中文摘要：

目的：对表面肌电信号进行分类识别。方法：30名健康的志愿者参加数据采集。每名志愿者用右手臂完成两个动作：前臂内旋和前臂外旋。在每个动作中，采集一组表面EMG信号。总共获得30组内旋和30组外旋的表面EMG信号。然后，运用小波包系数熵构成特征向量，用Baycs决策对两种模式信号进行分类识别。结果：当信号长度达350ms后．正确识别率达到100％。结论：采用小波包系数熵可以有效地提取表面EMG信号的特征信息，达到控制前臂假肢的目的。

英文摘要：

Objective： To identify Surface EMG （sEMG） signals. Methods： 30 healthy volunteers joined data acquisition during which every volunteer carded out two forearm actions： forearm pronation （FP） and forearm supination （FS）. A set of surface EMG signal was acquired during every forearm action. 30 sets of FP sEMG signals and 30 sets of FS sEMG signals were collected. Then, the feature vector consisted of wavelet packet coefficient entropy to identify FP sEMG signal and FS sEMG signal through Bayes decision. Results： The correct identification rate arrived to 100% when the lasted time of signal was 350ms or longer. Conclusions： Wavelet packet coefficient entropy is an effective parameter by which sEMG signals can be correctly classified.