MEMS Tri-Axial Accelerometer Based Fall Detection
Fangyi Li · Chuangan jishu xuebao · 2014
As a part of human activities,fall is one of the key factors affecting human health,especially for patients and elders,fall detection is of much importance. This paper presents a method of Signal Magnitude Vector Sliding Average( SVMSA) with Fixed Threshold,based on the acceleration signals of human activity acquired from a MEMS triaxial accelerometer. By extracting the characteristics of human activity acceleration signals,this algorithm accurately achieves human's fall detection,using the prefixed threshold to judge the SVMSA and the differential signal magnitude area( DSMA) to distinguish fast running. The major advance lies in the attempt to analyze and distinguish human's fall and other intense activities,like running fast. By testing eight participants,we get 94. 4% accuracy. Experimental results indicate the proposed algorithm can realize human's fall detection with much accuracy.