Pattern recognition of surface electromyography signals for real-time control of wrist exoskeletons

Surface electromyography (sEMG) signals have been used in numerous studies for the classification of hand gestures and successfully implemented in the position control of different prosthetic hands. An estimation of the intended torque of the user could also provide sufficient information for an effective force control of hand prosthesis or an assistive device. This thesis presents the use of pattern recognition to estimate the torque applied by a human wrist and its real-time implementation to control an exoskeleton prototype that can function as an assistive device. Data from eight volunteers was gathered and Support Vector Machines (SVM) was used for classification. An average testing accuracy of 88% was achieved for nineteen classes. The classification and control algorithm implemented was executed in less than 125 ms. The results of this study showed that real-time classification of sEMG using SVM for controlling an exoskeleton is feasible.