Review and Comparison of Methods which are resistant to subject shift for emotion recognition and emotion classification tasks on EEG signals

According to the recent improvements in communications and interactions between computers and humans, the need of recognizing and classifying human emotions is felt more; But one of the challenges we confront is individual differences between different subjects, so that sometimes we have to learn a specific model for a new subject, which is very time-consuming. Therefore, today we are trying to learn the common features and reduce the differences between the subjects so that we can complete emotion recognition and classification tasks in shorter time. We also decided to use EEG data for our work, which is one of the best and most available data in brain experiments.