Human emotion modeling based on salient global features of EEG signal

Feature extraction and accurate classification of the emotion-related EEG-characteristics have a key role in success of emotion recognition systems. This paper proposes an emotion modeling from EEG (Electroencephalogram) signals based on both time and frequency domain features by applying some statistical measures, Fourier and wavelet transform. After collecting the EEG signals, the various kinds of EEG features are investigated to build an emotion classification system. The main objective of this work is to compare the efficacy of the extracted features for classifying five types of emotional states relax, mental task, memory related task, pleasant, and fear. For this purpose support vector machine classifier was employed to classify the five emotional states by using salient global features. In case of statistical features the overall accuracy was obtained 54.2%, which is improved for FFT features 55.00% and the highest accuracy was obtained by DWT features 60.15%.