Waveform recognition using genetic programming: the myoelectric signal recognition problem

Authors:
Jaime J. Fernandez;Kristin A. Farry;John B. Cheatham
Affiliations:
Rice University, Sugar Land, TX;NASA/Johnson Space Center, ER Houston, TX;Rice University, Houston, TX
Venue:
GECCO '96 Proceedings of the 1st annual conference on Genetic and evolutionary computation
Year:
1996

Citing 4
Cited 1

Genetic programming: on the programming of computers by means of natural selection

Genetic programming: on the programming of computers by means of natural selection
Genetic programming II: automatic discovery of reusable programs

Genetic programming II: automatic discovery of reusable programs
Recombination, selection, and the genetic construction of computer programs

Recombination, selection, and the genetic construction of computer programs
Issues in myoelectric teleoperation of complex artificial hands

Issues in myoelectric teleoperation of complex artificial hands

Genetic programming for epileptic pattern recognition in electroencephalographic signals

Applied Soft Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a new strategy for multifunction myoelectric control of an upper arm prosthesis. We apply genetic programming to the classification of several anisometric myoelectric patterns (e.g., thumb flexion, extension and abduction), using features extracted from the myoelectric signal. This approach increases the number of possible control functions that can be extracted from myoelectric signals. This control scheme, combined with a multifunction myoelectric hand design, will provide the prosthesis user with more functions than now available. We present three different approaches each capable of recognizing 100% of the three motions. Finally, we present our ideas for the future of this project.