Preference Classification Using Electroencephalography (EEG) and Deep Learning

Abstract

Electroencephalogram (EEG)-based emotion classification is rapidly becoming one of the most intensely studied areas of brain-computer interfacing (BCI). The ability to passively identify yet accurately correlate brainwaves with our immediate emotions opens up truly meaningful and previously unattainable human-computer interactions such as in forensic neuroscience, rehabilitative medicine, affective entertainment and neuro-marketing. One particularly useful yet rarely explored areas of EEG-based emotion classification is preference recognition [1], which is simply the detection of like versus dislike. Within the limited investigations into preference classification, all reported studies were based on musicallyinduced stimuli except for a single study which used 2D images. We present two EEG-based preference classification studies: using (1) kNN for a 10-subject EEG classification problem; (2) deep learning for an expanded 16-subject EEG classification problem. We show that inter-subject variability introduces significant classification problems when larger cohorts of test subjects are used and that deep learning shows promising results in terms of addressing this inter-subject variability problem in EEG-based preference classification.