HUANG Peng cheng1, LIN Xue2, BAO Guan jun3, YANG Qing hua3

(1.Jinhua Polytechnic, Jinhua 321000, China; 2. Zhejiang Academy of Agricultural Machinery, 

Jinhua 321000, China; 3.Key Laboratory of E&M Zhejiang University of Technology, 

Ministry of Education & Zhejiang Province, Hangzhou 310032, China)

 

 

Abstract: Aiming at the limitation of traditional signal processing method in non stable signal processing, Sparse Decomposition and self adaptive overcomplete dictionary were studied. Sparse Decomposition was investigated in sEMG processing. And data partitioning was used in the signal preprocessing. Based on Orthogonal Matching Pursuit, the multi dimensional characteristic of sample blocks was reconstructed to one dimensional sparse coefficient by self adaptive overcomplete dictionary. And the dictionary was built by K SVD. Meanwhile, in order to facilitate practical application and continuous control, sample block sparse coefficients were recombined into single eigenvalue. The multi dimensional characteristic of sample block was shown in this signal eigenvalue. The result of data analysis indicates that one dimensional sparse coefficient inherits most energy from the original fourdimensional signal; the changes of original signal active segment could be reflected accurately by single eigenvalue.

Key words: sparse decomposition; orthogonal matching pursuit; K SVD; multi dimensional sEMG