Data Augmentation for Deep Learning-Based ECG Analysis

  • Qing PanEmail author
  • Xinyi Li
  • Luping FangEmail author


Deep learning has become the technology that gets the most attention in recent years owing to its admirable performance compared to the conventional methods in a series of tasks. Though its application in electrocardiogram (ECG) analysis has enhanced the understanding and the applicability of many disease diagnosis in clinic, lack of annotated data hampers the deep learning-based ECG analysis as large amount of data is required for a well-performed deep learning model. Data augmentation, which refers to the procedure that enriches the dataset by introducing unobserved samples, plays an important role in this respect. Despite the successful usage of data augmentation in the image-based deep learning analysis, its application in one-dimensional physiological signals, such as ECG, is still limited. In this chapter, we summarize the data augmentation methods applicable for ECG analysis and examine their performance on a task for detecting atrial fibrillation (AF).


Data augmentation Electrocardiogram Deep learning Atrial fibrillation 



This study was supported by the National Natural Science Foundation of China (Grant 31870938) and Zhejiang Provincial Key Laboratory of Communication Networks and Applications.


  1. 1.
    De Bacquer, D., De Backer, G., Kornitzer, M., et al.: Prognostic value of ECG findings for total, cardiovascular disease, and coronary heart disease death in men and women. Heart. 80, 570–577 (1998)CrossRefGoogle Scholar
  2. 2.
    Juergens, K.U., Grude, M., Fallenberg, E.M., et al.: Using ECG-gated multidetector CT to evaluate global left ventricular myocardial function in patients with coronary artery disease. Am. J. Roentgenol. 179, 1545–1550 (2002)CrossRefGoogle Scholar
  3. 3.
    Auer, R., Bauer, D.C., Marques-Vidal, P., et al.: Association of major and minor ECG abnormalities with coronary heart disease events. JAMA. 307, 1497–1505 (2012)CrossRefGoogle Scholar
  4. 4.
    Billman, G.E.: Heart rate variability—a historical perspective. Front. Physiol. 2, 86 (2011)CrossRefGoogle Scholar
  5. 5.
    Odinaka, I., Lai, P.-H., Kaplan, A.D., et al.: ECG biometric recognition: a comparative analysis. IEEE Trans. Inf. Forensics Secur. 7, 1812–1824 (2012)CrossRefGoogle Scholar
  6. 6.
    Agrafioti, F., Hatzinakos, D., Anderson, A.K.: ECG pattern analysis for emotion detection. IEEE Trans. Affect. Comput. 3, 102–115 (2011)CrossRefGoogle Scholar
  7. 7.
    Jalaleddine, S.M., Hutchens, C.G., Strattan, R.D., et al.: ECG data compression techniques—a unified approach. IEEE Trans. Biomed. Eng. 37, 329–343 (1990)CrossRefGoogle Scholar
  8. 8.
    Pietka, E.: Feature extraction in computerized approach to the ECG analysis. Pattern Recogn. 24, 139–146 (1991)CrossRefGoogle Scholar
  9. 9.
    Pan, J., Tompkins, W.J.: A real-time QRS detection algorithm. IEEE Trans. Biomed. Eng. 32, 230–236 (1985)CrossRefGoogle Scholar
  10. 10.
    Li, C., Zheng, C., Tai, C.: Detection of ECG characteristic points using wavelet transforms. IEEE Trans. Biomed. Eng. 42, 21–28 (1995)CrossRefGoogle Scholar
  11. 11.
    Sahambi, J., Tandon, S., Bhatt, R.: Using wavelet transforms for ECG characterization. An on-line digital signal processing system. IEEE Eng. Med. Biol. Mag. 16, 77–83 (1997)CrossRefGoogle Scholar
  12. 12.
    Senhadji, L., Carrault, G., Bellanger, J., et al.: Comparing wavelet transforms for recognizing cardiac patterns. IEEE Eng. Med. Biol. Mag. 14, 167–173 (1995)CrossRefGoogle Scholar
  13. 13.
    Zhao, Q., Zhang, L.: ECG feature extraction and classification using wavelet transform and support vector machines. In: 2005 International Conference on Neural Networks and Brain, vol. 2, pp. 1089–1092 (2005)Google Scholar
  14. 14.
    Emanet, N.: ECG beat classification by using discrete wavelet transform and Random Forest algorithm. In: 2009 Fifth International Conference on Soft Computing, Computing with Words and Perceptions in System Analysis, Decision and Control, pp. 1–4 (2009)Google Scholar
