from on-body devices are scarce. This problem is mainly due to the difficulty of data creation, i.e., recording, expensive annotation, and lack of standard definitions of human activities. Previous works demonstrated that transfer learning is a good strategy for addressing scenarios with scarce data. However, the scarcity of annotated on-body device datasets remains. This paper proposes using datasets intended for human-pose estimation as a source for transfer learning;specifically, it deploys sequences of annotated pixel coordinates of human joints from video datasets for HAR and human pose estimation. We pre-train a deep architecture on four benchmark video-based source datasets. Finally, an evaluation is carried out on three on-body device datasets improving HAR performance. Copyright © 2022, The Authors. All rights reserved.

关键词： Transfer learning

Multi-Channel Time-Series Person and Soft-Biometric Identification

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Nair, Nilah Ravi Rueda, Fernando Moya Reining, Christopher Fink, Gernot A. Material Handling and Warehousing TU Dortmund University Dortmund Germany Pattern Recognition in Embedded Systems Group TU Dortmund University Dortmund Germany

关键词： Deep neural networks

SEASONET: A SEASONAL SCENE CLASSIFICATION, SEGMENTATION AND RETRIEVAL DATASET FOR SATELLITE IMAGERY OVER GERMANY

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Koßmann, Dominik Brack, Viktor Wilhelm, Thorsten Pattern Recognition in Embedded Systems Group TU Dortmund University Germany Image Analysis Group TU Dortmund University Germany

This work presents SeasoNet, a new large-scale multi-label land cover and land use scene understanding dataset. It includes 1 759 830 images from Sentinel-2 tiles, with 12 spectral bands and patch sizes of up to 120 px ×120 px. Each image is annotated with large scale pixel level labels from the German land cover model LBM-DE2018 with land cover classes based on the CORINE Land Cover database (CLC) 2018 and a five times smaller minimum mapping unit (MMU) than the original CLC maps. We provide pixel synchronous examples from all four seasons, plus an additional snowy set. These properties make SeasoNet the currently most versatile and biggest remote sensing scene understanding dataset with possible applications ranging from scene classification over land cover mapping to content-based cross season image retrieval and self-supervised feature learning. We provide baseline results by evaluating state-of-the-art deep networks on the new dataset in scene classification and semantic segmentation scenarios. Copyright © 2022, The Authors. All rights reserved.

关键词： Mapping

Dataset Bias in Human Activity recognition

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Nair, Nilah Ravi Schmid, Lena Rueda, Fernando Moya Pauly, Markus Fink, Gernot A. Reining, Christopher Chair of Material Handling and Warehousing TU Dortmund University Germany Department of Statistics TU Dortmund University Germany Research Center Trustworthy Data Science and Security UA Ruhr Germany Pattern Recognition in Embedded Systems Group TU Dortmund University Germany

When creating multi-channel time-series datasets for Human Activity recognition (HAR), researchers are faced with the issue of subject selection criteria. It is unknown what physical characteristics and/or soft-biometrics, such as age, height, and weight, need to be taken into account to train a classifier to achieve robustness towards heterogeneous populations in the training and testing data. This contribution statistically curates the training data to assess to what degree the physical characteristics of humans influence HAR performance. We evaluate the performance of a state-of-the-art convolutional neural network on two HAR datasets that vary in the sensors, activities, and recording for time-series HAR. The training data is intentionally biased with respect to human characteristics to determine the features that impact motion behaviour. The evaluations brought forth the impact of the subjects’ characteristics on HAR. Thus, providing insights regarding the robustness of the classifier with respect to heterogeneous populations. The study is a step forward in the direction of fair and trustworthy artificial intelligence by attempting to quantify representation bias in multi-channel time series HAR data. Copyright © 2023, The Authors. All rights reserved.

关键词： Time series

Benchmarking Annotation Procedures for Multi-channel Time Series HAR Dataset

学校读者我要写书评

暂无评论

Benchmarking Annotation Procedures for Multi-channel Time Se...

