Application of neural network to brain-computer interface

Wei Yen Hsu, I. Jen Chiang

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

Abstract

In this study, an neural-network-based system is proposed for the applications of brain-computer interface (BCI). Applying event-related brain potential (ERP) data acquired from the sensorimotor cortices, the system consists of three procedures, including enhanced active segment selection, feature extraction, and classification. Firstly, combined with the use of continuous wavelet transform (CWT) and Student's two-sample t-statistics, the 2D anisotropic Gaussian filter is proposed to further refine the active-segment selection. Multiresolution fractal features are then extracted from wavelet data by means of modified fractal dimension. Finally, support vector machine (SVM) is used for classification. Compared with other approaches on motor imagery data, the results indicate that the proposed method is promising in BCI applications.

Original languageEnglish
Title of host publicationProceedings - 2012 IEEE International Conference on Granular Computing, GrC 2012
Pages163-168
Number of pages6
DOIs
Publication statusPublished - 2012
Event2012 IEEE International Conference on Granular Computing, GrC 2012 - HangZhou, China
Duration: Aug 11 2012Aug 13 2012

Other

Other2012 IEEE International Conference on Granular Computing, GrC 2012
CountryChina
CityHangZhou
Period8/11/128/13/12

Fingerprint

Brain computer interface
Neural networks
Fractal dimension
Fractals
Wavelet transforms
Support vector machines
Feature extraction
Brain
Statistics
Students

Keywords

  • Active segment selection
  • Brain-computer interface (BCI)
  • Electroencephalogram (EEG)
  • Modified fractal dimension
  • Support vector machine (SVM)
  • Wavelet transform

ASJC Scopus subject areas

  • Software

Cite this

Hsu, W. Y., & Chiang, I. J. (2012). Application of neural network to brain-computer interface. In Proceedings - 2012 IEEE International Conference on Granular Computing, GrC 2012 (pp. 163-168). [6468559] https://doi.org/10.1109/GrC.2012.6468559

Application of neural network to brain-computer interface. / Hsu, Wei Yen; Chiang, I. Jen.

Proceedings - 2012 IEEE International Conference on Granular Computing, GrC 2012. 2012. p. 163-168 6468559.

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

Hsu, WY & Chiang, IJ 2012, Application of neural network to brain-computer interface. in Proceedings - 2012 IEEE International Conference on Granular Computing, GrC 2012., 6468559, pp. 163-168, 2012 IEEE International Conference on Granular Computing, GrC 2012, HangZhou, China, 8/11/12. https://doi.org/10.1109/GrC.2012.6468559
Hsu WY, Chiang IJ. Application of neural network to brain-computer interface. In Proceedings - 2012 IEEE International Conference on Granular Computing, GrC 2012. 2012. p. 163-168. 6468559 https://doi.org/10.1109/GrC.2012.6468559
Hsu, Wei Yen ; Chiang, I. Jen. / Application of neural network to brain-computer interface. Proceedings - 2012 IEEE International Conference on Granular Computing, GrC 2012. 2012. pp. 163-168
@inproceedings{b39921587bde4738af7e148170bb1341,
title = "Application of neural network to brain-computer interface",
abstract = "In this study, an neural-network-based system is proposed for the applications of brain-computer interface (BCI). Applying event-related brain potential (ERP) data acquired from the sensorimotor cortices, the system consists of three procedures, including enhanced active segment selection, feature extraction, and classification. Firstly, combined with the use of continuous wavelet transform (CWT) and Student's two-sample t-statistics, the 2D anisotropic Gaussian filter is proposed to further refine the active-segment selection. Multiresolution fractal features are then extracted from wavelet data by means of modified fractal dimension. Finally, support vector machine (SVM) is used for classification. Compared with other approaches on motor imagery data, the results indicate that the proposed method is promising in BCI applications.",
keywords = "Active segment selection, Brain-computer interface (BCI), Electroencephalogram (EEG), Modified fractal dimension, Support vector machine (SVM), Wavelet transform",
author = "Hsu, {Wei Yen} and Chiang, {I. Jen}",
year = "2012",
doi = "10.1109/GrC.2012.6468559",
language = "English",
isbn = "9781467323093",
pages = "163--168",
booktitle = "Proceedings - 2012 IEEE International Conference on Granular Computing, GrC 2012",

}

TY - GEN

T1 - Application of neural network to brain-computer interface

AU - Hsu, Wei Yen

AU - Chiang, I. Jen

PY - 2012

Y1 - 2012

N2 - In this study, an neural-network-based system is proposed for the applications of brain-computer interface (BCI). Applying event-related brain potential (ERP) data acquired from the sensorimotor cortices, the system consists of three procedures, including enhanced active segment selection, feature extraction, and classification. Firstly, combined with the use of continuous wavelet transform (CWT) and Student's two-sample t-statistics, the 2D anisotropic Gaussian filter is proposed to further refine the active-segment selection. Multiresolution fractal features are then extracted from wavelet data by means of modified fractal dimension. Finally, support vector machine (SVM) is used for classification. Compared with other approaches on motor imagery data, the results indicate that the proposed method is promising in BCI applications.

AB - In this study, an neural-network-based system is proposed for the applications of brain-computer interface (BCI). Applying event-related brain potential (ERP) data acquired from the sensorimotor cortices, the system consists of three procedures, including enhanced active segment selection, feature extraction, and classification. Firstly, combined with the use of continuous wavelet transform (CWT) and Student's two-sample t-statistics, the 2D anisotropic Gaussian filter is proposed to further refine the active-segment selection. Multiresolution fractal features are then extracted from wavelet data by means of modified fractal dimension. Finally, support vector machine (SVM) is used for classification. Compared with other approaches on motor imagery data, the results indicate that the proposed method is promising in BCI applications.

KW - Active segment selection

KW - Brain-computer interface (BCI)

KW - Electroencephalogram (EEG)

KW - Modified fractal dimension

KW - Support vector machine (SVM)

KW - Wavelet transform

UR - http://www.scopus.com/inward/record.url?scp=84875039129&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84875039129&partnerID=8YFLogxK

U2 - 10.1109/GrC.2012.6468559

DO - 10.1109/GrC.2012.6468559

M3 - Conference contribution

SN - 9781467323093

SP - 163

EP - 168

BT - Proceedings - 2012 IEEE International Conference on Granular Computing, GrC 2012

ER -