An approach for fall detection of older population based on multi-sensor data fusion

Abstract

For the elderly may have the risk of falling during using the walking assistant robot, an approach for fall detection of older population based on multi-sensor data fusion is presented in this paper, which is making full use of tactile-slip sensor, acceleration sensor and gyroscope to acquire the older falling data and extract its feature. And then, the multi-sensor data fusion based on the BP neural network is realized to get the value of falling risk. Finally, the verifying experimental result shows that the proposed method can effectively distinguish the fall events and other daily life activities, and gets good result in predicting falls.