Single trial Motor Imagery classification in EEG measured during fMRI image acquisition - a first glance

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

Abstract

Non-invasive electroencephalogram (EEG) based Brain-Computer Interfaces (BCIs), which rely on event related desynchronization (ERD), are often affected
by large fluctuations of their accuracy. We want to overcome this drawback by using simultaneous EEG and functional magnetic imaging (fMRI). The question we are addressing in this work is if ERD is still classifiable in EEG on a single trial basis after the removement of fMRI related artefacts. In a first single participant recording we found the classical ERD distribution and were able to compute a leave-one-out-cross-validation (LOOCV) accuracy of 78%, which is significantly higher than chance level.
Original languageEnglish
Title of host publicationProceedings BMT (Biomedizinische Technik) 2013 - Dreiländertagung der Deutschen, Schweizerischen und Österreichischen Gesellschaft für Biomedizinische Technik, Graz
Publisherde Gruyter
Pages1-2
Volume58 (Suppl. 1)
DOIs
Publication statusPublished - 2013
EventBMT 2013, 3-Ländertagung D-A-CH, Gemeinsame Jahrestagung ÖGBMT, SGBT, DGBMT - Graz, Austria
Duration: 19 Sep 201321 Sep 2013

Publication series

NameBiomedical Engineering / Biomedizinische Technik
Publisherde Gruyter

Conference

ConferenceBMT 2013, 3-Ländertagung D-A-CH, Gemeinsame Jahrestagung ÖGBMT, SGBT, DGBMT
CountryAustria
CityGraz
Period19/09/1321/09/13

Fingerprint

electroencephalography
imagery
acquisition
brain
artifacts
recording

Fields of Expertise

  • Human- & Biotechnology

Cite this

Steyrl, D., Wriessnegger, S., & Müller-Putz, G. (2013). Single trial Motor Imagery classification in EEG measured during fMRI image acquisition - a first glance. In Proceedings BMT (Biomedizinische Technik) 2013 - Dreiländertagung der Deutschen, Schweizerischen und Österreichischen Gesellschaft für Biomedizinische Technik, Graz (Vol. 58 (Suppl. 1), pp. 1-2). (Biomedical Engineering / Biomedizinische Technik). de Gruyter. https://doi.org/10.1515/bmt-2013-4450

Single trial Motor Imagery classification in EEG measured during fMRI image acquisition - a first glance. / Steyrl, David; Wriessnegger, Selina; Müller-Putz, Gernot.

Proceedings BMT (Biomedizinische Technik) 2013 - Dreiländertagung der Deutschen, Schweizerischen und Österreichischen Gesellschaft für Biomedizinische Technik, Graz. Vol. 58 (Suppl. 1) de Gruyter, 2013. p. 1-2 (Biomedical Engineering / Biomedizinische Technik).

