Relevant feature selection from EEG signal for mental task classification

Authors:
Akshansh Gupta;R. K. Agrawal
Affiliations:
School of Computer and Systems Sciences, Jawaharlal Nehru University, New Delhi, India;School of Computer and Systems Sciences, Jawaharlal Nehru University, New Delhi, India
Venue:
PAKDD'12 Proceedings of the 16th Pacific-Asia conference on Advances in Knowledge Discovery and Data Mining - Volume Part II
Year:
2012

Citing 11
Cited 1

Wrappers for feature subset selection

Artificial Intelligence - Special issue on relevance
Gene Selection for Cancer Classification using Support Vector Machines

Machine Learning
An introduction to variable and feature selection

The Journal of Machine Learning Research
Pattern Classification (2nd Edition)

Pattern Classification (2nd Edition)
Incremental wrapper-based gene selection from microarray data for cancer classification

Pattern Recognition
Rough set based 1-v-1 and 1-v-r approaches to support vector machine multi-classification

Information Sciences: an International Journal
Forward selection method with regression analysis for optimal gene selection in cancer classification

International Journal of Computer Mathematics - Bioinformatics
Invited paper: Comparison of brain models for active vs. passive perception

Information Sciences: an International Journal
On detecting nonlinear patterns in discriminant problems

Information Sciences: an International Journal
Constructing L2-SVM-Based Fuzzy Classifiers in High-Dimensional Space With Automatic Model Selection and Fuzzy Rule Ranking

IEEE Transactions on Fuzzy Systems
On the Complexity of Finite Sequences

IEEE Transactions on Information Theory

A three phase approach for mental task classification using EEG

Proceedings of the International Conference on Advances in Computing, Communications and Informatics

Quantified Score

Hi-index	0.00

Visualization

Abstract

In last few years, the research community has shown interest in the development of Brain Computer Interface which may assists physically challenged people to communicate with the help of brain signal. The two important components of such BCI system are to determine appropriate features and classification method to achieve better performance. In literature, Empirical Mode Decomposition is suggested for feature extraction from EEG which is suitable for the analysis of non-linear and non-stationary time series. However, the features obtained from EEG may contain irrelevant and redundant features which make them inefficient for machine learning. Relevant features not only decrease the processing time to train a classifier but also provide better generalization. Hence, relevant features which provide maximum classification accuracy are selected using ratio of scatter matrices, Chernoff distance measure and linear regression. The performance of different mental task using different measures used for feature selection is compared and evaluated in terms of classification accuracy. Experimental results show that there is significant improvement in classification accuracy with features selected using all feature selection methods and in particular with ratio of scatter matrices.