IoT based fall detection system for elderly healthcare

Tahir, A., Taylor, W., Taha, A. , Usman, M., Shah, S. A. , Imran, M. A. and Abbasi, Q. T. (2022) IoT based fall detection system for elderly healthcare. In: Scataglini, S., Imbesi, S. and Marques, G. (eds.) Internet of Things for Human-Centered Design: Application to Elderly Healthcare. Series: Studies in Computational Intelligence, 1011. Springer: Singapore, pp. 209-232. ISBN 9789811684876 (doi: 10.1007/978-981-16-8488-3_10)

Abstract

Falls are a leading cause of immobility, morbidity, and mortality in older adults. Falls incur high cost to health services with millions of bed days. Half of the older adults over 65 years old, fall in a span of 5 years with 62% sustaining injuries and 28% protracting extensive injuries. Automatic fall detection system for elderly healthcare through Internet of Things (IoT) human-centered design can provide timely detection and communication of fall events for immediate medical aid in case of injury or unconsciousness. Fall detection systems have been reported to provide reduction in death rates of up to 80% due to timely medical support. In this chapter, we discuss elderly-centric IoT based fall detection system for smart homes and care centers with emphasis on edge, fog and cloud IoT layers. Sensing edge devices with wearable/environmental sensors, vision-based systems, and radio frequency sensing systems, such as WiFi-based sensing and RADAR are presented for an IoT-centered fall detection system. IoT gateways and communication protocols for the fog layer are discussed in the context of a fall detection system. Cloud processing of edge device data for fall activity detection and classification from activities of daily life is explained. Machine and deep learning algorithms for detection of fall events from 1 and 2D signals (image/video) are presented and various deployment scenarios are discussed in the context of edge or cloud IoT layers. This chapter is concluded with results and performance comparison of several IoT centered fall detection systems in terms of various sensing systems and state-of-the-art machine and deep learning models for effective detection of falls for elderly healthcare. Furthermore, future work and prospective improvements in IoT centered design for fall detection in elderly healthcare is discussed.

• Item Type: Book Sections
• Status: Published
• Glasgow Author(s) Enlighten ID: Taha, Dr Ahmad and Tahir, Dr Ahsen and Imran, Professor Muhammad and Usman, Dr Muhammad and Taylor, Mr William and Abbasi, Professor Qammer and Shah, Mr Syed
• Authors: Tahir, A., Taylor, W., Taha, A., Usman, M., Shah, S. A., Imran, M. A., and Abbasi, Q. T.
• College/School: College of Science and Engineering > School of Engineering > Autonomous Systems and Connectivity; College of Science and Engineering > School of Engineering > Systems Power and Energy
• Publisher: Springer
• ISSN: 1860-949X
• ISBN: 9789811684876
• Published Online: 25 February 2022
• Copyright Holders: Copyright © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2022
• Publisher Policy: Reproduced in accordance with the publisher copyright policy