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
T3 - Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings
SP - 7064
EP - 7067
BT - Proceedings of the 2005 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE-EMBS 2005
T2 - 2005 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE-EMBS 2005
Y2 - 1 September 2005 through 4 September 2005
ER -