Dergiler / Bilgisayar Bilimleri / 2026 / Cilt: 5 Sayı: 1

Heart Sound Classification for Murmur Abnormality Detection Using an Ensemble Approach Based on Traditional Classifiers and Feature Sets

Ali Fatih Gündüz(MALATYA TURGUT ÖZAL ÜNİVERSİTESİ, AKÇADAĞ MESLEK YÜKSEKOKULU)
Ali Karci(INONU UNIVERSITY)
Sayfa
1–13
Yayın Tarihi
2020-06-01
DOI
—
🏛️Bu makalenin bibliyografik verileri ve tam metin bağlantısı DergiPark üzerinden sağlanmıştır.
DergiPark Kaydı ↗
✨

Yapay Zeka Hızlı Bakış & Çıkarımlar

AI Insight
⚡ TL;DR(1 Cümlede Hızlı Çıkarım)

Classification performances of singular classifiers, single level ensemble classifiers and final ensemble classifier are compared and better results are obtained by the proposed method.

📌 3 Maddede Bu Makale

🎯
Amaç & Hipotez:Abstract— Phonocardiography (PCG) is a method based on examination of mechanical sounds coming from heart during its regular contraction/relaxation activities such as opening and closing of the valves and blood turbulence towards vessels and heart chambers.
📊
Temel Bulgular & Veri:Those features are used to form three separate feature vectors.
💡
Sonuç & Katkı:Classification performances of singular classifiers, single level ensemble classifiers and final ensemble classifier are compared and better results are obtained by the proposed method.
🔬Tür:Modelleme & Sayısal Simülasyon
📍Kapsam:Genişletilmiş Akademik Örneklem
⚙️Değişkenler:signal processing · data mining · classification

Özet

Abstract— Phonocardiography (PCG) is a method based on examination of mechanical sounds coming from heart during its regular contraction/relaxation activities such as opening and closing of the valves and blood turbulence towards vessels and heart chambers. The heart sounds in some pathological cases contains a noise called as heart murmurs. Thanks to auscultation and investigation of the heart sounds, many cardiac disorders can be a preliminarily diagnosed. Today there are high technology tools to record those sounds in electronic environment and enable us to analyze them in detail. The constraints such as human’s limited audible range, environment noise and inexperience of physicians can be overcome by the use of those tools and development of state-of-art signal processing and machine learning methods. There are possible benefits of those analyses ranging from its use at home-care units to rural areas where it is difficult to consult experienced physicians. In this study we examined heart sounds and classified them as normal or abnormal. Features of heart sounds are extracted by using Discrete Wavelet Transform (DWT), Mel-Frequency Cepstral Coefficients (MFCC) and time-domain morphological characteristics of the signals. Those features are used to form three separate feature vectors. K-Nearest Neighbor (kNN), Support Vector Machine (SVM), Multilayer Perceptron (MLP) classifiers and their ensembles are used for classification. Then the ensemble classifiers’ predictions based on distinct feature vectors are combined and an ensemble classifier built from team of ensemble classifiers. Classification performances of singular classifiers, single level ensemble classifiers and final ensemble classifier are compared and better results are obtained by the proposed method.

Abstract

Abstract— Phonocardiography (PCG) is a method based on examination of mechanical sounds coming from heart during its regular contraction/relaxation activities such as opening and closing of the valves and blood turbulence towards vessels and heart chambers. The heart sounds in some pathological cases contains a noise called as heart murmurs. Thanks to auscultation and investigation of the heart sounds, many cardiac disorders can be a preliminarily diagnosed. Today there are high technology tools to record those sounds in electronic environment and enable us to analyze them in detail. The constraints such as human’s limited audible range, environment noise and inexperience of physicians can be overcome by the use of those tools and development of state-of-art signal processing and machine learning methods. There are possible benefits of those analyses ranging from its use at home-care units to rural areas where it is difficult to consult experienced physicians. In this study we examined heart sounds and classified them as normal or abnormal. Features of heart sounds are extracted by using Discrete Wavelet Transform (DWT), Mel-Frequency Cepstral Coefficients (MFCC) and time-domain morphological characteristics of the signals. Those features are used to form three separate feature vectors. K-Nearest Neighbor (kNN), Support Vector Machine (SVM), Multilayer Perceptron (MLP) classifiers and their ensembles are used for classification. Then the ensemble classifiers’ predictions based on distinct feature vectors are combined and an ensemble classifier built from team of ensemble classifiers. Classification performances of singular classifiers, single level ensemble classifiers and final ensemble classifier are compared and better results are obtained by the proposed method.

🔖

Bu Makaleye Atıf Yap

Gündüz, A. F., Karci, A. (2020). Heart Sound Classification for Murmur Abnormality Detection Using an Ensemble Approach Based on Traditional Classifiers and Feature Sets. Bilgisayar Bilimleri, Cilt: 5 Sayı: 1, 1–13. https://ajindex.com/articles/1464347

📄 Tam Metin PDF Okuyucu

📄

PDF görüntüleyici hazırlanıyor...

