心电领域中的自监督学习方法综述

doi:10.3778/j.issn.1673-9418.2310043

摘要/Abstract

摘要： 深度学习因其强大的数据表征能力已被广泛应用于心电（ECG）信号分析领域，但有监督方法的训练过程需要大量标签，而心电数据标注通常是耗时且成本高昂的。且有监督方法受限于训练集中有限的数据类型，泛化性能有限。因此，如何利用海量无标记心电信号进行数据挖掘和通用特征表示已成为亟待解决的问题。自监督学习（SSL）通过预先设置的代理任务从无标签数据中学习泛化特征来提升模型的特征表示能力，是一种解决心电数据标注缺失问题和提升模型迁移能力的有效途径。然而，现有的自监督学习综述大都专注于图像或时序信号领域，针对心电领域的自监督学习综述相对缺乏。为了填补这一空白，全面回顾了用于心电领域的先进的自监督学习方法。首先，从对比式和预测式两种学习范式出发对心电自监督学习方法进行了系统的总结与分类，阐述了不同类别方法的基本原理，细致分析了各个方法的特点，指出了各个方法的优势以及局限性。然后，归纳汇总了心电自监督学习中常用的数据集以及应用场景，总结了常用于心电领域的数据增强方法，为后续研究提供了系统性的总结参考。最后，深入讨论了当前自监督学习在心电领域中的挑战，并对未来心电自监督学习的发展方向进行了展望，为后续心电领域的自监督学习研究提供了指导。

关键词: 心电（ECG）, 特征表示, 深度学习, 自监督学习

Abstract: Deep learning has been widely applied in the field of electrocardiogram (ECG) signal analysis due to its powerful data representation capability. However, supervised methods require a large amount of labeled data, and ECG data annotation is typically time-consuming and costly. Additionally, supervised methods are limited by the finite data types in the training set, resulting in limited generalization performance. Therefore, how to leverage massive unlabeled ECG signals for data mining and universal feature representation has become an urgent problem to be addressed. Self-supervised learning (SSL) is an effective approach to address the issue of missing annotated ECG data and improve the transfer ability of the model by learning generalized features from unlabeled data using pre-defined proxy tasks. However, existing surveys on self-supervised learning mostly focus on the domains of images or temporal signals, and there is a relative lack of comprehensive reviews on self-supervised learning in the ECG domain. To fill this gap, this paper provides a comprehensive review of advanced self-supervised learning methods used in the field of ECG. Firstly, a systematic summary and classification of self-supervised learning methods for ECG are presented, starting from two learning paradigms—contrastive and predictive. The basic principles of different categories of methods are elaborated, and the characteristics of each method are analyzed in detail, highlighting the advantages and limitations of each approach. Subsequently, a summary is provided for the commonly used datasets and application scenarios in ECG self-supervised learning, along with a review of data augmentation methods frequently applied in the ECG domain, offering a systematic reference for subsequent research. Finally, an in-depth discussion is presented on the current challenges of self-supervised learning within the ECG field, and future directions for the development of ECG self-supervised learning are explored, providing guidance for subsequent research in the field.

Key words: electrocardiogram (ECG), feature representation, deep learning, self-supervised learning

韩涵, 黄训华, 常慧慧, 樊好义, 陈鹏, 陈姞伽. 心电领域中的自监督学习方法综述[J]. 计算机科学与探索, 2024, 18(7): 1683-1704.

HAN Han, HUANG Xunhua, CHANG Huihui, FAN Haoyi, CHEN Peng, CHEN Jijia. Review of Self-supervised Learning Methods in Field of ECG[J]. Journal of Frontiers of Computer Science and Technology, 2024, 18(7): 1683-1704.

参考文献

[1] MURAT F, YILDIRIM O, TALO M, et al. Application of deep learning techniques for heartbeats detection using ECG signals-analysis and review[J]. Computers in Biology and Medicine, 2020, 120: 103726.
[2] CHEN S W, WANG S L, QI X Z, et al. Review of ECG detection and classification based on deep learning: coherent taxonomy, motivation, open challenges and recommendations[J]. Biomedical Signal Processing and Control, 2022, 74: 103493.
