基于FastICA和通道间相关的表面肌电信号分解研究

发布时间：2018-04-27 16:39

本文选题：FastICA + 通道间相关　；参考：《航天医学与医学工程》2017年03期

【摘要】：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。
[Abstract]:Objective to explore a new and effective method for the decomposition of surface EMG signals in neuromuscular diseases. Methods first the mixed matrix was solved by FastICA, then the measurement signal matrix was transformed, then s EMG signal was decomposed by correlation between channels. Results when the first group of signals with a signal to noise ratio of 0 dB was decomposed by simulation and real signal, 20 motor units were decomposed with an average accuracy of 95.6%, and the signal to noise ratio was 20 dB, and more MU were distributed. 29 MUs were decomposed with an average accuracy of 98.4% when the second group of signals with higher frequency was sent, and the average number of MU was 14.2when the real signal was decomposed, which was evaluated by "two-source method". The ratio of decomposing the same MU in the two groups was 80 and the average coincidence rate of the same MU release time was 95.1. Conclusion the method of combining Fast ICA with channel correlation can effectively decompose s EMG signal with high accuracy.
【作者单位】：浙江科技学院自动化与电气工程学院;浙江大学电气工程学院;
【基金】：国家自然科学基金项目(51677171) 浙江省自然科学基金项目(LY17C100001) 浙江省教育厅科研项目(Y201533132)
【分类号】：R741.044;TN911.7

【相似文献】