Real-time energy-efficient fall detection based on SSR energy efficiency strategy

Abstract

Falling of the elderly has become a growing concern of the community due to the increase of the ageing population and the serious consequences caused by falling. Devising a fall detection system that is not only highly accurate and reliable, but energy efficient and durable is a challenge. In this paper, we proposed an energy efficient fall detection algorithm based on segmented sampling rates. Most of the time, the algorithm uses a low sampling rate to minimise the energy consumption, but a higher sampling rate when a possible fall is sensed. This unique design helps to increase the fall detection accuracy, while reducing the total energy consumption. Results of comprehensive performance evaluation show that the accuracy rate of the proposed fall detection algorithm is 98.33%, meanwhile, the system can save energy by 9.13% comparing to other algorithms running with a high sampling rate without an energy efficient strategy.

Research of Fall Detection and Fall Prevention Technologies: A Systematic Review

“…As shown in our previous work [24], energy consumption of a fall detector dramatically impacts whether users use the system, and further affects the quality of the services. High energy consumption implies frequent battery recharging or replacement, which is disastrous for the elderly person to do this.…”

“…As we all know, the elderly performs ADLs for most of the time, while falls seldom occur. Therefore, in our former study [24], an energy efficient scheme of using a low sampling rate during most of time, but a high sampling rate when there is a possible fall to increase the performance of fall detection algorithm was proposed, which was called a segmented sampling rates scheme. This proposed low-power fall detection method was verified to improve both energy efficiency and detection accuracy.…”

A Real-Time Patient Monitoring Framework for Fall Detection

“…By using a reduced frequency of 50 Hz instead of 200 Hz, we reduced the amount of data that needed to be stored per day from 2.3 GB to 0.31 GB. Nevertheless, the data reduction also had a disadvantage of losing information, so a combination system as suggested by Ren et al [28] may be better. ey introduced an energy efficient mechanism where the data were usually collected at 50 Hz and changed to 200 Hz when a possible fall was detected.…”