IEEE Annual Conference on Pervasive Computing and Communications Workshops (PerCom)

作者： Hülya Avsar Erik Altermann Christopher Reining Fernando Moya Rueda Gernot A. Fink Michael ten Hompel Chair of Materials Handling and Warehousing TU Dortmund University Dortmund Pattern Recognition in Embedded Systems Group TU Dortmund University Dortmund

This contribution evaluates semi-automated annotation for generating high-quality data for multi-channel time series Human Activity recognition. For this purpose, time series data that consists of Optical Motion Capturing and inertial measurements from on-body devices for industrial deployment is created, annotated, and revised by four individuals. The semi-automated annotation consists of predictions from a temporal convolutional neural-network, and manual revisions for generating high-quality and fine-grained annotations for Human Activity recognition. This annotation approach reduces the annotation effort keeping similar quality as compared to manual annotation.

关键词： Pervasive computing Annotations Conferences Time series analysis Manuals Optical variables measurement Activity recognition

Annotation Performance for multi-channel time series HAR Dataset in Logistics

学校读者我要写书评

暂无评论

Annotation Performance for multi-channel time series HAR Dat...

IEEE Annual Conference on Pervasive Computing and Communications Workshops (PerCom)

作者： Christopher Reining Fernando Moya Rueda Friedrich Niemann Gernot A. Fink Michael ten Hompel Chair of Materials Handling and Warehousing TU Dortmund University Dortmund Pattern Recognition in Embedded Systems Group TU Dortmund University Dortmund

ISBN: (数字)9781728147161

ISBN: (纸本)9781728147178

This contribution proposes an approach for annotating human actions and their coarse semantic descriptions for multichannel time-series. For this purpose, a new dataset that consists of Optical Motion Capturing and IMU time-series data for industrial deployment is created and annotated by 6 individuals. The expenditure of time for labelling, both classes and semantic attributes, and the annotation consistency are examined. The initial annotations are revised by a single domain expert to measure its effect on the overall between-individual consistency. Consistency measurements by means of Cohen's κ are analysed. The results give insights on the effort for dataset creation in the field of Human Activity recognition for industrial application. The Cohen's κ for consistency assessment was moderate and substantial for the initial annotation, and it increased slightly after revision.

关键词： Semantics Labeling Synchronization Time series analysis Logistics Warehousing Activity recognition

A Residual Multi-Scale Convolutional Transformer Network with Chunk-level Log-Mel Spectrograms for Speech Emotion recognition

学校读者我要写书评

暂无评论

TechRxiv

TechRxiv 2022年

作者： Yan, Tianhao Meng, Hao Parada-Cabaleiro, Emilia Tao, Jianhua Schuller, Björn W. The College of Intelligent Systems Science and Engineering Harbin Engineering University Harbin150001 China Embedded Intelligence for Health Care & Wellbeing University of Augsburg Augsburg86159 Germany The Institute of Computational Perception Johannes Kepler University Linz Linz4040 Austria National Laboratory of Pattern Recognition University of Chinese Academy of Sciences Beijing100190 China The Group on Language Audio & Music Imperial College London LondonSW7 2AZ United Kingdom

The great variety of human emotional expression as well as the differences in the ways they perceive and annotate them make Speech Emotion recognition (SER) an ambiguous and challenging task. With the development of deep learning, long-term progress has been made in supervised SER systems. However, the existing convolutional neural networks present certain limitations, such as their inability to well capture global features, which contain important emotional information. In addition, due to the subjective nature and continuity of emotion, the instance segments in which emotional speech is typically segmented do not fully reflect the true labels and cannot describe dynamic temporal changes. Thus, accurate emotional representation cannot be learnt in the process of feature extraction. In order to overtake these limitations, we propose an end-to-end network only for speech that maps sequences of different lengths to a fixed number of chunks and strictly preserves the order of chunks by adaptively adjusting their overlap. Subsequently, it extracts log-mel spectrogram features from chunk-level segments and feeds them into the Residual Multi-Scale Convolutional Neutral Networks with Transformer(RMSCTx) model framework. Finally, by keeping the order of the chunk-level segments, a temporal domain mean layer is used to further extract utterance-level feature representations. With this method, we perform multidimensional SER, i. e., the prediction of arousal, valence, and dominance. The experimental results on three popular corpora demonstrate not only the superiority of our approach, but also the robustness of the model for SER, showing an improvement of the recognition accuracy in the newest version of the public dataset MSP-Podcast (1.9). © 2022, CC BY.

关键词： Convolution