Salient EEG channel selection in brain computer interfaces by mutual information maximization

Tian Lan, Deniz Erdogmus, Andre Adami, Misha Pavel, Santosh Mathan

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

51 Citations (Scopus)

Abstract

Modern brain computer interface (BCI) applications use information obtained from the user's electroencephalogram (EEG) to estimate the mental states. Selecting an optimal subset of the EEG channels instead of using all of them is especially important for ambulatory EEG where the user is mobile due to reduced data communication and computational load requirements. In addition, elimination of irrelevant sensors improves the robustness of the classification system by reducing dimensionality. In this paper, we propose a filter approach for EEG channel selection using mutual information (MI) maximization. This method ranks the EEG channels, such that the MI between the selected sensors and class labels is maximized. This selection criterion is known to reduce classification error. We employ a computationally efficient approach for MI estimation and EEG channel ranking. This approach is illustrated on EEG data recorded from three subjects performing two mental tasks. Experiment results show that the proposed approach works well and the position of the selected channels using the proposed method is consistent with the expected cortical areas for the mental tasks.

Original languageEnglish (US)
Title of host publicationAnnual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings
Pages7064-7067
Number of pages4
Volume7 VOLS
StatePublished - 2005
Event2005 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE-EMBS 2005 - Shanghai, China
Duration: Sep 1 2005Sep 4 2005

Other

Other2005 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE-EMBS 2005
CountryChina
CityShanghai
Period9/1/059/4/05

Fingerprint

Brain computer interface
Electroencephalography
Information use
Sensors
Labels
Communication

Keywords

  • Brain computer interface
  • EEG channel selection
  • Independent component analysis
  • Mutual information

ASJC Scopus subject areas

  • Bioengineering

Cite this

Lan, T., Erdogmus, D., Adami, A., Pavel, M., & Mathan, S. (2005). Salient EEG channel selection in brain computer interfaces by mutual information maximization. In Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings (Vol. 7 VOLS, pp. 7064-7067). [1616133]

Salient EEG channel selection in brain computer interfaces by mutual information maximization. / Lan, Tian; Erdogmus, Deniz; Adami, Andre; Pavel, Misha; Mathan, Santosh.

Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings. Vol. 7 VOLS 2005. p. 7064-7067 1616133.

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

Lan, T, Erdogmus, D, Adami, A, Pavel, M & Mathan, S 2005, Salient EEG channel selection in brain computer interfaces by mutual information maximization. in Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings. vol. 7 VOLS, 1616133, pp. 7064-7067, 2005 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE-EMBS 2005, Shanghai, China, 9/1/05.
Lan T, Erdogmus D, Adami A, Pavel M, Mathan S. Salient EEG channel selection in brain computer interfaces by mutual information maximization. In Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings. Vol. 7 VOLS. 2005. p. 7064-7067. 1616133
Lan, Tian ; Erdogmus, Deniz ; Adami, Andre ; Pavel, Misha ; Mathan, Santosh. / Salient EEG channel selection in brain computer interfaces by mutual information maximization. Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings. Vol. 7 VOLS 2005. pp. 7064-7067
@inproceedings{7fe917ff89224133ab997fa957fca654,
title = "Salient EEG channel selection in brain computer interfaces by mutual information maximization",
abstract = "Modern brain computer interface (BCI) applications use information obtained from the user's electroencephalogram (EEG) to estimate the mental states. Selecting an optimal subset of the EEG channels instead of using all of them is especially important for ambulatory EEG where the user is mobile due to reduced data communication and computational load requirements. In addition, elimination of irrelevant sensors improves the robustness of the classification system by reducing dimensionality. In this paper, we propose a filter approach for EEG channel selection using mutual information (MI) maximization. This method ranks the EEG channels, such that the MI between the selected sensors and class labels is maximized. This selection criterion is known to reduce classification error. We employ a computationally efficient approach for MI estimation and EEG channel ranking. This approach is illustrated on EEG data recorded from three subjects performing two mental tasks. Experiment results show that the proposed approach works well and the position of the selected channels using the proposed method is consistent with the expected cortical areas for the mental tasks.",
keywords = "Brain computer interface, EEG channel selection, Independent component analysis, Mutual information",
author = "Tian Lan and Deniz Erdogmus and Andre Adami and Misha Pavel and Santosh Mathan",
year = "2005",
language = "English (US)",
isbn = "0780387406",
volume = "7 VOLS",
pages = "7064--7067",
booktitle = "Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings",

}

TY - GEN

T1 - Salient EEG channel selection in brain computer interfaces by mutual information maximization

AU - Lan, Tian

AU - Erdogmus, Deniz

AU - Adami, Andre

AU - Pavel, Misha

AU - Mathan, Santosh

PY - 2005

Y1 - 2005

N2 - Modern brain computer interface (BCI) applications use information obtained from the user's electroencephalogram (EEG) to estimate the mental states. Selecting an optimal subset of the EEG channels instead of using all of them is especially important for ambulatory EEG where the user is mobile due to reduced data communication and computational load requirements. In addition, elimination of irrelevant sensors improves the robustness of the classification system by reducing dimensionality. In this paper, we propose a filter approach for EEG channel selection using mutual information (MI) maximization. This method ranks the EEG channels, such that the MI between the selected sensors and class labels is maximized. This selection criterion is known to reduce classification error. We employ a computationally efficient approach for MI estimation and EEG channel ranking. This approach is illustrated on EEG data recorded from three subjects performing two mental tasks. Experiment results show that the proposed approach works well and the position of the selected channels using the proposed method is consistent with the expected cortical areas for the mental tasks.

AB - Modern brain computer interface (BCI) applications use information obtained from the user's electroencephalogram (EEG) to estimate the mental states. Selecting an optimal subset of the EEG channels instead of using all of them is especially important for ambulatory EEG where the user is mobile due to reduced data communication and computational load requirements. In addition, elimination of irrelevant sensors improves the robustness of the classification system by reducing dimensionality. In this paper, we propose a filter approach for EEG channel selection using mutual information (MI) maximization. This method ranks the EEG channels, such that the MI between the selected sensors and class labels is maximized. This selection criterion is known to reduce classification error. We employ a computationally efficient approach for MI estimation and EEG channel ranking. This approach is illustrated on EEG data recorded from three subjects performing two mental tasks. Experiment results show that the proposed approach works well and the position of the selected channels using the proposed method is consistent with the expected cortical areas for the mental tasks.

KW - Brain computer interface

KW - EEG channel selection

KW - Independent component analysis

KW - Mutual information

UR - http://www.scopus.com/inward/record.url?scp=33846903365&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33846903365&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:33846903365

SN - 0780387406

SN - 9780780387409

VL - 7 VOLS

SP - 7064

EP - 7067

BT - Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings

ER -