Pattern recognition of Finger Motion's EMG signal based on improved BP neural networks

In the pattern recognition of Finger Motion's EMG signal, the Stability and Efficiency are both the problem. The paper proposes a new method of pattern recognition of EMG signal. The method uses AR model in the modern signal processing theory and numerical variance calculation to compress and make the feature extraction of the EMG. To make the classification of the eigenvalues of the EMG, these eigenvalues have been inputted to the MATLAB to build up a improved multilayer BP neural networks. For the recognition of three different kinds of finger motion's EMG signals, the experiment obtained more higher accuracy. It shows that the method is efficient.