EEG-CMT: spatial-temporal representation of EEG for emotion recognition using convolutional neural networks and vision transformers

Clinical Snapshot

Key Findings

• P Value: Not reported

• Effect Size: 97.51% accuracy on SEED dataset, 96.13% on SEED-IV dataset

• Primary Outcome: Classification accuracy for emotion recognition from EEG signals

• Nnt Or Sensitivity: Improvement margins: 0.86-11.43% (SEED), 9.49-39.52% (SEED-IV) over baseline methods

• Confidence Interval: Not reported

Clinical Application

Requires specialized EEG equipment and computational resources; implementation complexity moderate to high Relevant for Australian neuroscience research institutions and potential TGA-regulated medical device development for mental health applications Patients requiring emotion recognition for brain-computer interfaces, affective computing applications, mental health monitoring

Abstract

Background. Recent researches on electroencephalogram (EEG) based emotion recognition face challenges in effectively mapping the spatial positional relationships of EEG acquisition electrodes. Additionally, conventional models struggled to simultaneously capture both fine-grained temporal-spatial features and long-range dependencies in EEG signals.New method. To address these limitations, we propose a novel EEG data processing method that incorporates spatial relative position encoding and a hybrid neural architecture integrating convolutional neural networks (CNNs) with self-attention mechanisms. This approach systematically encodes the spatial topology of electrodes to enhance the representation of temporal-spatial information. CNNs are employed to extract localized temporal-spatial micro-patterns, while self-attention modules model global contextual dependencies across extended sequences, thereby enhancing model's representational capacity.Results. The experimental results and feature visualizations demonstrate that our method achieves state-of-the-art (SOTA) subject-dependent performance on two benchmark emotion recognition datasets, reaching an average accuracy of 97.51% on the SEED dataset and 96.13% on the SEED-IV dataset. Moreover, the learned spatial features align well with known neuroscientific patterns of emotional processing. Comprehensive ablation studies further validate the necessity and effectiveness of both the spatial-encoded data processing strategy and the hybrid architecture design.Comparison with Existing Methods. Compared to other hybrid neural network models, our proposed method (EEG-CMT) achieves the highest classification accuracy. Specifically, it outperforms baseline algorithms by margins ranging from 0.86% to 11.43% on the SEED dataset, and from 9.49% to 39.52% on the SEED-IV dataset.Conclusions. The proposed method effectively addresses key limitations in existing EEG-based emotion recognition models by jointly leveraging spatial topology and hybrid modeling techniques. These innovations significantly improve the model's ability to recognize emotions from EEG data and provide neural interpretable insights, offering a promising direction for future research in affective brain-computer interfaces.

References

1. 1.Mei, T., Wang, Y., Gou, H., Chang, C., Hu, S., & Zhang, X. (2026). EEG-CMT: spatial-temporal representation of EEG for emotion recognition using convolutional neural networks and vision transformers. Biomedical Physics & Engineering Express. https://doi.org/10.1088/2057-1976/ae55aa