Skip to Main content Skip to Navigation
Conference papers

A highly reliable wrist-worn acceleration-based fall detector

Abstract : 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 12 000 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. © 2019 IEEE
Document type :
Conference papers
Complete list of metadatas

https://hal-univ-rennes1.archives-ouvertes.fr/hal-02442594
Contributor : Laurent Jonchère <>
Submitted on : Thursday, January 16, 2020 - 3:32:34 PM
Last modification on : Friday, January 17, 2020 - 1:26:46 AM

Identifiers

Collections

Citation

M. Saleh, N. Georgi, M. Abbas, R. Le Bouquin Jeannès. A highly reliable wrist-worn acceleration-based fall detector. 27th European Signal Processing Conference, EUSIPCO 2019, Sep 2019, Coruña, Spain. ⟨10.23919/EUSIPCO.2019.8902563⟩. ⟨hal-02442594⟩

Share

Metrics

Record views

30