Emotion Recognition Using Chaotic Features And Symbolic Dynamic

Emotion is one of the most important aspects of human life and is largely part of the daily decisions of individuals. The Emotion in humans has made us understand the human behaviors and have made the experiences in humans life. In this article, the qualitative and quantitative analysis of symbolic dynamics, which is a nonlinear method suitable for studying the behavior of biological signals, has been created between different stages of emotional separation. Indeed, symbolic dynamical analysis has proven to be suitable for studying complex systems and dynamic time series descriptions. in addition to extraction of nonlinear and chaotic features (correlation dimension, recurrent quantification analysis (RQA), ...), used principal component analysis method (PCA) to reduce dimensions of features and then classified 3 emotional classes, LALV, HAHV, and neutral using the multilayer perceptron neural network (MLP with different configurations) and K nearest neighbor (KNN). In order to evaluate the proposed method, electroencephalogram (EEG) signals from the DEAP database is used. this database were recorded 32 EEG channels from 32 people while watching music video clips. The purpose of this study was to examine the brain signals of individuals during the onset of emotion. The results of this research have shown that the highest average accuracy of classifying 3 emotional classes with PCA as the method of selection / composition of the features for the 5-NN is 85%. the accuracy of the multilayered perceptron achieved 79%. The accuracy after using the PCA method has also increased by 7% (from 78% to 85%).