An enhanced feature extraction algorithm for EMG pattern classification

IEEE Trans Rehabil Eng. 1996 Dec;4(4):439-43. doi: 10.1109/86.547948.

Abstract

We 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.

Publication types

  • Research Support, Non-U.S. Gov't

MeSH terms

  • Algorithms*
  • Arm
  • Electric Stimulation Therapy / instrumentation*
  • Electric Stimulation Therapy / methods
  • Electromyography*
  • Humans
  • Motion
  • Prostheses and Implants*
  • Prosthesis Design