Attention based convolutional network for automatic sleep stage classification
-
Shasha Sun
Abstract
Sleep staging is an important basis for diagnosing sleep-related problems. In this paper, an attention based convolutional network for automatic sleep staging is proposed. The network takes time-frequency image as input and predict sleep stage for each 30-s epoch as output. For each CNN feature maps, our model generate attention maps along two separate dimensions, time and filter, and then multiplied to form the final attention map. Residual-like fusion structure is used to append the attention map to the input feature map for adaptive feature refinement. In addition, to get the global feature representation with less information loss, the generalized mean pooling is introduced. To prove the efficacy of the proposed method, we have compared with two baseline method on sleep-EDF data set with different setting of the framework and input channel type, the experimental results show that the paper model has achieved significant improvements in terms of overall accuracy, Cohen’s kappa, MF1, sensitivity and specificity. The performance of the proposed network is compared with that of the state-of-the-art algorithms with an overall accuracy of 83.4%, a macro F1-score of 77.3%, κ = 0.77, sensitivity = 77.1% and specificity = 95.4%, respectively. The experimental results demonstrate the superiority of the proposed network.
Research funding: None declared.
Author contributions: All authors have accepted responsibility for the entire content of this manuscript and approved its submission.
Conflict of interest: Authors state no conflict of interest.
References
1. Wulff, K, Gatti, S, Wettstein, JG, Foster, RG. Sleep and circadian rhythm disruption in psychiatric and neurodegenerative disease. Nat Rev Neurosci 2010;11:589. https://doi.org/10.1038/nrn2868.Search in Google Scholar PubMed
2. Agarwal, R, Gotman, J. Computer-assisted sleep staging. IEEE Trans Biomed Eng 2001;48:1412–23. https://doi.org/10.1109/10.966600.Search in Google Scholar PubMed
3. Berry, RB, Brooks, R, Gamaldo, CE, Harding, SM, Marcus, C, Vaughn, BV, et al.. The AASM manual for the scoring of sleep and associated events. Rules, Terminology and Technical Specifications, Darien, Illinois. Illinois: American Academy of Sleep Medicine; 2012:176 p.Search in Google Scholar
4. Lajnef, T, Chaibi, S, Ruby, P, Aguera, PE, Eichenlaub, JB, Samet, M, et al.. Learning machines and sleeping brains: automatic sleep stage classification using decision-tree multi-class support vector machines. J Neurosci Methods 2015;250:94–105. https://doi.org/10.1016/j.jneumeth.2015.01.022.Search in Google Scholar PubMed
5. Alickovic, E, Subasi, A. Ensemble SVM method for automatic sleep stage classification. IEEE Trans Instrum Meas 2018;67:1258–65. https://doi.org/10.1109/tim.2018.2799059.Search in Google Scholar
6. Memar, P, Faradji, F. A novel multi-class EEG-based sleep stage classification system. IEEE Trans Neural Syst Rehabil Eng 2017;26:84–95.10.1109/TNSRE.2017.2776149Search in Google Scholar PubMed
7. LeCun, Y, Bengio, Y, Hinton, G. Deep learning. Nature 2015;521:436. https://doi.org/10.1038/nature14539.Search in Google Scholar PubMed
8. Ronzhina, M, Janoušek, O, Kolářová, J, Nováková, M, Honzík, P, Provazník, I. Sleep scoring using artificial neural networks. Sleep Med Rev 2011;16:263.10.1016/j.smrv.2011.06.003Search in Google Scholar PubMed
9. Hsu, YL, Yang, YT, Wang, JS, Hsu, CY. Automatic sleep stage recurrent neural classifier using energy features of EEG signals. Neurocomputing 2012;104:105–14. https://doi.org/10.1016/j.neucom.2012.11.003.Search in Google Scholar
10. Supratak, A, Dong, H, Wu, C, Guo, Y. DeepSleepNet: a model for automatic sleep stage scoring based on raw single-channel EEG. IEEE Trans Neural Syst Rehabil Eng 2017:1.10.1109/TNSRE.2017.2721116Search in Google Scholar PubMed
