Abstract: This paper reports on the human emotion recon- ignition using different set of electroencephalogram (EEG) channels using discrete wavelet transform. Emotion recognition could be done from the text, speech, and facial. In the past few days, many studies have been done on emotion recognition. Anderson utilized facial expressions to recognize emotion. However, these signals shared the same disadvantage. They are not reliable or perfection is not there to detect emotion, especially when people want to conceal their feelings. In this paper, The EEG-based emotion recognition algorithm based on spectral features and neural network classifiers is proposed. In this algorithm, spectral, spatial and temporal features are selected from the emotion-related EEG signals by applying wavelet transform. We concentrate on recognition of “inner” emotions from electroencephalogram (EEG) signals as humans could control their facial expressions or vocal intonation. We observe the different brain position as Left Hemisphere and Right Hemisphere to recognize the significance according to different moods. The powers of alpha are more alert during National, Happy, Romantic mood as compared to Sad mood. We have used wavelet function for deriving a set of conventional and modified energy based features from the EEG signals for classifying emotions.
Keywords: EEG, Human Emotion, Discrete Wavelet Transform, Speech.