Sleep stage classification model by meta transfer learning in few-shot scenarios

doi:10.11772/j.issn.1001-9081.2023050747

Journal of Computer Applications ›› 2024, Vol. 44 ›› Issue (5): 1445-1451.DOI: 10.11772/j.issn.1001-9081.2023050747

Special Issue: 人工智能； 2023年中国计算机学会人工智能会议(CCFAI 2023)

• 2023 CCF Conference on Artificial Intelligence (CCFAI 2023) • Previous Articles Next Articles

Sleep stage classification model by meta transfer learning in few-shot scenarios

Wangjun SHI¹^,², Jing WANG¹^,²^,³(), Xiaojun NING¹^,², Youfang LIN¹^,²^,³

^1.School of Computer Science and Technology，Beijing Jiaotong University，Beijing 100044，China
^2.Beijing Key Lab of Traffic Data Analysis and Mining （Beijing Jiaotong University），Beijing 100044，China
^3.Key Laboratory of Intelligent Application Technology for Civil Aviation Passenger Services （Civil Aviation Administration of China），Beijing 101318，China

Received:2023-06-09 Revised:2023-07-05 Accepted:2023-07-09 Online:2023-08-01 Published:2024-05-10
Contact: Jing WANG
About author:SHI Wangjun， born in 1999， M. S. candidate. His research interests include data mining， machine learning.
NING Xiaojun， born in 1999， Ph. D. candidate. His research interests include brain computer interface， time series analysis and mining.
LIN Youfang， born in 1971， Ph. D.， professor. His research interests include intelligent systems， complex networks， traffic data mining.
Supported by:
Fundamental Research Funds for Central Universities(2023JBMC056)

小样本场景下的元迁移学习睡眠分期模型

时旺军¹^,², 王晶¹^,²^,³(), 宁晓军¹^,², 林友芳¹^,²^,³

^1.北京交通大学计算机科学与技术学院, 北京 100044
^2.交通数据分析与挖掘北京市重点实验室(北京交通大学), 北京 100044
^3.民航旅客服务智能化应用技术重点实验室(中国民用航空局), 北京 101318

通讯作者: 王晶
作者简介:时旺军（1999—），男，天津人，硕士研究生，主要研究方向：数据挖掘、机器学习
宁晓军（1999—），男，山东泰安人，博士研究生，CCF会员，主要研究方向：脑机接口、时间序列分析与挖掘
林友芳（1971—），男，福建武平人，教授，博士，CCF高级会员，主要研究方向：智能系统、复杂网络、交通数据挖掘。
第一联系人：王晶（1987—），女，安徽合肥人，副教授，博士，CCF会员，主要研究方向：时间序列分析与挖掘
基金资助:
中央高校基本科研业务费专项资金资助项目(2023JBMC056)

Abstract

Abstract:

Sleep disorders are receiving more and more attention， and the accuracy and generalization of automated sleep stage classification are facing more and more challenges. However， due to the very limited human sleep data publicly available， the sleep stage classification task is actually similar to a few-shot scenario. And due to the widespread individual differences in sleep features， it is difficult for existing machine learning models to guarantee accurate classification of data from new subjects who have not participated in the training. In order to achieve accurate stage classification of new subjects’ sleep data， existing studies usually require additional collection and labeling of large amounts of data from new subjects and personalized fine-tuning of the model. Based on this， a new sleep stage classification model， Meta Transfer Sleep Learner （MTSL）， was proposed. Inspired by the idea of Scale & Shift based weight transfer strategy in transfer learning， a new meta transfer learning framework was designed. The training phase included two steps： pre-training and meta transfer training， and many meta-tasks were used for meta transfer training. In the test phase， the model could be easily adapted to the feature distribution of new subjects by fine-tuning with only a few new subjects’ data， which greatly reduced the cost of accurate sleep stage classification for new subjects. Experimental results on two public sleep datasets show that MTSL model can achieve higher accuracy and F1-score under both single-dataset and cross-dataset conditions. This indicates that MTSL is more suitable for sleep stage classification tasks in few-shot scenarios.