[3] SERHANI M A, EL KASSABI H T, ISMAIL H, et al. ECG monitoring systems: review, architecture, processes, and key challenges[J]. Sensors, 2020, 20(6): 1796.
[4] LIU X, WANG H, LI Z, et al. Deep learning in ECG diagnosis: a review[J]. Knowledge-Based Systems, 2021, 227: 107187.
[5] KAMATH G S, COTIGA D, KONERU J N, et al. The utility of 12-lead Holter monitoring in patients with permanent atrial fibrillation for the identification of nonresponders after cardiac resynchronization therapy[J]. Journal of the American College of Cardiology, 2009, 53(12): 1050-1055.
[6] PINEDA-LóPEZ F, MARTíNEZ-FERNáNDEZ A, ROJO-áLVAREZ J L, et al. A flexible 12-Lead/Holter device with compression capabilities for low-bandwidth mobile-ECG telemedicine applications[J]. Sensors, 2018, 18(11): 3773.
[7] EBRAHIMI Z, LONI M, DANESHTALAB M, et al. A review on deep learning methods for ECG arrhythmia classification[J]. Expert Systems with Applications: X, 2020, 7: 100033.
[8] BENJAMIN E J, VIRANI S S, CALLAWAY C W, et al. Heart disease and stroke statistics—2018 update: a report from the American Heart Association[J]. Circulation, 2018, 137(12): 67-492.
[9] ERICSSON L, GOUK H, LOY C C, et al. Self-supervised representation learning: introduction, advances, and challenges[J]. IEEE Signal Processing Magazine, 2022, 39(3): 42-62.
[10] 李兴秀，唐建军，华晶. 结合CNN与双向LSTM的心律失常分类[J]. 计算机科学与探索，2021, 15(12): 2353-2361.
LI X X, TANG J J, HUA J. Arrhythmia classification based on CNN and bidirectional LSTM[J]. Journal of Frontiers of Computer Science and Technology, 2021, 15(12): 2353-2361.
[11] LONI M, ZOLJODI A, SINAEI S, et al. Neuropower: designing energy efficient convolutional neural network architecture for embedded systems[C]//Proceedings of the 2019 International Conference on Artificial Neural Networks and Machine Learning, Munich, Sep 17-19, 2019. Cham: Springer, 2019: 208-222.
[12] GU J, WANG Z, KUEN J, et al. Recent advances in convolutional neural networks[J]. Pattern Recognition, 2018, 77: 354-377.
[13] HUA Y, GUO J, ZHAO H. Deep belief networks and deep learning[C]//Proceedings of the 2015 International Conference on Intelligent Computing and Internet of Things. Piscataway: IEEE, 2015: 1-4.
[14] ZAREMBA W, SUTSKEVER I, VINYALS O. Recurrent neural network regularization[EB/OL]. [2023-09-03]. https://arxiv.org/abs/1409.2329.
[15] CHENG J, DONG L, LAPATA M. Long short-term memory-networks for machine reading[C]//Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. Stroudsburg: ACL, 2016: 551-561.
[16] CHEN X, QIU X, ZHU C, et al. Sentence modeling with gated recursive neural network[C]//Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing. Stroudsburg: ACL, 2015: 793-798.
[17] BO J Y, HUANG H W, CHAN A, et al. Pretraining ECG data with adversarial masking improves model generalizability for data-scarce tasks[EB/OL]. [2023-09-03]. https://arxiv.org/abs/2211.07889.
[18] SONG H M, KIM H K. Self-supervised anomaly detection for invehicle network using noised pseudo normal data[J]. IEEE Transactions on Vehicular Technology, 2021, 70(2): 1098-1108.
[19] P?PPELBAUM J, CHADHA G S, SCHWUNG A. Contrastive learning based self-supervised time-series analysis[J]. Applied Soft Computing, 2022, 117: 108397.
[20] 刘雅芬，郑艺峰，江铃燚，等. 深度半监督学习中伪标签方法综述[J]. 计算机科学与探索，2022, 16(6): 1279-1290.
