Denoising Method for sEMG Signal Based on CEEMD-VMD-SIST Algorithm
For gesture recognition based on surface electromyography(sEMG)signals,the sEMG signals have poor denoising characteristics such as improper decomposition of high-frequency parts or frequency aliasing in traditional denoising methods,resulting in a significant decrease in the gesture recognition accuracy,a sliding interval soft threshold(SIST)denoising algorithm based on com-plementary ensemble empirical mode decomposition and variational mode decomposition(CEEMD-VMD-SIST)is proposed for denois-ing the sEMG signals.The noisy signal is decomposed into multiple intrinsic mode functions(IMF)from high frequency to low fre-quency by using the CEEMD,and the modal component range of the signal is objectively determined according to the autocorrelation coefficients,the selected components are decomposed and denoised by the VMD-SIST and reconstructed with some remaining modal components.Experimental results show that compared with the traditional denoising methods and under different signal-to-noise ratios(SNR),the proposed algorithm significantly improves the denoising performances of SNR and root mean square error(RMSE),and preserves the useful components of signals to a large extent,the proposed algorithm has a better noise reduction performance.
万方数据
维普
