Predicting arousal with machine learning of EEG signals

The usage of brain-computer interface (BCI) is becoming more and more popular in real life settings. As BCI equipment increases in ubiquity, the potential for application areas also rises. Present utilization of BCI includes - among others - prosthesis control [1], neurofeedback training [2], and neuromarketing [3]. A now popular field of BCI is the automatic identification of emotions using different physiological devices [4], [5]. The following study represents our effort to identify the arousal component of emotion [6] using EEG. Contrary to previous studies - that have mostly used questionnaire responses to assess arousal [4], [7] - our approach involved the use of objective physiological markers to gauge arousal.