Boosting bit rates in noninvasive EEG single-trial classifications by feature combination and multiclass paradigms

Guido Dornhege, Benjamin Blankertz, Gabriel Curio, Klaus Muller

Research output: Contribution to journalArticle

411 Citations (Scopus)

Abstract

Noninvasive electroencephalogram (EEG) recordings provide for easy and safe access to human neocortical processes which can be exploited for a brain-computer interface (BCI). At present, however, the use of BCIs is severely limited by low bit-transfer rates. We systematically analyze and develop two recent concepts, both capable of enhancing the information gain from multichannel scalp EEG recordings: 1) the combination of classifiers, each specifically tailored for different physiological phenomena, e.g., slow cortical potential shifts, such as the premovement Bereitschaftspotential or differences in spatio-spectral distributions of brain activity (i.e., focal event-related desynchronizations) and 2) behavioral paradigms inducing the subjects to generate one out of several brain states (multiclass approach) which all bare a distinctive spatio-temporal signature well discriminable in the standard scalp EEG. We derive information-theoretic predictions and demonstrate their relevance in experimental data. We will show that a suitably arranged interaction between these concepts can significantly boost BCI performances.

Original languageEnglish
Pages (from-to)993-1002
Number of pages10
JournalIEEE Transactions on Biomedical Engineering
Volume51
Issue number6
DOIs
Publication statusPublished - 2004 Jun 1
Externally publishedYes

Fingerprint

Electroencephalography
Brain-Computer Interfaces
Brain computer interface
Scalp
Brain
Contingent Negative Variation
Physiological Phenomena
Classifiers

Keywords

  • Brain-computer interface (BCI)
  • Common spatial patterns
  • Electroencephalogram (EEG)
  • Event-related desynchronization
  • Feature combination
  • Movement related potential
  • Multiclass
  • Single-trial analysis

ASJC Scopus subject areas

  • Biomedical Engineering

Cite this

Boosting bit rates in noninvasive EEG single-trial classifications by feature combination and multiclass paradigms. / Dornhege, Guido; Blankertz, Benjamin; Curio, Gabriel; Muller, Klaus.

In: IEEE Transactions on Biomedical Engineering, Vol. 51, No. 6, 01.06.2004, p. 993-1002.

Research output: Contribution to journalArticle

Dornhege, Guido ; Blankertz, Benjamin ; Curio, Gabriel ; Muller, Klaus. / Boosting bit rates in noninvasive EEG single-trial classifications by feature combination and multiclass paradigms. In: IEEE Transactions on Biomedical Engineering. 2004 ; Vol. 51, No. 6. pp. 993-1002.
@article{bcb674635bf04fe6b403b85e7249f62a,
title = "Boosting bit rates in noninvasive EEG single-trial classifications by feature combination and multiclass paradigms",
abstract = "Noninvasive electroencephalogram (EEG) recordings provide for easy and safe access to human neocortical processes which can be exploited for a brain-computer interface (BCI). At present, however, the use of BCIs is severely limited by low bit-transfer rates. We systematically analyze and develop two recent concepts, both capable of enhancing the information gain from multichannel scalp EEG recordings: 1) the combination of classifiers, each specifically tailored for different physiological phenomena, e.g., slow cortical potential shifts, such as the premovement Bereitschaftspotential or differences in spatio-spectral distributions of brain activity (i.e., focal event-related desynchronizations) and 2) behavioral paradigms inducing the subjects to generate one out of several brain states (multiclass approach) which all bare a distinctive spatio-temporal signature well discriminable in the standard scalp EEG. We derive information-theoretic predictions and demonstrate their relevance in experimental data. We will show that a suitably arranged interaction between these concepts can significantly boost BCI performances.",
keywords = "Brain-computer interface (BCI), Common spatial patterns, Electroencephalogram (EEG), Event-related desynchronization, Feature combination, Movement related potential, Multiclass, Single-trial analysis",
author = "Guido Dornhege and Benjamin Blankertz and Gabriel Curio and Klaus Muller",
year = "2004",
month = "6",
day = "1",
doi = "10.1109/TBME.2004.827088",
language = "English",
volume = "51",
pages = "993--1002",
journal = "IEEE Transactions on Biomedical Engineering",
issn = "0018-9294",
publisher = "IEEE Computer Society",
number = "6",

}

TY - JOUR

T1 - Boosting bit rates in noninvasive EEG single-trial classifications by feature combination and multiclass paradigms

AU - Dornhege, Guido

AU - Blankertz, Benjamin

AU - Curio, Gabriel

AU - Muller, Klaus

PY - 2004/6/1

Y1 - 2004/6/1

N2 - Noninvasive electroencephalogram (EEG) recordings provide for easy and safe access to human neocortical processes which can be exploited for a brain-computer interface (BCI). At present, however, the use of BCIs is severely limited by low bit-transfer rates. We systematically analyze and develop two recent concepts, both capable of enhancing the information gain from multichannel scalp EEG recordings: 1) the combination of classifiers, each specifically tailored for different physiological phenomena, e.g., slow cortical potential shifts, such as the premovement Bereitschaftspotential or differences in spatio-spectral distributions of brain activity (i.e., focal event-related desynchronizations) and 2) behavioral paradigms inducing the subjects to generate one out of several brain states (multiclass approach) which all bare a distinctive spatio-temporal signature well discriminable in the standard scalp EEG. We derive information-theoretic predictions and demonstrate their relevance in experimental data. We will show that a suitably arranged interaction between these concepts can significantly boost BCI performances.

AB - Noninvasive electroencephalogram (EEG) recordings provide for easy and safe access to human neocortical processes which can be exploited for a brain-computer interface (BCI). At present, however, the use of BCIs is severely limited by low bit-transfer rates. We systematically analyze and develop two recent concepts, both capable of enhancing the information gain from multichannel scalp EEG recordings: 1) the combination of classifiers, each specifically tailored for different physiological phenomena, e.g., slow cortical potential shifts, such as the premovement Bereitschaftspotential or differences in spatio-spectral distributions of brain activity (i.e., focal event-related desynchronizations) and 2) behavioral paradigms inducing the subjects to generate one out of several brain states (multiclass approach) which all bare a distinctive spatio-temporal signature well discriminable in the standard scalp EEG. We derive information-theoretic predictions and demonstrate their relevance in experimental data. We will show that a suitably arranged interaction between these concepts can significantly boost BCI performances.

KW - Brain-computer interface (BCI)

KW - Common spatial patterns

KW - Electroencephalogram (EEG)

KW - Event-related desynchronization

KW - Feature combination

KW - Movement related potential

KW - Multiclass

KW - Single-trial analysis

UR - http://www.scopus.com/inward/record.url?scp=2442671691&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=2442671691&partnerID=8YFLogxK

U2 - 10.1109/TBME.2004.827088

DO - 10.1109/TBME.2004.827088

M3 - Article

C2 - 15188870

AN - SCOPUS:2442671691

VL - 51

SP - 993

EP - 1002

JO - IEEE Transactions on Biomedical Engineering

JF - IEEE Transactions on Biomedical Engineering

SN - 0018-9294

IS - 6

ER -