Real-time EEG-based emotion recognition for music therapy

Music could change our emotions, could have an influence on our mood, and finally could affect our health. Music therapy is one of the oldest methods used for treating some diseases. Since music therapy is proved to be the helpful approach, we proposed to combine music therapy process with the real-time EEG-based human emotion recognition algorithm. By this, we could identify the user's current emotional state, and based on such neurofeedback we could adjust the music therapy to the patient's needs. The proposed emotion recognition algorithm could recognize in real-time six emotions such as fear, frustrated, sad, happy, pleasant, and satisfied. As the algorithm is based on an Arousal-Valence emotion model, it has a potential to recognize all emotions that could be defined by the 2-dimensional model. The experiments on emotion induction with sound stimuli from International Affective Digitized Sounds (IADS) database and with music stimuli and implemented questionnaire were proposed and realized. In this paper, we proposed a general EEG-enabled music therapy algorithm. It allows us to adapt the therapy to the predefined time of the treatment and adjust the music therapy session to the current emotional state of the user in a way as an experienced music therapist works.