LIU Y F, ZHENG Y F, JIANG L Y, et al. Survey on pseudo-labeling methods in deep semi-supervised learning[J]. Journal of Frontiers of Computer Science and Technology, 2022, 16(6): 1279-1290.
[21] ELDELE E, RAGAB M, CHEN Z, et al. Label-efficient time series representation learning: a review[EB/OL]. [2023-09-03]. https://arxiv.org/abs/2302.06433.
[22] YU J, YIN H, XIA X, et al. Self-supervised learning for recommender systems: a survey[J]. IEEE Transactions on Know-ledge and Data Engineering, 2024, 36(1): 335-355.
[23] RANI V, NABI S T, KUMAR M, et al. Self-supervised learning: a succinct review[J]. Archives of Computational Methods in Engineering, 2023, 30(4): 2761-2775.
[24] CHEN X, DING M, WANG X, et al. Context autoencoder for self-supervised representation learning[J]. International Journal of Computer Vision, 2024, 132(1): 208-223.
[25] LIU X, ZHANG F, HOU Z, et al. Self-supervised learning: generative or contrastive[J]. IEEE Transactions on Knowledge and Data Engineering, 2021, 35(1): 857-876.
[26] ZHANG K, WEN Q, ZHANG C, et al. Self-supervised learn-ing for time series analysis: taxonomy, progress, and prospects[EB/OL]. [2023-09-03]. https://arxiv.org/abs/2306.10125.
[27] JAISWAL A, BABU A R, ZADEH M Z, et al. A survey on contrastive self-supervised learning[J]. Technologies, 2020, 9(1): 2.
[28] SCHIAPPA M C, RAWAT Y S, SHAH M. Self-supervised learning for videos: a survey[J]. ACM Computing Surveys, 2023, 55: 1-37.
[29] WANG Y, ALBRECHT C M, BRAHAM N A A, et al. Self-supervised learning in remote sensing: a review[EB/OL]. [2023-09-03]. https://arxiv.org/abs/2206.13188.
[30] ZHANG D, ZHOU F, WEI Y, et al. Unleashing the power of self-supervised image denoising: a comprehensive review[EB/OL]. [2023-09-03]. https://arxiv.org/abs/2308.00247.
[31] HAN K, XIAO A, WU E, et al. Transformer in transformer [C]//Advances in Neural Information Processing Systems 34, Dec 6-14, 2021: 15908-15919.
[32] XIE Y, XU Z, ZHANG J, et al. Self-supervised learning of graph neural networks: a unified review[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 45(2): 2412-2429.
[33] DEL PUP F, ATZORI M. Applications of self-supervised learning to biomedical signals: a survey[J]. IEEE Access, 2023, 11: 144180-144203.
[34] LIU Z, ALAVI A, LI M, et al. Self-supervised contrastive learning for medical time series: a systematic review[J]. Sensors, 2023, 23(9): 4221.
[35] KIYASSEH D, ZHU T, CLIFTON D A. CLOCS: contrastive learning of cardiac signals across space, time, and patients[C]//Proceedings of the 38th International Conference on Machine Learning, Jul 18-24, 2021: 5606-5615.
[36] LUO C, WANG G, DING Z, et al. Segment origin prediction: a self-supervised learning method for electrocardiogram arrhythmia classification[C]//Proceedings of the 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society. Piscataway: IEEE, 2021: 1132-1135.
[37] OH J, CHUNG H, KWON J, et al. Lead-agnostic self-supervised learning for local and global representations of electro-cardiogram[C]//Proceedings of the 2022 Conference on Health, Inference, and Learning, Apr 7-8, 2022: 338-353.
[38] NAKAMOTO M, KODERA S, TAKEUCHI H, et al. Self-supervised contrastive learning for electrocardiograms to detect left ventricular systolic dysfunction[C]//Advances in Neural Information Processing Systems 35, New Orleans, Nov 28-Dec 9, 2022: 1-7.
[39] RABBANI S, KHAN N. Contrastive self-supervised learning for stress detection from ECG data[J]. Bioengineering, 2022, 9(8): 374.
