Improvement of classification accuracy in a phase-tagged steady-state visual evoked potential-based brain computer interface using multiclass support vector machine

Chia Lung Yeh, Po Lei Lee, Wei Ming Chen, Chun Yen Chang, Yu Te Wu, Gong Yau Lan

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

Background: Brain computer interface (BCI) is an emerging technology for paralyzed patients to communicate with external environments. Among current BCIs, the steady-state visual evoked potential (SSVEP)-based BCI has drawn great attention due to its characteristics of easy preparation, high information transfer rate (ITR), high accuracy, and low cost. However, electroencephalogram (EEG) signals are electrophysiological responses reflecting the underlying neural activities which are dependent upon subject's physiological states (e.g., emotion, attention, etc.) and usually variant among different individuals. The development of classification approaches to account for each individual's difference in SSVEP is needed but was seldom reported.Methods: This paper presents a multiclass support vector machine (SVM)-based classification approach for gaze-target detections in a phase-tagged SSVEP-based BCI. In the training steps, the amplitude and phase features of SSVEP from off-line recordings were used to train a multiclass SVM for each subject. In the on-line application study, effective epochs which contained sufficient SSVEP information of gaze targets were first determined using Kolmogorov-Smirnov (K-S) test, and the amplitude and phase features of effective epochs were subsequently inputted to the multiclass SVM to recognize user's gaze targets.Results: The on-line performance using the proposed approach has achieved high accuracy (89.88 ± 4.76%), fast responding time (effective epoch length = 1.13 ± 0.02 s), and the information transfer rate (ITR) was 50.91 ± 8.70 bits/min.Conclusions: The multiclass SVM-based classification approach has been successfully implemented to improve the classification accuracy in a phase-tagged SSVEP-based BCI. The present study has shown the multiclass SVM can be effectively adapted to each subject's SSVEPs to discriminate SSVEP phase information from gazing at different gazed targets.

Original languageEnglish
Article number46
JournalBioMedical Engineering Online
Volume12
Issue number1
DOIs
Publication statusPublished - May 21 2013
Externally publishedYes

Fingerprint

Brain-Computer Interfaces
Brain computer interface
Visual Evoked Potentials
Bioelectric potentials
Support vector machines
Nonparametric Statistics
Electroencephalography
Support Vector Machine
Target tracking
Individuality
Emotions
Technology
Costs and Cost Analysis

ASJC Scopus subject areas

  • Radiological and Ultrasound Technology
  • Biomaterials
  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging

Cite this

Improvement of classification accuracy in a phase-tagged steady-state visual evoked potential-based brain computer interface using multiclass support vector machine. / Yeh, Chia Lung; Lee, Po Lei; Chen, Wei Ming; Chang, Chun Yen; Wu, Yu Te; Lan, Gong Yau.

In: BioMedical Engineering Online, Vol. 12, No. 1, 46, 21.05.2013.

Research output: Contribution to journalArticle

@article{6322b6ae05164adc983e7fdb3f9cafd8,
title = "Improvement of classification accuracy in a phase-tagged steady-state visual evoked potential-based brain computer interface using multiclass support vector machine",
abstract = "Background: Brain computer interface (BCI) is an emerging technology for paralyzed patients to communicate with external environments. Among current BCIs, the steady-state visual evoked potential (SSVEP)-based BCI has drawn great attention due to its characteristics of easy preparation, high information transfer rate (ITR), high accuracy, and low cost. However, electroencephalogram (EEG) signals are electrophysiological responses reflecting the underlying neural activities which are dependent upon subject's physiological states (e.g., emotion, attention, etc.) and usually variant among different individuals. The development of classification approaches to account for each individual's difference in SSVEP is needed but was seldom reported.Methods: This paper presents a multiclass support vector machine (SVM)-based classification approach for gaze-target detections in a phase-tagged SSVEP-based BCI. In the training steps, the amplitude and phase features of SSVEP from off-line recordings were used to train a multiclass SVM for each subject. In the on-line application study, effective epochs which contained sufficient SSVEP information of gaze targets were first determined using Kolmogorov-Smirnov (K-S) test, and the amplitude and phase features of effective epochs were subsequently inputted to the multiclass SVM to recognize user's gaze targets.Results: The on-line performance using the proposed approach has achieved high accuracy (89.88 ± 4.76{\%}), fast responding time (effective epoch length = 1.13 ± 0.02 s), and the information transfer rate (ITR) was 50.91 ± 8.70 bits/min.Conclusions: The multiclass SVM-based classification approach has been successfully implemented to improve the classification accuracy in a phase-tagged SSVEP-based BCI. The present study has shown the multiclass SVM can be effectively adapted to each subject's SSVEPs to discriminate SSVEP phase information from gazing at different gazed targets.",
keywords = "Support Vector Machine, Visual Stimulus, Input Vector, Phase Feature, Brain Computer Interface",
author = "Yeh, {Chia Lung} and Lee, {Po Lei} and Chen, {Wei Ming} and Chang, {Chun Yen} and Wu, {Yu Te} and Lan, {Gong Yau}",
year = "2013",
month = "5",
day = "21",
doi = "10.1186/1475-925X-12-46",
language = "English",
volume = "12",
journal = "BioMedical Engineering Online",
issn = "1475-925X",
publisher = "BioMed Central",
number = "1",

