A New Method to Improve Automated Classification of Heart Sound Signals: Filter Bank Learning in Convolutional Neural Networks

Document Type : Original Paper


Department of Biomedical Engineering, Iranian Research Organization for Science and Technology, Tehran, Iran


Introduction: Recent studies have acknowledged the potential of convolutional neural networks (CNNs) in distinguishing healthy and morbid samples by using heart sound analyses. Unfortunately the performance of CNNs is highly dependent on the filtering procedure which is applied to signal in their convolutional layer. The present study aimed to address this problem by applying filter bank learning concept in CNNs.
Material and Methods: In proposed method, the filter bank of CNN is updated based on a cross-entropy minimization rule to extract higher-level features from spectral characteristics of the heart sound signal. The deeper level of the extracted features in parallel with their spectral-based nature leads to better discrimination between healthy and morbid heart sounds. The proposed method was applied to three different heart sound datasets of PASCAL-A, PASCAL-B, and Kaggle, including normal and abnormal categories.
Results: The proposed method obtained a true positive rate (TPR) between minimally 86% and maximally 96% (if FPR=0%) among all the examined datasets. In addition, the false-positive rate (FPR) was obtained as 7-8% (if TPR=100%) among the mentioned datasets. Finally, the accuracy was achieved in the range of 93-98% when the FPR was 0% and within the range of 96-96.5% when the TRP was 100%.
Conclusion: Increased TPR in the proposed method (96% for the proposed method vs. 87% for CNN) in parallel with a decrease in its FPR (7% for the proposed method vs. 10% for CNN) showed the proposed method's superiority against its well-known alternative in automated self-assessment of the heart.


Main Subjects


    1. Brown EM. Heart sounds made easy. Elsevier Health Sciences. 2008.
    2. Wilkins R, Hodgkin J, Lopez B. Fundamentals of Lung and Heart Sounds, 3/e (Book and CD-ROM). CV Mosby. 2004.
    3. Feigen LP. Physical characteristics of sound and hearing. The American journal of cardiology. 1971;28(2):130-3.
    4. Thiyagaraja SR, Dantu R, Shrestha PL, Chitnis A, Thompson MA, Anumandla PT, Sarma T, Dantu S. A novel heart-mobile interface for detection and classification of heart sounds. Biomedical Signal Processing and Control. 2018; 45:313-24.
    5. Avendano-Valencia LD, Godino-Llorente JI, Blanco-Velasco M, Castellanos-Dominguez G. Feature extraction from parametric time–frequency representations for heart murmur detection. Annals of Biomedical Engineering. 2010;38(8):2716-32.
    6. Patidar S, Pachori RB, Garg N. Automatic diagnosis of septal defects based on tunable-Q wavelet transform of cardiac sound signals. Expert Systems with Applications. 2015;42(7):3315-26.
    7. Zheng Y, Guo X, Ding X. A novel hybrid energy fraction and entropy-based approach for systolic heart murmurs identification. Expert Systems with Applications. 2015;42(5):2710-21.
    8. SaraçOğLu R. Hidden Markov model-based classification of heart valve disease with PCA for dimension reduction. Engineering Applications of Artificial Intelligence. 2012 ;25(7):1523-8.
    9. Potes C, Parvaneh S, Rahman A, Conroy B. Ensemble of feature-based and deep learning-based classifiers for detection of abnormal heart sounds. In2016 Computing in Cardiology Conference (CinC). IEEE. 2016; 621-4.
    10. Rubin J, Abreu R, Ganguli A, Nelaturi S, Matei I, Sricharan K. Classifying heart sound recordings using deep convolutional neural networks and mel-frequency cepstral coefficients. In2016 Computing in cardiology conference (CinC). IEEE. 2016; 813-6.
    11. Dauphin YN, Pascanu R, Gulcehre C, Cho K, Ganguli S, Bengio Y. Identifying and attacking the saddle point problem in high-dimensional non-convex optimization. InAdvances in neural information processing systems. 2014; 2933-41.
    12. Pascanu R, Dauphin YN, Ganguli S, Bengio Y. On the saddle point problem for non-convex optimization. arXiv preprint arXiv:1405.4604. 2014. 
    13. Allahverdi N, Altan G, Kutlu Y. Diagnosis of Coronary Artery Disease Using Deep Belief Networks. 2 Int Conf Eng Nat Sci, Sarajevo, Bosnia. 2016;40-6.
    14. Bengio Y. Learning deep architectures for AI. Now Publishers Inc; 2009.
    15. Stutz  D. Understanding convolutional neural networks. In Seminar Report, Fakultät für Mathematik, Informatik und Naturwissenschaften Lehr-und Forschungsgebiet Informatik VIII Computer Vision. 2014.
    16. Ruder S. An overview of gradient descent optimization algorithms. arXiv preprint arXiv:1609.04747. 2016.
    17. Bentley P, Nordehn G, Coimbra M, Mannor S, Getz R. Classifying heart sounds challenge. Retrieved from Classifying Heart Sounds Challenge: http://www. peterjbentley. com/heartchallenge. 2011 Nov.
    18. Kaggle, heart sound signals. https://www.kaggle.com/sachinvernekar
    19. Nilanon T, Yao J, Hao J, Purushotham S, Liu Y. Normal/abnormal heart sound recordings classification using convolutional neural network. In2016 Computing in Cardiology Conference (CinC). IEEE. 2016; 585-8.
    20. Lifu K, Weilian W. Heart sound signals based on CNN classification research. InProceedings of the 6th International Conference on Bioinformatics and Biomedical Science. 2017; 44-8
    21. Georgoulas G, Stylios D, Groumpos P. Predicting the risk of metabolic acidosis for newborns based on fetal heart rate signal classification using support vector machines. IEEE Transactions on biomedical engineering. 2006;53(5):875-84.
    22. Dash S, Quirk JG, Djurić PM. Fetal heart rate classification using generative models. IEEE Transactions on Biomedical Engineering. 2014; 61(11):2796-805.
    23. [23]         Bonomi AG, Schipper F, Eerikäinen LM, Margarito J, Van Dinther R, Muesch G, et al. Atrial Fibrillation Detection Using a Novel Cardiac Ambulatory Monitor Based on Photo‐Plethysmography at the Wrist. Journal of the American Heart Association. 2018;7(15):e009351.
    24. Poddar MG, Birajdar AC, Virmani J. Automated classification of hypertension and coronary artery disease patients by PNN, KNN, and SVM classifiers using HRV analysis. InMachine Learning in Bio-Signal Analysis and Diagnostic Imaging; Academic Press. 2019; 99-125.
Volume 17, Issue 5
September and October 2020
Pages 331-339
  • Receive Date: 05 March 2019
  • Revise Date: 26 October 2019
  • Accept Date: 28 October 2019