Key words: sleep stage classification, few-shot, meta learning, transfer learning, deep learning, ElectroEncephaloGraphy (EEG)

摘要：

睡眠障碍受到越来越多的关注，且自动化睡眠分期的准确性、泛化性受到了越来越多的挑战。然而，公开的睡眠数据十分有限，睡眠分期任务实际上更近似于一种小样本场景；同时由于睡眠特征的个体差异普遍存在，现有的机器学习模型很难保证准确判读未参与训练的新受试者的数据。为了实现对新受试者睡眠数据的精准分期，现有研究通常需要额外采集、标注新受试者的大量数据，并对模型进行个性化微调。基于此，借鉴迁移学习中基于缩放-偏移的权重迁移思想，提出一种元迁移睡眠分期模型MTSL（Meta Transfer Sleep Learner），设计了一种新的元迁移学习框架：训练阶段包括预训练与元迁移训练两步，其中元迁移训练时使用大量的元任务进行训练；而在测试阶段仅使用极少的新受试者数据进行微调，模型就能轻松适应新受试者的特征分布，大幅减少对新受试者进行准确睡眠分期的成本。在两个公开的睡眠数据集上的实验结果表明，MTSL模型在单数据集、跨数据集两种条件下都能取得更高的准确率和F1分数，这表明MTSL更适合小样本场景下的睡眠分期任务。

关键词: 睡眠分期, 小样本, 元学习, 迁移学习, 深度学习, 脑电信号

CLC Number:

TP391

Wangjun SHI, Jing WANG, Xiaojun NING, Youfang LIN. Sleep stage classification model by meta transfer learning in few-shot scenarios[J]. Journal of Computer Applications, 2024, 44(5): 1445-1451.

时旺军, 王晶, 宁晓军, 林友芳. 小样本场景下的元迁移学习睡眠分期模型[J]. 《计算机应用》唯一官方网站, 2024, 44(5): 1445-1451.

