Multi-channel sEMG decomposition based on improved linear minimum mean square error

Konferenz: BIBE 2018 - International Conference on Biological Information and Biomedical Engineering
06.06.2018 - 08.06.2018 in Shanghai, China

Tagungsband: BIBE 2018

Seiten: 4Sprache: EnglischTyp: PDF

Persönliche VDE-Mitglieder erhalten auf diesen Artikel 10% Rabatt

He, Jinbao; Wang, Chaoqun; Hu, Qinbo (Electronic and Information Engineering, Ningbo University of Science and Technology, Ningbo,China)
Lic, Xin (Minzhou Hosptial, Zhejiang University, Ningbo, China)

An improved linear minimum mean square error (LMMSE) algorithm has been proposed by combining LMMSE framework and second-order difference waveform for multi-channel surface electromyography (sEMG) decomposition. The LMMSE method is first utilized to estimate the initial firing pattern, and then the convex shape of second-order difference waveform is conducted to determine the new firing pattern. Results from both simulations and experiments confirm that the proposed algorithm in this paper can decompose sEMG signals with high accuracy and efficiency.