Abstract
The paper considers the problem of improving the interpretability of a convolutional neural network on the example of ECG classification task. This is done by using an architecture based on attention modules. Each module generates a mask that selects only those features that are required to make the final prediction. By visualizing these masks, areas of the signal that are important for decision-making can be identified. The model was trained both on raw signals and on their logarithmic spectrograms. In the case of raw signals, generated masks did not perform any meaningful feature maps filtering, but in the case of spectrograms, interpretable masks responsible for noise reduction and arrhythmic parts detection were obtained.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Goldberger, A.L., Amaral, L.A.N., Glass, L., Hausdorff, J.M., Ivanov, P.C., Mark, R.G., Mietus, J.E., Moody, G.B., Peng, C.-K., Stanley, H.E.: PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals. Circulation 101(23), e215–e220 (2000)
Clifford, G., Liu, C., Moody, B., Lehman, L.H., Silva, I., Li, Q., Johnson, A., Mark, R.G.: AF classification from a short single lead ECG recording: the PhysioNet computing in cardiology challenge 2017. Comput. Cardiol. 44 (2017)
Moody, G.B., Mark, R.G.: A new method for detecting atrial fibrillation using R-R intervals. Comput. Cardiol. 10, 227–230 (1983)
Wang, F., Jiang, M., Qian, C., Yang, S., Li, C., Zhang, H., Wang, X., Tang, X.: Residual attention network for image classification. ArXiv e-prints, April 2017
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. ArXiv e-prints, December 2015
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15, 1929–1958 (2014)
Nair, V., Hinton, G.E.: Rectified linear units improve restricted boltzmann machines. In: International Conference on Machine Learning (2010)
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. ArXiv e-prints, February 2015
Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: International Conference on Artificial Intelligence and Statistics, pp. 249–256 (2010)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. ArXiv e-prints, December 2014
Khudorozhkov, R., Illarionov, E., Kuvaev, A., Podvyaznikov, D.: CardIO library for deep research of heart signals (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Kuvaev, A., Khudorozhkov, R. (2020). An Attention-Based CNN for ECG Classification. In: Arai, K., Kapoor, S. (eds) Advances in Computer Vision. CVC 2019. Advances in Intelligent Systems and Computing, vol 943. Springer, Cham. https://doi.org/10.1007/978-3-030-17795-9_49
Download citation
DOI: https://doi.org/10.1007/978-3-030-17795-9_49
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-17794-2
Online ISBN: 978-3-030-17795-9
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)