Real-time EEG-based User's Valence Monitoring

An integration of real-time EEG-based human emotion recognition algorithms in brain-computer interfaces can make the user's experience more complete, more engaging, less emotionally stressful or more stressful depending on the target of the application. Valence component of emotion, level of pleasantness, is one of the most important criteria of online assessment of social processes from brain signals. Currently, EEG-based emotion recognition algorithms usually allow recognition of two to three levels of valence. In this paper, we propose a novel real-time subject-dependent algorithm that allows recognizing four levels of valence having the short sessions of calibration. The algorithm uses fractal dimension thresholds and adopts weighted average voting strategy. The proposed algorithm has a great potential to be used to monitor emotions during human-computer interaction.