Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
169 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Generalizable Sleep Staging via Multi-Level Domain Alignment (2401.05363v4)

Published 13 Dec 2023 in eess.SP and cs.LG

Abstract: Automatic sleep staging is essential for sleep assessment and disorder diagnosis. Most existing methods depend on one specific dataset and are limited to be generalized to other unseen datasets, for which the training data and testing data are from the same dataset. In this paper, we introduce domain generalization into automatic sleep staging and propose the task of generalizable sleep staging which aims to improve the model generalization ability to unseen datasets. Inspired by existing domain generalization methods, we adopt the feature alignment idea and propose a framework called SleepDG to solve it. Considering both of local salient features and sequential features are important for sleep staging, we propose a Multi-level Feature Alignment combining epoch-level and sequence-level feature alignment to learn domain-invariant feature representations. Specifically, we design an Epoch-level Feature Alignment to align the feature distribution of each single sleep epoch among different domains, and a Sequence-level Feature Alignment to minimize the discrepancy of sequential features among different domains. SleepDG is validated on five public datasets, achieving the state-of-the-art performance.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (52)
  1. Inter-database validation of a deep learning approach for automatic sleep scoring. PloS one, 16(8): e0256111.
  2. Analysis of ensemble-combination strategies for improving inter-database generalization of deep-learning-based automatic sleep staging. In 2022 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI), 01–06. IEEE.
  3. Invariant Risk Minimization. ArXiv, abs/1907.02893.
  4. Generalizing from several related classification tasks to a new unlabeled sample. In Proceedings of the 24th International Conference on Neural Information Processing Systems, 2178–2186.
  5. Domain generalization via model-agnostic learning of semantic features. Advances in Neural Information Processing Systems, 32.
  6. 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.
  7. Unsupervised domain adaptation by statistics alignment for deep sleep staging networks. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 30: 205–216.
  8. Unsupervised domain adaptation by backpropagation. In International conference on machine learning, 1180–1189.
  9. Domain-adversarial training of neural networks. The journal of machine learning research, 17(1): 2096–2030.
  10. You snooze, you win: the physionet/computing in cardiology challenge 2018. In 2018 Computing in Cardiology Conference (CinC), volume 45, 1–4. IEEE.
  11. PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals. Circulation, 101 23: E215–20.
  12. In Search of Lost Domain Generalization. In International Conference on Learning Representations.
  13. The American Academy of Sleep Medicine (AASM) Manual for the Scoring of Sleep and Associated Events: Rules, Terminology and Technical Specifications, volume 1. American academy of sleep medicine Westchester, IL.
  14. SalientSleepNet: Multimodal Salient Wave Detection Network for Sleep Staging. In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21, 2614–2620.
  15. GraphSleepNet: adaptive spatial-temporal graph convolutional networks for sleep stage classification. In Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence, 1324–1330.
  16. Analysis of a sleep-dependent neuronal feedback loop: the slow-wave microcontinuity of the EEG. IEEE Transactions on Biomedical Engineering, 47: 1185–1194.
  17. ISRUC-Sleep: A comprehensive public dataset for sleep researchers. Computer methods and programs in biomedicine, 124: 180–192.
  18. Wilds: A benchmark of in-the-wild distribution shifts. In International Conference on Machine Learning, 5637–5664. PMLR.
  19. Domain generalization with adversarial feature learning. In Proceedings of the IEEE conference on computer vision and pattern recognition, 5400–5409.
  20. Domain generalization via conditional invariant representations. In Proceedings of the AAAI conference on artificial intelligence, volume 32, 3579–3587.
  21. Domain generalization using a mixture of multiple latent domains. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 34, 11749–11756.
  22. Domain generalization via invariant feature representation. In International Conference on Machine Learning, 10–18.
  23. Domain adaptation via transfer component analysis. IEEE transactions on neural networks, 22(2): 199–210.
  24. Synthetic to Real Adaptation with Generative Correlation Alignment Networks. In 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), 1982–1991. IEEE Computer Society.
  25. U-Sleep: resilient high-frequency sleep staging. NPJ digital medicine, 4(1): 72.
  26. U-Time: a fully convolutional network for time series segmentation applied to sleep staging. In Proceedings of the 33rd International Conference on Neural Information Processing Systems, 4415–4426.
  27. SeqSleepNet: End-to-End Hierarchical Recurrent Neural Network for Sequence-to-Sequence Automatic Sleep Staging. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 27: 400–410.
  28. XSleepNet: Multi-view sequential model for automatic sleep staging. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(9): 5903–5915.
  29. Sleeptransformer: Automatic sleep staging with interpretability and uncertainty quantification. IEEE Transactions on Biomedical Engineering, 69(8): 2456–2467.
  30. Enhancing Contextual Encoding With Stage-Confusion and Stage-Transition Estimation for EEG-Based Sleep Staging. In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 1301–1305. IEEE.
  31. A Residual Based Attention Model for EEG Based Sleep Staging. IEEE Journal of Biomedical and Health Informatics, 24: 2833–2843.
  32. The sleep heart health study: design, rationale, and methods. Sleep, 20(12): 1077–1085.
  33. Model-based domain generalization. Advances in Neural Information Processing Systems, 34: 20210–20229.
  34. Intra- and inter-epoch temporal context network (IITNet) using sub-epoch features for automatic sleep scoring on raw single-channel EEG. Biomed. Signal Process. Control., 61: 102037.
  35. Return of frustratingly easy domain adaptation. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 30.
  36. Deep coral: Correlation alignment for deep domain adaptation. In European conference on computer vision, 443–450. Springer.
  37. DeepSleepNet: A Model for Automatic Sleep Stage Scoring Based on Raw Single-Channel EEG. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 25: 1998–2008.
  38. TinySleepNet: An Efficient Deep Learning Model for Sleep Stage Scoring based on Raw Single-Channel EEG. 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), 641–644.
  39. Deep domain confusion: Maximizing for domain invariance. arXiv preprint arXiv:1412.3474.
  40. Visualizing data using t-SNE. Journal of machine learning research, 9(11).
  41. Transfer learning with dynamic distribution adaptation. ACM Transactions on Intelligent Systems and Technology (TIST), 11(1): 1–25.
  42. Visual domain adaptation with manifold embedded distribution alignment. In Proceedings of the 26th ACM international conference on Multimedia, 402–410.
  43. Generalizing to Unseen Domains: A Survey on Domain Generalization. IEEE Transactions on Knowledge and Data Engineering, 35(8): 8052–8072.
  44. DeepDG: Deep Domain Generalization Toolkit.
  45. Narcolepsy Diagnosis With Sleep Stage Features Using PSG Recordings. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 31: 3619–3629.
  46. Deep visual domain adaptation: A survey. Neurocomputing, 312: 135–153.
  47. Wolpert, E. A. 1969. A Manual of Standardized Terminology, Techniques and Scoring System for Sleep Stages of Human Subjects. Archives of General Psychiatry, 20: 246–247.
  48. Transferring structured knowledge in unsupervised domain adaptation of a sleep staging network. IEEE journal of biomedical and health informatics, 26(3): 1273–1284.
  49. The National Sleep Research Resource: towards a sleep data commons. Journal of the American Medical Informatics Association, 25(10): 1351–1358.
  50. Plug-and-play domain adaptation for cross-subject EEG-based emotion recognition. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, 863–870.
  51. Domain generalization with optimal transport and metric learning. arXiv preprint arXiv:2007.10573.
  52. Domain Generalization: A Survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(4): 4396–4415.
Citations (5)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets