Electrocardiogram Signals Recognition using Neural Network

  • Authors

    • Nahrain Najim department of medical instrumentation techniques engineering/ electrical engineering technical college/ middle technical university
    • Asst. prof. dr. jameel kadhim abed
    2018-12-17
    https://doi.org/10.14419/ijet.v7i4.19245
  • ElectroCardioGram (ECG), biometric recognition, non-fiducial feature extraction, AutoCorrelation (AC), Principal Component Analysis (PCA ), Discrete Cosine Transform (DCT), Neural Network (NN).

  • Abstract

    This paper displays a neural network developed to verify human individuals utilizing electrocardiogram (ECG) signals collected from the database on the network website [1][2][3].  In this paper, noises were first removed from the signals by wavelet filters.  ECG cycles were then extracted from the filtered signals and biometric feature extraction by two methods non-fiducial detection at first Autocorrelation, Principle Component Analysis (AC/PCA) and second Autocorrelation, Discrete Cosine Transform (AC/DCT). These coefficient structures were utilized as input vectors to a 2-layer feed forward neural network that generates the verification results.  In the present study, 400 sample collected from 20 individuals were applied to train the neural network, which then was tested with 20 new datasets from 20 different subjects.  All the 20 individuals in the research were successfully verified.  The testing results show that the neural network is effective 97.5 %.

     

     

  • References

    1. [1] The MIT-BIH Normal Sinus Rhythm Database, Available online:

      https://www.physionet.org/physiobank/database/nsrdb/ 10 October 2017.

      [2] The PTB Diagnostic ECG Database, Available online: https://www.physionet.org/physiobank/database/ptbdb/, 10 October 2017.

      [3] The QT Database, Available online: https:// https://physionet.org/physiobank/database/qtdb/, 10 October 2017.

      [4] Araújo T., Nunes N., Gamboa H. & Fred A. (2015), “Generic Biometry Algorithm Based on Signal Morphology Informationâ€, © Springer International Publishing Switzerland, Vol. 318, pp. 301–310.

      [5] Aqil M., Jbari A. & Bourouhou A. (2017),“ECG Signal Denoising by Discrete Wavelet Transformâ€, Mohamed V University, Rabat, Morocco, iJOE , Vol. 13, No. 9, pp. 1-12.

      [6] Fang S-C. & Chan H-L. (2013), “QRS detection-free electrocardiogram biometrics in the reconstructed phase spaceâ€, Pattern Recognition Letters, Vol. 34, No. 5, pp. 595-602.

      [7] Manal TM, Revett K., Fahmy TM & Salem A-B. (2012), “An evaluation of the generalisability and applicability of the Physionet electrocardiogram (ECG) repository as test cases for ECG-based biometricsâ€, Int. J. Cognitive Biometrics, Vol. 1, No. 1, pp.

      [8] Neural network, Wikipedia, Retrieved from, Available online: http://en.wikipedia.org/wiki/Neural_network.

      [9] Robyn B. & Philippe T., “Demonstration of Artificial Neural Network in Matlabâ€, Texas A&M University, Available online: https://ams.confex.com/ams/pdfpapers/116711

      [10] Artificial neural network, Wikipedia, Retrieved from, Available online: https://en.wikipedia.org/wiki/Artificial_neural_network

      [11] Study and Classification of ECG signals from, Available onlinehttps://www.physionet.org

      [12] Tan X. & LShu. (2014), “Classification of Electrocardiogram signal with RS and Quantum neural networksâ€, International Journal of Multimedia and Ubiquitous Engineering, Vol. 9, No. 2, pp. 363-372.

  • Downloads

  • How to Cite

    Najim, N., & jameel kadhim abed, A. prof. dr. (2018). Electrocardiogram Signals Recognition using Neural Network. International Journal of Engineering & Technology, 7(4), 4116-4121. https://doi.org/10.14419/ijet.v7i4.19245