Interpretable EEG-Based Emotion Recognition Using Fuzzy Cognitive Maps.

The brain is one of the most complex parts of the human body, consisting of billions of neurons and it is involved in almost all vital functions. To study the brain functionality, Electroencephalography (EEG) is used to record the electrical activity generated by the brain through electrodes placed on the scalp surface. In this paper, an auto-constructed Fuzzy Cognitive Map (FCM) model is used for interpretable emotion recognition, based on EEG signals. The introduced model constitutes the first FCM that automatically detects the cause-and-effects relations existing among brain regions and emotions induced by movies watched by volunteers. In addition, it is simple to implement and earns the trust of the user, while providing interpretable results. The effectiveness of the model over other baseline and state-of-the-art methods is examined using a publicly available dataset.