I. Introduction
Emotion recognition (ER) is the process of identifying the current mental state of a person, and brain signal is the most prospectus for ER. Emotions can be recognized with facial images [1], speech [2], brain signals [3] etc. Among these, brain signal is highly reliable as it is not affected by human subjective factors [3]. Electroencephalography (EEG) is a preferable brain signal for ER as it is non-invasive, fast, portable and easy to use [4] with respect to other neuroimaging techniques. EEG captures the electrical signals produced by neuronal activities of the brain through its sensors (i.e., EEG channels or electrodes) attached to the brain. It is anticipated that these signals will provide comprehensive information about the emotional process. EEG based ER is being explored in recent studies [3], [4], [13–16], [5]–[12] due to its prospect to be used in many areas such as entertainment, e-learning, online games and e-healthcare [13].