}

TY - JOUR

T1 - Improvement of classification accuracy in a phase-tagged steady-state visual evoked potential-based brain computer interface using multiclass support vector machine

AU - Yeh, Chia Lung

AU - Lee, Po Lei

AU - Chen, Wei Ming

AU - Chang, Chun Yen

AU - Wu, Yu Te

AU - Lan, Gong Yau

PY - 2013/5/21

Y1 - 2013/5/21

N2 - Background: Brain computer interface (BCI) is an emerging technology for paralyzed patients to communicate with external environments. Among current BCIs, the steady-state visual evoked potential (SSVEP)-based BCI has drawn great attention due to its characteristics of easy preparation, high information transfer rate (ITR), high accuracy, and low cost. However, electroencephalogram (EEG) signals are electrophysiological responses reflecting the underlying neural activities which are dependent upon subject's physiological states (e.g., emotion, attention, etc.) and usually variant among different individuals. The development of classification approaches to account for each individual's difference in SSVEP is needed but was seldom reported.Methods: This paper presents a multiclass support vector machine (SVM)-based classification approach for gaze-target detections in a phase-tagged SSVEP-based BCI. In the training steps, the amplitude and phase features of SSVEP from off-line recordings were used to train a multiclass SVM for each subject. In the on-line application study, effective epochs which contained sufficient SSVEP information of gaze targets were first determined using Kolmogorov-Smirnov (K-S) test, and the amplitude and phase features of effective epochs were subsequently inputted to the multiclass SVM to recognize user's gaze targets.Results: The on-line performance using the proposed approach has achieved high accuracy (89.88 ± 4.76%), fast responding time (effective epoch length = 1.13 ± 0.02 s), and the information transfer rate (ITR) was 50.91 ± 8.70 bits/min.Conclusions: The multiclass SVM-based classification approach has been successfully implemented to improve the classification accuracy in a phase-tagged SSVEP-based BCI. The present study has shown the multiclass SVM can be effectively adapted to each subject's SSVEPs to discriminate SSVEP phase information from gazing at different gazed targets.

AB - Background: Brain computer interface (BCI) is an emerging technology for paralyzed patients to communicate with external environments. Among current BCIs, the steady-state visual evoked potential (SSVEP)-based BCI has drawn great attention due to its characteristics of easy preparation, high information transfer rate (ITR), high accuracy, and low cost. However, electroencephalogram (EEG) signals are electrophysiological responses reflecting the underlying neural activities which are dependent upon subject's physiological states (e.g., emotion, attention, etc.) and usually variant among different individuals. The development of classification approaches to account for each individual's difference in SSVEP is needed but was seldom reported.Methods: This paper presents a multiclass support vector machine (SVM)-based classification approach for gaze-target detections in a phase-tagged SSVEP-based BCI. In the training steps, the amplitude and phase features of SSVEP from off-line recordings were used to train a multiclass SVM for each subject. In the on-line application study, effective epochs which contained sufficient SSVEP information of gaze targets were first determined using Kolmogorov-Smirnov (K-S) test, and the amplitude and phase features of effective epochs were subsequently inputted to the multiclass SVM to recognize user's gaze targets.Results: The on-line performance using the proposed approach has achieved high accuracy (89.88 ± 4.76%), fast responding time (effective epoch length = 1.13 ± 0.02 s), and the information transfer rate (ITR) was 50.91 ± 8.70 bits/min.Conclusions: The multiclass SVM-based classification approach has been successfully implemented to improve the classification accuracy in a phase-tagged SSVEP-based BCI. The present study has shown the multiclass SVM can be effectively adapted to each subject's SSVEPs to discriminate SSVEP phase information from gazing at different gazed targets.

KW - Support Vector Machine

KW - Visual Stimulus

KW - Input Vector

KW - Phase Feature

KW - Brain Computer Interface

UR - http://www.scopus.com/inward/record.url?scp=84878646711&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84878646711&partnerID=8YFLogxK

U2 - 10.1186/1475-925X-12-46

DO - 10.1186/1475-925X-12-46

M3 - Article

C2 - 23692974

AN - SCOPUS:84878646711

VL - 12

JO - BioMedical Engineering Online

JF - BioMedical Engineering Online

SN - 1475-925X

IS - 1

M1 - 46

ER -