An EMG classifying method based on Bayes´ criterion

Author

Lei, Min ; Wang, Zhi-bong ; Cai, Li-yu ; Zhang, Hai-hong ; Cai, Hua

Author_Institution

Dept. of Biomed. Eng., Shanghai Jiaotong Univ., China

Volume

5

fYear

1998

fDate

28 Oct-1 Nov 1998

Firstpage

2625

Abstract

To counter the applied request of electromyography prosthesis and the characteristics of EMG signal, a method of EMG pattern recognition based on Bayes´ criterion is presented. Two constraints of probability and time domain parameters are given to reduce the error rate of the prosthetic action. From the experiment to real EMG signals, this method is proved to be applicable to the control of EMG prosthesis

Keywords

Bayes methods; autoregressive processes; biocontrol; electromyography; medical signal processing; neuromuscular stimulation; pattern classification; probability; prosthetics; signal classification; Bayes criterion; EMG pattern recognition; EMG prosthesis control; autoregressive models; pattern classification; probability constraints; prosthetic action error rate; real EMG signals; time domain parameters; Biomedical engineering; Counting circuits; Electromyography; Error analysis; Gaussian distribution; Mathematical model; Mathematics; Pattern recognition; Prosthetics; Signal processing;

fLanguage

English

Publisher

ieee

Conference_Titel

Engineering in Medicine and Biology Society, 1998. Proceedings of the 20th Annual International Conference of the IEEE

Conference_Location

Hong Kong

ISSN

1094-687X

Print_ISBN

0-7803-5164-9

Type

conf

DOI

10.1109/IEMBS.1998.744998

Filename

744998