Online Augmentation for Quality Improvement of Neural Networks for Classification of Single-Channel Electrocardiograms

Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 1086)


Currently, on the market, there are mobile devices that are capable of reading a person’s single-lead electrocardiogram (ECG). These ECGs can be used to solve problems of determining various diseases. Neural networks are onearameters of augmentations of the approaches to solving such problems. In this paper, the usage of online augmentation during the training of neural networks was proposed to improve the quality of the ECGs classification. The possibility of using various types of online augmentations was explored. The most promising methods were highlighted. Experimental studies showed that the quality of the classification was improved for various tasks and various neural network architectures.


Deep learning Neural networks Single-lead ECG classification Online augmentation 



This article contains the results of a project carried out within the implementation of the Program of the Center for Competence of the National Technology Initiative “Center for Storage and Analysis of Big Data”, supported by the Ministry of Science and Higher Education of the Russian Federation under the Lomonosov Moscow State University Project Support Fund 13/1251/2018 from 11.12.2018.


  1. 1.
    Ribeiro, A.H., et al.: Automatic Diagnosis of Short-Duration 12-Lead ECG using a Deep Convolutional Network. arXiv preprint arXiv:1811.12194 (2018)
  2. 2.
    Houssein, E.H., Kilany, M., Hassanien, A.E.: ECG signals classification: a review. Int. J. Intell. Eng. Inform. 5, 376 (2017). Scholar
  3. 3.
  4. 4.
  5. 5.
    Yao, Z., Zhu, Z., Chen, Y.: Atrial fibrillation detection by multi-scale convolutional neural networks. In: 2017 20th International Conference on Information Fusion (Fusion). IEEE (2017).
  6. 6.
    Zihlmann, M., Perekrestenko, D., Tschannen, M.: Convolutional recurrent neural networks for electrocardiogram classification. In: 2017 Computing in Cardiology (CinC). IEEE (2017)Google Scholar
  7. 7.
    Buslaev, A., et al.: Albumentations: fast and flexible image augmentations. arXiv preprint arXiv:1809.06839 (2018)
  8. 8.
    Schlüter, J., Grill, T.: Exploring data augmentation for improved singing voice detection with neural networks. In: ISMIR (2015)Google Scholar
  9. 9.
    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
  10. 10.
    Tan, J.H., et al.: Application of stacked convolutional and long short-term memory network for accurate identification of CAD ECG signals. Comput. Biol. Med. 94, 19–26 (2018)CrossRefGoogle Scholar
  11. 11.
    Zhang, H., et al.: mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412 (2017)
  12. 12.
    DeVries, T., Taylor, G.W.: Dataset augmentation in feature space. arXiv preprint arXiv:1702.05538 (2017)
  13. 13.
    Liu, C.L.: A Tutorial of the Wavelet Transform, p. 1–72. National Taiwan University, Department of Electrical Engineering (NTUEE), Taiwan (2010)Google Scholar
  14. 14.
    Rajpurkar, P., et al.: Cardiologist-level arrhythmia detection with convolutional neural networks. arXiv preprint arXiv:1707.01836 (2017)
  15. 15.
    He, K., et al.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)Google Scholar
  16. 16.
    Clifford, G.D., et al.: AF classification from a short single lead ECG recording: the PhysioNet/Computing in Cardiology Challenge 2017. In: 2017 Computing in Cardiology (CinC). IEEE (2017)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Lomonosov Moscow State UniversityMoscowRussia

Personalised recommendations