[40] NATH R K, TERVONEN J, N?RV?INEN J, et al. Towards self-supervised learning of ECG signal representation for the classification of acute stress types[C]//Proceedings of the Great Lakes Symposium on Very Large Scale Integration 2023. New York: ACM, 2023: 85-90.
[41] SUH J, KIM J, LEE E, et al. Learning ECG representations for multi-label classification of cardiac abnormalities[C]//Proceedings of the 2021 Computing in Cardiology. Piscataway: IEEE, 2021: 1-4.
[42] SOLTANIEH S, ETEMAD A, HASHEMI J. Analysis of augmentations for contrastive ECG representation learning[C]//Proceedings of the 2022 International Joint Conference on Neural Networks. Piscataway: IEEE, 2022: 1-10.
[43] LAN X, NG D, HONG S, et al. Intra-inter subject self-supervised learning for multivariate cardiac signals[C]//Proceedings of the 2022 AAAI Conference on Artificial Intelligence. Menlo Park: AAAI, 2022: 4532-4540.
[44] KUMAR C B, MONDAL A K, BHATIA M, et al. Self-supervised representation learning based OSA detection method using single channel ECG signals[J]. IEEE Transactions on Instrumentation and Measurement, 2023, 72: 1-15.
[45] GOPAL B, HAN R, RAGHUPATHI G, et al. 3KG: contrastive learning of 12-lead electrocardiograms using physiologically-inspired augmentations[C]//Proceedings of the 2021 Machine Learning Research, Dec 4, 2021: 156-167.
[46] LAI J, TAN H, WANG J, et al. Practical intelligent diagnostic algorithm for wearable 12-lead ECG via self-supervised learning on large-scale dataset[J]. Nature Communications, 2023, 14(1): 3741.
[47] LE D, TRUONG S, BRIJESH P, et al. sCL-ST: supervised contrastive learning with semantic transformations for multi-ple lead ECG arrhythmia classification[J]. IEEE Journal of Biomedical and Health Informatics, 2023, 27(6): 2818-2828.
[48] CHEN H, WANG G, ZHANG G, et al. CLECG: a novel contrastive learning framework for electrocardiogram arrhythmia classification[J]. IEEE Signal Processing Letters, 2021, 28: 1993-1997.
[49] CHENG J Y, GOH H, DOGRUSOZ K, et al. Subject-aware contrastive learning for biosignals[EB/OL]. [2023-09-03]. https://arxiv.org/abs/2007.04871.
[50] KIYASSEH D, ZHU T, CLIFTON D. CROCS: clustering and retrieval of cardiac signals based on patient disease class, sex, and age[C]//Advances in Neural Information Processing Systems 34, Dec 6-14, 2021: 15557-15569.
[51] ATIENZA A, BARDRAM J, PUTHUSSERYPADY S. Subject-based non-contrastive self-supervised learning for ECG signal processing[EB/OL]. [2023-09-03]. https://arxiv.org/abs/2305.10347.
[52] LIU W, ZHANG H, CHANG S, et al. A joint cross-dimensional contrastive learning framework for 12-lead ECGs and its heterogeneous deployment on SoC[J]. Computers in Biology and Medicine, 2023, 152: 106390.
[53] WEI C T, HSIEH M E, LIU C L, et al. Contrastive heartbeats: contrastive learning for self-supervised ECG represen-tation and phenotyping[C]//Proceedings of the 2022 IEEE International Conference on Acoustics, Speech and Signal Processing. Piscataway: IEEE, 2022: 1126-1130.
[54] ZHANG X, ZHAO Z, TSILIGKARIDIS T, et al. Self-supervised contrastive pre-training for time series via time-frequency consistency[C]//Advances in Neural Information Processing Systems 35, New Orleans, Nov 28-Dec 9, 2022: 3988-4003.
[55] LI J, LIU C, CHENG S, et al. Frozen language model helps ECG zero-shot learning[EB/OL]. [2023-09-03]. https://arxiv.org/abs/2303.12311.
