A Lightweight Transformer Model for Robust EEG Emotion Recognition Using Channel-Wise Differential Entropy

With the increasing demand for emotion recognition technology in fields such as healthcare, humancomputer interaction, and education, efficiently and accurately decoding emotional information from EEG signals has become a research hotspot. This paper proposes a brain EEG emotion recognition model, Channel-wise Differential Entropy Transformer (CWDET), based on the combination of differential entropy (DE) features and Transformer encoder. In this method, DE features of EEG signals are first extracted in five frequency bands: δ, θ, α, β, and γ. Each channel is treated as an independent input token, and through simple but efficient embedding and positional encoding, low-dimensional information is mapped into highdimensional space. The multi-head self-attention mechanism is then employed to achieve global feature fusion across channels, effectively reducing data redundancy and computational cost. The experiments conducted on the SEED and SEED-IV datasets achieved high classification accuracies of 98.63% and 99.16%, respectively, with the model performing excellently in terms of standard deviation and stability. Further analysis of the attention weights reveals that the model automatically focuses on key brain regions such as the prefrontal area, central, and centralparietal junction. Even when selecting only a subset of channels, the model still maintained 93.44% recognition performance on the SEED-IV dataset. Comparative experiments with various existing advanced methods show that CWDET offers a simple structure and computational efficiency while maintaining high performance, providing a feasible low-resource solution for practical EEG emotion recognition applications. This work not only provides new theoretical and practical support for the development of EEG emotion recognition technology but also lays a solid foundation for future generalization research across subjects and sessions.