Survey of Sleep Staging Based on Relational Induction Biases

doi:10.3778/j.issn.1673-9418.2012003

Abstract

Abstract:

Sleep disorders seriously affect human health and life. Accurate classification of sleep stages is the key to detecting and treating sleep disorders. In recent years, methods based on deep learning have surpassed traditional machine learning methods and human experts. However, the internal structure of deep learning is complex and requires to be designed by expert who is familiar with the computer and medical fields. This paper aims to analyze the relational induction biases in the existing sleep staging model based on deep learning, and explores the basic principles of sleep staging model design. This paper analyzes relational induction biases such as translation invariance, time invariance and hierarchical processing. Firstly, the model is divided into three categories according to whether it contains convolution layer with translation invariance and recurrent layer with time invariance: convolutional neural network framework, recurrent neural network framework and hybrid neural network framework. Secondly, according to the hierarchical processing method of the frame, segment and sequence in the model, a more detailed classification is carried out. Thirdly, it analyzes the impact of different relational induction biases in the model on the performance of sleep staging. It is proposed that a relational inductive bias matched the task should be introduced when the automatic sleep staging model is designed. Finally, the advantages and limitations of sleep staging based on deep learning are discussed, and it may be necessary to use more advanced relationship induction bias to express knowledge more abstractly and combine it with other artificial intelligence technologies in the future.

Key words: deep learning, relational induction bias, convolutional neural network (CNN), recurrent neural network (RNN), sleep staging

摘要：

睡眠障碍严重影响人类健康和生活，将睡眠阶段准确分类是检测和治疗睡眠障碍的关键。近年来，基于深度学习的方法超越了传统机器学习方法及人类专家。然而，深度学习的内部结构复杂，需要对计算机及医学领域熟悉的专家进行设计。旨在分析现有基于深度学习的睡眠分期模型中的关系归纳偏置，探索睡眠分期模型设计基本原则。对平移不变性、时间不变性和分层处理等关系归纳偏置进行分析。首先按照模型中是否包含具有平移不变性的卷积层和具有时间不变性的循环层将其分为三类：卷积神经网络框架、循环神经网络框架和混合神经网络框架。然后按照模型中对帧、片段和序列的分层处理方式进行了更加细致的分类。接着分析模型中包含不同关系归纳偏置对睡眠分期的性能影响，提出了设计睡眠分期模型需要引入与任务相匹配的关系归纳偏置。最后讨论了基于深度学习睡眠分期方法的优越性与局限性，以及未来可能需要使用更加高级的关系归纳偏置对知识进行更加抽象的表达并与其他人工智能技术相结合。

关键词: 深度学习, 关系归纳偏置, 卷积神经网络（CNN）, 循环神经网络（RNN）, 睡眠分期

NENG Wenpeng, LU Jun, ZHAO Caihong. Survey of Sleep Staging Based on Relational Induction Biases[J]. Journal of Frontiers of Computer Science and Technology, 2021, 15(6): 1026-1037.

能文鹏, 陆军, 赵彩虹. 基于关系归纳偏置的睡眠分期综述[J]. 计算机科学与探索, 2021, 15(6): 1026-1037.