[56] BELGIU M, DR?GU? L. Random forest in remote sensing: a review of applications and future directions[J]. Journal of Photogrammetry and Remote Sensing, 2016, 114: 24-31.
[57] HEARST M A, DUMAIS S T, OSUNA E, et al. Support vector machines[J]. IEEE Intelligent Systems and Their Applications, 1998, 13(4): 18-28.
[58] GRILL J B, STRUB F, ALTCHé F, et al. Bootstrap your own latent—a new approach to self-supervised learning[C]//Advances in Neural Information Processing Systems 33, Dec 6-12, 2020: 21271-21284.
[59] GRABOWSKI B, G?OMB P, MASARCZYK W, et al. Classification and self-supervised regression of arrhythmic ECG signals using convolutional neural networks[EB/OL]. [2023-09-03]. https://arxiv.org/abs/2210.14253.
[60] GEDON D, RIBEIRO A H, WAHLSTR?M N, et al. First steps towards self-supervised pretraining of the 12-lead ECG[C]//Proceedings of the 2021 Computing in Cardiology. Piscataway: IEEE, 2021: 1-4.
[61] ZHANG H, LIU W, SHI J, et al. MaeFE: masked autoencoders family of electrocardiogram for self-supervised pretraining and transfer learning[J]. IEEE Transactions on Instrumentation and Measurement, 2022, 72: 1-15.
[62] VAZQUEZ-RODRIGUEZ J, LEFEBVRE G, CUMIN J, et al. Transformer-based self-supervised learning for emotion recognition[C]//Proceedings of the 2022 26th International Conference on Pattern Recognition. Piscataway: IEEE, 2022: 2605-2612.
[63] YANG S, LIAN C, ZENG Z. Masked autoencoder for ECG representation learning[C]//Proceedings of the 2022 12th International Conference on Information Science and Technology. Piscataway: IEEE, 2022: 95-98.
[64] SAWANO S, KODERA S, TAKEUCHI H, et al. Masked autoencoder-based self-supervised learning for electrocardiograms to detect left ventricular systolic dysfunction[C]//Advances in Neural Information Processing Systems 35, New Orleans, Nov 28-Dec 9, 2022: 1-8.
[65] LEE B T, KONG S T, SONG Y, et al. Self-supervised learning with electrocardiogram delineation for arrhythmia detection[C]//Proceedings of the 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society. Piscataway: IEEE, 2021: 591-594.
[66] CHOI S, MOUSAVI S, SI P, et al. ECGBERT: understanding hidden language of ECGs with self-supervised representation learning[EB/OL]. [2023-09-03]. https://arxiv.org/abs/2306.06340.
[67] SARKAR P, ETEMAD A. Self-supervised learning for ECG-based emotion recognition[C]//Proceedings of the 2020 IEEE International Conference on Acoustics, Speech and Signal Processing. Piscataway: IEEE, 2020: 3217-3221.
[68] SARKAR P, ETEMAD A. Self-supervised ECG representation learning for emotion recognition[J]. IEEE Transactions on Affective Computing, 2020, 13(3): 1541-1554.
[69] SARKAR P, LOBMAIER S, FABRE B, et al. Detection of maternal and fetal stress from the electrocardiogram with self-supervised representation learning[J]. Scientific Reports, 2021, 11(1): 24146.
[70] WU W, HUANG Y, WU X. A new deep learning method with self-supervised learning for delineation of the electrocardiogram[J]. Entropy, 2022, 24(12): 1828.
[71] ZHANG W, GENG S, HONG S. A simple self-supervised ECG representation learning method via manipulated temporal-spatial reverse detection[J]. Biomedical Signal Processing and Control, 2023, 79: 104194.
[72] LIU F, LIU C, ZHAO L, et al. An open access database for evaluating the algorithms of electrocardiogram rhythm and morphology abnormality detection[J]. Journal of Medical Imaging and Health Informatics, 2018, 8(7): 1368-1373.
[73] GAO H, LIU C, WANG X, et al. An open-access ECG database for algorithm evaluation of QRS detection and heart rate estimation[J]. Journal of Medical Imaging and Health Informatics, 2019, 9(9): 1853-1858.
