Title :
An enhanced feature extraction algorithm for EMG pattern classification
Author :
Lee, Seok-pil ; Kim, Jung-Sub ; Park, Sang-Hui
Author_Institution :
Dept. of Electr. Eng., Yonsei Univ., Seoul, South Korea
fDate :
12/1/1996 12:00:00 AM
Abstract :
The authors present an enhanced feature extraction algorithm which combines block and adaptive processing to identify motion command for the control of a prosthetic arm. The algorithm is capable of precise and stable feature extraction. A sample application with the block processing stationary model parameters is provided to evaluate the feasibility of the adaptive cepstrum vector extracted by the proposed algorithm for electromyographic (EMG) pattern classification
Keywords :
adaptive signal processing; algorithm theory; artificial limbs; electromyography; feature extraction; medical signal processing; EMG pattern classification; adaptive cepstrum vector; block processing; electromyographic pattern classification; enhanced feature extraction algorithm; motion command identification; precise stable feature extraction; prosthetic arm control; Cepstrum; Circuits; Displays; Electromyography; Feature extraction; Microcontrollers; Packaging; Pattern classification; Signal processing; Signal processing algorithms;
Journal_Title :
Rehabilitation Engineering, IEEE Transactions on
