Emotion Recognition from EEG during Self-Paced Emotional Imagery

摘要: Here we present an analysis of a 12-subject electroencephalographic (EEG) data set in which participants were asked to engage prolonged, self-paced episodes guided emotion imagination with eyes closed. Our goal is correctly predict, given short EEG segment, whether the participant was imagining positive respectively negative-valence emotional scenario during segment using predictive model learned via machine learning. The challenge lies generalizing novel (i.e., previously unseen) from wide variety scenarios including love, awe, frustration, anger, etc. based purely on spontaneous oscillatory activity without stimulus event-locked responses. Using variant Filter-Bank Common Spatial Pattern algorithm, achieve average accuracy 71.3% correct classification binary valence rating across 12 different imagery under rigorous block-wise cross-validation.