[74] CAI Z, LIU C, GAO H, et al. An open-access long-term wearable ECG database for premature ventricular contractions and supraventricular premature beat detection[J]. Journal of Medical Imaging and Health Informatics, 2020, 10(11): 2663-2667.
[75] WANG X, MA C, ZHANG X, et al. Paroxysmal atrial fibrillation events detection from dynamic ECG recordings: the 4th China physiological signal challenge 2021[J]. PhysioNet, 2021, 1: 1-83.
[76] AHAMED M A, HASAN K A, MONOWAR K F, et al. ECG heartbeat classification using ensemble of efficient machine learning approaches on imbalanced datasets[C]//Proceedings of the 2020 2nd International Conference on Advanced Information and Communication Technology. Piscataway: IEEE, 2020: 140-145.
[77] HANNUN A Y, RAJPURKAR P, HAGHPANAHI M, et al. Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network[J]. Nature Medicine, 2019, 25(1): 65-69.
[78] MOODY G B, MARK R G. The impact of the MIT-BIH arrhythmia database[J]. IEEE Engineering in Medicine and Biology Magazine, 2001, 20(3): 45-50.
[79] MOODY G. A new method for detecting atrial fibrillation using RR intervals[J]. Computers in Cardiology, 1983, 10: 227-230.
[80] GOLDBERGER A L, AMARAL L A N, GLASS L, et al. PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals[J]. Circulation, 2000, 101(23): 215-220.
[81] WAGNER P, STRODTHOFF N, BOUSSELJOT R D, et al. PTB-XL, a large publicly available electrocardiography data-set[J]. Scientific Data, 2020, 7(1): 154.
[82] ZHENG J, ZHANG J, DANIOKO S, et al. A 12-lead electro-cardiogram database for arrhythmia research covering more than 10,000 patients[J]. Scientific data, 2020, 7(1): 48.
[83] ZHENG J, CHU H, STRUPPA D, et al. Optimal multi-stage arrhythmia classification approach[J]. Scientific Reports, 2020, 10(1): 2898.
[84] ALKMIM M B, FIGUEIRA R M, MARCOLINO M S, et al. Improving patient access to specialized health care: the Telehealth Network of Minas Gerais, Brazil[J]. Bulletin of the World Health Organization, 2012, 90: 373-378.
[85] CLIFFORD G D, LIU C, MOODY B, et al. AF classification from a short single lead ECG recording: the PhysioNet/computing in cardiology challenge 2017[C]//Proceedings of the 2017 Computing in Cardiology. Piscataway: IEEE, 2017: 1-4.
[86] ALDAY E A P, GU A, SHAH A J, et al. Classification of 12-lead ECGs: the PhysioNet/computing in cardiology challenge 2020[J]. Physiological Measurement, 2020, 41(12): 124003.
[87] REYNA M A, SADR N, ALDAY E A P, et al. Will two do? Varying dimensions in electrocardiography: the PhysioNet/computing in cardiology challenge 2021[C]//Proceedings of the 2021 Computing in Cardiology. Piscataway: IEEE, 2021: 1-4.
[88] KOLDIJK S, SAPPELLI M, VERBERNE S, et al. The swell knowledge work dataset for stress and user modeling research[C]//Proceedings of the 16th International Conference on Multimodal Interaction. New York: ACM, 2014: 291-298.
[89] SCHMIDT P, REISS A, DUERICHEN R, et al. Introducing wesad, a multimodal dataset for wearable stress and affect detection[C]//Proceedings of the 20th ACM International Conference on Multimodal Interaction. New York: ACM, 2018: 400-408.
[90] AHMAD Z, RABBANI S, ZAFAR M R, et al. Multi-level stress assessment from ECG in a virtual reality environment using multimodal fusion[J]. IEEE Sensors Journal, 2023, 23: 29559-29570.
[91] KATSIGIANNIS S, RAMZAN N. DREAMER: a database for emotion recognition through EEG and ECG signals from wireless low-cost off-the-shelf devices[J]. IEEE Journal of Biomedical and Health Informatics, 2017, 22(1): 98-107.
