Print Email Facebook Twitter Fusion of Radar Data Domains for Human Activity Recognition in Assisted Living Title Fusion of Radar Data Domains for Human Activity Recognition in Assisted Living Author Le Kernec, Julien (University of Glasgow) Fioranelli, F. (TU Delft Microelectronics; TU Delft Microwave Sensing, Signals & Systems) Romain, Olivier (Observatoire de Paris) Bordat, Alexandre (Observatoire de Paris) Contributor Suryadevara, Nagender Kumar (editor) George, Boby (editor) Jayasundera, Krishanthi P. (editor) Roy, Joyanta Kumar (editor) Mukhopadhyay, Subhas Chandra (editor) Department Microelectronics Date 2022 Abstract Radar has long been considered an important technology for indoor monitoring and assisted living. As ageing has become a worldwide problem, it causes a huge burden on the government’s healthcare expenses and infrastructure. Radar-based human activity recognition (HAR) is foreseen to become a widespread sensing modality for health monitoring at home. Conventional radar-based HAR task usually adopts the amplitude of spectrograms as input to a convolutional neural network (CNN), which can limit the achieved performances. A hybrid fusion model is here proposed, which can integrate multiple radar data domains. The result shows that the proposed framework can achieve superior classification accuracy of 92.1% (+2.5% higher than conventional CNN) and a lighter computational load than the state-of-the-art techniques with 3D-CNN. Subject FusionHuman activity recognitionMachine learningRadar To reference this document use: http://resolver.tudelft.nl/uuid:1cb4027f-4af7-4fa5-bf72-30b3084cb8d7 DOI https://doi.org/10.1007/978-3-030-98886-9_7 Publisher Springer Embargo date 2023-01-02 ISBN 9783030988852 Source Sensing Technology - Proceedings of ICST 2022 Event 14th International Conference on Sensing Technology, ICST 2022, 2022-01-16 → 2022-01-18, Chennai, India Series Lecture Notes in Electrical Engineering, 1876-1100, 886 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 Julien Le Kernec, F. Fioranelli, Olivier Romain, Alexandre Bordat Files PDF LeKernec2022_Chapter_Fusi ... ForHum.pdf 589.51 KB Close viewer /islandora/object/uuid:1cb4027f-4af7-4fa5-bf72-30b3084cb8d7/datastream/OBJ/view