eprintid: 5987
rev_number: 2
eprint_status: archive
userid: 1
dir: disk0/00/00/59/87
datestamp: 2023-11-09 16:17:44
lastmod: 2023-11-09 16:17:44
status_changed: 2023-11-09 16:04:28
type: article
metadata_visibility: show
creators_name: Amin, H.U.
creators_name: Malik, A.S.
creators_name: Ahmad, R.F.
creators_name: Badruddin, N.
creators_name: Kamel, N.
creators_name: Hussain, M.
creators_name: Chooi, W.-T.
title: Feature extraction and classification for EEG signals using wavelet transform and machine learning techniques
ispublished: pub
keywords: Artificial intelligence; Classification (of information); Discrete wavelet transforms; Electroencephalography; Electrophysiology; Extraction; Feature extraction; Learning systems; Nearest neighbor search; Statistical tests; Wavelet decomposition; Wavelet transforms, Approximation coefficients; Cognitive task; Complex cognitive tasks; Feature extraction and classification; K-nearest neighbor classifier; Machine learning techniques; Multi layer perceptron; Wavelet energy feature, Biomedical signal processing, accuracy; adult; Article; cognition; comparative study; controlled study; electroencephalogram; human; human experiment; k nearest neighbor; learning algorithm; machine learning; male; mathematical computing; normal human; priority journal; psychometry; quantitative analysis; Raven advance progressive metric; sensitivity and specificity; support vector machine; task performance; validation study; wavelet analysis; classification; electroencephalography; physiology; reproducibility; young adult, Adult; Cognition; Electroencephalography; Humans; Machine Learning; Male; Reproducibility of Results; Task Performance and Analysis; Wavelet Analysis; Young Adult
note: cited By 200
abstract: This paper describes a discrete wavelet transform-based feature extraction scheme for the classification of EEG signals. In this scheme, the discrete wavelet transform is applied on EEG signals and the relative wavelet energy is calculated in terms of detailed coefficients and the approximation coefficients of the last decomposition level. The extracted relative wavelet energy features are passed to classifiers for the classification purpose. The EEG dataset employed for the validation of the proposed method consisted of two classes: (1) the EEG signals recorded during the complex cognitive task�Raven�s advance progressive metric test and (2) the EEG signals recorded in rest condition�eyes open. The performance of four different classifiers was evaluated with four performance measures, i.e., accuracy, sensitivity, specificity and precision values. The accuracy was achieved above 98  by the support vector machine, multi-layer perceptron and the K-nearest neighbor classifiers with approximation (A4) and detailed coefficients (D4), which represent the frequency range of 0.53�3.06 and 3.06�6.12 Hz, respectively. The findings of this study demonstrated that the proposed feature extraction approach has the potential to classify the EEG signals recorded during a complex cognitive task by achieving a high accuracy rate. © 2015, Australasian College of Physical Scientists and Engineers in Medicine.
date: 2015
publisher: Kluwer Academic Publishers
official_url: https://www.scopus.com/inward/record.uri?eid=2-s2.0-84930642013&doi=10.1007%2fs13246-015-0333-x&partnerID=40&md5=e0b9477182d677ba9c5d03e8d2a558c3
id_number: 10.1007/s13246-015-0333-x
full_text_status: none
publication: Australasian Physical and Engineering Sciences in Medicine
volume: 38
number: 1
pagerange: 139-149
refereed: TRUE
issn: 01589938
citation:   Amin, H.U. and Malik, A.S. and Ahmad, R.F. and Badruddin, N. and Kamel, N. and Hussain, M. and Chooi, W.-T.  (2015) Feature extraction and classification for EEG signals using wavelet transform and machine learning techniques.  Australasian Physical and Engineering Sciences in Medicine, 38 (1).  pp. 139-149.  ISSN 01589938