[92] MIRANDA-CORREA J A, ABADI M K, SEBE N, et al. AMIGOS: a dataset for affect, personality and mood research on individuals and groups[J]. IEEE Transactions on Affective Computing, 2018, 12(2): 479-493.
[93] SUBRAMANIAN R, WACHE J, ABADI M K, et al. ASCERTAIN: emotion and personality recognition using commercial sensors[J]. IEEE Transactions on Affective Computing, 2016, 9(2): 147-160.
[94] PENZEL T, MOODY G B, MARK R G, et al. The apnea-ECG database[C] //Proceedings of the Computers in Cardiology 2000. Piscataway: IEEE, 2000: 255-258.
[95] MOSTAFA S S, MENDON?A F, MORGADO-DIAS F, et al. SpO2 based sleep apnea detection using deep learning[C]//Proceedings of the 2017 IEEE 21st International Conference on Intelligent Engineering Systems. Piscataway: IEEE, 2017: 91-96.
[96] LEE J M, KIM D J, KIM I Y, et al. Detrended fluctuation analysis of EEG in sleep apnea using MIT/BIH polysomnography data[J]. Computers in Biology and Medicine, 2002, 32(1): 37-47.
[97] LAGUNA P, MARK R G, GOLDBERG A, et al. A database for evaluation of algorithms for measurement of QT and other waveform intervals in the ECG[C]//Proceedings of the Computers in Cardiology 1997. Piscataway: IEEE, 1997: 673-676.
[98] ZHANG J, WANG L, LIU X, et al. Chinese cardiovascular disease database (CCDD) and its management tool[C]//Proceedings of the 2010 IEEE International Conference on BioInformatics and BioEngineering. Piscataway: IEEE, 2010: 66-72.
[99] KALYAKULINA A I, YUSIPOV I I, MOSKALENKO V A, et al. LUDB: a new open-access validation tool for electrocardiogram delineation algorithms[J]. IEEE Access, 2020, 8: 186181-186190.
[100] PARVANEH S, RUBIN J, BABAEIZADEH S, et al. Cardiac arrhythmia detection using deep learning: a review[J]. Journal of Electrocardiology, 2019, 57: 70-74.
[101] SAHOO S, DASH M, BEHERA S, et al. Machine learning approach to detect cardiac arrhythmias in ECG signals: a survey[J]. Irbm, 2020, 41(4): 185-194.
[102] XIAO Q, LEE K, MOKHTAR S A, et al. Deep learning-based ECG arrhythmia classification: a systematic review[J]. Applied Sciences, 2023, 13(8): 4964.
[103] HONG S, ZHOU Y, SHANG J, et al. Opportunities and challenges of deep learning methods for electrocardiogram data: a systematic review[J]. Computers in Biology and Medicine, 2020, 122: 103801.
[104] PETMEZAS G, STEFANOPOULOS L, KILINTZIS V, et al. State-of-the-art deep learning methods on electrocardiogram data: systematic review[J]. JMIR Medical Informatics, 2022, 10(8): e38454.
[105] HASNUL M A, AZIZ N A A, ALELYANI S, et al. Electrocardiogram-based emotion recognition systems and their applications in healthcare—a review[J]. Sensors, 2021, 21(15): 5015.
[106] NIKOLOVA D, PETKOVA P, MANOLOVA A, et al. ECG-based emotion recognition: overview of methods and applications[C]//Advances in Neural Networks and Applications 2018. Piscataway: IEEE, 2018: 1-5.
[107] ABDULLAH S M S A, AMEEN S Y A, SADEEQ M A M, et al. Multimodal emotion recognition using deep learning[J]. Journal of Applied Science and Technology Trends, 2021, 2(2): 52-58.
[108] LIN W, LI C. Review of studies on emotion recognition and judgment based on physiological signals[J]. Applied Sciences, 2023, 13(4): 2573.
[109] BOTA P J, WANG C, FRED A L N, et al. A review, current challenges, and future possibilities on emotion recognition using machine learning and physiological signals[J]. IEEE Access, 2019, 7: 140990-141020.
