This project aims to introduce feedback loops to Mental Health Treatment. Mental Health Professionals are often partaking in treatment that is open-loop, where the patient is regularly quizzed about his/her/their feelings/emotions in order to make informed decisions. In order to limit this phenomenon, we propose a system that aims at predicting the emotions of the patient via a Deep Neural Network trained over the raw EEG data obtained from EEG headsets.
In the currently used dataset, music video clips are used as the visual stimuli to elicit different emotions. To this end, a relatively large set of music video clips was gathered.
• 32 participants took part in the experiment and their EEG and peripheral physiological signals were recorded as they watched the 40 selected music videos.
• Participants rated each video in terms of arousal, valence, like/dislike, dominance and familiarity. For 22 participants, frontal face video was also recorded.
• The database contains all recorded signal data, frontal face video for a subset of the participants and subjective ratings from the participants.