Feature Fusion Based on Mutual-Cross-Attention Mechanism for EEG Emotion Recognition
This work addresses the need for objective and accurate emotion diagnostic references for psychologists, particularly with patients who are difficult to communicate with, representing a strong specific gain in the domain of EEG emotion recognition.
The paper tackled the problem of excessive model complexity, mediocre accuracy, and limited interpretability in EEG-based emotion recognition systems by proposing a Mutual-Cross-Attention feature fusion mechanism combined with a 3D-CNN, achieving 99.49% accuracy for valence and 99.30% for arousal on the DEAP dataset.
An objective and accurate emotion diagnostic reference is vital to psychologists, especially when dealing with patients who are difficult to communicate with for pathological reasons. Nevertheless, current systems based on Electroencephalography (EEG) data utilized for sentiment discrimination have some problems, including excessive model complexity, mediocre accuracy, and limited interpretability. Consequently, we propose a novel and effective feature fusion mechanism named Mutual-Cross-Attention (MCA). Combining with a specially customized 3D Convolutional Neural Network (3D-CNN), this purely mathematical mechanism adeptly discovers the complementary relationship between time-domain and frequency-domain features in EEG data. Furthermore, the new designed Channel-PSD-DE 3D feature also contributes to the high performance. The proposed method eventually achieves 99.49% (valence) and 99.30% (arousal) accuracy on DEAP dataset.