基于卷积混合盲源分离技术的表面肌电信号分解研究

根据表面肌电信号（SEMG）形成的生理学特性，采用一种基于卷积混合过程的盲源分离技术来分析隐含在SEMG信号中的运动单位动作电位信息，利用仿真的SEMG信号对这种算法的分解性能进行实验研究，并与采用瞬时混合过程的独立分量分析（ICA）算法的分解性能进行比较，同时将该算法应用于真实SEMG信号的分解实验。研究结果表明，无论是对模拟SEMG信号还是真实SEMG信号，采用卷积混合盲源分离技术的分解方法均能得到较明显的分解效果，且该方法较符合表面肌电信号的形成过程，因而具有重要的研究价值。

A Study on the Decomposition of Surface EMG Signals Based on the Time Domain Blind Source Separation of Convolved Mixtures

According to the physiological characteristics of the generation process of surface electromyography(SEMG),a method of decomposition of SEMG signals based on the technique of convolutive mixing blind source separation was proposed to detect the information about motor unit action potentials.Using simulated SEMG signals,the performance of proposed decomposition algorithm was analyzed and compared with that of the decomposition technique adopting independent component analysis(ICA),the decomposition experiment of real SEMG signals that recorded at low contraction force was also done.The experimental results showed that the proposed method could decompose SEMG signals effectively,and the better performance parameters were acquired in the simulated experiments.The more complex convolutive mixing model was considered to decompose SEMG signals than instantaneous mixing model,and the proposed method was an effective approach for SEMG signal analysis.