CMAC-based Computational Model of Affects (CCMA) for profiling emotion from EEG signals

Abstract

Several studies have been perfo emotions using EEG signals through affe approach. It includes data acquisition, signa feature extraction and classification. Differen feature extraction and classification techn proposed. However, the results are subjective include subject-independent classification. In profiling model, known as CMAC-based Com of Affects (CCMA), is proposed. ), CMAC is reasonable model for processing EEG signa capabilities to solve non-linear problem organization feature mapping (SOFM). F extracted using CCMA are trained using Neural Network (EFuNN) as the classifier. classification of emotions using features that power spectral density (PSD) was also perfor shows that the performance of using CCM emotions outperforms the performance of cla from PSD features. Keywords-CMAC; EEG; affective com feature extractionI.

Understanding teacher stress when teaching the developed technology by using electroencephalogram (EEG) signals

“…In this research study, Russell's model [5] has been adapted to understand human emotion according to the current research [6], [7], [8]. Eight basic emotion, happy, clam, fear, sad, anger, disgust and surprise are commonly accepted according to [9].…”