Asynchronous detection of error-related potentials using a generic classifier

Publikation: Beitrag in Buch/Bericht/KonferenzbandBeitrag in einem KonferenzbandForschungBegutachtung

Abstract

Error-related potentials (ErrPs) can be usedto improve BCIs’ performance but its use is often with-held by long calibration periods. We recorded EEG dataof 15 participants while controlling a robotic arm towardsa target. In 30 % of the trials, the protocol prompted anerror during the trial in order to trigger ErrPs in the partic-ipants. For each participant, we trained an ErrP classifierusing the data of the remaining 14 participants. Each ofthese classifiers was tested asynchronously on the data ofthe selected participant. The threshold that maximizedthe product of the average true positive rate (TPR) andthe average true negative rate (TNR) wasτ=0.7. For thisthreshold, the average TPR was 53.6 % and the averageTNR was 82.0 %. These results hint at the feasibility oftransferring ErrPs between participants as a reliable strat-egy to reduce or even remove the calibration period whentraining ErrP classifiers to be used in an asynchronous manner
Originalspracheenglisch
TitelProceedings of the 8th Graz Brain Computer Interface Conference 2019
UntertitelBridging Science and Application
Redakteure/-innenGernot R. Müller-Putz, Jonas C. Ditz, Selina Wriessnegger
ErscheinungsortGraz
Herausgeber (Verlag)Verlag der Technischen Universität Graz
Seiten54-58
Seitenumfang5
ISBN (elektronisch)978-3-85125-682-6
DOIs
PublikationsstatusVeröffentlicht - 2019
Veranstaltung8th Graz Brain-Computer Interface Conference 2019: Bridging Science and Application - Petersgasse 16, Graz, Österreich
Dauer: 16 Sep 201920 Sep 2019
Konferenznummer: 8
https://www.tugraz.at/institutes/ine/graz-bci-conferences/8th-graz-bci-conference-2019/

Konferenz

Konferenz8th Graz Brain-Computer Interface Conference 2019
KurztitelGBCIC 2019
LandÖsterreich
OrtGraz
Zeitraum16/09/1920/09/19
Internetadresse

Fingerprint

Calibration
Robotics
Clinical Protocols
Electroencephalography

Dies zitieren

Lopes Dias, C., Sburlea, A. I., & Müller-Putz, G. (2019). Asynchronous detection of error-related potentials using a generic classifier. in G. R. Müller-Putz, J. C. Ditz, & S. Wriessnegger (Hrsg.), Proceedings of the 8th Graz Brain Computer Interface Conference 2019: Bridging Science and Application (S. 54-58). Graz: Verlag der Technischen Universität Graz. https://doi.org/10.3217/978-3-85125-682-6-11

Asynchronous detection of error-related potentials using a generic classifier. / Lopes Dias, Catarina; Sburlea, Andreea Ioana; Müller-Putz, Gernot.

Proceedings of the 8th Graz Brain Computer Interface Conference 2019: Bridging Science and Application. Hrsg. / Gernot R. Müller-Putz; Jonas C. Ditz; Selina Wriessnegger. Graz : Verlag der Technischen Universität Graz, 2019. S. 54-58.

Publikation: Beitrag in Buch/Bericht/KonferenzbandBeitrag in einem KonferenzbandForschungBegutachtung

