CMAC-Based Computational Model of Affects (CCMA) from self-organizing feature mapping weights for classification of emotion using EEG signals

Emotion is postulated to be generated at the brain. To capture the brain activities during emotional processing, several neuro-imaging techniques have been adopted, including electroencephalogram (EEG). In the existing studies, different techniques have been employed to extract features from EEG sig...

Full description

Bibliographic Details
Main Authors:	Yaacob, Hamwira Sakti, Abdul Rahman, Abdul Wahab, Kamaruddin, Norhaslinda
Format:	Article
Language:	English
Published:	International Society for Computers and Their Applications 2015
Subjects:	BF511 Affection. Feeling. Emotion T Technology (General)
Online Access:	http://irep.iium.edu.my/43494/ http://irep.iium.edu.my/43494/ http://irep.iium.edu.my/43494/4/4_Yaacob%2C_IJCA_Journal_March_2015.pdf

id	iium-43494
recordtype	eprints
spelling	iium-434942017-08-03T03:44:41Z http://irep.iium.edu.my/43494/ CMAC-Based Computational Model of Affects (CCMA) from self-organizing feature mapping weights for classification of emotion using EEG signals Yaacob, Hamwira Sakti Abdul Rahman, Abdul Wahab Kamaruddin, Norhaslinda BF511 Affection. Feeling. Emotion T Technology (General) Emotion is postulated to be generated at the brain. To capture the brain activities during emotional processing, several neuro-imaging techniques have been adopted, including electroencephalogram (EEG). In the existing studies, different techniques have been employed to extract features from EEG signals for emotion classification. However, existing feature extraction techniques do not consider spatial and temporal neural-dynamics of emotion. Furthermore, the non-linearity of EEG and self-adaptive of neural activations are disregard. Therefore, the classification accuracy of any feature extraction technique is inconsistent when applied with different classifiers. Hence, in this study, a new feature extraction technique that inculcates the qualities of EEG signal and the behavior of neural activations is proposed based on Cerebellar Model Articulation Controller (CMAC) model. The accuracy of classifying calm, fear, happiness and sadness emotional states using Evolving Fuzzy Neural Network (EFuNN) classifiers are reported based on subject-dependent and subject-independent validations. The classification performance of using features from power spectral density (PSD), kernel density estimation (KDE) and mel-frequency ceptral coefficients (MFCC) are also compared and reported. It is observed that the proposed technique is able to yield accuracy of above 50% to above 90% for subject-dependent classification. For subject-independent approach, the highest accuracy is barely 40%. The results suggest that this approach is comparable as a feature extraction technique for classifying emotions. International Society for Computers and Their Applications 2015-03 Article PeerReviewed application/pdf en http://irep.iium.edu.my/43494/4/4_Yaacob%2C_IJCA_Journal_March_2015.pdf Yaacob, Hamwira Sakti and Abdul Rahman, Abdul Wahab and Kamaruddin, Norhaslinda (2015) CMAC-Based Computational Model of Affects (CCMA) from self-organizing feature mapping weights for classification of emotion using EEG signals. International Journal of Computers and Their Applications, 22 (1). pp. 31-42. ISSN 1076-5204 http://www.isca-hq.org/journal.htm
repository_type	Digital Repository
institution_category	Local University
institution	International Islamic University Malaysia
building	IIUM Repository
collection	Online Access
language	English
topic	BF511 Affection. Feeling. Emotion T Technology (General)
spellingShingle	BF511 Affection. Feeling. Emotion T Technology (General) Yaacob, Hamwira Sakti Abdul Rahman, Abdul Wahab Kamaruddin, Norhaslinda CMAC-Based Computational Model of Affects (CCMA) from self-organizing feature mapping weights for classification of emotion using EEG signals
description	Emotion is postulated to be generated at the brain. To capture the brain activities during emotional processing, several neuro-imaging techniques have been adopted, including electroencephalogram (EEG). In the existing studies, different techniques have been employed to extract features from EEG signals for emotion classification. However, existing feature extraction techniques do not consider spatial and temporal neural-dynamics of emotion. Furthermore, the non-linearity of EEG and self-adaptive of neural activations are disregard. Therefore, the classification accuracy of any feature extraction technique is inconsistent when applied with different classifiers. Hence, in this study, a new feature extraction technique that inculcates the qualities of EEG signal and the behavior of neural activations is proposed based on Cerebellar Model Articulation Controller (CMAC) model. The accuracy of classifying calm, fear, happiness and sadness emotional states using Evolving Fuzzy Neural Network (EFuNN) classifiers are reported based on subject-dependent and subject-independent validations. The classification performance of using features from power spectral density (PSD), kernel density estimation (KDE) and mel-frequency ceptral coefficients (MFCC) are also compared and reported. It is observed that the proposed technique is able to yield accuracy of above 50% to above 90% for subject-dependent classification. For subject-independent approach, the highest accuracy is barely 40%. The results suggest that this approach is comparable as a feature extraction technique for classifying emotions.
format	Article
author	Yaacob, Hamwira Sakti Abdul Rahman, Abdul Wahab Kamaruddin, Norhaslinda
author_facet	Yaacob, Hamwira Sakti Abdul Rahman, Abdul Wahab Kamaruddin, Norhaslinda
author_sort	Yaacob, Hamwira Sakti
title	CMAC-Based Computational Model of Affects (CCMA) from self-organizing feature mapping weights for classification of emotion using EEG signals
title_short	CMAC-Based Computational Model of Affects (CCMA) from self-organizing feature mapping weights for classification of emotion using EEG signals
title_full	CMAC-Based Computational Model of Affects (CCMA) from self-organizing feature mapping weights for classification of emotion using EEG signals
title_fullStr	CMAC-Based Computational Model of Affects (CCMA) from self-organizing feature mapping weights for classification of emotion using EEG signals
title_full_unstemmed	CMAC-Based Computational Model of Affects (CCMA) from self-organizing feature mapping weights for classification of emotion using EEG signals
title_sort	cmac-based computational model of affects (ccma) from self-organizing feature mapping weights for classification of emotion using eeg signals
publisher	International Society for Computers and Their Applications
publishDate	2015
url	http://irep.iium.edu.my/43494/ http://irep.iium.edu.my/43494/ http://irep.iium.edu.my/43494/4/4_Yaacob%2C_IJCA_Journal_March_2015.pdf
first_indexed	2023-09-18T21:01:58Z
last_indexed	2023-09-18T21:01:58Z
_version_	1777410683249360896

CMAC-Based Computational Model of Affects (CCMA) from self-organizing feature mapping weights for classification of emotion using EEG signals

Similar Items