Dynamic Multi-Scale Feature Fusion for Robust Sleep Stage Classification Using Single-Channel EEG

Jiajun Zhong

doi:10.54097/1swr9p34

Authors

Jiajun Zhong

DOI:

https://doi.org/10.54097/1swr9p34

Keywords:

Sleep stage classification, Single-channel EEG, Adaptive selective kernel convolution, Multi-branch residual learning

Abstract

Sleep stage classification is pivotal in evaluating sleep quality and diagnosing sleep-related disorders. Recent advancements in automated single-channel electroencephalogram (EEG)--based classification have gained traction due to their cost-effectiveness and portability. However, the inherent non-stationarity of EEG signals and inter-class imbalance pose significant challenges for model design. This paper proposes MultiScaleSleepNet, an enhanced deep learning architecture that addresses these limitations through dynamic multi-scale feature fusion and residual structural optimizations. Our contributions are threefold: (1) A selective kernel convolution module (SKConv) that dynamically integrates multi-branch convolutional features (kernel sizes: 3, 5, 7) via attention mechanisms to adaptively capture frequency-specific patterns in EEG signals; (2) A residual multi-branch downsampling module that mitigates information loss while preserving high-frequency details for minority-stage classification; (3) Comprehensive experiments on the Sleep-EDF-20 dataset demonstrate superior performance, achieving a macro F1-score (MF1) of 79.6%—a 1.5% improvement over baseline models—with notable gains in classifying the N1 stage (F1-score: 47.0%, +4.4% relative improvement). Quantitative ablation studies validate the efficacy of SKConv and residual connections in enhancing feature discriminability. This study delivers a robust single-channel EEG-based sleep analysis framework, demonstrating significant clinical applicability in resource-constrained settings.

Downloads

Download data is not yet available.

References

[1] E. Tobaldini, E. M. Fiorelli, M. Solbiati, G. Costantino, L. Nobili, and N. Montano, “Short sleep duration and cardiometabolic risk: from pathophysiology to clinical evidence,” Nat. Rev. Cardiol. 2018 164, vol. 16, no. 4, pp. 213–224, Nov. 2018, doi: 10.1038/s41569-018-0109-6.

[2] G. Medic, M. Wille, and M. E. H. Hemels, “Short- and long-term health consequences of sleep disruption,” Nat. Sci. Sleep, vol. 9, pp. 151–161, 2017, doi: 10.2147/NSS.S134864.

[3] E. D. Chinoy et al., “Performance of seven consumer sleep-tracking devices compared with polysomnography,” Sleep, vol. 44, no. 5, May 2021, doi: 10.1093/SLEEP/ZSAA291.

[4] R. Zhao, Y. Xia, and Q. Wang, “Dual-modal and multi-scale deep neural networks for sleep staging using EEG and ECG signals,” Biomed. Signal Process. Control, vol. 66, p. 102455, Apr. 2021, doi: 10.1016/J.BSPC.2021.102455.

[5] A. Supratak, H. Dong, C. Wu, and Y. Guo, “DeepSleepNet: A model for automatic sleep stage scoring based on raw single-channel EEG,” IEEE Trans. Neural Syst. Rehabil. Eng., vol. 25, no. 11, pp. 1998–2008, 2017, doi: 10.1109/TNSRE.2017.2721116.

[6] H. Phan, F. Andreotti, N. Cooray, O. Y. Chen, and M. De Vos, “Joint Classification and Prediction CNN Framework for Automatic Sleep Stage Classification,” IEEE Trans. Biomed. Eng., vol. 66, no. 5, pp. 1285–1296, 2019, doi: 10.1109/TBME.2018.2872652.

[7] R. K. Tripathy, S. K. Ghosh, P. Gajbhiye, and U. R. Acharya, “Development of automated sleep stage classification system using multivariate projection-based fixed boundary empirical wavelet transform and entropy features extracted from multichannel eeg signals,” Entropy, vol. 22, no. 10, pp. 1–23, 2020, doi: 10.3390/e22101141.

[8] J. M. Kortelainen, M. O. Mendez, A. M. Bianchi, M. Matteucci, and S. Cerutti, “Sleep staging based on signals acquired through bed sensor,” IEEE Trans. Inf. Technol. Biomed., vol. 14, no. 3, pp. 776–785, 2010, doi: 10.1109/TITB.2010.2044797.

[9] S. Güneş, K. Polat, and Ş. Yosunkaya, “Efficient sleep stage recognition system based on EEG signal using k-means clustering based feature weighting,” Expert Syst. Appl., vol. 37, no. 12, pp. 7922–7928, 2010, doi: 10.1016/j.eswa.2010.04.043.

[10] [G. Zhu, Y. Li, and P. P. Wen, “Analysis and classification of sleep stages based on difference visibility graphs from a single-channel EEG signal,” IEEE J. Biomed. Heal. Informatics, vol. 18, no. 6, pp. 1813–1821, Nov. 2014, doi: 10.1109/JBHI.2014.2303991.

