Bimodal BCI using simultaneously NIRS and EEG

Yohei Tomita, Francois Benoit Vialatte, Gerard Dreyfus, Yasue Mitsukura, Hovagim Bakardjian, Andrzej Cichocki

Research output: Contribution to journalArticle

52 Citations (Scopus)

Abstract

Although noninvasive brain-computer interfaces (BCI) based on electroencephalographic (EEG) signals have been studied increasingly over the recent decades, their performance is still limited in two important aspects. First, the difficulty of performing a reliable detection of BCI commands increases when EEG epoch length decreases, which makes high information transfer rates difficult to achieve. Second, the BCI system often misclassifies the EEG signals as commands, although the subject is not performing any task. In order to circumvent these limitations, the hemodynamic fluctuations in the brain during stimulation with steady-state visual evoked potentials (SSVEP) were measured using near-infrared spectroscopy (NIRS) simultaneously with EEG. BCI commands were estimated based on responses to a flickering checkerboard (ON-period). Furthermore, an 'idle' command was generated from the signal recorded by the NIRS system when the checkerboard was not flickering (OFF-period). The joint use of EEG and NIRS was shown to improve the SSVEP classification. For 13 subjects, the relative improvement in error rates obtained by using the NIRS signal, for nine classes including the 'idle' mode, ranged from 85% to 53%, when the epoch length increase from 3 to 12 s. These results were obtained from only one EEG and one NIRS channel. The proposed bimodal NIRS-EEG approach, including detection of the idle mode, may make current BCI systems faster and more reliable.

Original languageEnglish
Article number6714514
Pages (from-to)1274-1284
Number of pages11
JournalIEEE Transactions on Biomedical Engineering
Volume61
Issue number4
DOIs
Publication statusPublished - 2014

Fingerprint

Brain computer interface
Near infrared spectroscopy
Flickering
Bioelectric potentials
Hemodynamics
Brain

Keywords

  • bimodal
  • Brain-computer interface (BCI)
  • simultaneous electroencephalographic (EEG) and near-infrared spectroscopy (NIRS)
  • steady-state visual evoked potentials (SSVEP)

ASJC Scopus subject areas

  • Biomedical Engineering

Cite this

Tomita, Y., Vialatte, F. B., Dreyfus, G., Mitsukura, Y., Bakardjian, H., & Cichocki, A. (2014). Bimodal BCI using simultaneously NIRS and EEG. IEEE Transactions on Biomedical Engineering, 61(4), 1274-1284. [6714514]. https://doi.org/10.1109/TBME.2014.2300492

Bimodal BCI using simultaneously NIRS and EEG. / Tomita, Yohei; Vialatte, Francois Benoit; Dreyfus, Gerard; Mitsukura, Yasue; Bakardjian, Hovagim; Cichocki, Andrzej.

In: IEEE Transactions on Biomedical Engineering, Vol. 61, No. 4, 6714514, 2014, p. 1274-1284.

Research output: Contribution to journalArticle

Tomita, Y, Vialatte, FB, Dreyfus, G, Mitsukura, Y, Bakardjian, H & Cichocki, A 2014, 'Bimodal BCI using simultaneously NIRS and EEG', IEEE Transactions on Biomedical Engineering, vol. 61, no. 4, 6714514, pp. 1274-1284. https://doi.org/10.1109/TBME.2014.2300492
Tomita Y, Vialatte FB, Dreyfus G, Mitsukura Y, Bakardjian H, Cichocki A. Bimodal BCI using simultaneously NIRS and EEG. IEEE Transactions on Biomedical Engineering. 2014;61(4):1274-1284. 6714514. https://doi.org/10.1109/TBME.2014.2300492
Tomita, Yohei ; Vialatte, Francois Benoit ; Dreyfus, Gerard ; Mitsukura, Yasue ; Bakardjian, Hovagim ; Cichocki, Andrzej. / Bimodal BCI using simultaneously NIRS and EEG. In: IEEE Transactions on Biomedical Engineering. 2014 ; Vol. 61, No. 4. pp. 1274-1284.
@article{989912fbae59434c98de1ac150d85d4b,
title = "Bimodal BCI using simultaneously NIRS and EEG",
abstract = "Although noninvasive brain-computer interfaces (BCI) based on electroencephalographic (EEG) signals have been studied increasingly over the recent decades, their performance is still limited in two important aspects. First, the difficulty of performing a reliable detection of BCI commands increases when EEG epoch length decreases, which makes high information transfer rates difficult to achieve. Second, the BCI system often misclassifies the EEG signals as commands, although the subject is not performing any task. In order to circumvent these limitations, the hemodynamic fluctuations in the brain during stimulation with steady-state visual evoked potentials (SSVEP) were measured using near-infrared spectroscopy (NIRS) simultaneously with EEG. BCI commands were estimated based on responses to a flickering checkerboard (ON-period). Furthermore, an 'idle' command was generated from the signal recorded by the NIRS system when the checkerboard was not flickering (OFF-period). The joint use of EEG and NIRS was shown to improve the SSVEP classification. For 13 subjects, the relative improvement in error rates obtained by using the NIRS signal, for nine classes including the 'idle' mode, ranged from 85{\%} to 53{\%}, when the epoch length increase from 3 to 12 s. These results were obtained from only one EEG and one NIRS channel. The proposed bimodal NIRS-EEG approach, including detection of the idle mode, may make current BCI systems faster and more reliable.",
keywords = "bimodal, Brain-computer interface (BCI), simultaneous electroencephalographic (EEG) and near-infrared spectroscopy (NIRS), steady-state visual evoked potentials (SSVEP)",
author = "Yohei Tomita and Vialatte, {Francois Benoit} and Gerard Dreyfus and Yasue Mitsukura and Hovagim Bakardjian and Andrzej Cichocki",
year = "2014",
doi = "10.1109/TBME.2014.2300492",
language = "English",
volume = "61",
pages = "1274--1284",
journal = "IEEE Transactions on Biomedical Engineering",
issn = "0018-9294",
publisher = "IEEE Computer Society",
number = "4",

