A fully on-line adaptive BCI

Carmen Vidaurre; Alois Schlögl; R. Cabeza; Reinhold Scherer; Gert Pfurtscheller

doi:10.1109/TBME.2006.873542

A fully on-line adaptive BCI

Carmen Vidaurre, Alois Schlögl, R. Cabeza, Reinhold Scherer, Gert Pfurtscheller

Research output: Contribution to journal › Article › peer-review

Abstract

A viable fully on-line adaptive brain computer interface (BCI) is introduced. On-line experiments with nine naive and able-bodied subjects were carried out using a continuously adaptive BCI system. The data were analyzed and the viability of the system was studied. The BCI was based on motor imagery, the feature extraction was performed with an adaptive autoregressive model and the classifier used was an adaptive quadratic discriminant analysis. The classifier was on-line updated by an adaptive estimation of the information matrix (ADIM). The system was also able to provide continuous feedback to the subject. The success of the feedback was studied analyzing the error rate and mutual information of each session and this analysis showed a clear improvement of the subject's control of the BCI from session to session.

Original language	English
Pages (from-to)	1214-1219
Journal	IEEE Transactions on Biomedical Engineering
Volume	53
Issue number	6
DOIs	https://doi.org/10.1109/TBME.2006.873542
Publication status	Published - 2006

Access to Document

10.1109/TBME.2006.873542

Cite this

@article{c3489ef24c1d484ca6e421c5d2c4dbed,

title = "A fully on-line adaptive BCI",

abstract = "A viable fully on-line adaptive brain computer interface (BCI) is introduced. On-line experiments with nine naive and able-bodied subjects were carried out using a continuously adaptive BCI system. The data were analyzed and the viability of the system was studied. The BCI was based on motor imagery, the feature extraction was performed with an adaptive autoregressive model and the classifier used was an adaptive quadratic discriminant analysis. The classifier was on-line updated by an adaptive estimation of the information matrix (ADIM). The system was also able to provide continuous feedback to the subject. The success of the feedback was studied analyzing the error rate and mutual information of each session and this analysis showed a clear improvement of the subject's control of the BCI from session to session.",

author = "Carmen Vidaurre and Alois Schl{\"o}gl and R. Cabeza and Reinhold Scherer and Gert Pfurtscheller",

year = "2006",

doi = "10.1109/TBME.2006.873542",

language = "English",

volume = "53",

pages = "1214--1219",

journal = "IEEE Transactions on Biomedical Engineering ",

issn = "1558-2531",

publisher = "IEEE Computer Society",

number = "6",

}

TY - JOUR

T1 - A fully on-line adaptive BCI

AU - Vidaurre, Carmen

AU - Schlögl, Alois

AU - Cabeza, R.

AU - Scherer, Reinhold

AU - Pfurtscheller, Gert

PY - 2006

Y1 - 2006

N2 - A viable fully on-line adaptive brain computer interface (BCI) is introduced. On-line experiments with nine naive and able-bodied subjects were carried out using a continuously adaptive BCI system. The data were analyzed and the viability of the system was studied. The BCI was based on motor imagery, the feature extraction was performed with an adaptive autoregressive model and the classifier used was an adaptive quadratic discriminant analysis. The classifier was on-line updated by an adaptive estimation of the information matrix (ADIM). The system was also able to provide continuous feedback to the subject. The success of the feedback was studied analyzing the error rate and mutual information of each session and this analysis showed a clear improvement of the subject's control of the BCI from session to session.

AB - A viable fully on-line adaptive brain computer interface (BCI) is introduced. On-line experiments with nine naive and able-bodied subjects were carried out using a continuously adaptive BCI system. The data were analyzed and the viability of the system was studied. The BCI was based on motor imagery, the feature extraction was performed with an adaptive autoregressive model and the classifier used was an adaptive quadratic discriminant analysis. The classifier was on-line updated by an adaptive estimation of the information matrix (ADIM). The system was also able to provide continuous feedback to the subject. The success of the feedback was studied analyzing the error rate and mutual information of each session and this analysis showed a clear improvement of the subject's control of the BCI from session to session.

U2 - 10.1109/TBME.2006.873542

DO - 10.1109/TBME.2006.873542

M3 - Article

SN - 1558-2531

VL - 53

SP - 1214

EP - 1219

JO - IEEE Transactions on Biomedical Engineering

JF - IEEE Transactions on Biomedical Engineering

IS - 6

ER -

A fully on-line adaptive BCI

Abstract

Access to Document

Fingerprint

Cite this