Boosting bit rates and error detection for the classification of fast-paced motor commands based on single-trial EEG analysis

Benjamin Blankertz, Guido Dornhege, Christin Schäfer, Roman Krepki, Jens Kohlmorgen, Klaus Muller, Volker Kunzmann, Florian Losch, Gabriel Curio

Research output: Contribution to journalArticle

161 Citations (Scopus)

Abstract

Brain-computer interfaces (BCIs) involve two coupled adapting systems - the human subject and the computer. In developing our BCI, our goal was to minimize the need for subject training and to impose the major learning load on the computer. To this end, we use behavioral paradigms that exploit single-trial EEG potentials preceding voluntary finger movements. Here, we report recent results on the basic physiology of such premovement event-related potentials (ERP). 1) We predict the laterality of imminent left- versus right-hand finger movements in a natural keyboard typing condition and demonstrate that a single-trial classification based on the lateralized Bereitschaftspotential (BP) achieves good accuracies even at a pace as fast as 2 taps/s. Results for four out of eight subjects reached a peak information transfer rate of more than 15 b/min; the four other subjects reached 6-10 b/min. 2) We detect cerebral error potentials from single false-response trials in a forced-choice task, reflecting the subject's recognition of an erroneous response. Based on a specifically tailored classification procedure that limits the rate of false positives at, e.g., 2%, the algorithm manages to detect 85% of error trials in seven out of eight subjects. Thus, concatenating a primary single-trial BP-paradigm involving finger classification feedback with such secondary error detection could serve as an efficient online confirmation/correction tool for improvement of bit rates in a future BCI setting. As the present variant of the Berlin BCI is designed to achieve fast classifications in normally behaving subjects, it opens a new perspective for assistance of action control in time-critical behavioral contexts; the potential transfer to paralyzed patients will require further study.

Original languageEnglish
Pages (from-to)127-131
Number of pages5
JournalIEEE Transactions on Neural Systems and Rehabilitation Engineering
Volume11
Issue number2
DOIs
Publication statusPublished - 2003 Jun 1
Externally publishedYes

Fingerprint

Brain-Computer Interfaces
Brain computer interface
Error detection
Electroencephalography
Contingent Negative Variation
Fingers
Bioelectric potentials
Physiology
Berlin
Evoked Potentials
Hand
Learning
Feedback
Transfer (Psychology)

Keywords

  • Bereitschaftspotential (BP)
  • Brain-computer interface (BCI)
  • Error potential
  • Fisher's discriminant
  • Linear classification
  • Multichannel EEG
  • Single-trial analysis

ASJC Scopus subject areas

  • Rehabilitation
  • Biophysics
  • Bioengineering
  • Health Professions(all)

Cite this

Boosting bit rates and error detection for the classification of fast-paced motor commands based on single-trial EEG analysis. / Blankertz, Benjamin; Dornhege, Guido; Schäfer, Christin; Krepki, Roman; Kohlmorgen, Jens; Muller, Klaus; Kunzmann, Volker; Losch, Florian; Curio, Gabriel.

In: IEEE Transactions on Neural Systems and Rehabilitation Engineering, Vol. 11, No. 2, 01.06.2003, p. 127-131.

Research output: Contribution to journalArticle

Blankertz, Benjamin ; Dornhege, Guido ; Schäfer, Christin ; Krepki, Roman ; Kohlmorgen, Jens ; Muller, Klaus ; Kunzmann, Volker ; Losch, Florian ; Curio, Gabriel. / Boosting bit rates and error detection for the classification of fast-paced motor commands based on single-trial EEG analysis. In: IEEE Transactions on Neural Systems and Rehabilitation Engineering. 2003 ; Vol. 11, No. 2. pp. 127-131.
@article{05ca8e175267440dbc2c56907cdb295d,
title = "Boosting bit rates and error detection for the classification of fast-paced motor commands based on single-trial EEG analysis",
abstract = "Brain-computer interfaces (BCIs) involve two coupled adapting systems - the human subject and the computer. In developing our BCI, our goal was to minimize the need for subject training and to impose the major learning load on the computer. To this end, we use behavioral paradigms that exploit single-trial EEG potentials preceding voluntary finger movements. Here, we report recent results on the basic physiology of such premovement event-related potentials (ERP). 1) We predict the laterality of imminent left- versus right-hand finger movements in a natural keyboard typing condition and demonstrate that a single-trial classification based on the lateralized Bereitschaftspotential (BP) achieves good accuracies even at a pace as fast as 2 taps/s. Results for four out of eight subjects reached a peak information transfer rate of more than 15 b/min; the four other subjects reached 6-10 b/min. 2) We detect cerebral error potentials from single false-response trials in a forced-choice task, reflecting the subject's recognition of an erroneous response. Based on a specifically tailored classification procedure that limits the rate of false positives at, e.g., 2{\%}, the algorithm manages to detect 85{\%} of error trials in seven out of eight subjects. Thus, concatenating a primary single-trial BP-paradigm involving finger classification feedback with such secondary error detection could serve as an efficient online confirmation/correction tool for improvement of bit rates in a future BCI setting. As the present variant of the Berlin BCI is designed to achieve fast classifications in normally behaving subjects, it opens a new perspective for assistance of action control in time-critical behavioral contexts; the potential transfer to paralyzed patients will require further study.",
keywords = "Bereitschaftspotential (BP), Brain-computer interface (BCI), Error potential, Fisher's discriminant, Linear classification, Multichannel EEG, Single-trial analysis",
author = "Benjamin Blankertz and Guido Dornhege and Christin Sch{\"a}fer and Roman Krepki and Jens Kohlmorgen and Klaus Muller and Volker Kunzmann and Florian Losch and Gabriel Curio",
year = "2003",
month = "6",
day = "1",
doi = "10.1109/TNSRE.2003.814456",
language = "English",
volume = "11",
pages = "127--131",
journal = "IEEE Transactions on Neural Systems and Rehabilitation Engineering",
issn = "1534-4320",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "2",

