Citation

Narasimhan R. Conf. Proc. IEEE Eng. Med. Biol. Soc. 2012; 2012: 4038-4041.

Copyright

(Copyright © 2012, IEEE (Institute of Electrical and Electronics Engineers))

DOI

10.1109/EMBC.2012.6346853

PMID

23366814

Abstract

This paper describes an adhesive sensor system worn on the skin that automatically detects human falls. The sensor, which consists of a tri-axial accelerometer, a microcon-troller and a Bluetooth Low Energy transceiver, can be worn anywhere on a subject's torso and in any orientation. In order to distinguish easily between falls and activities of daily living (ADL), a possible fall is detected only if an impact is detected and if the subject is horizontal shortly afterwards. As an additional criterion to reduce false positives, a fall is confirmed if the user activity level several seconds after a possible fall is below a threshold. Intentional falls onto a gymnastics mat were performed by 10 volunteers (total of 297 falls); ADL were performed by 15 elderly volunteers (total of 315 ADL). The fall detection algorithm provided a sensitivity of 99% and a specificity of 100%.

Language: en