Figures/Tables 7

References 22

1	WOLPERT E A. A manual of standardized terminology， techniques and scoring system for sleep stages of human subjects ［J］. Archives of General Psychiatry， 1969， 20（2）： 246-247. 10.1001/archpsyc.1969.01740140118016
2	BERRY R B， BROOKS R， GAMALDO C E， et al. The AASM manual for the scoring of sleep and associated events. Rules， terminology and technical specifications version 2.2 ［S/OL］. （2015）［2023-05-01］. . 10.5664/jcsm.5176
3	BANLUESOMBATKUL N， OUPPAPHAN P， LEELAARPORN P， et al. MetaSleepLearner： a pilot study on fast adaptation of bio-signals-based sleep stage classifier to new individual subject using meta-learning［J］. IEEE Journal of Biomedical and Health Informatics， 2021， 25（6）： 1949-1963. 10.1109/jbhi.2020.3037693
4	KOLEY B， DEY D. An ensemble system for automatic sleep stage classification using single channel EEG signal［J］. Computers in Biology and Medicine， 2012， 42（12）： 1186-1195. 10.1016/j.compbiomed.2012.09.012
5	ANDREOTTI F， PHAN H， COORAY N， et al. Multichannel sleep stage classification and transfer learning using convolutional neural networks［C］// Proceedings of the 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Piscataway： IEEE， 2018： 171-174. 10.1109/embc.2018.8512214
6	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. 10.1109/tnsre.2017.2721116
7	PERSLEV M， DARKNER S， KEMPFNER L， et al. U-Sleep： resilient high-frequency sleep staging［J］. npj Digital Medicine， 2021， 4： No.72. 10.1038/s41746-021-00440-5
8	金欢欢，尹海波，何玲娜. 基于生成少数类技术的深度自动睡眠分期模型［J］. 计算机应用， 2018， 38（9）： 2483-2488. 10.11772/j.issn.1001-9081.2018020440
	JIN H H， YIN H B， HE L N. Deep automatic sleep staging model using synthetic minority technique［J］. Journal of Computer Applications， 2018， 38（9）： 2483-2488. 10.11772/j.issn.1001-9081.2018020440
9	BOOSTANI R， KARIMZADEH F， NAMI M. A comparative review on sleep stage classification methods in patients and healthy individuals［J］. Computer Methods and Programs in Biomedicine， 2017， 140： 77-91. 10.1016/j.cmpb.2016.12.004
10	ANDREOTTI F， PHAN H， COORAY N， et al. Multichannel sleep stage classification and transfer learning using convolutional neural networks［C］// Proceedings of the 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Piscataway： IEEE， 2018： 171-174. 10.1109/embc.2018.8512214
11	RONNEBERGER O， FISCHER P， BROX T. U-Net： convolutional networks for biomedical image segmentation［C］// Proceedings of the 2015 Medical Image Computing and Computer-Assisted Intervention. Cham： Springer， 2015： 234-241. 10.1007/978-3-319-24574-4_28
12	WANG J X. Meta-learning in natural and artificial intelligence［J］. Current Opinion in Behavioral Sciences， 2021， 38： 90-95. 10.1016/j.cobeha.2021.01.002
13	FINN C， ABBEEL P， LEVINE S. Model-agnostic meta-learning for fast adaptation of deep networks［C］// Proceedings of the 34th International Conference on Machine Learning. New York： JMLR， 2017： 1126-1135. 10.1109/icra.2016.7487173
14	VINYALS O， BLUNDELL C， LILLICRAP T， et al. Matching networks for one shot learning［C］// Proceedings of the 30th International Conference on Neural Information Processing Systems. Red Hook： Curran Associates Inc.， 2016： 3637-3645.
15	SNELL J， SWERSKY K， ZEMEL R. Prototypical networks for few-shot learning［C］// Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook： Curran Associates Inc.， 2017： 4080-4090.
16	SUN Q， LIU Y， CHEN Z， et al. Meta-transfer learning through hard tasks［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2022， 44（3）： 1443-1456. 10.1109/tpami.2020.3018506
17	FRENCH R M. Catastrophic forgetting in connectionist networks［J］. Trends in Cognitive Sciences， 1999， 3（4）： 128-135. 10.1016/s1364-6613(99)01294-2
18	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. 10.1016/j.cmpb.2015.10.013
19	GOLDBERGER A L， AMARAL L A， GLASS L， et al. PhysioBank， PhysioToolkit， and PhysioNet： components of a new research resource for complex physiologic signals［J］. Circulation， 2000， 101（23）： e215-e220. 10.1161/01.cir.101.23.e215
20	KEMP B， ZWINDERMAN A H， TUK B， et al. Analysis of a sleep-dependent neuronal feedback loop： the slow-wave microcontinuity of the EEG［J］. IEEE Transactions on Biomedical Engineering， 2000， 47（9）： 1185-1194. 10.1109/10.867928
21	GOUTTE C， GAUSSIER E. A probabilistic interpretation of precision， recall and F-score， with implication for evaluation［C］// Proceedings of the 2005 27th European Conference on IR Research. Cham： Springer， 2005： 345-359. 10.1007/978-3-540-31865-1_25
22	BRENNAN R L， PREDIGER D J. Coefficient kappa： some uses， misuses， and alternatives［J］. Educational and Psychological Measurement， 1981， 41： 687-699. 10.1177/001316448104100307

