Classifier Selection for Locomotion Mode Recognition Using Wearable Capacitive Sensing Systems

Abstract

Capacitive sensing has been proven valid for locomotion mode recognition as an alternative of popular electromyography based methods in the control of powered prostheses. In this paper, we analyze the characteristics of the capacitive signals and extract suitable feature sets to improve the recognition accuracy. Then the classification results of different classifiers are compared and one optimal classifier which can offer highest accuracy within a reasonable time limit is selected. Experimental results show that the recognition accuracy of the wearable capacitive sensing system has been improved by using the selected classifier.