Lopes Dias, C, Sburlea, AI & Müller-Putz, G 2019, Asynchronous detection of error-related potentials using a generic classifier. in GR Müller-Putz, JC Ditz & S Wriessnegger (Hrsg.), Proceedings of the 8th Graz Brain Computer Interface Conference 2019: Bridging Science and Application. Verlag der Technischen Universität Graz, Graz, S. 54-58, 8th Graz Brain-Computer Interface Conference 2019, Graz, Österreich, 16/09/19. https://doi.org/10.3217/978-3-85125-682-6-11
Lopes Dias C, Sburlea AI, Müller-Putz G. Asynchronous detection of error-related potentials using a generic classifier. in Müller-Putz GR, Ditz JC, Wriessnegger S, Hrsg., Proceedings of the 8th Graz Brain Computer Interface Conference 2019: Bridging Science and Application. Graz: Verlag der Technischen Universität Graz. 2019. S. 54-58 https://doi.org/10.3217/978-3-85125-682-6-11
Lopes Dias, Catarina ; Sburlea, Andreea Ioana ; Müller-Putz, Gernot. / Asynchronous detection of error-related potentials using a generic classifier. Proceedings of the 8th Graz Brain Computer Interface Conference 2019: Bridging Science and Application. Hrsg. / Gernot R. Müller-Putz ; Jonas C. Ditz ; Selina Wriessnegger. Graz : Verlag der Technischen Universität Graz, 2019. S. 54-58
@inproceedings{f6ca2e2693ea47a68a5516795ea9c79a,
title = "Asynchronous detection of error-related potentials using a generic classifier",
abstract = "Error-related potentials (ErrPs) can be usedto improve BCIs’ performance but its use is often with-held by long calibration periods. We recorded EEG dataof 15 participants while controlling a robotic arm towardsa target. In 30 {\%} of the trials, the protocol prompted anerror during the trial in order to trigger ErrPs in the partic-ipants. For each participant, we trained an ErrP classifierusing the data of the remaining 14 participants. Each ofthese classifiers was tested asynchronously on the data ofthe selected participant. The threshold that maximizedthe product of the average true positive rate (TPR) andthe average true negative rate (TNR) wasτ=0.7. For thisthreshold, the average TPR was 53.6 {\%} and the averageTNR was 82.0 {\%}. These results hint at the feasibility oftransferring ErrPs between participants as a reliable strat-egy to reduce or even remove the calibration period whentraining ErrP classifiers to be used in an asynchronous manner",
author = "{Lopes Dias}, Catarina and Sburlea, {Andreea Ioana} and Gernot M{\"u}ller-Putz",
year = "2019",
doi = "10.3217/978-3-85125-682-6-11",
language = "English",
pages = "54--58",
editor = "M{\"u}ller-Putz, {Gernot R.} and Ditz, {Jonas C.} and Selina Wriessnegger",
booktitle = "Proceedings of the 8th Graz Brain Computer Interface Conference 2019",
publisher = "Verlag der Technischen Universit{\"a}t Graz",

}

TY - GEN

T1 - Asynchronous detection of error-related potentials using a generic classifier

AU - Lopes Dias, Catarina

AU - Sburlea, Andreea Ioana

AU - Müller-Putz, Gernot

PY - 2019

Y1 - 2019

N2 - Error-related potentials (ErrPs) can be usedto improve BCIs’ performance but its use is often with-held by long calibration periods. We recorded EEG dataof 15 participants while controlling a robotic arm towardsa target. In 30 % of the trials, the protocol prompted anerror during the trial in order to trigger ErrPs in the partic-ipants. For each participant, we trained an ErrP classifierusing the data of the remaining 14 participants. Each ofthese classifiers was tested asynchronously on the data ofthe selected participant. The threshold that maximizedthe product of the average true positive rate (TPR) andthe average true negative rate (TNR) wasτ=0.7. For thisthreshold, the average TPR was 53.6 % and the averageTNR was 82.0 %. These results hint at the feasibility oftransferring ErrPs between participants as a reliable strat-egy to reduce or even remove the calibration period whentraining ErrP classifiers to be used in an asynchronous manner

AB - Error-related potentials (ErrPs) can be usedto improve BCIs’ performance but its use is often with-held by long calibration periods. We recorded EEG dataof 15 participants while controlling a robotic arm towardsa target. In 30 % of the trials, the protocol prompted anerror during the trial in order to trigger ErrPs in the partic-ipants. For each participant, we trained an ErrP classifierusing the data of the remaining 14 participants. Each ofthese classifiers was tested asynchronously on the data ofthe selected participant. The threshold that maximizedthe product of the average true positive rate (TPR) andthe average true negative rate (TNR) wasτ=0.7. For thisthreshold, the average TPR was 53.6 % and the averageTNR was 82.0 %. These results hint at the feasibility oftransferring ErrPs between participants as a reliable strat-egy to reduce or even remove the calibration period whentraining ErrP classifiers to be used in an asynchronous manner

U2 - 10.3217/978-3-85125-682-6-11

DO - 10.3217/978-3-85125-682-6-11

M3 - Conference contribution

SP - 54

EP - 58

BT - Proceedings of the 8th Graz Brain Computer Interface Conference 2019

A2 - Müller-Putz, Gernot R.

A2 - Ditz, Jonas C.

A2 - Wriessnegger, Selina

PB - Verlag der Technischen Universität Graz

CY - Graz

ER -