[110] SALARI N, HOSSEINIAN-FAR A, MOHAMMADI M, et al. Detection of sleep apnea using machine learning algorithms based on ECG signals: a comprehensive systematic review[J]. Expert Systems with Applications, 2022, 187: 115950.
[111] MOSTAFA S S, MENDON?A F, RAVELO-GARCíA A G, et al. A systematic review of detecting sleep apnea using deep learning[J]. Sensors, 2019, 19(22): 4934.
[112] SHETA A, TURABIEH H, THAHER T, et al. Diagnosis of obstructive sleep apnea from ECG signals using machine learning and deep learning classifiers[J]. Applied Sciences, 2021, 11(14): 6622.
[113] BALDI P. Autoencoders, unsupervised learning, and deep architectures[C]//Proceedings of the 2011 International Con-ference on Unsupervised and Transfer Learning, Bellevue, Jul 2, 2011: 37-49.
[114] KINGMA D P, WELLING M. An introduction to variational autoencoders[J]. Foundations and Trends? in Machine Learning, 2019, 12(4): 307-392.
[115] KUZNETSOV V V, MOSKALENKO V A, GRIBANOV D V, et al. Interpretable feature generation in ECG using a variational autoencoder[J]. Frontiers in Genetics, 2021, 12: 638191.
[116] CRESWELL A, WHITE T, DUMOULIN V, et al. Generative adversarial networks: an overview[J]. IEEE Signal Processing Magazine, 2018, 35(1): 53-65.
[117] HAZRA D, BYUN Y C. SynSigGAN: generative adversarial networks for synthetic biomedical signal generation[J]. Biology, 2020, 9(12): 441.
[118] BANERJEE R, GHOSE A. Synthesis of realistic ECG waveforms using a composite generative adversarial network for classification of atrial fibrillation[C]//Proceedings of the 2021 29th European Signal Processing Conference. Piscataway: IEEE, 2021: 1145-1149.
[119] YANG L, ZHANG Z, SONG Y, et al. Diffusion models: a comprehensive survey of methods and applications[J]. ACM Computing Surveys, 2023, 56(4): 1-39.
[120] ALCARAZ J M L, STRODTHOFF N. Diffusion-based conditional ECG generation with structured state space models[J]. Computers in Biology and Medicine, 2023,163: 107115.
[121] ADIB E, FERNANDEZ A S, AFGHAH F, et al. Synthetic ECG signal generation using probabilistic diffusion models[J]. IEEE Access, 2023,11: 75818-75828.
[122] MAHARANA K, MONDAL S, NEMADE B. A review: data pre-processing and data augmentation techniques[J]. Global Transitions Proceedings, 2022, 3(1): 91-99.
[123] GARCEA F, SERRA A, LAMBERTI F, et al. Data augmentation for medical imaging: a systematic literature review[J]. Computers in Biology and Medicine, 2023, 152: 106391.
[124] 黄训华，张凤斌，樊好义，等. 基于多模态对抗学习的无监督时间序列异常检测[J]. 计算机研究与发展，2021, 58(8): 1655-1667.
HUANG X H, ZHANG F B, FAN H Y, et al. Unsupervised time series anomaly detection based on multi-modal adversarial learning[J]. Journal of Computer Research and Development, 2021, 58(8): 1655-1667.
[125] 赵小明，杨轶娇，张石清. 面向深度学习的多模态情感识别研究进展[J]. 计算机科学与探索，2022, 16(7): 1479-1503.
ZHAO X M, YANG Y J, ZHANG S Q. Research progress of multimodal emotion recognition oriented to deep learning[J]. Journal of Frontiers of Computer Science and Technology, 2022, 16(7): 1479-1503.
[126] LIU J, LI Z, JIN Y, et al. A review of arrhythmia detection based on electrocardiogram with artificial intelligence[J]. Expert Review of Medical Devices, 2022, 19(7): 549-560.
[127] AL-ZAITI S, BESOMI L, BOUZID Z, et al. Machine learning-based prediction of acute coronary syndrome using only the pre-hospital 12-lead electrocardiogram[J]. Nature Communications, 2020, 11(1): 3966.