An Emotion Classification Method Based on Energy Entropy of Principal Component

Emotional recognition based on electroencephalogram (EEG) has attracted more and more attention, and various methods emerge in an endless stream. An emotion classification method based on energy entropy of principal component (PCEE) is proposed in this paper. EEG data are divided into five rhythms (δ, θ, α, β and γ) by wavelet decomposition and reconstruction (WDR). Each rhythm signal uses principal component analysis (PCA) to perform dimensionality reduction on the channels (electrodes). The energy entropies of the principal components that meet the requirements are used as the classification feature. Results show that the classification accuracy can reach 87.61% by using the support vector machine (SVM) classifier.