Human distress sound analysis and characterization using advanced classification techniques

Abstract

The analysis of sounds generated in close proximity of a subject can often indicate emergency events like falls, pain and other distress situations. This paper presents a system for collecting and analyzing sounds and speech expressions utilizing on-body sensors and advanced classification techniques for emergency events detection. A variety of popular classification and meta-classification algorithms have been evaluated and the corresponding results are presented. © 2008 Springer-Verlag Berlin Heidelberg.