Optimizing Support Vector Machine with Genetic Algorithm for Capacitive Sensing-Based Locomotion Mode Recognition

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 order to obtain higher recognition accuracy, in this paper, we try to improve the support vector machine (SVM)-based classifier by selecting suitable kernel function and optimizing the parameters with genetic algorithm (GA). According to different phases of the gait, the phase-dependant GA-SVM models are built and the recognition accuracy increase from 94.0 to 99.1 %, which is satisfactory for practical applications.