Title :
A hybrid multi-channel surface EMG decomposition approach by combining CKC and FCM
Author :
Yong Ning ; Shanan Zhu ; Xiangjun Zhu ; Yingchun Zhang
Author_Institution :
Coll. of Electr. Eng., Zhejiang Univ., Hangzhou, China
Abstract :
A hybrid approach is successfully developed in this study by combining the fuzzy C means (FCM) clustering method and Convolution Kernel Compensation (CKC) method for multi-channel surface electromyogram (EMG) decomposition. The FCM is utilized to estimate the initial innervation pulse trains (IPTs) of motor units (MUs) from a few channel surface EMG signals, the CKC method is then employed to estimate the final IPTs. Computer simulation results demonstrate the improved efficiency and accuracy of the hybrid approach compared to the classic CKC method.
Keywords :
convolution; electromyography; medical signal processing; channel surface EMG signals; computer simulation; convolution kernel compensation method; fuzzy C means clustering method; hybrid multichannel surface EMG decomposition approach; initial innervation pulse trains; motor units; multichannel surface electromyogram decomposition; Convolution; Educational institutions; Electromyography; Kernel; Signal to noise ratio; Surface reconstruction;
Conference_Titel :
Neural Engineering (NER), 2013 6th International IEEE/EMBS Conference on
Conference_Location :
San Diego, CA
DOI :
10.1109/NER.2013.6695940
