Spatio-spectral filters for improving the classification of single trial EEG

Steven Lemm; Benjamin Blankertz; Gabriel Curio; Klaus Robert Müller

doi:10.1109/TBME.2005.851521

Spatio-spectral filters for improving the classification of single trial EEG

Steven Lemm, Benjamin Blankertz, Gabriel Curio, Klaus Robert Müller

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

576 Citations (Scopus)

Abstract

Data recorded in electroencephalogram (EEG)-based brain-computer interface experiments is generally very noisy, non-stationary, and contaminated with artifacts that can deteriorate discrimination/classification methods. In this paper, we extend the common spatial pattern (CSP) algorithm with the aim to alleviate these adverse effects. In particular, we suggest an extension of CSP to the state space, which utilizes the method of time delay embedding. As we will show, this allows for individually tuned frequency filters at each electrode position and, thus, yields an improved and more robust machine learning procedure. The advantages of the proposed method over the original CSP method are verified in terms of an improved information transfer rate (bits per trial) on a set of EEG-recordings from experiments of imagined limb movements.

Original language	English
Pages (from-to)	1541-1548
Number of pages	8
Journal	IEEE Transactions on Biomedical Engineering
Volume	52
Issue number	9
DOIs	https://doi.org/10.1109/TBME.2005.851521
Publication status	Published - 2005 Sept

Bibliographical note

Funding Information:
Manuscript received July 27, 2004; revised January 23, 2005. This work was supported in part by the Deutsche Forschungsgemeinschaft (DFG) SFB under Grant 618/B4, in part by the Bundesministerium für Forschung (BMBF) under Grant FKZ 01IBB02A,B, and in part by the PASCAL Network of Excellence under Grant EU 506778. Asterisk indicates corresponding author. *S. Lemm is with the Department of Intelligent Data Analysis, FIRST Fraunhofer Institute, 12489 Berlin, Germany and also with the Neurophysics Group, Department of Neurology, Campus Benjamin Franklin, Charité, University Medicine 12200 Berlin, Germany (e-mail: [email protected]).

Keywords

BCI
CSP
Classification
Feature extraction

ASJC Scopus subject areas

Biomedical Engineering

Access to Document

10.1109/TBME.2005.851521

Cite this

@article{4cd645dc42a942a6b57bb64aafb3b7a6,

title = "Spatio-spectral filters for improving the classification of single trial EEG",

abstract = "Data recorded in electroencephalogram (EEG)-based brain-computer interface experiments is generally very noisy, non-stationary, and contaminated with artifacts that can deteriorate discrimination/classification methods. In this paper, we extend the common spatial pattern (CSP) algorithm with the aim to alleviate these adverse effects. In particular, we suggest an extension of CSP to the state space, which utilizes the method of time delay embedding. As we will show, this allows for individually tuned frequency filters at each electrode position and, thus, yields an improved and more robust machine learning procedure. The advantages of the proposed method over the original CSP method are verified in terms of an improved information transfer rate (bits per trial) on a set of EEG-recordings from experiments of imagined limb movements.",

keywords = "BCI, CSP, Classification, Feature extraction",

author = "Steven Lemm and Benjamin Blankertz and Gabriel Curio and M{\"u}ller, {Klaus Robert}",

note = "Funding Information: Manuscript received July 27, 2004; revised January 23, 2005. This work was supported in part by the Deutsche Forschungsgemeinschaft (DFG) SFB under Grant 618/B4, in part by the Bundesministerium f{\"u}r Forschung (BMBF) under Grant FKZ 01IBB02A,B, and in part by the PASCAL Network of Excellence under Grant EU 506778. Asterisk indicates corresponding author. *S. Lemm is with the Department of Intelligent Data Analysis, FIRST Fraunhofer Institute, 12489 Berlin, Germany and also with the Neurophysics Group, Department of Neurology, Campus Benjamin Franklin, Charit{\'e}, University Medicine 12200 Berlin, Germany (e-mail: [email protected]).",

year = "2005",

month = sep,

doi = "10.1109/TBME.2005.851521",

language = "English",

volume = "52",

pages = "1541--1548",

journal = "IEEE Transactions on Biomedical Engineering",

issn = "0018-9294",

publisher = "IEEE Computer Society",

number = "9",

}

TY - JOUR

T1 - Spatio-spectral filters for improving the classification of single trial EEG

AU - Lemm, Steven

AU - Blankertz, Benjamin

AU - Curio, Gabriel

AU - Müller, Klaus Robert

N1 - Funding Information: Manuscript received July 27, 2004; revised January 23, 2005. This work was supported in part by the Deutsche Forschungsgemeinschaft (DFG) SFB under Grant 618/B4, in part by the Bundesministerium für Forschung (BMBF) under Grant FKZ 01IBB02A,B, and in part by the PASCAL Network of Excellence under Grant EU 506778. Asterisk indicates corresponding author. *S. Lemm is with the Department of Intelligent Data Analysis, FIRST Fraunhofer Institute, 12489 Berlin, Germany and also with the Neurophysics Group, Department of Neurology, Campus Benjamin Franklin, Charité, University Medicine 12200 Berlin, Germany (e-mail: [email protected]).

PY - 2005/9

Y1 - 2005/9

N2 - Data recorded in electroencephalogram (EEG)-based brain-computer interface experiments is generally very noisy, non-stationary, and contaminated with artifacts that can deteriorate discrimination/classification methods. In this paper, we extend the common spatial pattern (CSP) algorithm with the aim to alleviate these adverse effects. In particular, we suggest an extension of CSP to the state space, which utilizes the method of time delay embedding. As we will show, this allows for individually tuned frequency filters at each electrode position and, thus, yields an improved and more robust machine learning procedure. The advantages of the proposed method over the original CSP method are verified in terms of an improved information transfer rate (bits per trial) on a set of EEG-recordings from experiments of imagined limb movements.

AB - Data recorded in electroencephalogram (EEG)-based brain-computer interface experiments is generally very noisy, non-stationary, and contaminated with artifacts that can deteriorate discrimination/classification methods. In this paper, we extend the common spatial pattern (CSP) algorithm with the aim to alleviate these adverse effects. In particular, we suggest an extension of CSP to the state space, which utilizes the method of time delay embedding. As we will show, this allows for individually tuned frequency filters at each electrode position and, thus, yields an improved and more robust machine learning procedure. The advantages of the proposed method over the original CSP method are verified in terms of an improved information transfer rate (bits per trial) on a set of EEG-recordings from experiments of imagined limb movements.

KW - BCI

KW - CSP

KW - Classification

KW - Feature extraction

UR - http://www.scopus.com/inward/record.url?scp=26844572294&partnerID=8YFLogxK

U2 - 10.1109/TBME.2005.851521

DO - 10.1109/TBME.2005.851521

M3 - Article

C2 - 16189967

AN - SCOPUS:26844572294

SN - 0018-9294

VL - 52

SP - 1541

EP - 1548

JO - IEEE Transactions on Biomedical Engineering

JF - IEEE Transactions on Biomedical Engineering

IS - 9

ER -

Spatio-spectral filters for improving the classification of single trial EEG

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this