}

TY - JOUR

T1 - Boosting bit rates and error detection for the classification of fast-paced motor commands based on single-trial EEG analysis

AU - Blankertz, Benjamin

AU - Dornhege, Guido

AU - Schäfer, Christin

AU - Krepki, Roman

AU - Kohlmorgen, Jens

AU - Muller, Klaus

AU - Kunzmann, Volker

AU - Losch, Florian

AU - Curio, Gabriel

PY - 2003/6/1

Y1 - 2003/6/1

N2 - Brain-computer interfaces (BCIs) involve two coupled adapting systems - the human subject and the computer. In developing our BCI, our goal was to minimize the need for subject training and to impose the major learning load on the computer. To this end, we use behavioral paradigms that exploit single-trial EEG potentials preceding voluntary finger movements. Here, we report recent results on the basic physiology of such premovement event-related potentials (ERP). 1) We predict the laterality of imminent left- versus right-hand finger movements in a natural keyboard typing condition and demonstrate that a single-trial classification based on the lateralized Bereitschaftspotential (BP) achieves good accuracies even at a pace as fast as 2 taps/s. Results for four out of eight subjects reached a peak information transfer rate of more than 15 b/min; the four other subjects reached 6-10 b/min. 2) We detect cerebral error potentials from single false-response trials in a forced-choice task, reflecting the subject's recognition of an erroneous response. Based on a specifically tailored classification procedure that limits the rate of false positives at, e.g., 2%, the algorithm manages to detect 85% of error trials in seven out of eight subjects. Thus, concatenating a primary single-trial BP-paradigm involving finger classification feedback with such secondary error detection could serve as an efficient online confirmation/correction tool for improvement of bit rates in a future BCI setting. As the present variant of the Berlin BCI is designed to achieve fast classifications in normally behaving subjects, it opens a new perspective for assistance of action control in time-critical behavioral contexts; the potential transfer to paralyzed patients will require further study.

AB - Brain-computer interfaces (BCIs) involve two coupled adapting systems - the human subject and the computer. In developing our BCI, our goal was to minimize the need for subject training and to impose the major learning load on the computer. To this end, we use behavioral paradigms that exploit single-trial EEG potentials preceding voluntary finger movements. Here, we report recent results on the basic physiology of such premovement event-related potentials (ERP). 1) We predict the laterality of imminent left- versus right-hand finger movements in a natural keyboard typing condition and demonstrate that a single-trial classification based on the lateralized Bereitschaftspotential (BP) achieves good accuracies even at a pace as fast as 2 taps/s. Results for four out of eight subjects reached a peak information transfer rate of more than 15 b/min; the four other subjects reached 6-10 b/min. 2) We detect cerebral error potentials from single false-response trials in a forced-choice task, reflecting the subject's recognition of an erroneous response. Based on a specifically tailored classification procedure that limits the rate of false positives at, e.g., 2%, the algorithm manages to detect 85% of error trials in seven out of eight subjects. Thus, concatenating a primary single-trial BP-paradigm involving finger classification feedback with such secondary error detection could serve as an efficient online confirmation/correction tool for improvement of bit rates in a future BCI setting. As the present variant of the Berlin BCI is designed to achieve fast classifications in normally behaving subjects, it opens a new perspective for assistance of action control in time-critical behavioral contexts; the potential transfer to paralyzed patients will require further study.

KW - Bereitschaftspotential (BP)

KW - Brain-computer interface (BCI)

KW - Error potential

KW - Fisher's discriminant

KW - Linear classification

KW - Multichannel EEG

KW - Single-trial analysis

UR - http://www.scopus.com/inward/record.url?scp=0043244916&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0043244916&partnerID=8YFLogxK

U2 - 10.1109/TNSRE.2003.814456

DO - 10.1109/TNSRE.2003.814456

M3 - Article

C2 - 12899253

AN - SCOPUS:0043244916

VL - 11

SP - 127

EP - 131

JO - IEEE Transactions on Neural Systems and Rehabilitation Engineering

JF - IEEE Transactions on Neural Systems and Rehabilitation Engineering

SN - 1534-4320

IS - 2

ER -