基于小波包变换的表面肌电信号模式识别

Surface EMG Signal Mode Recognition Based on Wavelet Package Transform

采用小波包变换的方法对表面肌电信号sEMG进行了多尺度分解,并提取小波包分解系数的能量值构建特征矢量,采用四种方法设计多类最小二乘支持向量机(LS-SVM)分类器,对8种表面肌电信号进行了模式分类。实验结果表明,采用四种多类分类方法的LS-SVM分类器对8种表面肌电信号的平均识别率在90%以上,LS-SVM分类准确率明显优于传统的RBF神经网络分类器。

The surface electromyographic signal is analyzed by wavelet package transform. The feature vectors are built by extracting the energy value of the wavelet package coefficients. The multi-class least squares support vector machine classifier is designed by using four kinds of multi-class classification approach. The LS-SVM classifier is applied to the classification of eight movements with recording of the surface EMG. Experimental results show that the average recognition rate is over 90%, and the classification accuracy of LS-SVM classifier is significantly better than RBF neural network classifier.