基于虚拟仪器的表面肌电信号特征提取算法的研究

Feature Extraction Algorithm of Surface Electromyography Signal Based on Virtual Instrument

提出一种基于虚拟仪器的表面肌电信号的特征提取算法。该方法利用虚拟仪器丰富的函数功能,针对肌电信号的非平稳性特征,应用积分阈值法首先去除静息电位,保留最有价值的信号部分,然后利用小波包变换的方法对肌电信号进行小波包分解,根据其投影到不同频段上小波包系数能量的不同,利用能量较大的几组系数重构肌电信号。实验结果表明:该方法能有效地去除静息电位及噪声信号,且保留了肌电信号的细节信息,为肌电信号的模式识别创造了良好的条件。该研究依据虚拟仪器平台,为创建表面肌电信号实时控制机械臂系统提供了研究基础,具有潜在的工程应用价值。

A algorithm of surface electromyography signal （sEMG） feature extraction based on virtual instrument was presented. The method of integral threshold was applied to remove the resting potential, and the method of wavelet packet was used to decompose sEMG. Based on energy of wavelet packet coefficients projected to different frequency band, larger probability groups of the coefficient were selected to reconstruct sEMG. The experimental result shows that using the method, the resting potential and the noise signal can be effectively removed, and the details of sEMG information are retained. It creates a good condition for sEMG pattern recognition. The study based on virtual instrument platform, provides a good technical foundation for the development of real-time control system of using sEMG to control arm. It has the potential engineering application value.