关键词: 脑电信号, 情感识别, 近似熵, 排列熵, 奇异值分解熵, 卷积神经网络, 组合特征

Abstract:

In order to preserve the spatial information between the electrodes and fully extract the characteristics of Electroencephalogram（EEG） and improve the accuracy of emotion recognition, a feature learning and classification algorithm based on convolutional neural network with 3D input is proposed. The single entropy（approximate entropy, permutation entropy and singular value decomposing entropy） and its combined entropy characteristics are used to perform emotion recognition experiments in the DEAP dataset on the two dimensions of valenceand arousal. The experimental results show that the accuracy of the combined entropy feature is significantly higher than that of the single entropy feature in the emotion recognition experiments. The average accuracy of the highest combined entropy characteristics are 94.14% and 94.44% in the valence and arousal, respectively, which are 5.05 percentage points and 4.49 percentage points higher than the average accuracy of the highest single entropy.

Key words: Electroencephalogram（EEG）, emotion recognition, approximate entropy, permutation entropy, singular value decomposition entropy, convolutional neural network, combined features