Hand motion pattern classifier based on EMG using wavelet packet transform and LVQ neural networks

In this paper, a novel electromyographic (EMG) motion pattern classifier using wavelet packet transform (WPT) and Learning Vector Quantization (LVQ) Neural Networks is proposed. This motion pattern classifier can successfully identify wrist extension, wrist flexion, hand extension and hand grasp, by measuring the surface EMG signals through two electrodes mounted on forearm extensor carpi ulnaris and flexor carpi ulnaris. The experimental results show that the proposed method achieves a 98% recognition accuracy. Furthermore, via quantitative comparison with other neural networks classifiers, LVQ method has a better performance. Consequently, the classifier is applicable to myoelectric hand control of 2 degrees of freedom (DOF) because of its high recognition capability.