数据集	方法	总体指标			每个类别的F1分数
数据集	方法	准确率	F1分数	Kappa	Wake	N1	N2	N3	REM
ISRUC-S3	RF^［5］	0.640 0	0.622 9	0.550 0	0.797 1	0.363 7	0.398 1	0.869 5	0.686 3
	SVM^［4］	0.654 6	0.612 8	0.568 2	0.800 2	0.281 6	0.399 7	0.894 0	0.688 7
	Matching Network^［14］	0.634 5	0.577 2	0.543 1	0.811 7	0.082 9	0.525 5	0.859 6	0.606 3
	MetaSleepLearner^［3］	0.670 5	0.669 6	0.588 1	0.837 7	0.483 7	0.545 9	0.895 8	0.584 9
	Prototypical Network^［15］	0.713 2	0.708 8	0.641 6	0.861 5	0.538 8	0.569 8	0.898 4	0.675 8
	DeepSleepNet^［6］	0.732 6	0.721 4	0.665 8	0.866 9	0.507 2	0.618 0	0.903 9	0.710 8
	U-Sleep^［7］	0.763 8	0.754 7	0.704 7	0.911 1	0.646 4	0.485 9	0.888 8	0.841 3
	MTSL	0.778 8	0.776 7	0.723 5	0.898 5	0.650 2	0.643 5	0.901 6	0.789 7
Sleep-EDF	RF^［5］	0.660 0	0.655 4	0.575	0.827 9	0.516 8	0.587 2	0.816 3	0.528 8
	SVM^［4］	0.653 0	0.659 7	0.566 2	0.820 2	0.546 5	0.567 0	0.796 4	0.568 2
	Matching Network^［14］	0.669 1	0.664 5	0.586 4	0.852 3	0.510 0	0.684 2	0.875 5	0.400 6
	MetaSleepLearner^［3］	0.690 7	0.692 1	0.613 4	0.829 5	0.625 8	0.619 9	0.895 0	0.490 5
	Prototypical Network^［15］	0.714 5	0.715 8	0.643 1	0.836 9	0.637 8	0.651 4	0.900 4	0.552 7
	DeepSleepNet^［6］	0.764 5	0.764 6	0.705 6	0.877 4	0.694 2	0.704 0	0.900 7	0.646 8
	U‑Sleep^［7］	0.777 0	0.776 4	0.721 3	0.901 0	0.687 7	0.720 4	0.879 1	0.693 8
	MTSL	0.798 0	0.797 2	0.747 4	0.908 6	0.759 9	0.706 6	0.911 8	0.699 0

数据集	方法	总体指标			每个类别的F1分数
数据集	方法	准确率	F1分数	Kappa	Wake	N1	N2	N3	REM
ISRUC-S3	RF^［5］	0.640 0	0.622 9	0.550 0	0.797 1	0.363 7	0.398 1	0.869 5	0.686 3
	SVM^［4］	0.654 6	0.612 8	0.568 2	0.800 2	0.281 6	0.399 7	0.894 0	0.688 7
	Matching Network^［14］	0.634 5	0.577 2	0.543 1	0.811 7	0.082 9	0.525 5	0.859 6	0.606 3
	MetaSleepLearner^［3］	0.670 5	0.669 6	0.588 1	0.837 7	0.483 7	0.545 9	0.895 8	0.584 9
	Prototypical Network^［15］	0.713 2	0.708 8	0.641 6	0.861 5	0.538 8	0.569 8	0.898 4	0.675 8
	DeepSleepNet^［6］	0.732 6	0.721 4	0.665 8	0.866 9	0.507 2	0.618 0	0.903 9	0.710 8
	U-Sleep^［7］	0.763 8	0.754 7	0.704 7	0.911 1	0.646 4	0.485 9	0.888 8	0.841 3
	MTSL	0.778 8	0.776 7	0.723 5	0.898 5	0.650 2	0.643 5	0.901 6	0.789 7
Sleep-EDF	RF^［5］	0.660 0	0.655 4	0.575	0.827 9	0.516 8	0.587 2	0.816 3	0.528 8
	SVM^［4］	0.653 0	0.659 7	0.566 2	0.820 2	0.546 5	0.567 0	0.796 4	0.568 2
	Matching Network^［14］	0.669 1	0.664 5	0.586 4	0.852 3	0.510 0	0.684 2	0.875 5	0.400 6
	MetaSleepLearner^［3］	0.690 7	0.692 1	0.613 4	0.829 5	0.625 8	0.619 9	0.895 0	0.490 5
	Prototypical Network^［15］	0.714 5	0.715 8	0.643 1	0.836 9	0.637 8	0.651 4	0.900 4	0.552 7
	DeepSleepNet^［6］	0.764 5	0.764 6	0.705 6	0.877 4	0.694 2	0.704 0	0.900 7	0.646 8
	U‑Sleep^［7］	0.777 0	0.776 4	0.721 3	0.901 0	0.687 7	0.720 4	0.879 1	0.693 8
	MTSL	0.798 0	0.797 2	0.747 4	0.908 6	0.759 9	0.706 6	0.911 8	0.699 0