11. Phan, H, Andreotti, F, Cooray, N, Chén, OY, De Vos, M. SeqSleepNet: end-to-end hierarchical recurrent neural network for sequence-to-sequence automatic sleep staging. IEEE Trans Neural Syst Rehabil Eng 2019;27:400–10. https://doi.org/10.1109/tnsre.2019.2896659.Search in Google Scholar
12. Humayun, AI, Sushmit, AS, Hasan, T, Bhuiyan, MIH. End-to-end sleep staging with raw single channel EEG using deep residual ConvNets.Search in Google Scholar
13. Chambon, S, Galtier, MN, Arnal, PJ, Wainrib, G, Gramfort, A. A deep learning architecture for temporal sleep stage classification using multivariate and multimodal time series. IEEE Trans Neural Syst Rehabil Eng 2018;26:758–69. https://doi.org/10.1109/tnsre.2018.2813138.Search in Google Scholar PubMed
14. Andreotti, F, Phan, H, Cooray, N, Lo, C, Hu, MT, De Vos, M. Multichannel sleep stage classification and transfer learning using convolutional neural networks. In: 2018 40th annual international conference of the IEEE Engineering in medicine and biology society (EMBC). IEEE; 2018:171–4 pp.10.1109/EMBC.2018.8512214Search in Google Scholar PubMed
15. Phan, H, Andreotti, F, Cooray, N, Chèn, YO, De Vos, M. DNN filter bank improves 1-max pooling CNN for single-channel EEG automatic sleep stage classification. In: 2018 40th annual international conference of the IEEE engineering in medicine and biology society (EMBC). IEEE; 2018:453–6 pp.10.1109/EMBC.2018.8512286Search in Google Scholar PubMed
16. Phan, H, Andreotti, F, Cooray, N, Chén, OY, De Vos, M. Joint classification and prediction CNN framework for automatic sleep stage classification. IEEE Trans Biomed Eng 2018;66:1285–96.10.1109/TBME.2018.2872652Search in Google Scholar PubMed PubMed Central
17. Phan, H, Andreotti, F, Cooray, N, Chén, OY, De Vos, M. Automatic sleep stage classification using single-channel eeg: learning sequential features with attention-based recurrent neural networks. In: 2018 40th annual international conference of the IEEE engineering in medicine and biology society (EMBC). IEEE; 2018:1452–5 pp.10.1109/EMBC.2018.8512480Search in Google Scholar PubMed
18. Radenović, F, Tolias, G, Chum, O. Fine-tuning CNN image retrieval with no human annotation. IEEE Trans Pattern Anal Mach Intell 2018;41:1655–68.10.1109/TPAMI.2018.2846566Search in Google Scholar PubMed
19. Bahdanau, D, Cho, K, Bengio, Y. Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:14090473. 2014.Search in Google Scholar
20. Chorowski, JK, Bahdanau, D, Serdyuk, D, Cho, K, Bengio, Y. Attention-based models for speech recognition. In: Advances in neural information processing systems; 2015:577–85 pp.Search in Google Scholar
21. Xu, K, Ba, J, Kiros, R, Cho, K, Courville, A, Salakhudinov, R, et al.. Show, attend and tell: neural image caption generation with visual attention. In: International conference on machine learning; 2015:2048–57 pp.Search in Google Scholar
22. Rush, AM, Chopra, S, Weston, J. A neural attention model for abstractive sentence summarization. arXiv preprint arXiv:150900685; 2015.10.18653/v1/D15-1044Search in Google Scholar
23. Wang, F, Jiang, M, Qian, C, Yang, S, Li, C, Zhang, H, et al.. Residual attention network for image classification. In: proceedings of the IEEE conference on computer vision and pattern recognition; 2017:3156–64 pp.10.1109/CVPR.2017.683Search in Google Scholar
24. Woo, S, Park, J, Lee, JY, So Kweon, I. Cbam: convolutional block attention module. In: proceedings of the European conference on computer vision (ECCV); 2018:3–19 pp.10.1007/978-3-030-01234-2_1Search in Google Scholar
25. Kemp, B, Zwinderman, AH, Tuk, B, Kamphuisen, HA, Oberye, JJ. Analysis of a sleep-dependent neuronal feedback loop: the slow-wave microcontinuity of the EEG. IEEE Trans Biomed Eng 2000;47:1185–94. https://doi.org/10.1109/10.867928.Search in Google Scholar PubMed
