多视角手部肌肉疲劳动作智能识别方法仿真
Simulation of Intelligent Recognition Method for Hand Muscle Fatigue Actions from Multiple Perspectives
王子威 1郭苗苗1
作者信息
摘要
干扰信号工频和谐波频率噪声会影响动作识别效果,为了提升手部肌肉的识别精度,提出基于肌电信号的多视角手部肌肉疲劳动作识别方法.利用肌电信号采集系统采集手部肌肉疲劳动作肌电信号,利用空域相关滤波算法优化肌电信号,消除干扰信号工频和谐波频率的生理噪声,提升动作识别精度.从时域和频域两个角度出发提取肌电信号特征,并输入支持向量机中,根据支持向量机的分类结果,实现多视角手部肌肉疲劳动作识别.实验结果表明,所提方法识别性能较好、识别精度较高,能够有效提升多视角下手部肌肉疲劳动作识别效果.
Abstract
At present,the interference signal frequency and harmonic frequency noise may affect the effect of ac-tion recognition.In order to improve the accuracy of identifying hand muscle,a method of identifying hand muscle fa-tigue action from multiple perspectives based on electromyography(EMG)signal was proposed.Firstly,an EMG ac-quisition system was used to collect the EMG signals of hand muscle fatigue action.Then,a spatial filtering algorithm was applied to optimize the EMG signals and eliminate the physiological noise caused by the interference signal power frequency and harmonic frequency,thus improving the recognition accuracy.From the perspectives of time domain and frequency domain,the EMG features were extracted and input into a support vector machine(SVM).Based on the classification results of SVM,multi-view hand muscle fatigue action recognition was achieved.Experimental results show that the proposed method has better recognition performance and higher accuracy,and can effectively improve the multi-view hand muscle fatigue action recognition effect.
关键词
手部肌肉/肌电信号/降噪/特征提取/支持向量机Key words
Hand muscles/EMG signal/Noise reduction/Feature extraction/Support vector machine引用本文复制引用
出版年
2024
NETL
NSTL
维普
万方数据