A new (semantic) reflexive brain-computer interface

In search for a suitable classifier

A. Furdea, C. A. Ruf, S. Halder, D. De Massari, M. Bogdan, W. Rosenstiel, T. Matuz, N. Birbaumer

Research output: Contribution to journalArticle

25 Citations (Scopus)

Abstract

The goal of the current study is to find a suitable classifier for electroencephalogram (EEG) data derived from a new learning paradigm which aims at communication in paralysis. A reflexive semantic classical (Pavlovian) conditioning paradigm is explored as an alternative to the operant learning paradigms, currently used in most brain-computer interfaces (BCIs). Comparable with a lie-detection experiment, subjects are presented with true and false statements. The EEG activity following true and false statements was classified with the aim to separate covert 'yes' from covert 'no' responses. Four classification algorithms are compared for classifying off-line data collected from a group of 14 healthy participants: (i) stepwise linear discriminant analysis (SWLDA), (ii) shrinkage linear discriminant analysis (SLDA), (iii) linear support vector machine (LIN-SVM) and (iv) radial basis function kernel support vector machine (RBF-SVM).The results indicate that all classifiers perform at chance level when separating conditioned 'yes' from conditioned 'no' responses. However, single conditioned reactions could be successfully classified on a single-trial basis (single conditioned reaction against a baseline interval). All of the four investigated classification methods achieve comparable performance, however results with RBF-SVM show the highest single-trial classification accuracy of 68.8%. The results suggest that the proposed paradigm may allow affirmative and negative (disapproving negative) communication in a BCI experiment.

Original languageEnglish
Pages (from-to)233-240
Number of pages8
JournalJournal of Neuroscience Methods
Volume203
Issue number1
DOIs
Publication statusPublished - Jan 15 2012

Fingerprint

Brain-Computer Interfaces
Semantics
Discriminant Analysis
Electroencephalography
Lie Detection
Communication
Learning
Classical Conditioning
Paralysis
Healthy Volunteers
Support Vector Machine

Keywords

  • Brain-computer interface
  • Classical semantic conditioning
  • Electroencephalogram
  • Single-trial classification

ASJC Scopus subject areas

  • Neuroscience(all)

Cite this

Furdea, A., Ruf, C. A., Halder, S., De Massari, D., Bogdan, M., Rosenstiel, W., ... Birbaumer, N. (2012). A new (semantic) reflexive brain-computer interface: In search for a suitable classifier. Journal of Neuroscience Methods, 203(1), 233-240. https://doi.org/10.1016/j.jneumeth.2011.09.013

A new (semantic) reflexive brain-computer interface : In search for a suitable classifier. / Furdea, A.; Ruf, C. A.; Halder, S.; De Massari, D.; Bogdan, M.; Rosenstiel, W.; Matuz, T.; Birbaumer, N.

In: Journal of Neuroscience Methods, Vol. 203, No. 1, 15.01.2012, p. 233-240.

Research output: Contribution to journalArticle

Furdea, A, Ruf, CA, Halder, S, De Massari, D, Bogdan, M, Rosenstiel, W, Matuz, T & Birbaumer, N 2012, 'A new (semantic) reflexive brain-computer interface: In search for a suitable classifier', Journal of Neuroscience Methods, vol. 203, no. 1, pp. 233-240. https://doi.org/10.1016/j.jneumeth.2011.09.013
Furdea, A. ; Ruf, C. A. ; Halder, S. ; De Massari, D. ; Bogdan, M. ; Rosenstiel, W. ; Matuz, T. ; Birbaumer, N. / A new (semantic) reflexive brain-computer interface : In search for a suitable classifier. In: Journal of Neuroscience Methods. 2012 ; Vol. 203, No. 1. pp. 233-240.
@article{fb58ff09c5cc4fbcb2bf69e0aaafd52e,
title = "A new (semantic) reflexive brain-computer interface: In search for a suitable classifier",
abstract = "The goal of the current study is to find a suitable classifier for electroencephalogram (EEG) data derived from a new learning paradigm which aims at communication in paralysis. A reflexive semantic classical (Pavlovian) conditioning paradigm is explored as an alternative to the operant learning paradigms, currently used in most brain-computer interfaces (BCIs). Comparable with a lie-detection experiment, subjects are presented with true and false statements. The EEG activity following true and false statements was classified with the aim to separate covert 'yes' from covert 'no' responses. Four classification algorithms are compared for classifying off-line data collected from a group of 14 healthy participants: (i) stepwise linear discriminant analysis (SWLDA), (ii) shrinkage linear discriminant analysis (SLDA), (iii) linear support vector machine (LIN-SVM) and (iv) radial basis function kernel support vector machine (RBF-SVM).The results indicate that all classifiers perform at chance level when separating conditioned 'yes' from conditioned 'no' responses. However, single conditioned reactions could be successfully classified on a single-trial basis (single conditioned reaction against a baseline interval). All of the four investigated classification methods achieve comparable performance, however results with RBF-SVM show the highest single-trial classification accuracy of 68.8{\%}. The results suggest that the proposed paradigm may allow affirmative and negative (disapproving negative) communication in a BCI experiment.",
keywords = "Brain-computer interface, Classical semantic conditioning, Electroencephalogram, Single-trial classification",
author = "A. Furdea and Ruf, {C. A.} and S. Halder and {De Massari}, D. and M. Bogdan and W. Rosenstiel and T. Matuz and N. Birbaumer",
year = "2012",
month = "1",
day = "15",
doi = "10.1016/j.jneumeth.2011.09.013",
language = "English",
volume = "203",
pages = "233--240",
journal = "Journal of Neuroscience Methods",
issn = "0165-0270",
publisher = "Elsevier",
number = "1",

