Brain-TV Connection: Toward Establishing Emotional Connection with Smart TVs

Brain-computer interface (BCI) has changed the way to interact with external devices. Considering the role that computers and machines play in our daily life, recently, emotional interaction between human and machine has become an interesting area in BCI. Smart TVs, on the other hand, are becoming ubiquitous. Although recently a growing trend toward developing new features in Smart TVs has emerged, these devices are not yet aware of emotional states of audiences. This study aims at improving the quality of interaction between audiences and Smart TVs by establishing an emotional connection between them. In this work, 19 subjects aged 19-32 years participated in an EEG experiment, while watching a movie clip that evoked 3 emotional states: horror, neutral and relaxation. Firstly, the acquired EEG signals were denoised by stationary wavelet transform (SWT). For the majority of participants, a correlation mean energy of EEG sub-bands and between emotional states was observed for relaxing and scary movies. Thereby, the mean energy of EEG frequency bands 4-50Hz, were extracted so as to classify the emotional states. We managed to classify the EEG signals induced by relaxing and horror movies with average rate of 92% accuracy over all subjects using support vector machine (SVM). The classified data were then given to smart TV in order to establish interaction with audience based on his/her emotional state for each subject (subject-dependent classification).