CIT-EmotionNet: CNN Interactive Transformer Network for EEG Emotion Recognition

TL;DR

This paper introduces CIT-EmotionNet, a novel CNN-Transformer hybrid model that effectively combines local and global EEG features for emotion recognition, achieving state-of-the-art accuracy on public datasets.

Contribution

The paper presents a new CNN-Interactive Transformer architecture that fuses local and global EEG features for improved emotion recognition performance.

Findings

Achieved 98.57% accuracy on SEED dataset.

Achieved 92.09% accuracy on SEED-IV dataset.

Outperforms existing state-of-the-art methods.

Abstract

Emotion recognition using Electroencephalogram (EEG) signals has emerged as a significant research challenge in affective computing and intelligent interaction. However, effectively combining global and local features of EEG signals to improve performance in emotion recognition is still a difficult task. In this study, we propose a novel CNN Interactive Transformer Network for EEG Emotion Recognition, known as CIT-EmotionNet, which efficiently integrates global and local features of EEG signals. Initially, we convert raw EEG signals into spatial-frequency representations, which serve as inputs. Then, we integrate Convolutional Neural Network (CNN) and Transformer within a single framework in a parallel manner. Finally, we design a CNN interactive Transformer module, which facilitates the interaction and fusion of local and global features, thereby enhancing the model's ability to extract both types of features from EEG spatial-frequency representations. The proposed CIT-EmotionNet outperforms state-of-the-art methods, achieving an average recognition accuracy of 98.57\% and 92.09\% on two publicly available datasets, SEED and SEED-IV, respectively.