A Virtual Prosthesis Control Based on Neural Networks for Emg Parttern Classification

On of the major difficulties faced by those who are fitted with prosthetic devices is the great mental effort needed during the first stages of training. When working with myographic prosthesis, that effort increases dramatically. In this sense, the authors decided to devise a mechanism to help patients during the learning stages, without actually having to wear the prosthesis all the time. The system is based on a real hardware and software for detecting and processing electromyografic (EMG) signal. The association of autoregressive (AR) models and a neural network is used for EMG pattern discrimination. The outputs of the neural network are then used to control the movements of a virtual prosthesis which mimics what the real prosthesis would be doing. This strategy resulted in rates of success of 100% when discriminating EMG signals collected from the upper arm muscle groups. The results show a very easy-to-use system which can greatly reduce the duration of the training stages.