数据集	方法	准确率	F1分数	Kappa
Sleep-EDF ↓ ISRUC-S3	RF^［5］	0.411 6	0.401 5	0.264 5
	SVM^［54］	0.353 6	0.349 8	0.192 0
	Matching Network^［14］	0.598 5	0.568 6	0.498 1
	MetaSleepLearner^［3］	0.610 6	0.611 4	0.513 2
	Prototypical Network^［15］	0.652 2	0.657 0	0.565 3
	DeepSleepNet^［6］	0.636 7	0.632 9	0.545 9
	U-Sleep^［7］	0.613 8	0.609 1	0.517 2
	MTSL	0.669 2	0.669 0	0.586 4
ISRUC-S3 ↓ Sleep-EDF	RF^［5］	0.391 2	0.360 4	0.239 0
	SVM^［4］	0.475 8	0.408 6	0.344 8
	Matching Network^［14］	0.575 6	0.569 3	0.469 5
	MetaSleepLearner^［3］	0.616 3	0.614 1	0.520 3
	Prototypical Network^［15］	0.660 7	0.656 0	0.575 9
	DeepSleepNet^［6］	0.653 7	0.648 4	0.567 1
	U-Sleep^［7］	0.646 7	0.632 5	0.558 3
	MTSL	0.677 9	0.676 3	0.597 3

数据集	方法	准确率	F1分数	Kappa
Sleep-EDF ↓ ISRUC-S3	RF^［5］	0.411 6	0.401 5	0.264 5
	SVM^［54］	0.353 6	0.349 8	0.192 0
	Matching Network^［14］	0.598 5	0.568 6	0.498 1
	MetaSleepLearner^［3］	0.610 6	0.611 4	0.513 2
	Prototypical Network^［15］	0.652 2	0.657 0	0.565 3
	DeepSleepNet^［6］	0.636 7	0.632 9	0.545 9
	U-Sleep^［7］	0.613 8	0.609 1	0.517 2
	MTSL	0.669 2	0.669 0	0.586 4
ISRUC-S3 ↓ Sleep-EDF	RF^［5］	0.391 2	0.360 4	0.239 0
	SVM^［4］	0.475 8	0.408 6	0.344 8
	Matching Network^［14］	0.575 6	0.569 3	0.469 5
	MetaSleepLearner^［3］	0.616 3	0.614 1	0.520 3
	Prototypical Network^［15］	0.660 7	0.656 0	0.575 9
	DeepSleepNet^［6］	0.653 7	0.648 4	0.567 1
	U-Sleep^［7］	0.646 7	0.632 5	0.558 3
	MTSL	0.677 9	0.676 3	0.597 3

数据集	模型变体	准确率	F1分数	Kappa
ISRUC-S3	MTSL-SC	0.770 3	0.766 0	0.712 8
	MTSL-MC	0.769 3	0.767 2	0.711 7
	MTSL-LC	0.760 4	0.757 7	0.700 5
	MTSL-RI	0.757 6	0.753 3	0.697 0
	MTSL-PT	0.743 5	0.740 3	0.679 4
	MTSL	0.778 8	0.776 7	0.723 5
Sleep-EDF	MTSL-SC	0.781 7	0.780 8	0.727 1
	MTSL-MC	0.785 6	0.785 6	0.732 1
	MTSL-LC	0.790 2	0.790 8	0.737 8
	MTSL-RI	0.772 8	0.772 2	0.716 0
	MTSL-PT	0.775 0	0.774 2	0.718 8
	MTSL	0.798 0	0.797 2	0.747 4