[11] P. Memar and F. Faradji, “A Novel Multi-Class EEG-Based Sleep Stage Classification System,” IEEE Trans. Neural Syst. Rehabil. Eng., vol. 26, no. 1, pp. 84–95, Jan. 2018, doi: 10.1109/TNSRE.2017.2776149.

[12] S. I. Dimitriadis, C. Salis, and D. Linden, “A novel, fast and efficient single-sensor automatic sleep-stage classification based on complementary cross-frequency coupling estimates,” Clin. Neurophysiol., vol. 129, no. 4, pp. 815–828, Apr. 2018, doi: 10.1016/J.CLINPH.2017.12.039.

[13] G. Zhu, Y. Li, P. (Paul) Wen, and S. Wang, “Analysis of alcoholic EEG signals based on horizontal visibility graph entropy,” Brain Informatics, vol. 1, no. 1–4, pp. 19–25, Dec. 2014, doi: 10.1007/S40708-014-0003-X/MEDIAOBJECTS/40708_2014_3_MOESM2_ESM.EPS.

[14] A. R. Hassan and M. I. H. Bhuiyan, “Computer-aided sleep staging using Complete Ensemble Empirical Mode Decomposition with Adaptive Noise and bootstrap aggregating,” Biomed. Signal Process. Control, vol. 24, pp. 1–10, Feb. 2016, doi: 10.1016/J.BSPC.2015.09.002.

[15] O. Tsinalis, P. M. Matthews, Y. Guo, and S. Zafeiriou, “Automatic Sleep Stage Scoring with Single-Channel EEG Using Convolutional Neural Networks,” Oct. 2016, Accessed: Feb. 05, 2025. [Online]. Available: https://arxiv.org/abs/1610.01683v1

[16] A. Sors, S. Bonnet, S. Mirek, L. Vercueil, and J. F. Payen, “A convolutional neural network for sleep stage scoring from raw single-channel EEG,” Biomed. Signal Process. Control, vol. 42, pp. 107–114, Apr. 2018, doi: 10.1016/J.BSPC.2017.12.001.

[17] S. Chambon, M. N. Galtier, P. J. Arnal, G. Wainrib, and A. Gramfort, “A Deep Learning Architecture for Temporal Sleep Stage Classification Using Multivariate and Multimodal Time Series,” IEEE Trans. Neural Syst. Rehabil. Eng., vol. 26, no. 4, pp. 758–769, Apr. 2018, doi: 10.1109/TNSRE.2018.2813138.

[18] N. Michielli, U. R. Acharya, and F. Molinari, “Cascaded LSTM recurrent neural network for automated sleep stage classification using single-channel EEG signals,” Comput. Biol. Med., vol. 106, pp. 71–81, Mar. 2019, doi: 10.1016/J.COMPBIOMED.2019.01.013.

[19] X. Li, W. Wang, X. Hu, and J. Yang, “Selective kernel networks,” Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., vol. 2019-June, pp. 510–519, 2019, doi: 10.1109/CVPR.2019.00060.

[20] T. Zhu, W. Luo, and F. Yu, “Convolution- and Attention-Based Neural Network for Automated Sleep Stage Classification,” Int. J. Environ. Res. Public Heal. 2020, Vol. 17, Page 4152, vol. 17, no. 11, p. 4152, Jun. 2020, doi: 10.3390/IJERPH17114152.

[21] S. Mousavi, F. Afghah, and U. Rajendra Acharya, “SleepEEGNet: Automated sleep stage scoring with sequence to sequence deep learning approach,” PLoS One, vol. 14, no. 5, p. e0216456, May 2019, doi: 10.1371/JOURNAL.PONE.0216456.

[22] E. Eldele et al., “An Attention-Based Deep Learning Approach for Sleep Stage Classification with Single-Channel EEG,” IEEE Trans. Neural Syst. Rehabil. Eng., vol. 29, pp. 809–818, 2021, doi: 10.1109/TNSRE.2021.3076234.

[23] A. L. Goldberger et al., “PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals.,” Circulation, vol. 101, no. 23, Jun. 2000, doi: 10.1161/01.CIR.101.23.E215/ASSET/9716B30D-2E4D-4D06-8F9E-A21157DFE97C/ASSETS/GRAPHIC/HC2304183003.JPEG.

[24] Y. Tang and Y. Zhang, “SVMs Modeling for Highly Imbalanced Classification,” vol. 39, no. 1, pp. 281–288, 2009.

[25] Y. Sun, B. Wang, J. Jin, and X. Wang, “Deep Convolutional Network Method for Automatic Sleep Stage Classification Based on Neurophysiological Signals,” Proc. - 2018 11th Int. Congr. Image Signal Process. Biomed. Eng. Informatics, CISP-BMEI 2018, Jul. 2018, doi: 10.1109/CISP-BMEI.2018.8633058.