A Highly Reliable Wrist-Worn Acceleration-Based Fall Detector

Automatic fall detection for the elderly is one of the most important health-care applications since it enables a rapid medical intervention preventing serious consequences of falls. Wrist-worn fall detectors represent one of the most convenient solutions. However, power consumption has a notable impact on the acceptability of such devices since it affects the size and weight of the required battery and the rate of replacing/recharging it. In this paper, an acceleration-based fall detection system is proposed for wrist-worn devices. It consists of two stages. The first one is a highly-sensitive low computational complexity algorithm to be embedded in the wearable device. When a potential fall is detected, raw data are transmitted to a remote server for accurate analysis in order to reduce the number of false alarms. The second stage algorithm is based on machine learning and applied to highly discriminant features. The latter are selected using powerful feature selection algorithms where the input is 12000 features extracted from each entry of a large activity dataset. The proposed system achieved an accuracy of 100% when evaluated on a 2400-file dataset. Moreover, the feasibility of the proposed system has been validated in real world conditions where it has been realized and tested using a smart watch and a server.