1.
Journal of Biomedical Engineering
; (6): 901-904, 2004.
Artículo
en Chino
| WPRIM (Pacífico Occidental)
| ID: wpr-342584
RESUMEN
A new method based on gray correlation was introduced to improve the identification rate in artificial limb. The electromyography (EMG) signal was first transformed into time-frequency domain by wavelet transform. Singular value decomposition (SVD) was then used to extract feature vector from the wavelet coefficient for pattern recognition. The decision was made according to the maximum gray correlation coefficient. Compared with neural network recognition, this robust method has an almost equivalent recognition rate but much lower computation costs and less training samples.