A probabilistic approach to spatio-spectral filters optimization in Brain-Computer Interface

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

Abstract

EEG-based motor imagery classification has been widely studied for Brain-Computer Interfaces (BCIs) due to its asynchronous and continuous elicitation and its great potential to many applications. Many research groups have devoted their efforts to either the frequency band selection or optimal spatial filters learning via the Common Spatial Pattern (CSP) algorithm. However, since the spectral filtering and the spatial filtering are generally operated in order in a motor imagery classification system the optimization of the spatial filters and the spectral filters should be considered simultaneously in a unified framework. In this paper, we propose a novel probabilistic approach for the spatio-spectral filters optimization in an EEG-based BCI with a particle-filter algorithm and mutual information between feature vectors and class labels. There are two main contributions of the proposed method. The one is that it finds the optimal frequency bands that maximally discriminate the feature vectors of two classes in terms of an information theoretic approach. The other is that we construct a spectrally-weighted label decision rule by linearly combining the outputs from multiple SVMs, one for each frequency band, with the weight of the corresponding frequency band. From our experiments with two publicly available dataset, we confirm that the proposed method outperforms the other competing methods.

Original languageEnglish
Title of host publicationConference Proceedings - IEEE International Conference on Systems, Man and Cybernetics
Pages19-24
Number of pages6
DOIs
Publication statusPublished - 2011 Dec 23
Event2011 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2011 - Anchorage, AK, United States
Duration: 2011 Oct 92011 Oct 12

Other

Other2011 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2011
CountryUnited States
CityAnchorage, AK
Period11/10/911/10/12

Fingerprint

Brain computer interface
Frequency bands
Electroencephalography
Labels
Experiments

Keywords

  • Brain-Computer Interface (BCI)
  • Common Spatial Pattern (CSP)
  • ElectroEncephaloGraphy (EEG)
  • Spatio-Spectral Filters Optimization

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Control and Systems Engineering
  • Human-Computer Interaction

Cite this

Suk, H-I., & Lee, S. W. (2011). A probabilistic approach to spatio-spectral filters optimization in Brain-Computer Interface. In Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics (pp. 19-24). [6083636] https://doi.org/10.1109/ICSMC.2011.6083636

A probabilistic approach to spatio-spectral filters optimization in Brain-Computer Interface. / Suk, Heung-Il; Lee, Seong Whan.

Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics. 2011. p. 19-24 6083636.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Suk, H-I & Lee, SW 2011, A probabilistic approach to spatio-spectral filters optimization in Brain-Computer Interface. in Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics., 6083636, pp. 19-24, 2011 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2011, Anchorage, AK, United States, 11/10/9. https://doi.org/10.1109/ICSMC.2011.6083636
Suk H-I, Lee SW. A probabilistic approach to spatio-spectral filters optimization in Brain-Computer Interface. In Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics. 2011. p. 19-24. 6083636 https://doi.org/10.1109/ICSMC.2011.6083636
Suk, Heung-Il ; Lee, Seong Whan. / A probabilistic approach to spatio-spectral filters optimization in Brain-Computer Interface. Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics. 2011. pp. 19-24
@inproceedings{66bca43813fb4481bcd5973d33197df7,
title = "A probabilistic approach to spatio-spectral filters optimization in Brain-Computer Interface",
abstract = "EEG-based motor imagery classification has been widely studied for Brain-Computer Interfaces (BCIs) due to its asynchronous and continuous elicitation and its great potential to many applications. Many research groups have devoted their efforts to either the frequency band selection or optimal spatial filters learning via the Common Spatial Pattern (CSP) algorithm. However, since the spectral filtering and the spatial filtering are generally operated in order in a motor imagery classification system the optimization of the spatial filters and the spectral filters should be considered simultaneously in a unified framework. In this paper, we propose a novel probabilistic approach for the spatio-spectral filters optimization in an EEG-based BCI with a particle-filter algorithm and mutual information between feature vectors and class labels. There are two main contributions of the proposed method. The one is that it finds the optimal frequency bands that maximally discriminate the feature vectors of two classes in terms of an information theoretic approach. The other is that we construct a spectrally-weighted label decision rule by linearly combining the outputs from multiple SVMs, one for each frequency band, with the weight of the corresponding frequency band. From our experiments with two publicly available dataset, we confirm that the proposed method outperforms the other competing methods.",
keywords = "Brain-Computer Interface (BCI), Common Spatial Pattern (CSP), ElectroEncephaloGraphy (EEG), Spatio-Spectral Filters Optimization",
author = "Heung-Il Suk and Lee, {Seong Whan}",
year = "2011",
month = "12",
day = "23",
doi = "10.1109/ICSMC.2011.6083636",
language = "English",
isbn = "9781457706523",
pages = "19--24",
booktitle = "Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics",