  15. 15.
    Li, Q., Rajagopalan, C., Clifford, G.D.: Ventricular fibrillation and tachycardia classification using a machine learning approach. IEEE Trans. Biomed. Eng. 61, 1607–1613 (2013)PubMedGoogle Scholar
  16. 16.
    LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature. 521, 436 (2015)CrossRefGoogle Scholar
  17. 17.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Adv. Neural Inf. Proces. Syst. 25, 1097–1105 (2012)Google Scholar
  18. 18.
    Farabet, C., Couprie, C., Najman, L., et al.: Learning hierarchical features for scene labeling. IEEE Trans. Pattern Anal. Mach. Intell. 35, 1915–1929 (2012)CrossRefGoogle Scholar
  19. 19.
    Tompson, J.J., Jain, A., LeCun, Y., et al.: Joint training of a convolutional network and a graphical model for human pose estimation. Adv. Neural Inf. Proces. Syst. 1799–1807 (2014)Google Scholar
  20. 20.
    Mikolov, T., Deoras, A., Povey, D., et al.: Strategies for training large scale neural network language models. In: 2011 IEEE Workshop on Automatic Speech Recognition & Understanding, pp. 196–201 (2011)Google Scholar
  21. 21.
    Hinton, G., Deng, L., Yu, D., et al.: Deep neural networks for acoustic modeling in speech recognition. IEEE Signal Process. Mag. 29, 82 (2012)CrossRefGoogle Scholar
  22. 22.
    Sainath, T.N., Mohamed, A.-R., Kingsbury, B., et al.: Deep convolutional neural networks for LVCSR. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 8614–8618 (2013)Google Scholar
  23. 23.
    Hubel, D.H., Wiesel, T.N.: Receptive fields and functional architecture of monkey striate cortex. J. Physiol. 195, 215–243 (1968)CrossRefGoogle Scholar
  24. 24.
    Graves, A., Liwicki, M., Fernández, S., et al.: A novel connectionist system for unconstrained handwriting recognition. IEEE Trans. Pattern Anal. Mach. Intell. 31, 855–868 (2008)CrossRefGoogle Scholar
  25. 25.
    Sak, H., Senior, A., Beaufays, F.: Long short-term memory recurrent neural network architectures for large scale acoustic modeling. In: Fifteenth Annual Conference of the International Speech Communication Association (2014)Google Scholar
  26. 26.
    Li, X., Wu, X.: Constructing long short-term memory based deep recurrent neural networks for large vocabulary speech recognition. In: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4520–4524 (2015)Google Scholar
  27. 27.
    Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9, 1735–1780 (1997)CrossRefGoogle Scholar
  28. 28.
    Hannun, A.Y., Rajpurkar, P., Haghpanahi, M.: Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network. Nat. Med. 25, 65–69 (2019)CrossRefGoogle Scholar
  29. 29.
    Übeyli, E.D.: Recurrent neural networks employing Lyapunov exponents for analysis of ECG signals. Expert Syst. Appl. 37, 1192–1199 (2010)CrossRefGoogle Scholar
  30. 30.
    Chauhan, S., Vig, L.: Anomaly detection in ECG time signals via deep long short-term memory networks. In: 2015 IEEE International Conference on Data Science and Advanced Analytics (DSAA), pp. 1–7 (2015)Google Scholar
  31. 31.
    Al Rahhal, M.M., Bazi, Y., AlHichri, H., et al.: Deep learning approach for active classification of electrocardiogram signals. Inf. Sci. 345, 340–354 (2016)CrossRefGoogle Scholar
  32. 32.
    Mousavi, S., Afghah, F., Razi, A., et al.: ECGNET: learning where to attend for detection of atrial fibrillation with deep visual attention. In: IEEE-EMBS International Conferences on Biomedical and Health Informatics (IEEE BHI) (2019)Google Scholar
  33. 33.
    Van Dyk, D.A., Meng, X.L.: The art of data augmentation. J. Comput. Graph. Stat. 10, 1–50 (2001)CrossRefGoogle Scholar
  34. 34.
    Zhao, A., Balakrishnan, G., Durand, F., et al.: Data augmentation using learned transformations for one-shot medical image segmentation. Proc. IEEE Conf. Comput. Vis. Pattern Recognit. 8543–8553 (2019)Google Scholar
