CSP patches: An ensemble of optimized spatial filters. An evaluation study

Claudia Sannelli, Carmen Vidaurre, Klaus Muller, Benjamin Blankertz

Research output: Contribution to journalArticle

27 Citations (Scopus)

Abstract

Laplacian filters are widely used in neuroscience. In the context of brain-computer interfacing, they might be preferred to data-driven approaches such as common spatial patterns (CSP) in a variety of scenarios such as, e.g., when no or few user data are available or a calibration session with a multi-channel recording is not possible, which is the case in various applications. In this paper we propose the use of an ensemble of local CSP patches (CSPP) which can be considered as a compromise between Laplacian filters and CSP. Our CSPP only needs a very small number of trials to be optimized and significantly outperforms Laplacian filters in all settings studied. Additionally, CSPP also outperforms multi-channel CSP and a regularized version of CSP even when only very few calibration data are available, acting as a CSP regularizer without the need of additional hyperparameters and at a very low cost: 2-5 min of data recording, i.e. ten times less than CSP.

Original languageEnglish
Article number025012
JournalJournal of Neural Engineering
Volume8
Issue number2
DOIs
Publication statusPublished - 2011 Apr 1
Externally publishedYes

Fingerprint

Calibration
Data recording
Neurosciences
Brain
Costs and Cost Analysis
Costs

ASJC Scopus subject areas

  • Biomedical Engineering
  • Cellular and Molecular Neuroscience

Cite this

CSP patches : An ensemble of optimized spatial filters. An evaluation study. / Sannelli, Claudia; Vidaurre, Carmen; Muller, Klaus; Blankertz, Benjamin.

In: Journal of Neural Engineering, Vol. 8, No. 2, 025012, 01.04.2011.

Research output: Contribution to journalArticle

Sannelli, Claudia ; Vidaurre, Carmen ; Muller, Klaus ; Blankertz, Benjamin. / CSP patches : An ensemble of optimized spatial filters. An evaluation study. In: Journal of Neural Engineering. 2011 ; Vol. 8, No. 2.
@article{9abaa6dd28a64ee187d7cf5ada3b98a4,
title = "CSP patches: An ensemble of optimized spatial filters. An evaluation study",
abstract = "Laplacian filters are widely used in neuroscience. In the context of brain-computer interfacing, they might be preferred to data-driven approaches such as common spatial patterns (CSP) in a variety of scenarios such as, e.g., when no or few user data are available or a calibration session with a multi-channel recording is not possible, which is the case in various applications. In this paper we propose the use of an ensemble of local CSP patches (CSPP) which can be considered as a compromise between Laplacian filters and CSP. Our CSPP only needs a very small number of trials to be optimized and significantly outperforms Laplacian filters in all settings studied. Additionally, CSPP also outperforms multi-channel CSP and a regularized version of CSP even when only very few calibration data are available, acting as a CSP regularizer without the need of additional hyperparameters and at a very low cost: 2-5 min of data recording, i.e. ten times less than CSP.",
author = "Claudia Sannelli and Carmen Vidaurre and Klaus Muller and Benjamin Blankertz",
year = "2011",
month = "4",
day = "1",
doi = "10.1088/1741-2560/8/2/025012",
language = "English",
volume = "8",
journal = "Journal of Neural Engineering",
issn = "1741-2560",
publisher = "IOP Publishing Ltd.",
number = "2",

}

TY - JOUR

T1 - CSP patches

T2 - An ensemble of optimized spatial filters. An evaluation study

AU - Sannelli, Claudia

AU - Vidaurre, Carmen

AU - Muller, Klaus

AU - Blankertz, Benjamin

PY - 2011/4/1

Y1 - 2011/4/1

N2 - Laplacian filters are widely used in neuroscience. In the context of brain-computer interfacing, they might be preferred to data-driven approaches such as common spatial patterns (CSP) in a variety of scenarios such as, e.g., when no or few user data are available or a calibration session with a multi-channel recording is not possible, which is the case in various applications. In this paper we propose the use of an ensemble of local CSP patches (CSPP) which can be considered as a compromise between Laplacian filters and CSP. Our CSPP only needs a very small number of trials to be optimized and significantly outperforms Laplacian filters in all settings studied. Additionally, CSPP also outperforms multi-channel CSP and a regularized version of CSP even when only very few calibration data are available, acting as a CSP regularizer without the need of additional hyperparameters and at a very low cost: 2-5 min of data recording, i.e. ten times less than CSP.

AB - Laplacian filters are widely used in neuroscience. In the context of brain-computer interfacing, they might be preferred to data-driven approaches such as common spatial patterns (CSP) in a variety of scenarios such as, e.g., when no or few user data are available or a calibration session with a multi-channel recording is not possible, which is the case in various applications. In this paper we propose the use of an ensemble of local CSP patches (CSPP) which can be considered as a compromise between Laplacian filters and CSP. Our CSPP only needs a very small number of trials to be optimized and significantly outperforms Laplacian filters in all settings studied. Additionally, CSPP also outperforms multi-channel CSP and a regularized version of CSP even when only very few calibration data are available, acting as a CSP regularizer without the need of additional hyperparameters and at a very low cost: 2-5 min of data recording, i.e. ten times less than CSP.

UR - http://www.scopus.com/inward/record.url?scp=79954531903&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79954531903&partnerID=8YFLogxK

U2 - 10.1088/1741-2560/8/2/025012

DO - 10.1088/1741-2560/8/2/025012

M3 - Article

C2 - 21436539

AN - SCOPUS:79954531903

VL - 8

JO - Journal of Neural Engineering

JF - Journal of Neural Engineering

SN - 1741-2560

IS - 2

M1 - 025012

ER -