IIUM Repository

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

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

[img] PDF - Published Version
Restricted to Repository staff only

Download (5MB) | Request a copy

Abstract

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.

Item Type: Article (Journal)
Additional Information: 4870/43494
Uncontrolled Keywords: Affective computing, encephalogram (EEG), cerebellar model of articulation controller (CMAC), evolving fuzzy neural network (EFuNN), valence, arousal.
Subjects: B Philosophy. Psychology. Religion > BF Psychology > BF511 Affection. Feeling. Emotion
T Technology > T Technology (General)
Kulliyyahs/Centres/Divisions/Institutes (Can select more than one option. Press CONTROL button): Kulliyyah of Information and Communication Technology > Department of Computer Science
Kulliyyah of Information and Communication Technology > Department of Computer Science
Depositing User: Dr Hamwira Yaacob
Date Deposited: 24 Jun 2015 11:40
Last Modified: 03 Aug 2017 11:44
URI: http://irep.iium.edu.my/id/eprint/43494

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year