基于Hilbert-Huang边际谱的肌电信号特征提取  

SEMG feature extraction based on the HHT

作　　者：叶明[1] 孙承奎[1] 马文杰[1] 

机构地区：[1]杭州电子科技大学智能控制机器人研究所,浙江杭州310018

出　　处：《机电工程》2008年第9期80-84,共5页Journal of Mechanical & Electrical Engineering

基　　金：国家自然科学基金资助项目(60474754)

摘　　要：提出了一种基于固有模态函数(IMF)瞬时频率的自适应边际谱分段方法。该方法基于各层IMF的频率有效度,选择合适的IMF,通过自适应边际谱分段方法来确定边际谱分段,然后求取边际谱各段能量,以获得边际谱形状特征。经实验得到了一种优化的归一化处理方法,最后通过仿真得到了HHT边际谱形状特征。In the HHT margin spectrum shape feature extraction algorithm, there were four steps. Firstly, the useful intrinsic made funetion（IMF） was selected and the self-adapting subsection for HHT margin spectrum was determined. The algorithm was proposed . Secondly, the energy of each margin spectrum subsection was considered as the sharp feature of the margin spectrum for each surface eleetronmyography（SEMG）. Thirdly, two feature vectors eorresponding to the two channels SEMG were merged into one hand-motion feature. Finally, each dimension of the feature vector was normalized based on the method. Ultimately, the margin spectrum shape feature vector was obtained, according to the above approach.

关 键 词：固有模态函数 表面肌电信号 Hilbert—Huang变换 特征提取 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] TP274[自动化与计算机技术—控制科学与工程]