EEG-basierte Brain-Computer Interfaces zur Echtzeit-Dekodierung mentaler Zustände

G. Curio; B. Blankertz; K. R. Müller

doi:10.1055/s-0032-1316304

EEG-basierte Brain-Computer Interfaces zur Echtzeit-Dekodierung mentaler Zustände

Translated title of the contribution: EEG-based brain-computer interfaces for real-time decoding of mental states

G. Curio, B. Blankertz, K. R. Müller

Research output: Contribution to journal › Article › peer-review

Abstract

Brain-computer interfaces (BCI) employ algorithmic procedures of machine learning in order to extract user-specific patterns of high-dimensional EEG features. These patterns are optimised to decode intention-related brain states in real-time. Characteristic BCI applications for paralysed patients are control of active prostheses or speller software. To recognise a users motor intention a BCI system utilises individual EEG activation indices, such as the readiness potential or the modulation of regional EEG rhythms. Also beyond the borders of rehabilitation, this neurotechnology enables a growing set of novel application scenarios, e.g., BCIs can serve as optimised feedback tools for the stabilisation of mental states such as vigilance or attention.

Translated title of the contribution	EEG-based brain-computer interfaces for real-time decoding of mental states
Original language	German
Pages (from-to)	213-219
Number of pages	7
Journal	Klinische Neurophysiologie
Volume	43
Issue number	3
DOIs	https://doi.org/10.1055/s-0032-1316304
Publication status	Published - 2012
Externally published	Yes

Keywords

brain-computer interface (BCI)
machine learning
neuro-feedback
prosthesis control
readiness potential

ASJC Scopus subject areas

Clinical Neurology
Physiology (medical)

Access to Document

10.1055/s-0032-1316304

Cite this

@article{bc6ff00f0de448afaf5c63c9a58605d6,

title = "EEG-basierte Brain-Computer Interfaces zur Echtzeit-Dekodierung mentaler Zust{\"a}nde",

abstract = "Brain-computer interfaces (BCI) employ algorithmic procedures of machine learning in order to extract user-specific patterns of high-dimensional EEG features. These patterns are optimised to decode intention-related brain states in real-time. Characteristic BCI applications for paralysed patients are control of active prostheses or speller software. To recognise a users motor intention a BCI system utilises individual EEG activation indices, such as the readiness potential or the modulation of regional EEG rhythms. Also beyond the borders of rehabilitation, this neurotechnology enables a growing set of novel application scenarios, e.g., BCIs can serve as optimised feedback tools for the stabilisation of mental states such as vigilance or attention.",

keywords = "brain-computer interface (BCI), machine learning, neuro-feedback, prosthesis control, readiness potential",

author = "G. Curio and B. Blankertz and M{\"u}ller, {K. R.}",

year = "2012",

doi = "10.1055/s-0032-1316304",

language = "German",

volume = "43",

pages = "213--219",

journal = "Klinische Neurophysiologie",

issn = "1434-0275",

publisher = "Georg Thieme Verlag",

number = "3",

}

TY - JOUR

T1 - EEG-basierte Brain-Computer Interfaces zur Echtzeit-Dekodierung mentaler Zustände

AU - Curio, G.

AU - Blankertz, B.

AU - Müller, K. R.

PY - 2012

Y1 - 2012

N2 - Brain-computer interfaces (BCI) employ algorithmic procedures of machine learning in order to extract user-specific patterns of high-dimensional EEG features. These patterns are optimised to decode intention-related brain states in real-time. Characteristic BCI applications for paralysed patients are control of active prostheses or speller software. To recognise a users motor intention a BCI system utilises individual EEG activation indices, such as the readiness potential or the modulation of regional EEG rhythms. Also beyond the borders of rehabilitation, this neurotechnology enables a growing set of novel application scenarios, e.g., BCIs can serve as optimised feedback tools for the stabilisation of mental states such as vigilance or attention.

AB - Brain-computer interfaces (BCI) employ algorithmic procedures of machine learning in order to extract user-specific patterns of high-dimensional EEG features. These patterns are optimised to decode intention-related brain states in real-time. Characteristic BCI applications for paralysed patients are control of active prostheses or speller software. To recognise a users motor intention a BCI system utilises individual EEG activation indices, such as the readiness potential or the modulation of regional EEG rhythms. Also beyond the borders of rehabilitation, this neurotechnology enables a growing set of novel application scenarios, e.g., BCIs can serve as optimised feedback tools for the stabilisation of mental states such as vigilance or attention.

KW - brain-computer interface (BCI)

KW - machine learning

KW - neuro-feedback

KW - prosthesis control

KW - readiness potential

UR - http://www.scopus.com/inward/record.url?scp=84866412247&partnerID=8YFLogxK

U2 - 10.1055/s-0032-1316304

DO - 10.1055/s-0032-1316304

M3 - Article

AN - SCOPUS:84866412247

SN - 1434-0275

VL - 43

SP - 213

EP - 219

JO - Klinische Neurophysiologie

JF - Klinische Neurophysiologie

IS - 3

ER -

EEG-basierte Brain-Computer Interfaces zur Echtzeit-Dekodierung mentaler Zustände

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this