@inbook{e09ba90883f94849920f5c71e2f8d3fa,
title = "IoT Based Fall Detection System for Elderly Healthcare",
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.",
keywords = "Deep learning, Fall detection system, Internet-of-Things, Machine learning, Wearable systems, WiFi/Radar sensing",
author = "Ahsen Tahir and William Taylor and Ahmad Taha and Muhammad Usman and Shah, {Syed Aziz} and Imran, {Muhammad Ali} and Abbasi, {Qammer H.}",
year = "2022",
month = feb,
day = "25",
doi = "10.1007/978-981-16-8488-3_10",
language = "English",
isbn = "978-981-16-8487-6",
series = "Internet of Things for Human-Centered Design",
publisher = "SpringerOpen",
pages = "209--232",
editor = "Scataglini, {Sofia } and Imbesi, {Silvia } and Marques, {Gon{\c c}alo }",
booktitle = "Studies in Computational Intelligence",
address = "United Kingdom",
}