摘要
为了有效提取表面肌电信号SEMG(Surface Electromyographic)的特征,更好的识别人体上肢运动模式,提出了一种小波包核主元分析(WPKPCA)和支持向量机(SVM)相结合的新方法。通过虚拟仪器采集桡侧腕屈肌和肱桡肌两路表面肌电信号,应用小波包核主元分析法对表面肌电信号进行特征提取,采用支持向量机对表面肌电信号特征数据进行分类识别。实验结果表明,采用此方法能够从表面肌电信号中识别出握拳、展拳、手腕内翻和手腕外翻4种动作,更能有效提取表面肌电信号信息,动作识别率高达98%。
To extract surface electromyography （SEMG） features and discriminate upper limb motion mode better, a new method which combining wavelet packet kernel principal component analysis （WPKPCA） and support vector machine （SVM） is proposed. Through the acquisition of two channels of SEMG on flexor carpi radialis and brachioradialis with virtual instruments, wavelet packet kernel principal component analysis is used to extract SEMG features. Support vector machine is used to classify and recognize the characteristics of SEMG signal data. Experiments show that this method can successfully identify four kinds of motions, such as hand grasping, hand opening, radial flexion and ulnar flexion, and effectively extract the information of SEMG signal, and the ac- tion recognition rate is up to 98%.
出处
《电子技术应用》
北大核心
2014年第4期84-87,共4页
Application of Electronic Technique
基金
河南省科技厅攻关项目(0624260043)