26. Abadi, M, Agarwal, A, Barham, P, Brevdo, E, Chen, Z, Citro, C, et al.. Tensorflow: large-scale machine learning on heterogeneous distributed systems. arXiv preprint arXiv:160304467; 2016.Search in Google Scholar
27. Kingma, DP, Ba, J. Adam: a method for stochastic optimization. arXiv preprint arXiv:14126980; 2014.Search in Google Scholar
28. Back, S, Lee, S, Seo, H, Park, D, Kim, T, Lee, K. Intra-and inter-epoch temporal context network (IITNet) for automatic sleep stage scoring. arXiv preprint arXiv:190206562; 2019.Search in Google Scholar
29. Tsinalis, O, Matthews, PM, Guo, Y, Zafeiriou, S. Automatic sleep stage scoring with single-channel EEG using convolutional neural networks. arXiv preprint arXiv:161001683; 2016.Search in Google Scholar
30. Tsinalis, O, Matthews, PM, Guo, Y. Automatic sleep stage scoring using time-frequency analysis and stacked sparse autoencoders. Annals Biomed Eng 2016;44:1587–97. https://doi.org/10.1007/s10439-015-1444-y.Search in Google Scholar PubMed PubMed Central
31. Vilamala, A, Madsen, KH, Hansen, LK. Deep convolutional neural networks for interpretable analysis of EEG sleep stage scoring. In: 2017 IEEE 27th international workshop on machine learning for signal processing (MLSP). IEEE; 2017:1–6 pp.10.1109/MLSP.2017.8168133Search in Google Scholar
© 2021 Walter de Gruyter GmbH, Berlin/Boston
Articles in the same Issue
- Frontmatter
- Research Articles
- Attention based convolutional network for automatic sleep stage classification
- Emotion recognition using time–frequency ridges of EEG signals based on multivariate synchrosqueezing transform
- A novel signal to image transformation and feature level fusion for multimodal emotion recognition
- PVC arrhythmia classification based on fractional order system modeling
- A clinical set-up for noninvasive blood pressure monitoring using two photoplethysmograms and based on convolutional neural networks
- Virtual simulation of otolith movement for the diagnosis and treatment of benign paroxysmal positional vertigo
- Development and control of a home-based training device for hand rehabilitation with a spring and cable driven mechanism
- An easy and low-cost biomagnetic methodology to study regional gastrointestinal transit in rats
- Detection of adverse events leading to inadvertent injury during laparoscopic cholecystectomy using convolutional neural networks
- Comparison of a standardized four-point bending test to an implant system test of an osteosynthetic system under static and dynamic load condition
- An application of finite element method in material selection for dental implant crowns
Articles in the same Issue
- Frontmatter
- Research Articles
- Attention based convolutional network for automatic sleep stage classification
- Emotion recognition using time–frequency ridges of EEG signals based on multivariate synchrosqueezing transform
- A novel signal to image transformation and feature level fusion for multimodal emotion recognition
- PVC arrhythmia classification based on fractional order system modeling
- A clinical set-up for noninvasive blood pressure monitoring using two photoplethysmograms and based on convolutional neural networks
- Virtual simulation of otolith movement for the diagnosis and treatment of benign paroxysmal positional vertigo
- Development and control of a home-based training device for hand rehabilitation with a spring and cable driven mechanism
- An easy and low-cost biomagnetic methodology to study regional gastrointestinal transit in rats
- Detection of adverse events leading to inadvertent injury during laparoscopic cholecystectomy using convolutional neural networks
- Comparison of a standardized four-point bending test to an implant system test of an osteosynthetic system under static and dynamic load condition
- An application of finite element method in material selection for dental implant crowns
