Emotion recognition algorithm based on convolution neural network

Emotional recognition is a very challenging nature of the topic in the field of Brain — Computer Interface (BCI). This technology has been applied in many fields, such as The electroencephalogram (EEG) signals. The EEG signals can intuitively express the human emotional state and has attracted attentions of many researchers. Besides, it has a strong correlation during a period. To preserve the correlation, this paper presents an emotion recognition algorithm based on convolution neural network (ERACNN). In this paper, the EEG signals are pretreated, and then the parameters of CNN are selected. Finally, the classification model of emotion recognition is trained. Experimental results show that the results based on ERACNN is more robust than these based on Support Vector Machine (SVM). Besides, ERACNN can improve the classification accuracy of emotion recognition compared with the similar CNN algorithm.