Sleep stage classification model by meta transfer learning in few-shot scenarios

小样本场景下的元迁移学习睡眠分期模型

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 7

References 22

Related Articles 15

Recommended Articles

Metrics

[1]	Jing QIN, Zhiguang QIN, Fali LI, Yueheng PENG. Diagnosis of major depressive disorder based on probabilistic sparse self-attention neural network [J]. Journal of Computer Applications, 2024, 44(9): 2970-2974.
[2]	Xiyuan WANG, Zhancheng ZHANG, Shaokang XU, Baocheng ZHANG, Xiaoqing LUO, Fuyuan HU. Unsupervised cross-domain transfer network for 3D/2D registration in surgical navigation [J]. Journal of Computer Applications, 2024, 44(9): 2911-2918.
[3]	Yexin PAN, Zhe YANG. Optimization model for small object detection based on multi-level feature bidirectional fusion [J]. Journal of Computer Applications, 2024, 44(9): 2871-2877.
[4]	Yunchuan HUANG, Yongquan JIANG, Juntao HUANG, Yan YANG. Molecular toxicity prediction based on meta graph isomorphism network [J]. Journal of Computer Applications, 2024, 44(9): 2964-2969.
[5]	Shunyong LI, Shiyi LI, Rui XU, Xingwang ZHAO. Incomplete multi-view clustering algorithm based on self-attention fusion [J]. Journal of Computer Applications, 2024, 44(9): 2696-2703.
[6]	Yuhan LIU, Genlin JI, Hongping ZHANG. Video pedestrian anomaly detection method based on skeleton graph and mixed attention [J]. Journal of Computer Applications, 2024, 44(8): 2551-2557.
[7]	Yanjie GU, Yingjun ZHANG, Xiaoqian LIU, Wei ZHOU, Wei SUN. Traffic flow forecasting via spatial-temporal multi-graph fusion [J]. Journal of Computer Applications, 2024, 44(8): 2618-2625.
[8]	Qianhong SHI, Yan YANG, Yongquan JIANG, Xiaocao OUYANG, Wubo FAN, Qiang CHEN, Tao JIANG, Yuan LI. Multi-granularity abrupt change fitting network for air quality prediction [J]. Journal of Computer Applications, 2024, 44(8): 2643-2650.
[9]	Yiqun ZHAO, Zhiyu ZHANG, Xue DONG. Anisotropic travel time computation method based on dense residual connection physical information neural networks [J]. Journal of Computer Applications, 2024, 44(7): 2310-2318.
[10]	Song XU, Wenbo ZHANG, Yifan WANG. Lightweight video salient object detection network based on spatiotemporal information [J]. Journal of Computer Applications, 2024, 44(7): 2192-2199.
[11]	Xun SUN, Ruifeng FENG, Yanru CHEN. Monocular 3D object detection method integrating depth and instance segmentation [J]. Journal of Computer Applications, 2024, 44(7): 2208-2215.
[12]	Zheng WU, Zhiyou CHENG, Zhentian WANG, Chuanjian WANG, Sheng WANG, Hui XU. Deep learning-based classification of head movement amplitude during patient anaesthesia resuscitation [J]. Journal of Computer Applications, 2024, 44(7): 2258-2263.
[13]	Huanhuan LI, Tianqiang HUANG, Xuemei DING, Haifeng LUO, Liqing HUANG. Public traffic demand prediction based on multi-scale spatial-temporal graph convolutional network [J]. Journal of Computer Applications, 2024, 44(7): 2065-2072.
[14]	Zhi ZHANG, Xin LI, Naifu YE, Kaixi HU. DKP： defending against model stealing attacks based on dark knowledge protection [J]. Journal of Computer Applications, 2024, 44(7): 2080-2086.
[15]	Yajuan ZHAO, Fanjun MENG, Xingjian XU. Review of online education learner knowledge tracing [J]. Journal of Computer Applications, 2024, 44(6): 1683-1698.