Towards the classification of heart sounds based on convolutional deep neural network

  • Fatih Demir
  • Abdulkadir Şengür
  • Varun Bajaj
  • Kemal PolatEmail author
Part of the following topical collections:
  1. Special Issue on Artificial Intelligence in Health Informatics


Background and objective

Heart sound contains various important quantities that help early detection of heart diseases. Many methods have been proposed so far where various signal-processing techniques have been used on heart sounds for heart disease detection.


In this paper, a methodology is introduced for heart disease detection based on heart sounds. The proposed method employs three successive stages, such as spectrogram generation, deep feature extraction, and classification. In the spectrogram generation stage, the heart sounds are converted to spectrogram images by using time–frequency transformation.


The deep features are extracted from three different pre-trained convolutional neural network models such as AlexNet, VGG16, and VGG19. Support vector machine classifier is used in the third stage of the proposed method. The proposed method is evaluated on two datasets, which are taken from The Classifying Heart Sounds Challenge.


The obtained results are compared with some of the existing methods. The comparisons show that the proposed method outperformed.


Heart sound Convolutional neural network (CNN) Modeling Classification 


Authors contribution

All authors have contributed equally in all the areas such as implementation, paper writing, and experimentations.

Compliance with ethical standards

Conflict of interest

The authors of the paper declare that they have no conflict of interest.


