Fall detection using sound sensors

Abstract

[ACCESS RESTRICTED TO THE UNIVERSITY OF MISSOURI AT REQUEST OF AUTHOR.] More than 1/3 of adults aged 65 and older fall each year in the US. The fall causes injures or serious health problems which have the related medical cost of $19 billion. Since many falls are not reported, this may be an indication of increasing frailty. To address the above problem we propose to develop fall detection system (FADE) that will automatically report a fall to the monitoring caregiver. As opposed to many existing fall detection systems, our system is completely unobtrusive by using microphone array rather than requiring any wearable devices. We use kinds of features (MFCC, ERSB, etc.) and classifiers ( Nearest Neighbor, Fuzzy rule system, etc.) to detect the falls and try to reduce the false alarm rate. The proposed fall detection system will leverage the existing research and expertise from the Center for Eldercare and Rehabilitation Technologies at the University of Missouri. The proposed technology will reduce the time between the fall and the medical intervention, thus increasing the rehabilitation chances.