A SUBBAND CODING SCHEME AND THE BAYESIAN NEURAL NETWORK FOR EMG FUNCTION ANALYSIS

Kuo Sheng Cheng, Din Yuen Chan, Sheeng Horng Liou

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper presents a subband coding scheme and Bayesian Neural Network(BNN) approach to analyze the EMG signals of upptr extremity limb functions. Three channels of EMG signals recorded from the biceps, triceps and one muscle of the forearm are used for discriminating six primitive motions associated with the limb[1]. A set of parameters is extracted from die spectrum of the EMG signals combining with the sub-band coding technique for data compression. Each sequency of EMG signals is cut into five frames from the primary point located by the energy threshold method. From each frame, the parameters are then obtained by the integration of the subbands. Thus, the temporal as well as the spectral characterics may be implicitly or directly included in the parameters. These parameters are assumed to be independent so that the conditional probability may be calculated simply. The BNN is used a subnet for discriminating one motion. From the results, it is shown that an average recognition rate for 85% may be achieved. The BNN may be implemented very easily, and spend much less time for training and recalling than the other neuralnets. However, the parameters for the BNN are restricted. In the future, the more improvement of hardware device is made, the more efficient prosthetics control will be obtained[2][3].

Original languageEnglish
Title of host publicationProceedings - 1992 International Joint Conference on Neural Networks, IJCNN 1992
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages931-934
Number of pages4
ISBN (Electronic)0780305590
DOIs
Publication statusPublished - 1992
Event1992 International Joint Conference on Neural Networks, IJCNN 1992 - Baltimore, United States
Duration: 1992 Jun 71992 Jun 11

Publication series

NameProceedings of the International Joint Conference on Neural Networks
Volume2

Conference

Conference1992 International Joint Conference on Neural Networks, IJCNN 1992
Country/TerritoryUnited States
CityBaltimore
Period92-06-0792-06-11

All Science Journal Classification (ASJC) codes

  • Software
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'A SUBBAND CODING SCHEME AND THE BAYESIAN NEURAL NETWORK FOR EMG FUNCTION ANALYSIS'. Together they form a unique fingerprint.

Cite this