Evaluation of feature extraction and classification techniques for EEG-based subject identification

The ability to identify a subject is indispensable in affective computing research due to its wide range of applications. User profiling was created based on the strength of emotional patterns of the subject, which can be used for subject identification. Such system is made based on the emotional st...

Full description

Bibliographic Details
Main Authors:	Handayani, Dini Oktarina Dwi, Abdul Rahman, Abdul Wahab, Yaacob, Hamwira Sakti
Format:	Article
Language:	English English English
Published:	UTM Press 2016
Subjects:	T Technology (General)
Online Access:	http://irep.iium.edu.my/56434/ http://irep.iium.edu.my/56434/ http://irep.iium.edu.my/56434/ http://irep.iium.edu.my/56434/1/56434_Evaluation%20of%20feature%20extraction%20and%20classification.pdf http://irep.iium.edu.my/56434/2/56434_Evaluation%20of%20feature%20extraction%20and%20classification_Scopus.pdf http://irep.iium.edu.my/56434/3/56434_Evaluation%20of%20feature%20extraction%20and%20classification_WoS.pdf

id	iium-56434
recordtype	eprints
spelling	iium-564342017-04-18T01:28:54Z http://irep.iium.edu.my/56434/ Evaluation of feature extraction and classification techniques for EEG-based subject identification Handayani, Dini Oktarina Dwi Abdul Rahman, Abdul Wahab Yaacob, Hamwira Sakti T Technology (General) The ability to identify a subject is indispensable in affective computing research due to its wide range of applications. User profiling was created based on the strength of emotional patterns of the subject, which can be used for subject identification. Such system is made based on the emotional states of happiness and sadness, indicated by the electroencephalogram (EEG) data. In this paper, we examine several techniques used for subject profiling or identification purposed. Those techniques include feature extraction and classification techniques. In the experimental study, we compare three techniques for feature extraction namely, Power Spectral Density (PSD), Kernel Density Estimation (KDE), and Mel Frequency Cepstral Coefficients (MFCC). As for classification we compare three classification techniques, they are; Multilayer Perceptron (MLP), Naive Bayesian (NB), and Support Vector Machine (SVM). The best result achieved was 59.66%, using the MFCC and MLP-based techniques using 5-fold cross validation. The experiment results indicated that these profiles could be more accurate in identifying subject compared to NB and SVM. The comparisons demonstrated that profile-based methods for subject identification provide a viable and simple alternative to this problem. UTM Press 2016 Article PeerReviewed application/pdf en http://irep.iium.edu.my/56434/1/56434_Evaluation%20of%20feature%20extraction%20and%20classification.pdf application/pdf en http://irep.iium.edu.my/56434/2/56434_Evaluation%20of%20feature%20extraction%20and%20classification_Scopus.pdf application/pdf en http://irep.iium.edu.my/56434/3/56434_Evaluation%20of%20feature%20extraction%20and%20classification_WoS.pdf Handayani, Dini Oktarina Dwi and Abdul Rahman, Abdul Wahab and Yaacob, Hamwira Sakti (2016) Evaluation of feature extraction and classification techniques for EEG-based subject identification. Jurnal Teknologi, 78 (9). pp. 41-48. E-ISSN 2180–3722 http://www.jurnalteknologi.utm.my/index.php/jurnalteknologi/article/view/9717/5894 10.11113/jt.v78.9717
repository_type	Digital Repository
institution_category	Local University
institution	International Islamic University Malaysia
building	IIUM Repository
collection	Online Access
language	English English English
topic	T Technology (General)
spellingShingle	T Technology (General) Handayani, Dini Oktarina Dwi Abdul Rahman, Abdul Wahab Yaacob, Hamwira Sakti Evaluation of feature extraction and classification techniques for EEG-based subject identification
description	The ability to identify a subject is indispensable in affective computing research due to its wide range of applications. User profiling was created based on the strength of emotional patterns of the subject, which can be used for subject identification. Such system is made based on the emotional states of happiness and sadness, indicated by the electroencephalogram (EEG) data. In this paper, we examine several techniques used for subject profiling or identification purposed. Those techniques include feature extraction and classification techniques. In the experimental study, we compare three techniques for feature extraction namely, Power Spectral Density (PSD), Kernel Density Estimation (KDE), and Mel Frequency Cepstral Coefficients (MFCC). As for classification we compare three classification techniques, they are; Multilayer Perceptron (MLP), Naive Bayesian (NB), and Support Vector Machine (SVM). The best result achieved was 59.66%, using the MFCC and MLP-based techniques using 5-fold cross validation. The experiment results indicated that these profiles could be more accurate in identifying subject compared to NB and SVM. The comparisons demonstrated that profile-based methods for subject identification provide a viable and simple alternative to this problem.
format	Article
author	Handayani, Dini Oktarina Dwi Abdul Rahman, Abdul Wahab Yaacob, Hamwira Sakti
author_facet	Handayani, Dini Oktarina Dwi Abdul Rahman, Abdul Wahab Yaacob, Hamwira Sakti
author_sort	Handayani, Dini Oktarina Dwi
title	Evaluation of feature extraction and classification techniques for EEG-based subject identification
title_short	Evaluation of feature extraction and classification techniques for EEG-based subject identification
title_full	Evaluation of feature extraction and classification techniques for EEG-based subject identification
title_fullStr	Evaluation of feature extraction and classification techniques for EEG-based subject identification
title_full_unstemmed	Evaluation of feature extraction and classification techniques for EEG-based subject identification
title_sort	evaluation of feature extraction and classification techniques for eeg-based subject identification
publisher	UTM Press
publishDate	2016
url	http://irep.iium.edu.my/56434/ http://irep.iium.edu.my/56434/ http://irep.iium.edu.my/56434/ http://irep.iium.edu.my/56434/1/56434_Evaluation%20of%20feature%20extraction%20and%20classification.pdf http://irep.iium.edu.my/56434/2/56434_Evaluation%20of%20feature%20extraction%20and%20classification_Scopus.pdf http://irep.iium.edu.my/56434/3/56434_Evaluation%20of%20feature%20extraction%20and%20classification_WoS.pdf
first_indexed	2023-09-18T21:19:37Z
last_indexed	2023-09-18T21:19:37Z
_version_	1777411793955586048

Evaluation of feature extraction and classification techniques for EEG-based subject identification

Similar Items