A wearable method for autonomous fall detection based on Kalman filter and k-NN algorithm
Jian He, Mingwo Zhou, Xiaoyi Wang, Yi Han · 2016
The activity model based on tri-axial acceleration and gyroscope is proposed in this paper, and the difference between activities of daily living of (ADLs) and falls is analyzed at first. Meanwhile, Kalman filter is proposed to reduce noise. kNN algorithm and slide window are introduced to develop a wearable system for fall detection and alert, which is composed of a wearable motion sensor and a smart phone. It is shown by experiment that the system identifies simulated falls from ADLs with a high accuracy of 97.17%, while sensitivity and specificity are 97.00% and 97.50%, respectively. Moreover, the smart phone can issue an alarm to caregivers so as to provide timely and accurate help for the elderly, as soon as a fall is detected.