Hemodynamic characteristics for improvement of EEG-BCI performance

Yohei Tomita, Yasue Mitsukura

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

9 Citations (Scopus)

Abstract

Although brain computer interfaces (BCI) based on electroencephalographic (EEG) signals have been studied increasingly over decades, their performance is still limited in two main aspects. First, the shorter the EEG epochs, the more difficult the detection of a BCI command. Second, BCI commands are often misclassified while the subject is not performing any tasks by not focusing on a command (offset condition) because the EEG characteristics of the offset condition are not unique. 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. The offset condition is distinguished from the onset condition (focusing on a command) with extracted NIRS features through the design of low-pass filter. BCI command estimates were based on EEG SSVEP response. Simultaneous evaluation of EEG and NIRS was shown to improve the SSVEP classification, notably including the offset condition as an independent class, using a novel offset condition estimation approach. For 13 subjects, wrong classification for 9 classes with inclusion of offset condition were decreased. This proposed bimodal approach including the offset condition detection may render current BCI systems more reliable.

Original languageEnglish
Title of host publication2013 6th International Conference on Human System Interactions, HSI 2013
Pages495-500
Number of pages6
DOIs
Publication statusPublished - 2013
Externally publishedYes
Event2013 6th International Conference on Human System Interactions, HSI 2013 - Gdansk, Sopot, Poland
Duration: 2013 Jun 62013 Jun 8

Other

Other2013 6th International Conference on Human System Interactions, HSI 2013
CountryPoland
CityGdansk, Sopot
Period13/6/613/6/8

Fingerprint

Brain computer interface
Hemodynamics
Near infrared spectroscopy
Bioelectric potentials
Low pass filters
Brain

ASJC Scopus subject areas

  • Human-Computer Interaction

Cite this

Tomita, Y., & Mitsukura, Y. (2013). Hemodynamic characteristics for improvement of EEG-BCI performance. In 2013 6th International Conference on Human System Interactions, HSI 2013 (pp. 495-500). [6577871] https://doi.org/10.1109/HSI.2013.6577871

Hemodynamic characteristics for improvement of EEG-BCI performance. / Tomita, Yohei; Mitsukura, Yasue.

2013 6th International Conference on Human System Interactions, HSI 2013. 2013. p. 495-500 6577871.

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

Tomita, Y & Mitsukura, Y 2013, Hemodynamic characteristics for improvement of EEG-BCI performance. in 2013 6th International Conference on Human System Interactions, HSI 2013., 6577871, pp. 495-500, 2013 6th International Conference on Human System Interactions, HSI 2013, Gdansk, Sopot, Poland, 13/6/6. https://doi.org/10.1109/HSI.2013.6577871
Tomita Y, Mitsukura Y. Hemodynamic characteristics for improvement of EEG-BCI performance. In 2013 6th International Conference on Human System Interactions, HSI 2013. 2013. p. 495-500. 6577871 https://doi.org/10.1109/HSI.2013.6577871
Tomita, Yohei ; Mitsukura, Yasue. / Hemodynamic characteristics for improvement of EEG-BCI performance. 2013 6th International Conference on Human System Interactions, HSI 2013. 2013. pp. 495-500
@inproceedings{2c2ce592b99e4a4ea9c7c54a65cf5e31,
title = "Hemodynamic characteristics for improvement of EEG-BCI performance",
abstract = "Although brain computer interfaces (BCI) based on electroencephalographic (EEG) signals have been studied increasingly over decades, their performance is still limited in two main aspects. First, the shorter the EEG epochs, the more difficult the detection of a BCI command. Second, BCI commands are often misclassified while the subject is not performing any tasks by not focusing on a command (offset condition) because the EEG characteristics of the offset condition are not unique. 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. The offset condition is distinguished from the onset condition (focusing on a command) with extracted NIRS features through the design of low-pass filter. BCI command estimates were based on EEG SSVEP response. Simultaneous evaluation of EEG and NIRS was shown to improve the SSVEP classification, notably including the offset condition as an independent class, using a novel offset condition estimation approach. For 13 subjects, wrong classification for 9 classes with inclusion of offset condition were decreased. This proposed bimodal approach including the offset condition detection may render current BCI systems more reliable.",
author = "Yohei Tomita and Yasue Mitsukura",
year = "2013",
doi = "10.1109/HSI.2013.6577871",
language = "English",
isbn = "9781467356374",
pages = "495--500",
booktitle = "2013 6th International Conference on Human System Interactions, HSI 2013",

}

TY - GEN

T1 - Hemodynamic characteristics for improvement of EEG-BCI performance

AU - Tomita, Yohei

AU - Mitsukura, Yasue

PY - 2013

Y1 - 2013

N2 - Although brain computer interfaces (BCI) based on electroencephalographic (EEG) signals have been studied increasingly over decades, their performance is still limited in two main aspects. First, the shorter the EEG epochs, the more difficult the detection of a BCI command. Second, BCI commands are often misclassified while the subject is not performing any tasks by not focusing on a command (offset condition) because the EEG characteristics of the offset condition are not unique. 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. The offset condition is distinguished from the onset condition (focusing on a command) with extracted NIRS features through the design of low-pass filter. BCI command estimates were based on EEG SSVEP response. Simultaneous evaluation of EEG and NIRS was shown to improve the SSVEP classification, notably including the offset condition as an independent class, using a novel offset condition estimation approach. For 13 subjects, wrong classification for 9 classes with inclusion of offset condition were decreased. This proposed bimodal approach including the offset condition detection may render current BCI systems more reliable.

AB - Although brain computer interfaces (BCI) based on electroencephalographic (EEG) signals have been studied increasingly over decades, their performance is still limited in two main aspects. First, the shorter the EEG epochs, the more difficult the detection of a BCI command. Second, BCI commands are often misclassified while the subject is not performing any tasks by not focusing on a command (offset condition) because the EEG characteristics of the offset condition are not unique. 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. The offset condition is distinguished from the onset condition (focusing on a command) with extracted NIRS features through the design of low-pass filter. BCI command estimates were based on EEG SSVEP response. Simultaneous evaluation of EEG and NIRS was shown to improve the SSVEP classification, notably including the offset condition as an independent class, using a novel offset condition estimation approach. For 13 subjects, wrong classification for 9 classes with inclusion of offset condition were decreased. This proposed bimodal approach including the offset condition detection may render current BCI systems more reliable.

UR - http://www.scopus.com/inward/record.url?scp=84883714446&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84883714446&partnerID=8YFLogxK

U2 - 10.1109/HSI.2013.6577871

DO - 10.1109/HSI.2013.6577871

M3 - Conference contribution

SN - 9781467356374

SP - 495

EP - 500

BT - 2013 6th International Conference on Human System Interactions, HSI 2013

ER -