Detecting finger movement through classification of electromyography signals for use in control of robots

Abstract

This paper introduces a new method for surface electromyography (EMG) classification that it is used for controlling robot. EMG signals from individual's muscles are important items for controlling the prosthesis movements. For this purpose, two EMG electrodes located on the human forearm are utilized to collect the EMG data. Time and frequency sets such as Number of Zero Crossings (ZC), Autoregressive (AR) and wavelet coefficients are considered as features. On the other hand, Support Vector Machine (SVM) is used as a classification method. Results show accuracy of proposed approach is ≅ 80%. Finally to show the effectiveness and applicability of results, outputs of classification system are implemented on a fixed robot named Tabriz-Puma.