EMG-based hand gesture classification by scale average wavelet transform and CNN

Predicting and accurately classifying intentions for human hand gestures can be used not only for active prosthetic hands, rehabilitation robots and entertainment robots but also for artificial intelligence robots in general. In this paper, first of all, source data of three hand gestures of grasping and three hand gestures of sign language are acquired by using the armband combined with 8 sEMG (surface Electromyography) sensors. To classify these hand gestures, basic CNN (Convolutional Neural Network) and wavelet transform CNN are applied and compared as a deep learning algorithm. Finally, it is shown that by using wavelet transform and an average value of the transformed data according to scale change of mother function, the accuracy can be improved up to 94% for selected hand gestures.