Subject independent EEG-based BCI decoding

Siamac Fazli, Cristian Grozea, Márton Danóczy, Florin Popescu, Benjamin Blankertz, Klaus Robert Müller

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

31 Citations (Scopus)

Abstract

In the quest to make Brain Computer Interfacing (BCI) more usable, dry electrodes have emerged that get rid of the initial 30 minutes required for placing an electrode cap. Another time consuming step is the required individualized adaptation to the BCI user, which involves another 30 minutes calibration for assessing a subject's brain signature. In this paper we aim to also remove this calibration proceedure from BCI setup time by means of machine learning. In particular, we harvest a large database of EEG BCI motor imagination recordings (83 subjects) for constructing a library of subject-specific spatio-temporal filters and derive a subject independent BCI classifier. Our offline results indicate that BCI-naïve users could start real-time BCI use with no prior calibration at only a very moderate performance loss.

Original languageEnglish
Title of host publicationAdvances in Neural Information Processing Systems 22 - Proceedings of the 2009 Conference
Pages513-521
Number of pages9
Publication statusPublished - Dec 1 2009
Event23rd Annual Conference on Neural Information Processing Systems, NIPS 2009 - Vancouver, BC, Canada
Duration: Dec 7 2009Dec 10 2009

Publication series

NameAdvances in Neural Information Processing Systems 22 - Proceedings of the 2009 Conference

Conference

Conference23rd Annual Conference on Neural Information Processing Systems, NIPS 2009
CountryCanada
CityVancouver, BC
Period12/7/0912/10/09

Fingerprint

Electroencephalography
Decoding
Brain
Calibration
Electrodes
Learning systems
Classifiers

ASJC Scopus subject areas

  • Information Systems

Cite this

Fazli, S., Grozea, C., Danóczy, M., Popescu, F., Blankertz, B., & Müller, K. R. (2009). Subject independent EEG-based BCI decoding. In Advances in Neural Information Processing Systems 22 - Proceedings of the 2009 Conference (pp. 513-521). (Advances in Neural Information Processing Systems 22 - Proceedings of the 2009 Conference).

Subject independent EEG-based BCI decoding. / Fazli, Siamac; Grozea, Cristian; Danóczy, Márton; Popescu, Florin; Blankertz, Benjamin; Müller, Klaus Robert.

Advances in Neural Information Processing Systems 22 - Proceedings of the 2009 Conference. 2009. p. 513-521 (Advances in Neural Information Processing Systems 22 - Proceedings of the 2009 Conference).

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

Fazli, S, Grozea, C, Danóczy, M, Popescu, F, Blankertz, B & Müller, KR 2009, Subject independent EEG-based BCI decoding. in Advances in Neural Information Processing Systems 22 - Proceedings of the 2009 Conference. Advances in Neural Information Processing Systems 22 - Proceedings of the 2009 Conference, pp. 513-521, 23rd Annual Conference on Neural Information Processing Systems, NIPS 2009, Vancouver, BC, Canada, 12/7/09.
Fazli S, Grozea C, Danóczy M, Popescu F, Blankertz B, Müller KR. Subject independent EEG-based BCI decoding. In Advances in Neural Information Processing Systems 22 - Proceedings of the 2009 Conference. 2009. p. 513-521. (Advances in Neural Information Processing Systems 22 - Proceedings of the 2009 Conference).
Fazli, Siamac ; Grozea, Cristian ; Danóczy, Márton ; Popescu, Florin ; Blankertz, Benjamin ; Müller, Klaus Robert. / Subject independent EEG-based BCI decoding. Advances in Neural Information Processing Systems 22 - Proceedings of the 2009 Conference. 2009. pp. 513-521 (Advances in Neural Information Processing Systems 22 - Proceedings of the 2009 Conference).
@inproceedings{0a5d8e4c7c8d4e59a443a204e4632fd6,
title = "Subject independent EEG-based BCI decoding",
abstract = "In the quest to make Brain Computer Interfacing (BCI) more usable, dry electrodes have emerged that get rid of the initial 30 minutes required for placing an electrode cap. Another time consuming step is the required individualized adaptation to the BCI user, which involves another 30 minutes calibration for assessing a subject's brain signature. In this paper we aim to also remove this calibration proceedure from BCI setup time by means of machine learning. In particular, we harvest a large database of EEG BCI motor imagination recordings (83 subjects) for constructing a library of subject-specific spatio-temporal filters and derive a subject independent BCI classifier. Our offline results indicate that BCI-na{\"i}ve users could start real-time BCI use with no prior calibration at only a very moderate performance loss.",
author = "Siamac Fazli and Cristian Grozea and M{\'a}rton Dan{\'o}czy and Florin Popescu and Benjamin Blankertz and M{\"u}ller, {Klaus Robert}",
year = "2009",
month = "12",
day = "1",
language = "English",
isbn = "9781615679119",
series = "Advances in Neural Information Processing Systems 22 - Proceedings of the 2009 Conference",
pages = "513--521",
booktitle = "Advances in Neural Information Processing Systems 22 - Proceedings of the 2009 Conference",

}

TY - GEN

T1 - Subject independent EEG-based BCI decoding

AU - Fazli, Siamac

AU - Grozea, Cristian

AU - Danóczy, Márton

AU - Popescu, Florin

AU - Blankertz, Benjamin

AU - Müller, Klaus Robert

PY - 2009/12/1

Y1 - 2009/12/1

N2 - In the quest to make Brain Computer Interfacing (BCI) more usable, dry electrodes have emerged that get rid of the initial 30 minutes required for placing an electrode cap. Another time consuming step is the required individualized adaptation to the BCI user, which involves another 30 minutes calibration for assessing a subject's brain signature. In this paper we aim to also remove this calibration proceedure from BCI setup time by means of machine learning. In particular, we harvest a large database of EEG BCI motor imagination recordings (83 subjects) for constructing a library of subject-specific spatio-temporal filters and derive a subject independent BCI classifier. Our offline results indicate that BCI-naïve users could start real-time BCI use with no prior calibration at only a very moderate performance loss.

AB - In the quest to make Brain Computer Interfacing (BCI) more usable, dry electrodes have emerged that get rid of the initial 30 minutes required for placing an electrode cap. Another time consuming step is the required individualized adaptation to the BCI user, which involves another 30 minutes calibration for assessing a subject's brain signature. In this paper we aim to also remove this calibration proceedure from BCI setup time by means of machine learning. In particular, we harvest a large database of EEG BCI motor imagination recordings (83 subjects) for constructing a library of subject-specific spatio-temporal filters and derive a subject independent BCI classifier. Our offline results indicate that BCI-naïve users could start real-time BCI use with no prior calibration at only a very moderate performance loss.

UR - http://www.scopus.com/inward/record.url?scp=79955908479&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79955908479&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781615679119

T3 - Advances in Neural Information Processing Systems 22 - Proceedings of the 2009 Conference

SP - 513

EP - 521

BT - Advances in Neural Information Processing Systems 22 - Proceedings of the 2009 Conference

ER -