A simple algorithm for primary emotion recognition from dual channel EEG signals

With the development of neuroscience and computer science, there is a push to employ automated methods to assist individuals in identifying their emotions. Emotion detection is normally carried out by using electroencephalogram (EEG) signals. However, the medical equipment is costly, uncomfortable, and inconvenient because of the numerous electrodes and hair-covered scalp. This challenge demands for a solution to this problem where the requirement of so many electrodes will be replaced by one or two electrodes followed by a simpler signal processing steps. As a solution to this, the current study proposes an algorithm which uses only a pair of EEG electrodes for identifying primary emotions and classifies them based on threshold based rule along with standard classification techniques. The algorithm utilizes two simple features based on signal energy variations in the sub band levels and a feature fusion technique is adopted to further reduce the computational burden. This will lead to reduction in processing power to a greater extent and practical viability will be enhanced. The experimental results prove that the feature fusion strategy does raise recognition accuracy from 97.7 % to 98.4 %. It is shown that the suggested method for emotional recognition is workable and efficient which can be implemented on portable hardware platforms with minimum memory and computational power requirement.