Real time identification of μ wave with wavelet neural networks

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

3 Citations (Scopus)

Abstract

In the rehabilitation of paralyzed patients, the functional electrical stimulation (FES) or prostheses is often adopted in clinical practice. One of the key issues in these new technologies is the source for generating control commands. The brain computer interface (BCI) creates an alternative pathway from the brain potentials. In this investigation, we construct real-time system to percept the voluntary movement of right thumb as a basic study of BCI. We combine the wavelet transformation and neural network as Wavelet Neural Network (WNN) identify the attempt of voluntary thumb movement. Three types of classification methods: realtime classification without network update, real-time classification with update and conevntional power spectral analyses are compared, and it was found that the WNN with off-line retraining shows better successful rate up to 80%.

Original languageEnglish
Title of host publicationConference Proceedings - 1st International IEEE EMBS Conference on Neural Engineering
PublisherIEEE Computer Society
Pages218-220
Number of pages3
Volume2003-January
ISBN (Electronic)0780375793
DOIs
Publication statusPublished - 2003
Event1st International IEEE EMBS Conference on Neural Engineering - Capri Island, Italy
Duration: 2003 Mar 202003 Mar 22

Other

Other1st International IEEE EMBS Conference on Neural Engineering
CountryItaly
CityCapri Island
Period03-03-2003-03-22

Fingerprint

Brain computer interface
Neural networks
Prosthetics
Real time systems
Patient rehabilitation
Brain

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Mechanical Engineering

Cite this

Chen, C. W., Ju, M-S., & Lin, C-C. (2003). Real time identification of μ wave with wavelet neural networks. In Conference Proceedings - 1st International IEEE EMBS Conference on Neural Engineering (Vol. 2003-January, pp. 218-220). [1196797] IEEE Computer Society. https://doi.org/10.1109/CNE.2003.1196797
Chen, Chi Way ; Ju, Ming-Shaung ; Lin, Chou-Ching. / Real time identification of μ wave with wavelet neural networks. Conference Proceedings - 1st International IEEE EMBS Conference on Neural Engineering. Vol. 2003-January IEEE Computer Society, 2003. pp. 218-220
@inproceedings{e4fd2ebd79094a28a91d68976206c5e4,
title = "Real time identification of μ wave with wavelet neural networks",
abstract = "In the rehabilitation of paralyzed patients, the functional electrical stimulation (FES) or prostheses is often adopted in clinical practice. One of the key issues in these new technologies is the source for generating control commands. The brain computer interface (BCI) creates an alternative pathway from the brain potentials. In this investigation, we construct real-time system to percept the voluntary movement of right thumb as a basic study of BCI. We combine the wavelet transformation and neural network as Wavelet Neural Network (WNN) identify the attempt of voluntary thumb movement. Three types of classification methods: realtime classification without network update, real-time classification with update and conevntional power spectral analyses are compared, and it was found that the WNN with off-line retraining shows better successful rate up to 80{\%}.",
author = "Chen, {Chi Way} and Ming-Shaung Ju and Chou-Ching Lin",
year = "2003",
doi = "10.1109/CNE.2003.1196797",
language = "English",
volume = "2003-January",
pages = "218--220",
booktitle = "Conference Proceedings - 1st International IEEE EMBS Conference on Neural Engineering",
publisher = "IEEE Computer Society",
address = "United States",

}

Chen, CW, Ju, M-S & Lin, C-C 2003, Real time identification of μ wave with wavelet neural networks. in Conference Proceedings - 1st International IEEE EMBS Conference on Neural Engineering. vol. 2003-January, 1196797, IEEE Computer Society, pp. 218-220, 1st International IEEE EMBS Conference on Neural Engineering, Capri Island, Italy, 03-03-20. https://doi.org/10.1109/CNE.2003.1196797

Real time identification of μ wave with wavelet neural networks. / Chen, Chi Way; Ju, Ming-Shaung; Lin, Chou-Ching.

Conference Proceedings - 1st International IEEE EMBS Conference on Neural Engineering. Vol. 2003-January IEEE Computer Society, 2003. p. 218-220 1196797.

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

TY - GEN

T1 - Real time identification of μ wave with wavelet neural networks

AU - Chen, Chi Way

AU - Ju, Ming-Shaung

AU - Lin, Chou-Ching

PY - 2003

Y1 - 2003

N2 - In the rehabilitation of paralyzed patients, the functional electrical stimulation (FES) or prostheses is often adopted in clinical practice. One of the key issues in these new technologies is the source for generating control commands. The brain computer interface (BCI) creates an alternative pathway from the brain potentials. In this investigation, we construct real-time system to percept the voluntary movement of right thumb as a basic study of BCI. We combine the wavelet transformation and neural network as Wavelet Neural Network (WNN) identify the attempt of voluntary thumb movement. Three types of classification methods: realtime classification without network update, real-time classification with update and conevntional power spectral analyses are compared, and it was found that the WNN with off-line retraining shows better successful rate up to 80%.

AB - In the rehabilitation of paralyzed patients, the functional electrical stimulation (FES) or prostheses is often adopted in clinical practice. One of the key issues in these new technologies is the source for generating control commands. The brain computer interface (BCI) creates an alternative pathway from the brain potentials. In this investigation, we construct real-time system to percept the voluntary movement of right thumb as a basic study of BCI. We combine the wavelet transformation and neural network as Wavelet Neural Network (WNN) identify the attempt of voluntary thumb movement. Three types of classification methods: realtime classification without network update, real-time classification with update and conevntional power spectral analyses are compared, and it was found that the WNN with off-line retraining shows better successful rate up to 80%.

UR - http://www.scopus.com/inward/record.url?scp=30044435080&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=30044435080&partnerID=8YFLogxK

U2 - 10.1109/CNE.2003.1196797

DO - 10.1109/CNE.2003.1196797

M3 - Conference contribution

VL - 2003-January

SP - 218

EP - 220

BT - Conference Proceedings - 1st International IEEE EMBS Conference on Neural Engineering

PB - IEEE Computer Society

ER -

Chen CW, Ju M-S, Lin C-C. Real time identification of μ wave with wavelet neural networks. In Conference Proceedings - 1st International IEEE EMBS Conference on Neural Engineering. Vol. 2003-January. IEEE Computer Society. 2003. p. 218-220. 1196797 https://doi.org/10.1109/CNE.2003.1196797