caa a22 4500 605469679 CHVBK 20210128100323.0 cr unu---uuuuu 210128e20151001xx s 000 0 eng 10.1007/s00500-014-1443-1 doi (NATIONALLICENCE)springer-10.1007/s00500-014-1443-1 Performance enhancement of mental task classification using EEG signal: a study of multivariate feature selection methods [Elektronische Daten] [Akshansh Gupta, R. Agrawal, Baljeet Kaur] In the recent years, the research community has shown interest in the development of brain-computer interface applications which assist physically challenged people to communicate with their brain electroencephalogram (EEG) signal. Representation of these EEG signals for mental task classification in terms of relevant features is important to achieve higher performance in terms of accuracy and computation time. For feature extraction from the EEG, empirical mode decomposition and wavelet transform are more appropriate as they are suitable for the analysis of non-linear and non-stationary time series signals. However, the size of the feature vector obtained from them is huge and may hinder the performance of mental task classification. To obtain a minimal set of relevant and non-redundant features for classification, six popular multivariate filter methods have been investigated which are based on different criteria: distance measure, causal effect and mutual information. Experimental results demonstrate that the classification accuracy improves while the computation time reduces considerably with the use of each of the six multivariate feature selection methods. Among all the combinations of feature extraction and selection methods that are investigated, the combination of wavelet transform and linear regression performs the best. Ranking analysis and statistical tests are also performed to validate the empirical results. Springer-Verlag Berlin Heidelberg, 2014 Empirical mode decomposition nationallicence Wavelet transform nationallicence Bhattacharyya distance nationallicence Kullback-Leibler distance nationallicence Ratio of scatter matrices nationallicence Linear regression nationallicence Minimum redundancy and maximum relevance nationallicence Gupta Akshansh School of Computer and Systems Sciences, Jawaharlal Nehru University, 110067, New Delhi, India aut Agrawal R. School of Computer and Systems Sciences, Jawaharlal Nehru University, 110067, New Delhi, India aut Kaur Baljeet Department of Computer Science, Hansraj College, University of Delhi, 110007, Delhi, India aut Soft Computing Springer Berlin Heidelberg 19/10(2015-10-01), 2799-2812 1432-7643 19:10<2799 2015 19 500 https://doi.org/10.1007/s00500-014-1443-1 text/html Onlinezugriff via DOI BK010053 XK010053 XK010000 Metadata rights reserved Springer special CC-BY-NC licence nationallicence 1 research-article jats NATIONALLICENCE NATIONALLICENCE NL-springer NATIONALLICENCE 856 40 https://doi.org/10.1007/s00500-014-1443-1 text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Gupta Akshansh School of Computer and Systems Sciences, Jawaharlal Nehru University, 110067, New Delhi, India aut NATIONALLICENCE 700 1- Agrawal R. School of Computer and Systems Sciences, Jawaharlal Nehru University, 110067, New Delhi, India aut NATIONALLICENCE 700 1- Kaur Baljeet Department of Computer Science, Hansraj College, University of Delhi, 110007, Delhi, India aut NATIONALLICENCE 773 0- Soft Computing Springer Berlin Heidelberg 19/10(2015-10-01), 2799-2812 1432-7643 19:10<2799 2015 19 500