eprintid: 8139
rev_number: 2
eprint_status: archive
userid: 1
dir: disk0/00/00/81/39
datestamp: 2023-11-09 16:20:00
lastmod: 2023-11-09 16:20:00
status_changed: 2023-11-09 16:11:53
type: article
metadata_visibility: show
creators_name: Amin, H.U.
creators_name: Mumtaz, W.
creators_name: Subhani, A.R.
creators_name: Saad, M.N.M.
creators_name: Malik, A.S.
title: Classification of EEG signals based on pattern recognition approach
ispublished: pub
keywords: Artificial intelligence; Barium compounds; Classification (of information); Electroencephalography; Extraction; Feature extraction; Learning systems; Nearest neighbor search; Pattern recognition; Principal component analysis; Sodium compounds; Statistical tests, Classification performance; Coefficient approximation; Complex cognitive tasks; Electro-encephalogram (EEG); Electroencephalogram signals; Feature extraction methods; K nearest neighbor (KNN); Multi resolution decomposition, Biomedical signal processing, article; classification; classifier; decomposition; electroencephalogram; extraction; eye; human; human experiment; k nearest neighbor; pattern recognition; perceptron; principal component analysis
note: cited By 125
abstract: Feature extraction is an important step in the process of electroencephalogram (EEG) signal classification. The authors propose a �pattern recognition� approach that discriminates EEG signals recorded during different cognitive conditions. Wavelet based feature extraction such as, multi-resolution decompositions into detailed and approximate coefficients as well as relative wavelet energy were computed. Extracted relative wavelet energy features were normalized to zero mean and unit variance and then optimized using Fisher�s discriminant ratio (FDR) and principal component analysis (PCA). A high density EEG dataset validated the proposed method (128-channels) by identifying two classifications: (1) EEG signals recorded during complex cognitive tasks using Raven�s Advance Progressive Metric (RAPM) test; (2) EEG signals recorded during a baseline task (eyes open). Classifiers such as, K-nearest neighbors (KNN), Support VectorMachine (SVM),Multi-layer Perceptron (MLP), and Naïve Bayes (NB) were then employed. Outcomes yielded 99.11 accuracy via SVM classifier for coefficient approximations (A5) of low frequencies ranging from 0 to 3.90Hz. Accuracy rates for detailed coefficients were 98.57 and 98.39 for SVM and KNN, respectively; and for detailed coefficients (D5) deriving from the sub-band range (3.90�7.81Hz). Accuracy rates for MLP and NB classifiers were comparable at 97.11�89.63 and 91.60�81.07 for A5 and D5 coefficients, respectively. In addition, the proposed approach was also applied on public dataset for classification of two cognitive tasks and achieved comparable classification results, i.e., 93.33 accuracy with KNN. The proposed scheme yielded significantly higher classification performances using machine learning classifiers compared to extant quantitative feature extraction. These results suggest the proposed feature extraction method reliably classifies EEG signals recorded during cognitive tasks with a higher degree of accuracy. © 2017 Amin, Mumtaz, Subhani, Saad and Malik.
date: 2017
publisher: Frontiers Media S.A.
official_url: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85040942259&doi=10.3389%2ffncom.2017.00103&partnerID=40&md5=c4bdc83e0bcab59e4234ce6319aef508
id_number: 10.3389/fncom.2017.00103
full_text_status: none
publication: Frontiers in Computational Neuroscience
volume: 11
refereed: TRUE
issn: 16625188
citation:   Amin, H.U. and Mumtaz, W. and Subhani, A.R. and Saad, M.N.M. and Malik, A.S.  (2017) Classification of EEG signals based on pattern recognition approach.  Frontiers in Computational Neuroscience, 11.   ISSN 16625188