Pervasive alert system for fall detection based on mobile phones

Falls are an everyday potential health hazards that all of us are exposed to. A fall can cause injuries or hurt people especially the elderly. Critical injuries provoked by falls are among the major causes of hospitalization in elderly persons, diminishing their quality of life and often resulting in a rapid decline in functionality or death. Rapid response can improve the patients outcome, but this is often lacking when the injured person lives alone and the nature of the injury complicates calling for help. This paper presents pervasive alert system for fall detection using common commercially available Android-based smart phone with an integrated tri-axial accelerometer. The focus of this research was developing the most successful algorithm for detecting falls and distinguishing them from non-falls. Hybrid algorithm concentrating on acceleration magnitude and angle change was developed for fall detection. We implement a prototype system on the Android phone and conduct experiments to evaluate its performances on real-world falls. Experimental results show that the system achieves strong detection performance and power efficiency