  1. 1.
    Roth GA, Johnson C, Abajobir A, Abd-Allah F, Abyu G, et al. Global, regional, and national burden of cardiovascular diseases for 10 causes, 1990 to 2015. J Am Coll Cardiol. 2017;70(1):1–25. Scholar
  2. 2.
    Mozaffarian D, Benjamin EJ, Go AS, Arnett DK, Blaha MJ, et al. Heart disease and stroke statistics—2016 update a report from the American Heart Association. Circulation. 2016;133(4):38–48. Scholar
  3. 3.
    Wang Y, Li W, Zhou J, Li X, Pu Y. Identification of the normal and abnormal heart sounds using wavelet-time entropy features based on OMS-WPD. Future Gener Comput Syst. 2014;37:488–95. Scholar
  4. 4.
    Roy D, Sargeant J, Gray J, Hoyt B, Allen M, et al. Helping family physicians improve their cardiac auscultation skills with an interactive CD-ROM. J Contin Educ Health Prof Banner. 2002;22(3):152–9. Scholar
  5. 5.
    Etchells E, Bell C, Robb K. Does this patient have an abnormal systolic murmur? JAMA. 1997;277(7):564–71. Scholar
  6. 6.
    Strunic SL, Rios-Guti’errez F, Alba-Flores R, Nordehn G, Bums S, et al. Detection and classification of cardiac murmurs using segmentation techniques and artificial neural networks. In: FLAIRS conference, Honolulu, HI, USA, 2007, pp. 128–33.Google Scholar
  7. 7.
    Ejaz K, Nordehn G, Alba-Flores R, Rios-Guti’errez F, Burns S, et al. A heart murmur detection system using spectrograms and artificial neural networks. In: Circuits, signals, Clearwater Beach, FL, USA, 2004, pp. 374–9.Google Scholar
  8. 8.
    Bentley P, Nordehn G, Coimbra M, Mannor S. The PASCAL Classifying Heart Sounds_Challenge_2011_(CHSC2011)_Results. Accessed Aug 2019.
  9. 9.
    Zhang W, Han J, Deng S. Heart sound classification based on scaled spectrogram and partial least squares regression. Biomed Signal Process Control. 2017;32:20–8. Scholar
  10. 10.
    Dokur Z, Ölmez T. Heart sound classification using wavelet transform and incremental self-organizing map. Digit Signal Process. 2008;18(6):951–9. Scholar
  11. 11.
    Hamidi M, Ghassemian H, Imani M. Classification of heart sound signal using curve fitting and fractal dimension. Biomed Signal Process Control. 2018;39:351–9. Scholar
  12. 12.
    Randhawa K, Singh M. Classification of heart sound signals using multi-modal features. Procedia Comput Sci. 2015;58:165–71. Scholar
  13. 13.
    Dominguez-Morales JP, Jimenez-Fernandez AF, Dominguez-Morales MJ, Jimenez-Moreno G. Deep neural networks for the recognition and classification of heart murmurs using neuromorphic auditory sensors. IEEE Trans Biomed Circuits Syst. 2017;12(1):1–11. Scholar
  14. 14.
    Chen TE, Yang SI, Ho LT, Tsai KH, Chen YH, et al. S1 and S2 heart sound recognition using deep neural networks. IEEE Trans Biomed Eng. 2017;64(2):372–80. Scholar
  15. 15.
    Potes C, Parvaneh S, Rahman A, Conroy B. Ensemble of feature-based and deep learning-based classifiers for detection of abnormal heart sounds. In: Computing in cardiology conference (CinC), Vancouver, BC, Canada, 2016, pp. 621–4.Google Scholar
  16. 16.
    Ohkawa K, Yamashita M, Matsunaga S. Classification between abnormal and normal respiration through observation rate of heart sounds within lung sounds. In: 26th European signal processing conference (EUSIPCO), Rome, Italy, 2016, pp. 1142–6.Google Scholar
  17. 17.
    Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. In: Advances in neural information processing systems, Lake Tahoe, Nevada, USA, 2012, pp. 1097–105.Google Scholar
  18. 18.
    Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. In: ICLR, San Diego, USA, 2015, pp. 1–14.Google Scholar
  19. 19.
    Freitag M, Amiriparian S, Cummins N, Gerczuk M, Schuller B. An ‘End-to-Evolution’ hybrid approach for snore sound classification. In: Interspeech, Stockholm, Sweden, 2017, pp. 3507–11.Google Scholar
  20. 20.
    Amiriparian S, Gerczuk M, Ottl S, Cummins N, Freitag M. Snore sound classification using image-based deep spectrum features. In: Interspeech, Stockholm, Sweden, 2017, pp. 3512–6.Google Scholar
  21. 21.
    Fan RE, Chang KW, Hsieh CJ, Wang XR, Lin CJ. LIBLINEAR: a library for large linear classification. J Mach Learn Res. 2008;9:1871–4.zbMATHGoogle Scholar
  22. 22.
    Vedaldi A, Zisserman A. Efficient additive kernels via explicit feature maps. IEEE Trans Pattern Anal Mach Intell. 2012;34(3):480–92. Scholar
  23. 23.
    Gomes EF, Pereira E. Classifying heart sounds using peak location for segmentation and feature construction. In: Workshop Classifying Heart Sounds, La Palma, Canary Islands, 2012, pp. 480–92.Google Scholar
  24. 24.
    Deng Y, Bentley, PJ. A robust heart sound segmentation and classification algorithm using wavelet decomposition and spectrogram. In: Workshop Classifying Heart Sounds, La Palma, Canary Islands, 2012, pp. 1–6.Google Scholar
  25. 25.
    Deng SW, Han JQ. Towards heart sound classification without segmentation via autocorrelation feature and diffusion maps. Future Gener Comput Syst. 2016;60:13–21. Scholar
  26. 26.
    Avendano-Valencia L, Godino-Llorente J, Blanco-Velasco M. Feature extraction from parametric time–frequency representations for heart murmur detection. Ann Biomed Eng. 2010;38(8):2716–32. Scholar
  27. 27.
    Oliveira SC, Gomes EF, Jorge AM. Heart sounds classification using motif based segmentation. In: International database engineering and applications symposium, Porto, Portugal, 2014, pp. 370–1.Google Scholar
  28. 28.
    Zhang W, Han J, Deng S. Heart sound classification based on scaled spectrogram and tensor decomposition. Expert Syst Appl. 2017;84:220–31. Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Fatih Demir
    • 1
  • Abdulkadir Şengür
    • 1
  • Varun Bajaj
    • 2
  • Kemal Polat
    • 3
    Email author
  1. 1.Electrical and Electronics Engineering, Technology FacultyFirat UniversityElazigTurkey
  2. 2.Discipline of Electronics and Communication EngineeringPDPM Indian Institute of Information Technology, Design and ManufacturingJabalpurIndia
  3. 3.Department of Electrical and Electronics Engineering, Faculty of EngineeringBolu Abant Izzet Baysal UniversityBoluTurkey

Personalised recommendations