Feature analysis for the EMG signals based on the class distance

Author

Yazama, Yuuki ; Fukumi, Minoru ; Mitsukura, Yasue ; Akamatsu, Norio

Author_Institution

Dept. of Inf. Sci. & Intelligent Syst., Tokushima Univ., Japan

Volume

2

fYear

2003

fDate

16-20 July 2003

Firstpage

860

Abstract

In this paper, a feature vector is extracted from an electromyography (EMG) signal at a wrist, and the EMG signals based on 7 motions are recognized. In order to perform good pattern recognition, it is desirable that the distance in feature vector between classes is far, and that the variance in a class is small. In consideration of these, important frequency bands of EMG signals are selected by using a genetic algorithm. We use the selected frequency band to perform the recognition experiment of EMG signal by a neural network. Finally, the effectiveness of this method is demonstrated by means of computer simulations.

Keywords

digital simulation; electromyography; feature extraction; genetic algorithms; medical signal processing; neural nets; EMG signals; class distance; electromyography; feature vector; frequency bands; genetic algorithm; neural network; pattern recognition; Data mining; Electromyography; Frequency; Information science; Intelligent systems; Neural networks; Personal digital assistants; Signal analysis; Systems engineering and theory; Wrist;

fLanguage

English

Publisher

ieee

Conference_Titel

Computational Intelligence in Robotics and Automation, 2003. Proceedings. 2003 IEEE International Symposium on

Print_ISBN

0-7803-7866-0

Type

conf

DOI

10.1109/CIRA.2003.1222292

Filename

1222292