A real time emotional interaction between EEG brain signals and robot

Abstract

In this paper, emotion recognition using frontal electroencephalogram (EEG) asymmetry signals is presented. A total of four channels are used in representing EEG frontal asymmetry, consisting of the left and right hemisphere of the brain. Arousal and valence for two-dimensional emotion models are used in classifying four basic emotions; happy, sad, angry, and relaxed. The mirror neuron system (MNS) for emotion elicitation is utilized in finding correlation between participant's emotion rating and EEG data. This is achieved by showing images and music to each participant. These images are used to elicit emotions in applying the imitation concept. In addition, an emotion recognition method based on a combination of two algorithms, fractal dimension for feature extraction and multidimensional direct information on finding correlation between left and right EEG frontal asymmetry is proposed. Good performances are achieved from the combination and rating process, where it can be utilized to indicate correlation between participants rating and EEG recorded data. The final results of the EEG recorded data are represented as robot emotions. Therefore, the main contribution is to create a real-time emotional interaction based on the analyzed EEG recorded data.