References

[1] BOOSTANI R, KARIMZADEH F, NAMI M, et al. A comparative review on sleep stage classification methods in patients and healthy individuals[J]. Computer Methods and Programs in Biomedicine, 2017, 140: 77-91.
[2] YI R H, ENAYATI M, KELLER J M, et al. Non-invasive in-home sleep stage classification using a ballistocardiography bed sensor[C]//Proceedings of the 2019 IEEE EMBS International Conference on Biomedical & Health Informatics, Chicago, May 19-22, 2019. Piscataway: IEEE, 2019: 1-4.
[3] BATTAGLIA P W, HAMRICK J B, BAPST V, et al. Relational inductive biases, deep learning, and graph networks[J]. arXiv:1806.01261, 2018.
[4] FAUST O, RAZAGHI H, BARIKA R, et al. A review of automated sleep stage scoring based on physiological signals for the new millennia[J]. Computer Methods and Programs in Biomedicine, 2019, 176: 81-91.
[5] ROSENBERG R S, HOUT S V. The American academy of sleep medicine inter-scorer reliability program: sleep stage scoring[J]. Journal of Clinical Sleep Medicine, 2013, 9(1): 81-87.
[6] GOLDBERGER A L, AMARAL L A N, GLASS L, et al. Components of a new research resource for complex physiologic signals[J]. PhysioBank, PhysioToolkit, and Physionet, 2000, 101(23): E215-E220.
[7] O’REILLY C, GOSSELIN N, CARRIER J, et al. Montreal archive of sleep studies: an open-access resource for instrument benchmarking and exploratory research[J]. Journal of Sleep Research, 2015, 23(6): 628-635.
[8] KHALIGHI S, SOUSA T, SANTOS J M, et al. ISRUC-Sleep: a comprehensive public dataset for sleep researchers[J]. Computer Methods and Programs in Biomedicine, 2016, 124: 180-192.
[9] TERZANO M G, PARRINO L, SHERIERI A, et al. Atlas, rules, and recording techniques for the scoring of cyclic alternating pattern (CAP) in human sleep[J]. Sleep Medicine, 2001, 2(6): 537-553.
[10] MANZANO M, GUILLéN A, ROJAS I, et al. Deep learning using EEG data in time and frequency domains for sleep stage classification[C]//LNCS 10305: Proceedings of the 14th International Work-Conference on Artificial Neural Networks, Cadiz, Jun 14-16, 2017. Berlin, Heidelberg: Springer, 2017: 132-141.
[11] SORS A, BONNET S, MIREK S, et al. A convolutional neural network for sleep stage scoring from raw single-channel EEG[J]. Biomedical Signal Processing and Control, 2018, 42: 107-114.
[12] TSINALIS O, MATTHEWS P M, GUO Y, et al. Automatic sleep stage scoring with single-channel EEG using convolutional neural networks[J]. arXiv:1610.01683, 2016.
[13] LI Y H, LIU Q, WEI X, et al. Classification of electroencephalogram signals based on convolutional neural network[J]. Science Technology and Engineering, 2020, 20(15): 6135-6140.
李玉花, 柳倩, 韦新, 等. 基于卷积神经网络的脑电信号分类[J]. 科学技术与工程, 2020, 20(15): 6135-6140.
[14] JIA Z Y, LIN Y F, ZHANG H J, et al. Sleep stage classification model based on deep convolutional neural network[J]. Journal of Zhejiang University (Engineering Science), 2020, 54(10): 1899-1905.
贾子钰, 林友芳, 张宏钧, 等. 基于深度卷积神经网络的睡眠分期模型[J]. 浙江大学学报(工学版), 2020, 54(10): 1899-1905.
[15] ZHANG J, WU Y. A new method for automatic sleep stage classification[J]. IEEE Transactions on Biomedical Circuits and Systems, 2017, 11(5): 1097-1110.
[16] ZHANG J, WU Y. Complex-valued unsupervised convolutional neural networks for sleep stage classification[J]. Computer Methods and Programs in Biomedicine, 2018, 164: 181-191.
[17] HUMAYUN A I, SUSHMIT A S, HASAN T, et al. End-to-end sleep staging with raw single channel EEG using deep residual ConvNets[C]//Proceedings of the 2019 IEEE EMBS International Conference on Biomedical & Health Informatics, Chicago, May 19-22, 2019. Piscataway: IEEE, 2019: 1-5.
[18] WEI L J, LIN Y F, WANG J, et al. Time-frequency convolutional neural network for automatic sleep stage classification based on single-channel EEG[C]//Proceedings of the 29th IEEE International Conference on Tools with Artificial Intelligence, Boston, Nov 6-8, 2017. Washington: IEEE Computer Society, 2017: 88-95.
[19] PHAN H, ANDREOTTI F, COORAY N, et al. DNN filter bank improves 1-max pooling CNN for single-channel EEG automatic sleep stage classification[C]//Proceedings of the 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Honolulu, Jul 18-21, 2018. Piscataway: IEEE, 2018: 453-456.
[20] ZHANG J M, YAO R X, GE W G, et al. Orthogonal convolutional neural networks for automatic sleep stage classification based on single-channel EEG[J]. Computer Methods and Programs in Biomedicine, 2020, 183: 105089.
[21] FERNáNDEZ-VARELA I, HERNáNDEZ-PEREIRA E, áLVAREZ-ESTéVEZ D, et al. A convolutional network for sleep stages classification[J]. arXiv:1902.05748, 2019.