Kaynakça (98)

  1. WHO.2017 world statistics on cardiovascular disease. URL
  2. Arslan, Ayse, and Oktay Yildiz. "Automated Auscultative Diagnosis System for Evaluation of Phonocardiogram Signals Associated with Heart Murmur Diseases." Gazi University Journal of Science 31.1 (2018): 112-124
  3. Thompson, W. Reid, et al. "Artificial intelligence-assisted auscultation of heart murmurs: validation by virtual clinical trial." Pediatric cardiology 40.3 (2019): 623-629
  4. Delgado-Trejos, Edilson, et al. "Digital auscultation analysis for heart murmur detection." Annals of biomedical engineering 37.2 (2009): 337-353
  5. El-Segaier, Milad, et al. "Computer-based detection and analysis of heart sound and murmur." Annals of Biomedical Engineering 33.7 (2005): 937-942
  6. Balili CC, Sobrepena M, Naval PC, Classification of heart sounds using discrete and continuous wavelet transform and random forests. In 3rd IAPR Asian Conference on Pattern Recognition, Kuala Lumpur, 2015
  7. Potes, Cristhian, et al. "Ensemble of feature-based and deep learning-based classifiers for detection of abnormal heart sounds." 2016 Computing in Cardiology Conference (CinC). IEEE, 2016
  8. Zabihi, Morteza, et al. "Heart sound anomaly and quality detection using ensemble of neural networks without segmentation." 2016 Computing in Cardiology Conference (CinC). IEEE, 2016
  9. Kay, Edmund, and Anurag Agarwal. "Dropconnected neural network trained with diverse features for classifying heart sounds." 2016 Computing in Cardiology Conference (CinC). IEEE, 2016
  10. Clifford, Gari D., et al. "Classification of normal/abnormal heart sound recordings: The PhysioNet/Computing in Cardiology Challenge 2016." 2016 Computing in Cardiology Conference (CinC). IEEE, 2016
  11. Quiceno-Manrique, A. F., et al. "Selection of dynamic features based on time{frequency representations for heart murmur detection from phonocardiographic signals." Annals of biomedical engineering 38.1 (2010): 118-137
  12. Dokur, Zümray, and Tamer Olmez. "Feature determination for heart sounds based on divergence analysis." Digital Signal Processing 19.3 (2009): 521-531
  13. Chakrabarti, Tamal, et al. "Phonocardiogram signal analysis-practices, trends and challenges: A critical review." 2015 International conference and workshop on computing and communication (IEMCON). IEEE, 2015
  14. Silverman, Mark E., and Charles F. Wooley. "Samuel A. Levine and the history of grading systolic murmurs." The American journal of cardiology 102.8 (2008): 1107-1110
  15. Bozkurt, Baris, Ioannis Germanakis, and Yannis Stylianou. "A study of time-frequency features for CNN-based automatic heart sound classification for pathology detection." Computers in biology and medicine 100 (2018): 132-143
  16. Hanbay, Davut. "An expert system based on least square support vector machines for diagnosis of the valvular heart disease." Expert Systems with Applications 36.3 (2009): 4232-4238
  17. Munia, Tamanna TK, et al. "Heart sound classification from wavelet decomposed signal using morphological and statistical features." 2016 Computing in Cardiology Conference (CinC). IEEE, 2016
  18. Koçyiğit, Yücel. "Heart sound signal classification using fast independent component analysis." Turkish Journal of Electrical Engineering & Computer Sciences 24.4 (2016): 2949-2960
  19. Uzunhisarcikli, Esma. "Nonlinear dynamic analysis of mitral valve doppler signals: surrogate data analysis." Turkish Journal of Electrical Engineering & Computer Sciences 18.2 (2010): 327-337
  20. Das, Sangita, Saurabh Pal, and Madhuchhanda Mitra. "Supervised model for Cochleagram feature based fundamental heart sound identification." Biomedical Signal Processing and Control 52 (2019): 32-40
  21. Springer DB, Tarassenko L, Clifford GD. Logistic regression-HSMM-based heart sound segmentation. IEEE Transactions on Biomedical Engineering 2016;63(4):822{832
  22. Zhang D, He J, Jiang Y, Du M. Analysis and classification of heart sounds with mechanical prosthetic heart valves based on Hilbert-Huang transform. International Journal of Cardiology2011;151(1):126{127
  23. Kao WC, Wei CC. Automatic phonocardiograph signal analysis for detecting heart valve disorders. Expert Systems with Applications 2011;38(6):6458{68
  24. Yuenyong S, Nishihara A, Kongprawechnon W, Tungpimolrut K. A framework for automatic heart sound analysis without segmentation. In BioMedical Engineering OnLine, 2011; 10-13
