基于sEMG信号几何特征的肌肉疲劳分类  

Muscle fatigue classification based on geometric features of sEMG signal

作　　者：曹震 吕东澔 张勇[1] 张鹏[1] 姚贺龙 CAO Zhen;LDonghao;ZHANG Yong;ZHANG Peng;YAO Helong(School of Information Engineering,Inner Mongolia University of Science and Technology,Baotou 014010,China)

机构地区：[1]内蒙古科技大学信息工程学院,内蒙古包头014010

出　　处：《传感器与微系统》2024年第7期145-148,共4页Transducer and Microsystem Technologies

基　　金：内蒙古自治区自然科学基金资助项目(2019BS06004,2020LH06006);国家自然科学基金资助项目(62263026)。

摘　　要：为了更好地区分肌肉疲劳程度,本文通过小波变换的方法,分析不同频段中表面肌电(sEMG)信号的能量变化情况,提取信号几何特征,对肌肉非疲劳和疲劳状态进行区分。从几何边界区域中提取周长、面积、圆度特征,分析几何特征变化情况。同时,使用分类器对肌肉疲劳进行分类。实验结果表明:几何特征对肌肉疲劳状态有更加直观的区分效果。几何特征在肌肉疲劳前后有明显变化,相比传统时域、频域特征,具有更好的分类效果,对几何特征进行特征融合,能够有效提升分类准确度。In order to better distinguish the degree of muscle fatigue,the energy changes of surface electromyography(sEMG)signals are analyzed in different frequency bands by the wavelet transform method,and the geometric features of the signals are extracted to distinguish the non-fatigue and fatigue states of the muscles.The features of perimeter,area,and roundness are extracted from the geometric boundary area,and geometric feature transformation is analyzed.At the same time,a classifier is used to classify muscle fatigue.The experimental results show that the geometric features have a more intuitive distinguishing effect on fatigue state of muscle.Geometric features have obvious changes before and after muscle fatigue.Compared with traditional time domain and frequency domain features,they have better classification effects.Feature fusion of geometric features can effectively improve the classification accuracy.

关 键 词：表面肌电信号 几何特征 肌肉疲劳 疲劳分类 

分 类 号：TN911.7[电子电信—通信与信息系统]