A falling detection system with wireless sensor for the elderly people based on ergnomics

Abstract

Fall detection is an important problem in the application research of wireless sensor. The paper presents wireless sensor architecture based human falling detection system especially for elderly people. The falling detection system is implemented using 3-axis acceleration sensor to measures and collects the elderly people activities acceleration and transfer data by zigbee-3G network to remote medical monitoring system platform, which makes a pre-processing method that suspected data is acquired based on one -class SVM classification algorithm. The algorithm analyzed different action which expended different threshold ranges of energy to judgment, and then analyzed the special temporal speed, displacement and angle as an auxiliary criterion for judgment. The experiments show that the application can offer a new guarantee for the elderly health. © 2014 SERSC.