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

Steyrl, D, Wriessnegger, S & Müller-Putz, G 2013, Single trial Motor Imagery classification in EEG measured during fMRI image acquisition - a first glance. in Proceedings BMT (Biomedizinische Technik) 2013 - Dreiländertagung der Deutschen, Schweizerischen und Österreichischen Gesellschaft für Biomedizinische Technik, Graz. vol. 58 (Suppl. 1), Biomedical Engineering / Biomedizinische Technik, de Gruyter, pp. 1-2, BMT 2013, 3-Ländertagung D-A-CH, Gemeinsame Jahrestagung ÖGBMT, SGBT, DGBMT, Graz, Austria, 19/09/13. https://doi.org/10.1515/bmt-2013-4450
Steyrl D, Wriessnegger S, Müller-Putz G. Single trial Motor Imagery classification in EEG measured during fMRI image acquisition - a first glance. In Proceedings BMT (Biomedizinische Technik) 2013 - Dreiländertagung der Deutschen, Schweizerischen und Österreichischen Gesellschaft für Biomedizinische Technik, Graz. Vol. 58 (Suppl. 1). de Gruyter. 2013. p. 1-2. (Biomedical Engineering / Biomedizinische Technik). https://doi.org/10.1515/bmt-2013-4450
Steyrl, David ; Wriessnegger, Selina ; Müller-Putz, Gernot. / Single trial Motor Imagery classification in EEG measured during fMRI image acquisition - a first glance. Proceedings BMT (Biomedizinische Technik) 2013 - Dreiländertagung der Deutschen, Schweizerischen und Österreichischen Gesellschaft für Biomedizinische Technik, Graz. Vol. 58 (Suppl. 1) de Gruyter, 2013. pp. 1-2 (Biomedical Engineering / Biomedizinische Technik).
@inproceedings{45b2da16c2984be8b857e340881d7bc1,
title = "Single trial Motor Imagery classification in EEG measured during fMRI image acquisition - a first glance",
abstract = "Non-invasive electroencephalogram (EEG) based Brain-Computer Interfaces (BCIs), which rely on event related desynchronization (ERD), are often affectedby large fluctuations of their accuracy. We want to overcome this drawback by using simultaneous EEG and functional magnetic imaging (fMRI). The question we are addressing in this work is if ERD is still classifiable in EEG on a single trial basis after the removement of fMRI related artefacts. In a first single participant recording we found the classical ERD distribution and were able to compute a leave-one-out-cross-validation (LOOCV) accuracy of 78{\%}, which is significantly higher than chance level.",
author = "David Steyrl and Selina Wriessnegger and Gernot M{\"u}ller-Putz",
year = "2013",
doi = "10.1515/bmt-2013-4450",
language = "English",
volume = "58 (Suppl. 1)",
series = "Biomedical Engineering / Biomedizinische Technik",
publisher = "de Gruyter",
pages = "1--2",
booktitle = "Proceedings BMT (Biomedizinische Technik) 2013 - Dreil{\"a}ndertagung der Deutschen, Schweizerischen und {\"O}sterreichischen Gesellschaft f{\"u}r Biomedizinische Technik, Graz",
address = "Germany",

}

TY - GEN

T1 - Single trial Motor Imagery classification in EEG measured during fMRI image acquisition - a first glance

AU - Steyrl, David

AU - Wriessnegger, Selina

AU - Müller-Putz, Gernot

PY - 2013

Y1 - 2013

N2 - Non-invasive electroencephalogram (EEG) based Brain-Computer Interfaces (BCIs), which rely on event related desynchronization (ERD), are often affectedby large fluctuations of their accuracy. We want to overcome this drawback by using simultaneous EEG and functional magnetic imaging (fMRI). The question we are addressing in this work is if ERD is still classifiable in EEG on a single trial basis after the removement of fMRI related artefacts. In a first single participant recording we found the classical ERD distribution and were able to compute a leave-one-out-cross-validation (LOOCV) accuracy of 78%, which is significantly higher than chance level.

AB - Non-invasive electroencephalogram (EEG) based Brain-Computer Interfaces (BCIs), which rely on event related desynchronization (ERD), are often affectedby large fluctuations of their accuracy. We want to overcome this drawback by using simultaneous EEG and functional magnetic imaging (fMRI). The question we are addressing in this work is if ERD is still classifiable in EEG on a single trial basis after the removement of fMRI related artefacts. In a first single participant recording we found the classical ERD distribution and were able to compute a leave-one-out-cross-validation (LOOCV) accuracy of 78%, which is significantly higher than chance level.

U2 - 10.1515/bmt-2013-4450

DO - 10.1515/bmt-2013-4450

M3 - Conference contribution

VL - 58 (Suppl. 1)

T3 - Biomedical Engineering / Biomedizinische Technik

SP - 1

EP - 2

BT - Proceedings BMT (Biomedizinische Technik) 2013 - Dreiländertagung der Deutschen, Schweizerischen und Österreichischen Gesellschaft für Biomedizinische Technik, Graz

PB - de Gruyter

ER -