The non-invasive Berlin Brain-Computer Interface: Fast acquisition of effective performance in untrained subjects

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

Research output: Contribution to journalArticle

489 Citations (Scopus)

Abstract

Brain-Computer Interface (BCI) systems establish a direct communication channel from the brain to an output device. These systems use brain signals recorded from the scalp, the surface of the cortex, or from inside the brain to enable users to control a variety of applications. BCI systems that bypass conventional motor output pathways of nerves and muscles can provide novel control options for paralyzed patients. One classical approach to establish EEG-based control is to set up a system that is controlled by a specific EEG feature which is known to be susceptible to conditioning and to let the subjects learn the voluntary control of that feature. In contrast, the Berlin Brain-Computer Interface (BBCI) uses well established motor competencies of its users and a machine learning approach to extract subject-specific patterns from high-dimensional features optimized for detecting the user's intent. Thus the long subject training is replaced by a short calibration measurement (20 min) and machine learning (1 min). We report results from a study in which 10 subjects, who had no or little experience with BCI feedback, controlled computer applications by voluntary imagination of limb movements: these intentions led to modulations of spontaneous brain activity specifically, somatotopically matched sensorimotor 7-30 Hz rhythms were diminished over pericentral cortices. The peak information transfer rate was above 35 bits per minute (bpm) for 3 subjects, above 23 bpm for two, and above 12 bpm for 3 subjects, while one subject could achieve no BCI control. Compared to other BCI systems which need longer subject training to achieve comparable results, we propose that the key to quick efficiency in the BBCI system is its flexibility due to complex but physiologically meaningful features and its adaptivity which respects the enormous inter-subject variability.

Original languageEnglish
Pages (from-to)539-550
Number of pages12
JournalNeuroImage
Volume37
Issue number2
DOIs
Publication statusPublished - 2007 Aug 15
Externally publishedYes

Fingerprint

Brain-Computer Interfaces
Berlin
Computer Systems
Brain
Electroencephalography
Efferent Pathways
Imagination
Scalp
Calibration
Extremities
Communication
Efficiency
Equipment and Supplies
Muscles

ASJC Scopus subject areas

  • Cognitive Neuroscience
  • Neurology

Cite this

The non-invasive Berlin Brain-Computer Interface : Fast acquisition of effective performance in untrained subjects. / Blankertz, Benjamin; Dornhege, Guido; Krauledat, Matthias; Muller, Klaus; Curio, Gabriel.

In: NeuroImage, Vol. 37, No. 2, 15.08.2007, p. 539-550.

Research output: Contribution to journalArticle

Blankertz, Benjamin ; Dornhege, Guido ; Krauledat, Matthias ; Muller, Klaus ; Curio, Gabriel. / The non-invasive Berlin Brain-Computer Interface : Fast acquisition of effective performance in untrained subjects. In: NeuroImage. 2007 ; Vol. 37, No. 2. pp. 539-550.
@article{5bf912abf1b64c64b3c1e7c8062d4021,
title = "The non-invasive Berlin Brain-Computer Interface: Fast acquisition of effective performance in untrained subjects",
abstract = "Brain-Computer Interface (BCI) systems establish a direct communication channel from the brain to an output device. These systems use brain signals recorded from the scalp, the surface of the cortex, or from inside the brain to enable users to control a variety of applications. BCI systems that bypass conventional motor output pathways of nerves and muscles can provide novel control options for paralyzed patients. One classical approach to establish EEG-based control is to set up a system that is controlled by a specific EEG feature which is known to be susceptible to conditioning and to let the subjects learn the voluntary control of that feature. In contrast, the Berlin Brain-Computer Interface (BBCI) uses well established motor competencies of its users and a machine learning approach to extract subject-specific patterns from high-dimensional features optimized for detecting the user's intent. Thus the long subject training is replaced by a short calibration measurement (20 min) and machine learning (1 min). We report results from a study in which 10 subjects, who had no or little experience with BCI feedback, controlled computer applications by voluntary imagination of limb movements: these intentions led to modulations of spontaneous brain activity specifically, somatotopically matched sensorimotor 7-30 Hz rhythms were diminished over pericentral cortices. The peak information transfer rate was above 35 bits per minute (bpm) for 3 subjects, above 23 bpm for two, and above 12 bpm for 3 subjects, while one subject could achieve no BCI control. Compared to other BCI systems which need longer subject training to achieve comparable results, we propose that the key to quick efficiency in the BBCI system is its flexibility due to complex but physiologically meaningful features and its adaptivity which respects the enormous inter-subject variability.",
author = "Benjamin Blankertz and Guido Dornhege and Matthias Krauledat and Klaus Muller and Gabriel Curio",
year = "2007",
month = "8",
day = "15",
doi = "10.1016/j.neuroimage.2007.01.051",
language = "English",
volume = "37",
pages = "539--550",
journal = "NeuroImage",
issn = "1053-8119",
publisher = "Academic Press Inc.",
number = "2",

