Machine learning for real-time single-trial EEG-analysis: From brain-computer interfacing to mental state monitoring

Klaus Muller, Michael Tangermann, Guido Dornhege, Matthias Krauledat, Gabriel Curio, Benjamin Blankertz

Research output: Contribution to journalArticle

267 Citations (Scopus)

Abstract

Machine learning methods are an excellent choice for compensating the high variability in EEG when analyzing single-trial data in real-time. This paper briefly reviews preprocessing and classification techniques for efficient EEG-based brain-computer interfacing (BCI) and mental state monitoring applications. More specifically, this paper gives an outline of the Berlin brain-computer interface (BBCI), which can be operated with minimal subject training. Also, spelling with the novel BBCI-based Hex-o-Spell text entry system, which gains communication speeds of 6-8 letters per minute, is discussed. Finally the results of a real-time arousal monitoring experiment are presented.

Original languageEnglish
Pages (from-to)82-90
Number of pages9
JournalJournal of Neuroscience Methods
Volume167
Issue number1
DOIs
Publication statusPublished - 2008 Jan 15
Externally publishedYes

Fingerprint

Brain-Computer Interfaces
Berlin
Electroencephalography
Brain
Arousal
Communication
Machine Learning

Keywords

  • α-Rhythm
  • EEG
  • Machine learning
  • Mental state monitoring
  • Real-time
  • Sensorimotor rhythms
  • Single-trial EEG-analysis

ASJC Scopus subject areas

  • Neuroscience(all)

Cite this

Machine learning for real-time single-trial EEG-analysis : From brain-computer interfacing to mental state monitoring. / Muller, Klaus; Tangermann, Michael; Dornhege, Guido; Krauledat, Matthias; Curio, Gabriel; Blankertz, Benjamin.

In: Journal of Neuroscience Methods, Vol. 167, No. 1, 15.01.2008, p. 82-90.

Research output: Contribution to journalArticle

Muller, Klaus ; Tangermann, Michael ; Dornhege, Guido ; Krauledat, Matthias ; Curio, Gabriel ; Blankertz, Benjamin. / Machine learning for real-time single-trial EEG-analysis : From brain-computer interfacing to mental state monitoring. In: Journal of Neuroscience Methods. 2008 ; Vol. 167, No. 1. pp. 82-90.
@article{80def6c317a24c40b28ff8bfc87875c0,
title = "Machine learning for real-time single-trial EEG-analysis: From brain-computer interfacing to mental state monitoring",
abstract = "Machine learning methods are an excellent choice for compensating the high variability in EEG when analyzing single-trial data in real-time. This paper briefly reviews preprocessing and classification techniques for efficient EEG-based brain-computer interfacing (BCI) and mental state monitoring applications. More specifically, this paper gives an outline of the Berlin brain-computer interface (BBCI), which can be operated with minimal subject training. Also, spelling with the novel BBCI-based Hex-o-Spell text entry system, which gains communication speeds of 6-8 letters per minute, is discussed. Finally the results of a real-time arousal monitoring experiment are presented.",
keywords = "α-Rhythm, EEG, Machine learning, Mental state monitoring, Real-time, Sensorimotor rhythms, Single-trial EEG-analysis",
author = "Klaus Muller and Michael Tangermann and Guido Dornhege and Matthias Krauledat and Gabriel Curio and Benjamin Blankertz",
year = "2008",
month = "1",
day = "15",
doi = "10.1016/j.jneumeth.2007.09.022",
language = "English",
volume = "167",
pages = "82--90",
journal = "Journal of Neuroscience Methods",
issn = "0165-0270",
publisher = "Elsevier",
number = "1",

}

TY - JOUR

T1 - Machine learning for real-time single-trial EEG-analysis

T2 - From brain-computer interfacing to mental state monitoring

AU - Muller, Klaus

AU - Tangermann, Michael

AU - Dornhege, Guido

AU - Krauledat, Matthias

AU - Curio, Gabriel

AU - Blankertz, Benjamin

PY - 2008/1/15

Y1 - 2008/1/15

N2 - Machine learning methods are an excellent choice for compensating the high variability in EEG when analyzing single-trial data in real-time. This paper briefly reviews preprocessing and classification techniques for efficient EEG-based brain-computer interfacing (BCI) and mental state monitoring applications. More specifically, this paper gives an outline of the Berlin brain-computer interface (BBCI), which can be operated with minimal subject training. Also, spelling with the novel BBCI-based Hex-o-Spell text entry system, which gains communication speeds of 6-8 letters per minute, is discussed. Finally the results of a real-time arousal monitoring experiment are presented.

AB - Machine learning methods are an excellent choice for compensating the high variability in EEG when analyzing single-trial data in real-time. This paper briefly reviews preprocessing and classification techniques for efficient EEG-based brain-computer interfacing (BCI) and mental state monitoring applications. More specifically, this paper gives an outline of the Berlin brain-computer interface (BBCI), which can be operated with minimal subject training. Also, spelling with the novel BBCI-based Hex-o-Spell text entry system, which gains communication speeds of 6-8 letters per minute, is discussed. Finally the results of a real-time arousal monitoring experiment are presented.

KW - α-Rhythm

KW - EEG

KW - Machine learning

KW - Mental state monitoring

KW - Real-time

KW - Sensorimotor rhythms

KW - Single-trial EEG-analysis

UR - http://www.scopus.com/inward/record.url?scp=36549029758&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=36549029758&partnerID=8YFLogxK

U2 - 10.1016/j.jneumeth.2007.09.022

DO - 10.1016/j.jneumeth.2007.09.022

M3 - Article

C2 - 18031824

AN - SCOPUS:36549029758

VL - 167

SP - 82

EP - 90

JO - Journal of Neuroscience Methods

JF - Journal of Neuroscience Methods

SN - 0165-0270

IS - 1

ER -