Print Email Facebook Twitter Elderly Care Title Elderly Care: Using Deep Learning for Multi-Domain Activity Classification Author Li, Shaoxuan (University of Glasgow) Jia, Mu (University of Glasgow) Le Kernec, Julien (University of Glasgow) Yang, Shufan (University of Glasgow) Fioranelli, F. (TU Delft Microwave Sensing, Signals & Systems) Romain, Olivier (University of Cergy-Pontoise) Date 2020 Abstract Nowadays, health monitoring issues are increasing as the worldwide population is aging. In this paper, the radar modality is used to classify with radar signature automatically. The classic approach is to extract features from micro-Doppler signatures for classification. This data representation domain has its limitations for activities presenting similar accelerations like a frontal fall and picking up an object from the floor that lead to wrongly labeled activities. In this work, we propose to combine multiple radar data domains with deep learning. Features are extracted from four domains, namely, Range-Time, Range-Doppler, Doppler-Time, and Cadence Velocity Diagram. The extracted features are set as the input of a Convolutional Neural Network, yielding 91% accuracy with 10-fold cross-validation based on the University of Glasgow “Radar signatures of human activities” open dataset. Subject Machine LearningRadarAssisted LivingHuman Activity RecognitionMulti-domain To reference this document use: http://resolver.tudelft.nl/uuid:56520932-a44d-4192-8728-ca74237c8bf6 DOI https://doi.org/10.1109/UCET51115.2020.9205464 Publisher IEEE Embargo date 2021-03-29 ISBN 978-1-7281-9489-9 Source 2020 International Conference on UK-China Emerging Technologies (UCET) Event UCET 2020, 2020-08-20 → 2020-08-21, Glasgow, United Kingdom 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 © 2020 Shaoxuan Li, Mu Jia, Julien Le Kernec, Shufan Yang, F. Fioranelli, Olivier Romain Files PDF 09205464.pdf 399.23 KB Close viewer /islandora/object/uuid:56520932-a44d-4192-8728-ca74237c8bf6/datastream/OBJ/view