肌电信号特征提取方法综述

Summary of EMG Feature Extraction

肌电信号分析在肌肉的临床诊断、康复、仿生控制和工程应用等领域具有重要的研究价值,而特征提取是肌电信号分析的基础.文章总结回顾了现有肌电信号特征的提取方法,并将其归纳为四大类:时域分析方法、频域分析方法、时频分析方法和非线性动力学方法.在简单介绍各类特征提取方法的基础上,比较了各类方法的特点与优劣,并对其在肌电分析相关领域的应用前景进行了展望.

Electromyography （EMG） signal analysis has great value in the fields of clinical diagnosis, rehabilitation, bionic control, engineering application and so on, while feature extraction is the basis of EMG signal analysis. After reviewing such methods that are used to extract the characteristics of EMG signals, the paper concluded four main kinds of methods： time-domain, frequency-domain, time-frequency and nonlinear dynamics analysis methods. Based on a brief introduction to above methods, the paper compares the advantages and disadvantages of each method and predicts their application prospects in the correlative fields of EMG analysis.