Abstract:
With advances in medicine and healthcare systems, the average life expectancy of human beings has increased to more than 80 years. As a result, the demographic old-age dependency ratio (people aged 65 or above relative to those aged 15–64) is expected to increase, by 2060, from ~28 to ~50% in the European Union and from ~33 to ~45% in Asia [1]. Therefore, the percentage of people who need additional care is also expected to increase. Geriatric health care, which pertains to care for the elderly, has gained a lot of prominence in the recent years, with specific focus on fall and sleep apnea detection systems because of their impact on public lives. In the recent years, there has been widespread application of Internet of things (IoT) and machine learning in the geriatric healthcare domain because of the potential cost reduction such technologies can bring in. In this paper, we present the architecture and design of an end-to-end geriatric healthcare system, with focus on wearable device based fall detection using machine learning. We explain the major components of the system architecture, under a certain deployment scenario, and present the communication protocol between these system components. We also present the salient aspects of the multi-channel variable time-division multiple access (multi-channel V-TDMA) MAC protocol designed to suit the requirements of such a system. This protocol combines the strengths of both standard time-division multiple access (TDMA) that is modified to support flexibility and frequency-division multiple access (FDMA).