中文摘要：

为了实现基于表面肌电信号（SEMG）的手部动作运动模式识别，提出一种Hilbert—Huang变换（HHT）和自回归（AR）模型相结合的特征提取算法．该方法依据HHT后各层固有模态函数（IMF）的瞬时频率定义每层IMF的频率有效度，由频率有效度选取6层平稳的IMF，同时考察具有最大频率有效度的IMF，并以该IMF的瞬时幅值确定动作信号的起止点．对6层IMF中的动作信号建立AR模型提取手部运动模式的特征向量．提取主成分后，将降维的动作特征向量输入SVM分类器，实现基于SEMG信号的手部多运动模式的识别．对伸腕、屈腕、握拳、展拳4种手部动作的识别实验表明，该方法的识别正确率可达91％．

英文摘要：

In order to recognize the hand motions based on the surface electromyogram （SEMG）, a feature extraction algorithm is presented which is built by the combination of Hilbert-Huang transform （HHT） and AR-model. According to the frequency-credit of each intrinsic mode function （IMF） after HHT, six intrinsic mode functions （IMFs） are selected. In the meantime, the rectangle window is built to cut motion signals of the six IMFs based on the motion-start and the motion-end points. The motion-start and motion-end points are decided by the instantaneous amplitude of the IMF with the largest frequency-credit. AR-model of each IMF is built to extract the hand-motion features. Finally, the motion-feature vector processed by principal component analysis （PCA） is input into the SVM classifier to recognize the hand motions. The experimental results indicate that the proposed method can discriminate the four hand-motion patterns （namely, palmar dorsiflexion and flexion, hand opening and closing） with the correct rate up to 91%.