文献类型：期刊文献

中文题名：基于肌音信号的四种手部动作模式的识别方法

英文题名：A Recognition Method for Four Hand-Motion Patterns Based on Mechanomyographic Signal

作者：曹炜[1];夏春明[1];曾勇[1];曹恒[1]

机构：[1]华东理工大学机械与动力工程学院,上海200237

年份：2011

卷号：37

期号：5

起止页码：644

中文期刊名：华东理工大学学报（自然科学版）

外文期刊名：Journal of East China University of Science and Technology

收录：CSTPCD;;Scopus;北大核心:【北大核心2008】；CSCD:【CSCD2011_2012】；

基金：国家自然科学基金资助项目(50775072)

语种：中文

中文关键词：肌音;手部动作;模式识别;主成分分析;线性分类器

外文关键词：mechanomyography; hand-motion; pattern recognition; principal component analysis; linear classifier

摘要：肌音(MMG)是指肌肉收缩时发出的2～100 Hz的低频"声音"。近年来,有研究将前臂肌音信号作为生理信号源应用于假肢手的控制,并取得了一定的进展。利用主成分分析法(PCA)对多通道采集的前臂肌音信号的18个时、频域特征的特征空间进行降维,并采用线性分类器对4种手部动作模式(手掌握紧、手掌张开、腕部弯曲、腕部伸直)进行判别。用本方法对32名受试者的前臂肌音信号进行采集分析研究,并对通道数的确定和采集位置敏感性等作了研究。实验结果表明:该方法可以实现高达95%以上的识别率,在1～4通道采集点分布于前臂4块肌肉的情况下,采用3个通道综合性能最优,采用4个通道无明显优势,4块肌肉采集位置的选取对识别效果基本没有影响。
Mechanomyography（MMG） refers to the ＂sound＂ of muscle contracting,with frequency band from 2 to 100 Hz.MMG signal as a physiological signal source has been gradually utilized and justified in the control of prosthetic hands recently.This paper developed a way of constructing a forearm hand-motion MMG feature space containing 18 time and frequency features,and principal component analysis（PCA） is adopted to reduce the feature dimensionality.Linear classifier algorithm is then applied to identify the four hand-motion patterns（hand close,hand open,wrist flexion and wrist extension）.Forearm hand-motion MMG signals are acquired from 32 volunteers.The analysis results show that the average accuracy rate is above 95%,the recognition with three-channel acquisition configuration has the best overall performance,and the placement distribution of acquisition points on four forearm muscles has few effects on the accuracy rate.