CaT-SleepNet: A Cross-Attention and Transformer-Based Hybrid Framework for EEG–EOG Sleep Stage Classification
DOI:
https://doi.org/10.24297/ijct.v25i.9815Keywords:
Sleep staging, EEG, Transformer, Cross-attention, Multimodal fusion, XGBoostAbstract
sleep disorders and understanding sleep mechanisms. However, traditional deep learning models often fail to effectively
capture both temporal dependencies within Electroencephalogram(EEG) signals and the semantic correlations between
multimodal inputs. In this study, we propose a dual-stream Transformer-based framework that integrates raw EEG and
electro-oculogram (EOG) signals and their corresponding time-frequency (TF) representations through a cross-attention
fusion mechanism. Each modality is first processed by independent feature extractors, followed by pre-trained channellevel Transformers to capture intra-channel temporal dependencies. Finally, a global Transformer module is used for feature extraction, and the learned representations are classified using an optimized XGBoost classifier to enhance
discrimination ability. Experimental results on the Sleep-EDF-20, Sleep-EDF-78, and ISRUC-S3 datasets show that
the proposed model achieves accuracies of 88.5%, 86.8%, and 84.0%, respectively, outperforming several state-of-the-art
baselines and confirming the effectiveness of the proposed multimodal fusion and hybrid Transformer-XGBoost design
for sleep stage classification.
Downloads
References
Dai, Y., Li, X., Liang, S., Wang, L., Duan, Q., Yang, H., . . . Liao, X. (2023). Multichannelsleepnet: A transformer-based
model for automatic sleep stage classification with psg. IEEE Journal of Biomedical and Health Informatics,
(9), 4204-4215.
Eldele, E., Ragab, M., Chen, Z., Wu, M., Kwoh, C. K., Li, X., & Guan, C. (2021). An attention-based deep learning
approach for sleep stage classification with single-channel eeg. IEEE Transactions on Neural Systems and
Rehabilitation Engineering, 29 , 809–818. doi: 10.1109/TNSRE.2021.3076234
Fu, G., Zhou, Y., Gong, P., Wang, P., Shao, W., & Zhang, D. (2023). A temporal-spectral fused and attention-based
deep model for automatic sleep staging. IEEE Transactions on Neural Systems and Rehabilitation Engineering,
, 1008–1018. doi: 10.1109/TNSRE.2023.3238852
Guo, Y., Nowakowski, M., & Dai, W. (2024). Flexsleeptransformer: a transformer-based sleep staging model with
flexible input channel configurations. Scientific Reports, 14 , 26312. doi: 10.1038/s41598-024-76197-0
Huang, J., Ren, L., Ji, Z., et al. (2022). Single-channel eeg automatic sleep staging based on transition optimized hmm.
Multimedia Tools and Applications, 81 , 43063–43081. doi: 10.1007/s11042-022-12551-6
Ji, X., Li, Y., Wen, P., Barua, P., & Acharya, U. R. (2024). Mixsleepnet: A multi-type convolution combined
sleep stage classification model. Computer Methods and Programs in Biomedicine, 244 , 107992. doi: 10.1016/
j.cmpb.2023.107992
Jia, Z., Lin, Y., Wang, J., Wang, X., Xie, P., & Zhang, Y. (2021). Salientsleepnet: Multimodal salient wave
detection network for sleep staging. In Proceedings of the thirtieth international joint conference on artificial
intelligence (ijcai-21) (pp. 2614–2620). International Joint Conferences on Artificial Intelligence Organization.
doi: 10.24963/ijcai.2021/360
Lee, H., Choi, Y., Lee, H., et al. (2025). Explainable vision transformer for automatic visual sleep staging on multimodal
psg signals. npj Digital Medicine, 8 , 55. doi: 10.1038/s41746-024-01378-0
Ma, S., et al. (2025). Ubiquitous sleep staging via supervised multimodal coordination (sleepsmc). In International
conference on learning representations (iclr).
Phan, H., Andreotti, F., Cooray, N., Chén, O. Y., & De Vos, M. (2019). Seqsleepnet: End-to-end hierarchical recurrent
neural network for sequence-to-sequence automatic sleep staging. IEEE Transactions on Neural Systems and
Rehabilitation Engineering, 27 (3), 400–410. doi: 10.1109/TNSRE.2019.2896659
Phan, H., Chén, O. Y., Tran, M. C., Koch, P., Mertins, A., & De Vos, M. (2022). Xsleepnet: Multi-view sequential
model for automatic sleep staging. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44 (9),
-5915. doi: 10.1109/TPAMI.2021.3070057
Phan, H., Mikkelsen, K., Chén, O. Y., Koch, P., Mertins, A., & De Vos, M. (2022). Sleeptransformer: Automatic
sleep staging with interpretability and uncertainty quantification. IEEE Transactions on Biomedical Engineering,
(8), 2456–2467. doi: 10.1109/TBME.2022.3147187
Shen, H., Ran, F., Xu, M., Guez, A., Li, A., & Guo, A. (2020). An automatic sleep stage classification algorithm using
improved model based essence features. Sensors, 20 (17), 4677. doi: 10.3390/s20174677
Sors, A., Bonnet, S., Mirek, S., Vercueil, L., & Payen, J.-F. (2018). A convolutional neural network for sleep
stage scoring from raw single-channel eeg. Biomedical Signal Processing and Control, 42 , 107–114. doi:
1016/j.bspc.2017.12.001
Supratak, A., Dong, H., Wu, C., & Guo, Y. (2017). Deepsleepnet: A model for automatic sleep stage scoring based on
raw single-channel eeg. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 25 (11), 1998–2008.
doi: 10.1109/TNSRE.2017.2721116
Wang, W., et al. (2023). Dynamicsleepnet: a multi-exit neural network with adaptive inference time for sleep stage
classification. Frontiers in Physiology, 14 , 1171467. doi: 10.3389/fphys.2023.1171467
Wang, Y., et al. (2024). Research on sleep staging based on support vector machine and extreme gradient boosting
algorithm. Nature and Science of Sleep, 16 , 1827–1847. doi: 10.2147/NSS.S467111
Zheng, Y., Luo, Y., Zou, B., Zhang, L., & Li, L. (2022). Mmasleepnet: A multimodal attention network based on
electrophysiological signals for automatic sleep staging. Frontiers in Neuroscience, 16 , 973761. doi: 10.3389/
fnins.2022.973761
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Jin Peng, Haodong Fang, Yuanyuan Sheng, Wensheng Liu, Yuyue Wu, Ruiheng Xie, Li Zhu
This work is licensed under a Creative Commons Attribution 4.0 International License.
