Feature selection by independent component analysis and mutual information maximization in EEG signal classification

Tian Lan; Deniz Erdogmus; Andre Adami; Michael Pavel

doi:10.1109/IJCNN.2005.1556405

Feature selection by independent component analysis and mutual information maximization in EEG signal classification

Tian Lan, Deniz Erdogmus, Andre Adami, Michael Pavel

Biomedical Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

21 Scopus citations

Abstract

Feature selection and dimensionality reduction are important steps in pattern recognition. In this paper, we propose a scheme for feature selection using linear independent component analysis and mutual information maximization method. The method is theoretically motivated by the fact that the classification error rate is related to the mutual information between the feature vectors and the class labels. The feasibility of the principle is illustrated on a synthetic dataset and its performance is demonstrated using EEG signal classification. Experimental results show that this method works well for feature selection.

Original language	English (US)
Title of host publication	Proceedings of the International Joint Conference on Neural Networks, IJCNN 2005
Pages	3011-3016
Number of pages	6
DOIs	https://doi.org/10.1109/IJCNN.2005.1556405
State	Published - 2005
Event	International Joint Conference on Neural Networks, IJCNN 2005 - Montreal, QC, Canada Duration: Jul 31 2005 → Aug 4 2005

Publication series

Name	Proceedings of the International Joint Conference on Neural Networks
Volume	5

Other

Other	International Joint Conference on Neural Networks, IJCNN 2005
Country/Territory	Canada
City	Montreal, QC
Period	7/31/05 → 8/4/05

Keywords

Brain-Computer Interface
EEG
Entropy Estimation
Feature Selection
Independent Component Analysis
Mutual Information

ASJC Scopus subject areas

Software
Artificial Intelligence

Access to Document

10.1109/IJCNN.2005.1556405

Cite this

Lan, T., Erdogmus, D., Adami, A., & Pavel, M. (2005). Feature selection by independent component analysis and mutual information maximization in EEG signal classification. In Proceedings of the International Joint Conference on Neural Networks, IJCNN 2005 (pp. 3011-3016). Article 1556405 (Proceedings of the International Joint Conference on Neural Networks; Vol. 5). https://doi.org/10.1109/IJCNN.2005.1556405

Feature selection by independent component analysis and mutual information maximization in EEG signal classification. / Lan, Tian; Erdogmus, Deniz; Adami, Andre et al.
Proceedings of the International Joint Conference on Neural Networks, IJCNN 2005. 2005. p. 3011-3016 1556405 (Proceedings of the International Joint Conference on Neural Networks; Vol. 5).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Lan, T, Erdogmus, D, Adami, A & Pavel, M 2005, Feature selection by independent component analysis and mutual information maximization in EEG signal classification. in Proceedings of the International Joint Conference on Neural Networks, IJCNN 2005., 1556405, Proceedings of the International Joint Conference on Neural Networks, vol. 5, pp. 3011-3016, International Joint Conference on Neural Networks, IJCNN 2005, Montreal, QC, Canada, 7/31/05. https://doi.org/10.1109/IJCNN.2005.1556405

Lan T, Erdogmus D, Adami A, Pavel M. Feature selection by independent component analysis and mutual information maximization in EEG signal classification. In Proceedings of the International Joint Conference on Neural Networks, IJCNN 2005. 2005. p. 3011-3016. 1556405. (Proceedings of the International Joint Conference on Neural Networks). doi: 10.1109/IJCNN.2005.1556405

@inproceedings{d10f9ee0f6fc4db7a6b25d7d3c3a6ef1,

title = "Feature selection by independent component analysis and mutual information maximization in EEG signal classification",

abstract = "Feature selection and dimensionality reduction are important steps in pattern recognition. In this paper, we propose a scheme for feature selection using linear independent component analysis and mutual information maximization method. The method is theoretically motivated by the fact that the classification error rate is related to the mutual information between the feature vectors and the class labels. The feasibility of the principle is illustrated on a synthetic dataset and its performance is demonstrated using EEG signal classification. Experimental results show that this method works well for feature selection.",

keywords = "Brain-Computer Interface, EEG, Entropy Estimation, Feature Selection, Independent Component Analysis, Mutual Information",

author = "Tian Lan and Deniz Erdogmus and Andre Adami and Michael Pavel",

year = "2005",

doi = "10.1109/IJCNN.2005.1556405",

language = "English (US)",

isbn = "0780390482",

series = "Proceedings of the International Joint Conference on Neural Networks",

pages = "3011--3016",

booktitle = "Proceedings of the International Joint Conference on Neural Networks, IJCNN 2005",

}

TY - GEN

T1 - Feature selection by independent component analysis and mutual information maximization in EEG signal classification

AU - Lan, Tian

AU - Erdogmus, Deniz

AU - Adami, Andre

AU - Pavel, Michael

PY - 2005

Y1 - 2005

N2 - Feature selection and dimensionality reduction are important steps in pattern recognition. In this paper, we propose a scheme for feature selection using linear independent component analysis and mutual information maximization method. The method is theoretically motivated by the fact that the classification error rate is related to the mutual information between the feature vectors and the class labels. The feasibility of the principle is illustrated on a synthetic dataset and its performance is demonstrated using EEG signal classification. Experimental results show that this method works well for feature selection.

AB - Feature selection and dimensionality reduction are important steps in pattern recognition. In this paper, we propose a scheme for feature selection using linear independent component analysis and mutual information maximization method. The method is theoretically motivated by the fact that the classification error rate is related to the mutual information between the feature vectors and the class labels. The feasibility of the principle is illustrated on a synthetic dataset and its performance is demonstrated using EEG signal classification. Experimental results show that this method works well for feature selection.

KW - Brain-Computer Interface

KW - EEG

KW - Entropy Estimation

KW - Feature Selection

KW - Independent Component Analysis

KW - Mutual Information

UR - http://www.scopus.com/inward/record.url?scp=33745701301&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33745701301&partnerID=8YFLogxK

U2 - 10.1109/IJCNN.2005.1556405

DO - 10.1109/IJCNN.2005.1556405

M3 - Conference contribution

AN - SCOPUS:33745701301

SN - 0780390482

SN - 9780780390485

T3 - Proceedings of the International Joint Conference on Neural Networks

SP - 3011

EP - 3016

BT - Proceedings of the International Joint Conference on Neural Networks, IJCNN 2005

T2 - International Joint Conference on Neural Networks, IJCNN 2005

Y2 - 31 July 2005 through 4 August 2005

ER -

Feature selection by independent component analysis and mutual information maximization in EEG signal classification

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this