The dynamic emotion recognition system based on functional connectivity of brain regions

Emotion perception similar to thinking, learning and remembering is consequent of complicated brain processes which are related to specific biological metabolism. Different human´s emotional states are recognizable by measuring and interpreting of human physiological signals. Bio-sensors possess a number of advantages against other emotion recognition methods as they are relatively more consistent across cultures and nations. Emotions have a serious effect on driving. Human beings in negative and sometimes positive emotional states can be distracted which will increase the risk of driving. This paper presents an EEG-based emotion recognition system. Mutual information and magnitude squared coherence are applied to investigate the interconnectivity between 8 scalp regions. A study was performed to collect 8 channels of EEG data from 26 healthy right-handed subjects in experiencing 4 emotional states while exposed to audio-visual emotional stimuli. After feature extraction, 5-fold cross-validation was then performed using the KNN and SVM classifier. The results showed existence of different kind of functional brain connectivity in different emotional states.