A novel technique for classification of myoelectric signals for prosthesis

This paper presents an investigation into classifying myoelectric signals using a new fuzzy clustering neural network architecture for control of multifunction prostheses. Moreover, a comparative study of the classification accuracy of myoelectric signals using multi-layer perceptron with back-propagation algorithm, and the new fuzzy clustering neural network (FCNN) is presented. The myoelectric signals considered are used to classify four upper-limb movements, which are elbow flexion, elbow extension, wrist pronation and wrist supination, grasp, and resting. The results suggest that FCNN can generalise better than the multi-layer perceptron without requiring extra computational effort. The proposed neural network algorithm allows the user to learn better and faster. Copyright © 2002 IFAC.