论文部分内容阅读
目的为了对神经肌肉疾病进行相关的研究和临床上诊断治疗,探索新的和有效的表面肌电(surface EMG,sEMG)信号分解方法。方法首先用FastICA求解混矩阵,然后对测量信号矩阵进行变换,再用通道间相关性分解s EMG信号。结果经过仿真和真实信号进行测试,分解信噪比为0 d B的第一组信号时,以平均95.6%的准确率分解出20个运动单元(motor unit,MU);分解信噪比为20 d B,且参与发放的MU更多,发放频率更高的第二组信号时,以平均98.4%的准确率分解出29个MU;分解真实信号时,得到的平均MU个数为14.2,并用“二源法”进行评测,两组中分解出相同MU的比例为80%,且相同MU发放时刻的平均重合率为95.1%。结论这种结合Fast ICA和通道间相关的方法能以较高的准确率实现s EMG信号的有效分解。
Objective To explore new and effective surface EMG (sEMG) signal decomposition methods for the related research and clinical diagnosis and treatment of neuromuscular diseases. The method first uses FastICA to solve the mixed matrix, then transforms the measurement signal matrix, and then decomposes the s EMG signals with the inter-channel correlation. Results After the simulation and the real signal were tested, the first group of signals with signal to noise ratio 0 d B was decomposed into 20 motion units (MU) with an average accuracy of 95.6%. The decomposition signal to noise ratio was 20 d B, and more MU were involved in the distribution, and 29 more MU were decomposed with an average accuracy of 98.4% when the second group of signals were issued more frequently. When the real signal was decomposed, the average number of MU was 14.2 and used “Two source method ” evaluation, the two groups split the same MU ratio was 80%, and the average coincidence rate of the same MU release time was 95.1%. Conclusion This combination of Fast ICA and channel-related methods enables efficient resolution of s EMG signals with high accuracy.