}

TY - JOUR

T1 - A new (semantic) reflexive brain-computer interface

T2 - In search for a suitable classifier

AU - Furdea, A.

AU - Ruf, C. A.

AU - Halder, S.

AU - De Massari, D.

AU - Bogdan, M.

AU - Rosenstiel, W.

AU - Matuz, T.

AU - Birbaumer, N.

PY - 2012/1/15

Y1 - 2012/1/15

N2 - The goal of the current study is to find a suitable classifier for electroencephalogram (EEG) data derived from a new learning paradigm which aims at communication in paralysis. A reflexive semantic classical (Pavlovian) conditioning paradigm is explored as an alternative to the operant learning paradigms, currently used in most brain-computer interfaces (BCIs). Comparable with a lie-detection experiment, subjects are presented with true and false statements. The EEG activity following true and false statements was classified with the aim to separate covert 'yes' from covert 'no' responses. Four classification algorithms are compared for classifying off-line data collected from a group of 14 healthy participants: (i) stepwise linear discriminant analysis (SWLDA), (ii) shrinkage linear discriminant analysis (SLDA), (iii) linear support vector machine (LIN-SVM) and (iv) radial basis function kernel support vector machine (RBF-SVM).The results indicate that all classifiers perform at chance level when separating conditioned 'yes' from conditioned 'no' responses. However, single conditioned reactions could be successfully classified on a single-trial basis (single conditioned reaction against a baseline interval). All of the four investigated classification methods achieve comparable performance, however results with RBF-SVM show the highest single-trial classification accuracy of 68.8%. The results suggest that the proposed paradigm may allow affirmative and negative (disapproving negative) communication in a BCI experiment.

AB - The goal of the current study is to find a suitable classifier for electroencephalogram (EEG) data derived from a new learning paradigm which aims at communication in paralysis. A reflexive semantic classical (Pavlovian) conditioning paradigm is explored as an alternative to the operant learning paradigms, currently used in most brain-computer interfaces (BCIs). Comparable with a lie-detection experiment, subjects are presented with true and false statements. The EEG activity following true and false statements was classified with the aim to separate covert 'yes' from covert 'no' responses. Four classification algorithms are compared for classifying off-line data collected from a group of 14 healthy participants: (i) stepwise linear discriminant analysis (SWLDA), (ii) shrinkage linear discriminant analysis (SLDA), (iii) linear support vector machine (LIN-SVM) and (iv) radial basis function kernel support vector machine (RBF-SVM).The results indicate that all classifiers perform at chance level when separating conditioned 'yes' from conditioned 'no' responses. However, single conditioned reactions could be successfully classified on a single-trial basis (single conditioned reaction against a baseline interval). All of the four investigated classification methods achieve comparable performance, however results with RBF-SVM show the highest single-trial classification accuracy of 68.8%. The results suggest that the proposed paradigm may allow affirmative and negative (disapproving negative) communication in a BCI experiment.

KW - Brain-computer interface

KW - Classical semantic conditioning

KW - Electroencephalogram

KW - Single-trial classification

UR - http://www.scopus.com/inward/record.url?scp=81555219169&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=81555219169&partnerID=8YFLogxK

U2 - 10.1016/j.jneumeth.2011.09.013

DO - 10.1016/j.jneumeth.2011.09.013

M3 - Article

VL - 203

SP - 233

EP - 240

JO - Journal of Neuroscience Methods

JF - Journal of Neuroscience Methods

SN - 0165-0270

IS - 1

ER -