An Emotion Recognition Method for Game Evaluation Based on Electroencephalogram

Players-based emotion recognition can help understanding game players emotional states, contributing to the improvement of the games quality and value. This paper proposes a new hybrid neural network learning framework called convolutional smooth feedback fuzzy network (CSFFN) to detect a players emotional states in real-time during a gaming process based on electroencephalogram (EEG) signals. Specifically, CSFFN rationally combines three subnetworks: a convolutional neural network (CNN), a fuzzy neural network (FNN), and a recurrent neural network (RNN). CNN not only captures spatial characteristics between EEG signals from different channels but also eliminates noise from EEG signals, effectively improving the accuracy and anti-noise performance in game emotion recognition. FNN effectively extracts the membership degree of a players different emotional states, further improving the emotion recognition accuracy. Since a players current emotional state is influenced by the previous emotional states during the entire game process, RNN is employed to capture the temporal characteristics of EEG signals, better improving the emotion recognition accuracy. Experimental results show that the CSFFN model has higher recognition accuracy and better noise resistance in identifying four emotional states (happiness, sadness, superiority, and anger) compared to support vector machine (SVM) with different kernels, linear discrimination analysis (LDA), AlexNet, and VGG16 methods.