Improving EEG-based Emotion Recognition by Fusing Time-frequency And Spatial Representations

Using deep learning methods to classify EEG signals can accurately identify people's emotions. However, previous studies have rarely considered the application of the information in other modal representations to feature selection in the time-frequency domain. We propose a classification network of EEG signals based on the multi-modal feature fusion method, which makes the network more focused on the features most related to brain activities and thinking changes by using the multi-modal attention mechanism. In addition, we propose a two-step fusion method and apply these methods to the EEG emotion recognition network. Experimental results show that our proposed EEG emotion recognition network, which combines multiple representations in the time-frequency domain and spatial domain, outperforms previous methods on public datasets and achieves state-of-the-art performance.