A novel selection of optimal statistical features in the DWPT domain for discrimination of ictal and seizure-free electroencephalography signals

Ong, Pauline and Zainuddin, Zarita and Kee, Huong Lai (2018) A novel selection of optimal statistical features in the DWPT domain for discrimination of ictal and seizure-free electroencephalography signals. Pattern Analysis and Applications, 21. pp. 515-527. ISSN 1433-7541

Text AJ 2018 (190).pdf Restricted to Registered users only Download (1MB) | Request a copy

Abstract

Properly determining the discriminative features which characterize the inherent behaviors of electroencephalography (EEG) signals remains a great challenge for epileptic seizure detection. In this present study, a novel feature selection scheme based on the discrete wavelet packet decomposition and cuckoo search algorithm (CSA) was proposed. The normal as well as epileptic EEG recordings were frst decomposed into various frequency bands by means of wavelet packet decomposition, and subsequently, statistical features at all developed nodes in the wavelet packet decomposition tree were derived. Instead of using the complete set of the extracted features to construct a wavelet neural networks-based classifer, an optimal feature subset that maximizes the predictive competence of the classifer was selected by using the CSA. Experimental results on the publicly available benchmarks demonstrated that the proposed feature subset selection scheme achieved promising recognition accuracies of 98.43–100%, and the results were statistically signifcant using z-test with p value <0.0001.

Item Type:	Article
Uncontrolled Keywords:	Cuckoo search algorithm; Discrete wavelet packet decomposition; EEG signals; Epileptic seizure classifcation; Wavelet neural networks
Subjects:	R Medicine > RC Internal medicine
Divisions:	Faculty of Mechanical and Manufacturing Engineering > Department of Mechanical Engineering
Depositing User:	UiTM Student Praktikal
Date Deposited:	09 Jan 2022 07:37
Last Modified:	09 Jan 2022 07:37
URI:	http://eprints.uthm.edu.my/id/eprint/5453

Actions (login required)

View Item