基于sEMG的人体上肢动作特征提取与识别分类的实验研究  

Experimental study of human upper limb motion feature extraction and classification based on sEMG

作　　者：陈健宁 刘蓉 CHEN Jianning;LIU Rong(Department of Biomedical Engineering,Faculty of Electronic Information and Electrical Engineering,Dalian University of Technology,Dalian Liaoning 116024,China)

机构地区：[1]大连理工大学电子信息与电气工程学部生物医学工程学院,辽宁大连116024

出　　处：《智能计算机与应用》2020年第3期321-324,共4页Intelligent Computer and Applications

基　　金：2019年大连理工大学大学生创新创业训练计划项目(2019101410201011053)。

摘　　要：本文以人体上肢动作的sEMG信号为例,提出了基于Noraxon无线表面肌电系统采集不同运动范式肌电信号,并对采集的信号进行特征提取和基于支持向量机算法的分类。经过实践测试,支持向量机算法可以很好地适应上肢康复训练所要求的动作分类要求,为上肢自主康复训练系统设计提供了分类算法支撑。Taking the sEMG signal of human upper limb motion as an example,this paper proposes collecting different motion paradigm EMG signals based on the Noraxon wireless surface electromyography system,and performing feature extraction and classification based on support vector machine algorithm for the collected signals.After practical tests,the support vector machine algorithm can well adapt to the movement classification requirements of upper limb rehabilitation training,and provides a classification algorithm support for the design of an upper limb autonomous rehabilitation training system.

关 键 词：sEMG信号处理 特征提取 识别分类 

分 类 号：TP242.6[自动化与计算机技术—检测技术与自动化装置]