}

TY - GEN

T1 - A probabilistic approach to spatio-spectral filters optimization in Brain-Computer Interface

AU - Suk, Heung-Il

AU - Lee, Seong Whan

PY - 2011/12/23

Y1 - 2011/12/23

N2 - EEG-based motor imagery classification has been widely studied for Brain-Computer Interfaces (BCIs) due to its asynchronous and continuous elicitation and its great potential to many applications. Many research groups have devoted their efforts to either the frequency band selection or optimal spatial filters learning via the Common Spatial Pattern (CSP) algorithm. However, since the spectral filtering and the spatial filtering are generally operated in order in a motor imagery classification system the optimization of the spatial filters and the spectral filters should be considered simultaneously in a unified framework. In this paper, we propose a novel probabilistic approach for the spatio-spectral filters optimization in an EEG-based BCI with a particle-filter algorithm and mutual information between feature vectors and class labels. There are two main contributions of the proposed method. The one is that it finds the optimal frequency bands that maximally discriminate the feature vectors of two classes in terms of an information theoretic approach. The other is that we construct a spectrally-weighted label decision rule by linearly combining the outputs from multiple SVMs, one for each frequency band, with the weight of the corresponding frequency band. From our experiments with two publicly available dataset, we confirm that the proposed method outperforms the other competing methods.

AB - EEG-based motor imagery classification has been widely studied for Brain-Computer Interfaces (BCIs) due to its asynchronous and continuous elicitation and its great potential to many applications. Many research groups have devoted their efforts to either the frequency band selection or optimal spatial filters learning via the Common Spatial Pattern (CSP) algorithm. However, since the spectral filtering and the spatial filtering are generally operated in order in a motor imagery classification system the optimization of the spatial filters and the spectral filters should be considered simultaneously in a unified framework. In this paper, we propose a novel probabilistic approach for the spatio-spectral filters optimization in an EEG-based BCI with a particle-filter algorithm and mutual information between feature vectors and class labels. There are two main contributions of the proposed method. The one is that it finds the optimal frequency bands that maximally discriminate the feature vectors of two classes in terms of an information theoretic approach. The other is that we construct a spectrally-weighted label decision rule by linearly combining the outputs from multiple SVMs, one for each frequency band, with the weight of the corresponding frequency band. From our experiments with two publicly available dataset, we confirm that the proposed method outperforms the other competing methods.

KW - Brain-Computer Interface (BCI)

KW - Common Spatial Pattern (CSP)

KW - ElectroEncephaloGraphy (EEG)

KW - Spatio-Spectral Filters Optimization

UR - http://www.scopus.com/inward/record.url?scp=83755173950&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=83755173950&partnerID=8YFLogxK

U2 - 10.1109/ICSMC.2011.6083636

DO - 10.1109/ICSMC.2011.6083636

M3 - Conference contribution

AN - SCOPUS:83755173950

SN - 9781457706523

SP - 19

EP - 24

BT - Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics

ER -