Individual hand motion classification through EMG pattern recognition: Supervise and unsupervised methods

The EMG signals are being used in electronic systems with biofeedback control for tracking and classifying of hand motion. These systems present a challenge in identifying the movement due to the variation of the EMG signals between subjects, therefore different pattern recognition techniques have been implemented to overcome this challenge. In response to the previous problem, the present study compares the performance of both K - means and SVM methods to identify five individual movements of the hand. Therefore two techniques of classification were implemented, the first one consist of classifying the movements individually. while the second classifies all five movements through technic based on decision trees. Also this paper analyses the influence of the signal normalization over the performance of the classification. In general, SVM classifier performed better against K - means in the two tests with the error percentage below 9%.