基于线性判别分析的表面肌电信号特征识别  

SEMG feature recognition based on linear discriminant analysis

作　　者：王红旗[1] 毛啊敏 李林伟[1] 

机构地区：[1]河南理工大学电气工程与自动化学院,河南焦作454000

出　　处：《河南理工大学学报（自然科学版）》2015年第6期831-835,共5页Journal of Henan Polytechnic University（Natural Science）

基　　金：国家自然科学基金资助项目(61104119);河南理工大学博士基金资助项目(B2010-60)

摘　　要：通过虚拟仪器同时采集桡侧腕屈肌和肱桡肌两路表面肌电信号,取其平均绝对值(MAV)和均方根(RMS)作为特征参数,并应用线性判别分析(LDA)方法对采集的样本进行模式识别。与其它特征识别方式的实验对比表明,所提的识别方法能够成功地从表面肌电信号中识别握拳、展拳、手腕内翻和手腕外翻4种动作,且动作识别精度更高。Through the acquisition of two channels of surface electromyogram signals（ SEMG） on flexor carpi radialis and brachioradialis with a virtual instrument,the mean absolute value（ MAV） and root-mean-square（ RMS） are taken as feature parameters,and the linear discriminant analysis（ LDA） method is applied to the pattern recognition of collected samples. The experiments compared with other identification methods show that the proposed recognition method can successfully identify four kinds of motions such as hand grasping,hand opening,radial flexion and ulnar flexion,and the recognition accuracy is much higher.

关 键 词：表面肌电信号 线性判别分析 模式识别 虚拟仪器 

分 类 号：R318[医药卫生—生物医学工程]