Characterization of human motion by the use of an accelerometer-based detection system

Abstract

Human motion mode detection is of great value in evaluating motor ability. In this study, a method of human motion mode detection based on an acceleration sensor was characterized. A human motion mode detection system was designed using the standard deviation, peak, valley and peak-valley interval as characteristic values and a particle swarm optimization – support vector machine (PSO-SVM) algorithm as the detection method. The measurements of 10 subjects in static, walking and running stages were collected and evaluated. The experimental results showed that the static, walking and running detection accuracy values were 96%, 90% and 92% respectively, and the overall value was 94%. Using the same number of samples, the detection accuracy of SVM was 82.57%, while that of PSO-SVM was 93.1%, which had the highest reliability. This study demonstrates the validity of the human motion mode detection method based on an acceleration sensor which can accurately detect static state, walking and running, and the method is worth further promotion and application.

Keywords:

• Acceleration sensor
• motion mode
• support vector machine