Print Email Facebook Twitter Evaluation Metrics for Continuous Human Activity Classification Using Distributed Radar Networks Title Evaluation Metrics for Continuous Human Activity Classification Using Distributed Radar Networks Author Guendel, Ronny (TU Delft Microwave Sensing, Signals & Systems) Fioranelli, F. (TU Delft Microwave Sensing, Signals & Systems) Yarovoy, Alexander (TU Delft Microwave Sensing, Signals & Systems) Date 2022 Abstract Continuous Human Activity Recognition (HAR) in arbitrary directions is investigated using 5 spatially distributed pulsed Ultra-Wideband (UWB) radars. Such activities performed in arbitrary and unconstrained trajectories render a more natural occurrence of Activities of Daily Living (ADL) to be recognized. An innovative signal level fusion method was applied on the Range-Time (RT) maps, and deep learning classification via Recurrent Neural Networks (RNN) with and without bidi-rectionality was used on the computed micro-Doppler (μD) spectrogram. To assess classification performances, novel evaluation metrics accounting for the continuous nature of the sequence of activities and for imbalances in the dataset are proposed and compared with existing metrics. It is shown that conventional accuracy evaluation is too coarse, and that the proposed metrics need to be considered for a more comprehensive evaluation. Subject Micro-Doppler ClassificationDistributed RadarLSTMHuman Activity Recognition To reference this document use: http://resolver.tudelft.nl/uuid:53eb2707-4243-464b-bda9-3f9f218bbe84 DOI https://doi.org/10.1109/RadarConf2248738.2022.9764181 Publisher IEEE, Piscataway Embargo date 2022-11-03 ISBN 978-1-7281-5369-8 Source 2022 IEEE Radar Conference (RadarConf22) Proceedings Event 2022 IEEE Radar Conference , 2022-03-21 → 2022-03-25, New York City, United States Series Proceedings of the IEEE Radar Conference, 1097-5764 Bibliographical note Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public. Part of collection Institutional Repository Document type conference paper Rights © 2022 Ronny Guendel, F. Fioranelli, Alexander Yarovoy Files PDF Evaluation_Metrics_for_Co ... tworks.pdf 1.74 MB Close viewer /islandora/object/uuid:53eb2707-4243-464b-bda9-3f9f218bbe84/datastream/OBJ/view