Application of Deep Learning Method in Emotional Brain computer Interface

Brain computer Interface (BCI) is attracting increasing attention in neural engineering, which can encode brain signals into control command. In recent years, with computer science growing, deep learning has been gradually applied to BCI system, which greatly increases the precision of target recognition in BCI. This paper first introduces several models commonly used in deep learning, such as convolutional neural networks (CNN), recurrent neural networks (RNN), and Deep Belief Networks (DBN). Then, some research on BCI systems based on deep learning in various application scenarios is listed. In particular, emotional BCI has been widely studied among all kinds of BCI systems based on Electroencephalogram (EEG) signals. This paper also reviews research on the emotion BCI system based on deep learning. Finally, the current research status of deep learning in BCI systems and the factors affecting BCI recognition accuracy are summarized and the future research directions and the trend of emotional BCI system are discussed.