[22] NIROSHANA S M I, ZHU X, CHEN Y, et al. Automatic sleep stage classification based on convolutional neural networks[C]//Proceedings of the IEEE 1st Global Conference on Life Sciences and Technologies, Osaka, Mar 12-14, 2019. Piscataway: IEEE, 2019: 275-276.
[23] PHAN H, ANDREOTTI F, COORAY N, et al. Joint classification and prediction CNN framework for automatic sleep stage classification[J]. IEEE Transactions on Biomedical Engineering, 2019, 66(5): 1285-1296.
[24] OLESEN A N, JENNUM P, PEPPARD P E, et al. Deep residual networks for automatic sleep stage classification of raw polysomnographic waveforms[C]//Proceedings of the 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Honolulu, Jul 18-21, 2018. Piscataway: IEEE, 2018: 1-4.
[25] CHAMBON S, GALTIER M N, ARNAL P J, et al. A deep learning architecture for temporal sleep stage classification using multivariate and multimodal time series[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2018, 26(4): 758-769.
[26] CUI Z, ZHENG X, SHAO X, et al. Automatic sleep stage classification based on convolutional neural network and fine-grained segments[J]. Complexity, 2018: 1-13.
[27] MA J R, WANG B, JIN J, et al. Deep automatic sleep staging model integrated with state transition rule[J]. Computer Engineering and Design, 2020, 41(10): 2878-2883.
马家睿, 王蓓, 金晶, 等. 结合状态转移规则的深度睡眠分期模型[J]. 计算机工程与设计, 2020, 41(10): 2878-2883.
[28] PERSLEV M, JENSEN M H, DARKNER S, et al. U-Time: a fully convolutional network for time series segmentation applied to sleep staging[C]//Proceedings of the Annual Conference on Neural Information Processing Systems, Vancouver, Dec 8-14, 2019: 4415-4428.
[29] PHAN H, ANDREOTTI F, COORAY N, et al. Automatic sleep stage classification using single-channel EEG: learning sequential features with attention-based recurrent neural networks[C]//Proceedings of the 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Honolulu, Jul 18-21, 2018. Piscataway: IEEE, 2018: 1452-1455.
[30] MICHIELLI N, ACHARYA U R, MOLINARI F, et al. Cascaded LSTM recurrent neural network for automated sleep stage classification using single-channel EEG signals[J]. Computers in Biology and Medicine, 2019, 106: 71-81.
[31] ZHANG X, KOU W, CHANG E, et al. Sleep stage classification based on multi-level feature learning and recurrent neural networks via wearable device[J]. Computers in Biology and Medicine, 2018, 103: 71-81.
[32] ZHANG Y, YANG Z, LAN K, et al. Sleep stage classification using bidirectional LSTM in wearable multi-sensor systems[C]//Proceedings of the 2019 IEEE Conference on Computer Communications Workshops, Paris, Apr 29-May 2, 2019. Piscataway: IEEE, 2019: 443-448.
[33] PHAN H, ANDREOTTI F, COORAY N, et al. Seq-SleepNet: end-to-end hierarchical recurrent neural network for sequence-to-sequence automatic sleep staging[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2019, 27(3): 400-410.
[34] HUANG G J, CHU C H, WU X D. A deep learning-based method for sleep stage classification using physiological signal[C]//LNCS 10983: Proceedings of the International Conference on Smart Health, Wuhan, Jul 1-3, 2018. Berlin, Heidelberg: Springer, 2018: 249-260.
[35] YANG Y, ZHENG X W, YUAN F. A study on automatic sleep stage classification based on CNN-LSTM[C]//Proceedings of the 3rd International Conference on Crowd Science and Engineering, Singapore, Jul 28-31, 2018. New York: ACM, 2018.
[36] JIN H H, YIN H B, HE L N. End-to-end single-channel automatic staging model for sleep EEG signal[J]. Computer Science, 2019, 46(3): 242-247.
金欢欢, 尹海波, 何玲娜. 端到端单通道睡眠EEG自动分期模型[J]. 计算机科学, 2019, 46(3): 242-247.
[37] LUO S L, HAO J W, PAN L M. An automatic sleep staging method based on CNN-BiLSTM[J]. Journal of Beijing Institute of Technology, 2020, 40(7): 746-752.
罗森林, 郝靖伟, 潘丽敏. 基于CNN-BiLSTM的自动睡眠分期方法[J]. 北京理工大学学报, 2020, 40(7): 746-752.
[38] YUAN Y, JIA K, MA F, et al. A hybrid self-attention deep learning framework for multivariate sleep stage classification [J]. BMC Bioinformatics, 2019, 20(16): 1-10.
[39] SUPRATAK A, DONG H, WU C, et al. DeepSleepNet: a model for automatic sleep stage scoring based on raw single-channel EEG[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2017, 25(11): 1998-2008.
[40] MOUSAVI S, AFGHAH F, ACHARYA U R, et al. Sleep-EEGNet: automated sleep stage scoring with sequence to sequence deep learning approach[J]. PLoS ONE, 2019, 14(5): 1-11.
[41] SUN Y D, WANG B, JIN J, et al. Deep convolutional network method for automatic sleep stage classification based on neurophysiological signals[C]//Proceedings of the 11th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, Beijing, Oct 13-15, 2018. Piscataway: IEEE, 2018: 1-5.