Pattern classi"cation of time-series EMG signals using neural networks

This paper proposes a pattern classi"cation method of time-series EMG signals for prosthetic control. To achieve successful classi"cation for non-stationary EMG signals, a new neural network structure that combines a common back-propagation neural network with recurrent neural "lters is used. A convergence time of the network learning can be regulated by a new learning method based on dynamics of a terminal attractor. The experiments of pattern classi"cation and prosthetic control are carried out for several subjects including an amputee. It is shown from the results that the proposed method improves learning/classi"cation ability for stationary and non-stationary EMG signals during a series of continuous motions. Copyright ( 2000 John Wiley & Sons, Ltd.