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

TL;DR

This paper introduces a novel EEG emotion recognition network that fuses time-frequency and spatial domain features using a multi-domain attention mechanism, significantly improving accuracy over previous methods.

Contribution

It presents a cross-domain feature fusion approach with a two-step fusion method and multi-domain attention, enhancing EEG-based emotion recognition performance.

Findings

Outperforms previous methods on public datasets

Achieves state-of-the-art accuracy in EEG emotion recognition

Effectively integrates multi-domain features for better classification

Abstract

Using deep learning methods to classify EEG signals can accurately identify people's emotions. However, existing studies have rarely considered the application of the information in another domain's representations to feature selection in the time-frequency domain. We propose a classification network of EEG signals based on the cross-domain feature fusion method, which makes the network more focused on the features most related to brain activities and thinking changes by using the multi-domain 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 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 at present.