sEMG Gestures Recognition Based on Wavelet Broad Learning System

Abstract

Gestures recognition plays an important role in the robot systems, which can change existing human-computer interaction. In the existing researches, surface electromyography(sEMG) signals are widely used to classify and recognize gestures. However, the existing classification algorithms of gesture recognition spend a lot of time to train and update the parameters, such as deep learning system. Hence, our work proposes a sEMG gestures recognition algorithm based on wavelet broad learning system(WBLS). Finally, a simulation experiment is carried out and the results verify the effectiveness and efficiency of new method.