Emotion Classification System Based on Non-Linear EEG Signal using Backpropagation Neural Network

Emotion classification rapidly gains popularity in research world, especially in healthcare field. EEG signal used to classify human emotional state might provide wider range of information rather using other types of signal, yet this data need more complex processes because of its dimensions and noises. ANN is one of many techniques used to classify human emotion, by using DEAP's EEG dataset this research will provide higher recognition rate of 2-dimensional emotion classification, which is using EEG's non-linear features, including every frequency bands in EEG signal except delta rhythm which produced when subjects are sleeping. In this research PCA played a big role in computational optimization and provide higher number of recognition rates up to 60,15%. To achieve this recognition rate, the system is given an additional part, which is BPNN as data train's correction so that training rate will be on its maximum. Through this correlation, we will analyze the correlation of those additions for human emotional classification. And the result of this paper will give possibility of further research in human emotional classification using BPNN as correction factor of recognition rate.