}

TY - JOUR

T1 - Bimodal BCI using simultaneously NIRS and EEG

AU - Tomita, Yohei

AU - Vialatte, Francois Benoit

AU - Dreyfus, Gerard

AU - Mitsukura, Yasue

AU - Bakardjian, Hovagim

AU - Cichocki, Andrzej

PY - 2014

Y1 - 2014

N2 - Although noninvasive brain-computer interfaces (BCI) based on electroencephalographic (EEG) signals have been studied increasingly over the recent decades, their performance is still limited in two important aspects. First, the difficulty of performing a reliable detection of BCI commands increases when EEG epoch length decreases, which makes high information transfer rates difficult to achieve. Second, the BCI system often misclassifies the EEG signals as commands, although the subject is not performing any task. In order to circumvent these limitations, the hemodynamic fluctuations in the brain during stimulation with steady-state visual evoked potentials (SSVEP) were measured using near-infrared spectroscopy (NIRS) simultaneously with EEG. BCI commands were estimated based on responses to a flickering checkerboard (ON-period). Furthermore, an 'idle' command was generated from the signal recorded by the NIRS system when the checkerboard was not flickering (OFF-period). The joint use of EEG and NIRS was shown to improve the SSVEP classification. For 13 subjects, the relative improvement in error rates obtained by using the NIRS signal, for nine classes including the 'idle' mode, ranged from 85% to 53%, when the epoch length increase from 3 to 12 s. These results were obtained from only one EEG and one NIRS channel. The proposed bimodal NIRS-EEG approach, including detection of the idle mode, may make current BCI systems faster and more reliable.

AB - Although noninvasive brain-computer interfaces (BCI) based on electroencephalographic (EEG) signals have been studied increasingly over the recent decades, their performance is still limited in two important aspects. First, the difficulty of performing a reliable detection of BCI commands increases when EEG epoch length decreases, which makes high information transfer rates difficult to achieve. Second, the BCI system often misclassifies the EEG signals as commands, although the subject is not performing any task. In order to circumvent these limitations, the hemodynamic fluctuations in the brain during stimulation with steady-state visual evoked potentials (SSVEP) were measured using near-infrared spectroscopy (NIRS) simultaneously with EEG. BCI commands were estimated based on responses to a flickering checkerboard (ON-period). Furthermore, an 'idle' command was generated from the signal recorded by the NIRS system when the checkerboard was not flickering (OFF-period). The joint use of EEG and NIRS was shown to improve the SSVEP classification. For 13 subjects, the relative improvement in error rates obtained by using the NIRS signal, for nine classes including the 'idle' mode, ranged from 85% to 53%, when the epoch length increase from 3 to 12 s. These results were obtained from only one EEG and one NIRS channel. The proposed bimodal NIRS-EEG approach, including detection of the idle mode, may make current BCI systems faster and more reliable.

KW - bimodal

KW - Brain-computer interface (BCI)

KW - simultaneous electroencephalographic (EEG) and near-infrared spectroscopy (NIRS)

KW - steady-state visual evoked potentials (SSVEP)

UR - http://www.scopus.com/inward/record.url?scp=84897127294&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84897127294&partnerID=8YFLogxK

U2 - 10.1109/TBME.2014.2300492

DO - 10.1109/TBME.2014.2300492

M3 - Article

VL - 61

SP - 1274

EP - 1284

JO - IEEE Transactions on Biomedical Engineering

JF - IEEE Transactions on Biomedical Engineering

SN - 0018-9294

IS - 4

M1 - 6714514

ER -