  35. 35.
    Perez, L., Wang, J.: The effectiveness of data augmentation in image classification using deep learning. arXiv preprint arXiv:1712.04621 (2017)Google Scholar
  36. 36.
    Mikołajczyk, A., Grochowski, M.: Data augmentation for improving deep learning in image classification problem. In: 2018 International Interdisciplinary PhD Workshop (IIPhDW), pp. 117–122 (2018)Google Scholar
  37. 37.
    Fawzi, A., Samulowitz, H., Turaga, D., et al.: Adaptive data augmentation for image classification. In: 2016 IEEE International Conference on Image Processing (ICIP) pp. 3688–3692 (2016)Google Scholar
  38. 38.
    Cui, Z., Chen, W., Chen, Y.: Multi-scale convolutional neural networks for time series classification. arXiv preprint arXiv:1603.06995 (2016)Google Scholar
  39. 39.
    Fawaz, H.I., Forestier, G., Weber, J., et al.: Deep learning for time series classification: a review. Data Min. Knowl. Disc. 33, 917–963 (2019)CrossRefGoogle Scholar
  40. 40.
    Ramponi, G., Protopapas, P., Brambilla, M., et al.: T-CGAN: conditional generative adversarial network for data augmentation in noisy time series with irregular sampling. arXiv preprint arXiv:1811.08295 (2018)Google Scholar
  41. 41.
    Karim, F., Majumdar, S., Darabi, H., et al.: LSTM fully convolutional networks for time series classification. IEEE Access. 6, 1662–1669 (2017)CrossRefGoogle Scholar
  42. 42.
    Um, T.T., Pfister, F.M.J., Pichler, D., et al.: Data augmentation of wearable sensor data for Parkinson’s disease monitoring using convolutional neural networks. arXiv preprint arXiv:1706.00527 (2017)Google Scholar
  43. 43.
    Cao, P., Li, X., Mao, K., et al.: A novel data augmentation method to enhance deep neural networks for detection of atrial fibrillation. Biomed. Signal Process. Control. 56, 101675 (2020)CrossRefGoogle Scholar
  44. 44.
    Yeh, J.-R., Sun, W.-Z., Shieh, J.-S., et al.: Intrinsic mode analysis of human heartbeat time series. Ann. Biomed. Eng. 38, 1337–1344 (2010)CrossRefGoogle Scholar
  45. 45.
    Le Guennec, A., Malinowski, S., Tavenard, R.: Data augmentation for time series classification using convolutional neural networks. In: ECML/PKDD Workshop on Advanced Analytics and Learning on Temporal Data (2016)Google Scholar
  46. 46.
    Acharya, U.R., Oh, S.L., Hagiwara, Y., et al.: A deep convolutional neural network model to classify heartbeats. Comput. Biol. Med. 89, 389–396 (2017)CrossRefGoogle Scholar
  47. 47.
    Jun, T.J., Nguyen, H.M., Kang, D., et al.: ECG arrhythmia classification using a 2-D convolutional neural network. arXiv preprint arXiv:1804.06812 (2018)Google Scholar
  48. 48.
    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. Comput. Cardiol. (CinC). 2017, 1–4 (2017)Google Scholar
  49. 49.
    Kingma, J.B.D.P.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations, pp. 1–15 (2015)Google Scholar
  50. 50.
    Srivastava, N., Hinton, G., Krizhevsky, A., et al.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15, 1929–1958 (2014)Google Scholar
  51. 51.
    Gal, Y., Ghahramani, Z.: A theoretically grounded application of dropout in recurrent neural networks. Adv. Neural Inf. Proces. Syst. 1019–1027 (2016)Google Scholar
  52. 52.
    Goodfellow, I., Pouget-Abadie, J., Mirza, M., et al. Generative adversarial nets. Adv. Neural Inf. Proces. Syst. 2672–2680 (2014)Google Scholar
  53. 53.
    Nagasawa, T., Sato, T., Nambu, I., et al.: Improving fNIRS-BCI accuracy using GAN-based data augmentation. In: 2019 9th International IEEE/EMBS Conference on Neural Engineering (NER), pp. 1208–1211 (2019)Google Scholar
  54. 54.
    Nikolaidis, K., Kristiansen, S., Goebel, V., et al.: Augmenting physiological time series data: a case study for sleep apnea detection. arXiv preprint arXiv:1905.09068 (2019)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  1. 1.College of Information Engineering, Zhejiang University of TechnologyHangzhouPeople’s Republic of China

Personalised recommendations