}

TY - JOUR

T1 - The non-invasive Berlin Brain-Computer Interface

T2 - Fast acquisition of effective performance in untrained subjects

AU - Blankertz, Benjamin

AU - Dornhege, Guido

AU - Krauledat, Matthias

AU - Muller, Klaus

AU - Curio, Gabriel

PY - 2007/8/15

Y1 - 2007/8/15

N2 - Brain-Computer Interface (BCI) systems establish a direct communication channel from the brain to an output device. These systems use brain signals recorded from the scalp, the surface of the cortex, or from inside the brain to enable users to control a variety of applications. BCI systems that bypass conventional motor output pathways of nerves and muscles can provide novel control options for paralyzed patients. One classical approach to establish EEG-based control is to set up a system that is controlled by a specific EEG feature which is known to be susceptible to conditioning and to let the subjects learn the voluntary control of that feature. In contrast, the Berlin Brain-Computer Interface (BBCI) uses well established motor competencies of its users and a machine learning approach to extract subject-specific patterns from high-dimensional features optimized for detecting the user's intent. Thus the long subject training is replaced by a short calibration measurement (20 min) and machine learning (1 min). We report results from a study in which 10 subjects, who had no or little experience with BCI feedback, controlled computer applications by voluntary imagination of limb movements: these intentions led to modulations of spontaneous brain activity specifically, somatotopically matched sensorimotor 7-30 Hz rhythms were diminished over pericentral cortices. The peak information transfer rate was above 35 bits per minute (bpm) for 3 subjects, above 23 bpm for two, and above 12 bpm for 3 subjects, while one subject could achieve no BCI control. Compared to other BCI systems which need longer subject training to achieve comparable results, we propose that the key to quick efficiency in the BBCI system is its flexibility due to complex but physiologically meaningful features and its adaptivity which respects the enormous inter-subject variability.

AB - Brain-Computer Interface (BCI) systems establish a direct communication channel from the brain to an output device. These systems use brain signals recorded from the scalp, the surface of the cortex, or from inside the brain to enable users to control a variety of applications. BCI systems that bypass conventional motor output pathways of nerves and muscles can provide novel control options for paralyzed patients. One classical approach to establish EEG-based control is to set up a system that is controlled by a specific EEG feature which is known to be susceptible to conditioning and to let the subjects learn the voluntary control of that feature. In contrast, the Berlin Brain-Computer Interface (BBCI) uses well established motor competencies of its users and a machine learning approach to extract subject-specific patterns from high-dimensional features optimized for detecting the user's intent. Thus the long subject training is replaced by a short calibration measurement (20 min) and machine learning (1 min). We report results from a study in which 10 subjects, who had no or little experience with BCI feedback, controlled computer applications by voluntary imagination of limb movements: these intentions led to modulations of spontaneous brain activity specifically, somatotopically matched sensorimotor 7-30 Hz rhythms were diminished over pericentral cortices. The peak information transfer rate was above 35 bits per minute (bpm) for 3 subjects, above 23 bpm for two, and above 12 bpm for 3 subjects, while one subject could achieve no BCI control. Compared to other BCI systems which need longer subject training to achieve comparable results, we propose that the key to quick efficiency in the BBCI system is its flexibility due to complex but physiologically meaningful features and its adaptivity which respects the enormous inter-subject variability.

UR - http://www.scopus.com/inward/record.url?scp=34249029672&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34249029672&partnerID=8YFLogxK

U2 - 10.1016/j.neuroimage.2007.01.051

DO - 10.1016/j.neuroimage.2007.01.051

M3 - Article

C2 - 17475513

AN - SCOPUS:34249029672

VL - 37

SP - 539

EP - 550

JO - NeuroImage

JF - NeuroImage

SN - 1053-8119

IS - 2

ER -