Improving acoustic fall recognition by adaptive signal windowing

Each year more than a third of elderly fall in the United States. To address this problem we are developing an acoustic fall detection system based on a microphone array. The main task of the acoustic system is to detect all the falls that occur in an indoor environment while producing as few as possible false alarms. One of the challenges of this task is to accurately locate where the fall signal comes from so that beamforming can be applied to improve the recognition of fall signals. In this paper we describe a simple fall signal location procedure that proved effective in preliminary testing.