Contactless Fall Detection using RFID Wall and AI

Khan, M. Z., Qayyum, A., Arshad, K., Assaleh, K., Abbas, H. , Imran, M. A. and Abbasi, Q. H. (2023) Contactless Fall Detection using RFID Wall and AI. In: 2023 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting, Portland, Oregon, USA, 23–28 July 2023, pp. 1491-1492. ISBN 9781665442282 (doi: 10.1109/USNC-URSI52151.2023.10238313)

Abstract

Fall detection (FD) in elderly people is crucial for preventing serious injuries that could lead to prolonged dependence and even death in severe cases. The world health organization reports that 50% of elderly people fall annually, underscoring the need for early FD to prevent hospitalized or dying in accidents. Contactless FD systems have developed as a viable alternative to wearable sensor-based systems for detecting falls amid concern to security and privacy. This paper proposes a contactless FD system that leverages a passive UHF RFID tag array to measure the received signal strength indicator (RSSI) and utilizes deep learning (DL) to accurately predict fall activity by observing RSSI fluctuations. The system can effectively differentiate between standing and falling activities by training the DL-based classifiers on features extracted from raw data. Our proposed contactless system is capable of detecting indoor falling activity with an accuracy of 95%, which demonstrates the efficacy of the approach.

• Item Type: Conference Proceedings
• Additional Information: This work is supported in parts by EPSRC grant no. EP/T021020/1 and EP/T021063/1.
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Abbas, Dr Hasan and Abbasi, Professor Qammer and Khan, Muhammad Zakir and Imran, Professor Muhammad and Qayyum, Adnan
• Authors: Khan, M. Z., Qayyum, A., Arshad, K., Assaleh, K., Abbas, H., Imran, M. A., and Abbasi, Q. H.
• College/School: College of Science and Engineering > School of Engineering; College of Science and Engineering > School of Engineering > Autonomous Systems and Connectivity; College of Science and Engineering > School of Engineering > Electronics and Nanoscale Engineering
• ISSN: 1947-1491
• ISBN: 9781665442282
• Published Online: 07 September 2023
• Copyright Holders: Copyright © 2023 IEEE
• First Published: First published in 2023 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting: 1491-1492
• Publisher Policy: Reproduced in accordance with the publisher copyright policy

Related URLs

• Organisation

Project Code	Award No	Project Name	Principal Investigator	Funder's Name	Funder Ref	Lead Dept
307829		Quantum-Inspired Imaging for Remote Monitoring of Health & Disease in Community Healthcare	Jonathan Cooper	Engineering and Physical Sciences Research Council (EPSRC)	EP/T021020/1	ENG - Biomedical Engineering