ECG signal de-noising based on deep learning auto encoder and discrete wavelet transform

  • Authors

    • Aqeel M.Hamad alhussainy alnahrain university
    • Ammar D. Jasim alnahrain university
    2020-04-18
    https://doi.org/10.14419/ijet.v9i2.30499
  • WT-DAE, ECG, DL, DWT and De-Noising Auto Encoder

  • Abstract

    ECG is very important tool for diagnosis of heart disease, this signal is suffered from different types of noises such as baseline wander (BW), muscle artifact (MA) and electrode motion (EM) , which lead to wrong interpretation. In order to prevent or reduce the effect of these noises, different approaches have been applied to enhance the ECG signal. In this paper, we have proposed a new method for ECG signal de-noising based on deep learning Auto encoder (DL-DAE) and wavelet transform named as (WT-DAE). The proposed system (WT-DAE) is constructed from two stages, in the first stage, the wavelet transform is used to isolate the most significant coefficient of the signal (approximation sub-band) from de-tails coefficients (details sub-band). The details coefficients is fed to new proposed threshold method , which is used to evaluate the threshold value according to the feature of ECG signal, this threshold value is used to threshold the detail coefficients, in order to remove the details noise that is contained as high frequencly component , then invers wavelet transform is used to reconstruct the signal . Different wavelet filters and threshold functions are applied in this stage. The second stage of signal de-noising is performed by using DAE method, which is designed for reconstruct the de-noised sig-nal. The proposed DAE model is constructed from 14 layers of convolutional, relu and max_ pooling layer with different parameters. We perform training and testing the model with MIT-BIH ECG database and the performance of the pro-posed system is evaluated by terms of MSE, RMSE, PRD and PSNR. The experimental results are compared with other approaches and show that, the proposed system demonstrated the superiority for de-noising ECG signal.

     

  • References

    1. [1] P.xiang, H. Wang, M.liu, S.Zhou, Z.Hou and X.liu,â€ECG signal enhancement based on improved denoising autoencoderâ€,Eng.Appl.Artif.Intell., Vol.52,pp.194-202,2016. https://doi.org/10.1016/j.engappai.2016.02.015.

      [2] O.ElBcharri, L.rechared , K.Elmansouri,A.Abenau and W.Jenkal, “ECG signal performance de-noising assessment based on thresholding of dual tree wavelet trans Formâ€, Biomed.Eng. Vol.16,No.1 , 2017. https://doi.org/10.1186/s12938-017-0315-1.

      [3] Xiong, P., Wang, H., Liu, M., and Liu, X.,†Denoising Autoencoder for Eletrocardiogram Signal Enhancementâ€, Journal of Medical Imaging and Health Informatics, 5(8):1804–1810, (2015). https://doi.org/10.1166/jmihi.2015.1649.

      [4] Mohammed almoahamdy and Bryan riley,â€Performance study of different denoising methods foe ECG signalsâ€,procedia computer science 37,Elsevier,325-332,2014. https://doi.org/10.1016/j.procs.2014.08.048.

      [5] Ilham Muhammadet.al, “ECG signal classification using deep learning with stack denoising autoencoderâ€, e-Proceeding of Engineering: Vol.4, No.3, ISSN: 2355-9365 , Desember 2017 .

      [6] L.Gornada, “medical image denoising using convolutional denoising autoencoderâ€, in proc. IEEE16th int. Conf. Data Mining Workshops (ICDMW), pp 241-246,2016. https://doi.org/10.1109/ICDMW.2016.0041.

      [7] O.Yilidirim , T.R.San and U.R.Acharya, “ An efficient compression of Ecg signal using deep convolutional autoencodersâ€, Cognit.Syst.Res., Vol.52, pp 198-211,2018. https://doi.org/10.1016/j.cogsys.2018.07.004.

      [8] Jing Jiang, Huaifeng Zhang, Dechang Pi and Chenglong Dai, “A novel multi-module neural network system for imbalanced heartbeats classificationâ€, Expert Systems with Applications, Elsevier Ltd. 2019. https://doi.org/10.1016/j.eswax.2019.100003.

      [9] Afonso Eduardo, Helena Aidos and Ana Fred,â€ECG-based Biometrics using a Deep Autoencoder for Feature Learningâ€, 6th International Conference on Pattern Recognition Applications and Methods (ICPRAM 2017), pages 463-470 .ISBN: 978-989-758-222-6 by SCITEPRESS – Science and Technology Publications, Lda, 2017.

      [10] Alan S. Said Ahmad, Majd S. Matti2, Omar A.M. ALhabiband Sabri Shaikhow, “Denoising of Arrhythmia ECG Signalsâ€, International Journal of Medical Research & Health Sciences, 2018, 7(3): 83-93.

      [11] Hsin-tien Chian,Yi-Yen,Szu-Wei, Kuo-Hsuan,Yu-Tsao and Shao-Yi chen ,â€Noise reduction in ECG signals Using fully convolutional denoising autoencodersâ€, IEEE Acess,Vol 7,2019. https://doi.org/10.1109/ACCESS.2019.2912036.

      [12] GB Moody, RG Mark, in Computers in Cardiology 1990. Proceedings, "The mit-bih arrhythmia database on cd-rom and software for use with itâ€, (IEEE, Chicago, 1990), pp. 185–188

      [13] Goldberger AL, Amaral LAN, Glass L, Hausdorff JM, Ivanov PCh, Mark RG, Mietus JE, Moody GB, Peng C-K, Stanley HE. PhysioBank, PhysioToolkit, and PhysioNet: Components of a New Research Resource for Complex Physiologic Signals (2003). Circulation. 101(23): e215-e220. https://doi.org/10.1161/01.CIR.101.23.e215.

  • Downloads

  • How to Cite

    M.Hamad alhussainy, A., & D. Jasim, A. (2020). ECG signal de-noising based on deep learning auto encoder and discrete wavelet transform. International Journal of Engineering & Technology, 9(2), 415-423. https://doi.org/10.14419/ijet.v9i2.30499

    Received date: 2020-03-05

    Accepted date: 2020-03-30

    Published date: 2020-04-18