  25. Deng SW, Han JQ. Towards heart sound classification without segmentation via autocorrelation feature and diffusion maps. Future Generation Computer Systems 2016;60:13{21
  26. Liu C, Springer D, Li Q, Moody B, Juan RA, Chorro FJ, Castells F, Roig JM, Silva I, Johnson AE, Syed Z, Schmidt SE, Papadaniil CD, Hadjileontiadis L, Naseri H, Moukadem A, Dieterlen A, Brandt C, Tang H, Samieinasab M, Samieinasab MR, Sameni R, Mark RG, Clifford GD. An open access database for the evaluation of heart sound algorithms. Physiological Measurement 2016;37(9)
  27. Naseri, H., and M. R. Homaeinezhad. "Detection and boundary identification of phonocardiogram sounds using an expert frequency-energy based metric." Annals of biomedical engineering 41.2 (2013): 279-292
  28. Gharehbaghi, Arash, et al. "A novel method for discrimination between innocent and pathological heart murmurs." Medical engineering & physics 37.7 (2015): 674-682
  29. Cömert, Zafer, and Adnan Fatih Kocamaz. "Evaluation of fetal distress diagnosis during delivery stages based on linear and nonlinear features of fetal heart rate for neural network community." Int. J. Comput. Appl. 156.4 (2016): 26-31
  30. Ahlstrom, Christer, et al. "Feature extraction for systolic heart murmur classification." Annals of biomedical engineering 34.11 (2006): 1666-1677
  31. PhysioNet. Classification of normal/abnormal heart sound recordings: the PhysioNet/Computing in Cardiology Challenge 2016[internet].PhysioNet; 2016. Available from
  32. Karci, Ali. "Fractional order entropy: New perspectives." Optik 127.20 (2016): 9172-9177
  33. Homsi, Masun Nabhan, et al. "Automatic heart sound recording classification using a nested set of ensemble algorithms." 2016 Computing in Cardiology Conference (CinC). IEEE, 2016
  34. Huang X, Acero A, Hon HW. Spoken Language Processing. A Guide to Theory, Algorithm, and System Development. Prentice Hall, 2001
  35. Antony, Anett, and R. Gopikakumari. "Speaker identification based on combination of MFCC and UMRT based features." Procedia computer science 143 (2018): 250-257
  36. Tuğal, Ihsan, and Ali Karcı. "Comparisons of Karcı and Shannon entropies and their effects on centrality of social networks." Physica A: Statistical Mechanics and its Applications 523 (2019): 352-363
  37. Eibe Frank, Mark A. Hall, and Ian H. Witten (2016). The WEKA Workbench. Online Appendix for "Data Mining: Practical Machine Learning Tools and Techniques", Morgan Kaufmann, Fourth Edition, 2016
  38. J. Kittler, M. Hatef, Robert P.W. Duin, J. Matas (1998). On combining classifiers. IEEE Transactions on Pattern Analysis and Machine Intelligence. 20(3):226-239
  39. Mondejar-Guerra, V., et al. "Heartbeat classification fusing temporal and morphological information of ECGs via ensemble of classifiers." Biomedical Signal Processing and Control 47 (2019): 41-48
  40. Ludmila I. Kuncheva (2004). Combining Pattern Classifiers: Methods and Algorithms. John Wiley and Sons, Inc
  41. Aha, David W., Dennis Kibler, and Marc K. Albert. "Instance-based learning algorithms." Machine learning 6.1 (1991): 37-66
  42. J. C. Platt, Advances in Kernel Methods: Support Vector Machines, B. Schölkopf, C. Burges, and A. Smola, Eds. Cambridge, MA: MIT Press, Dec. 1998. Fast training of support vector machines using sequential minimal optimization
  43. Shevade, Shirish K., et al. "Improvements to the SMO algorithm for SVM regression." IEEE transactions on neural networks 11.5 (2000): 1188-1193
  44. Keerthi, S. Sathiya, et al. "Improvements to Platt’s SMO algorithm for SVM classifier design." Neural computation 13.3 (2001): 637-649
  45. Trevor Hastie, Robert Tibshirani: Classification by Pairwise Coupling. In: Advances in Neural Information Processing Systems, 1998
  46. Hussain, Muhammad, et al. "A comparison of SVM kernel functions for breast cancer detection." 2011 Eighth International Conference Computer Graphics, Imaging and Visualization. IEEE, 2011
  47. J. Davis and M. Goadrich, \The Relationship Between Precision-Recall and ROC Curves," Proceedings of the 23rd International Conference on Machine Learning, Pittsburgh, 2006
  48. Galdi, Paola, and Roberto Tagliaferri. "Data mining: accuracy and error measures for classification and prediction." Encyclopedia of Bioinformatics and Computational Biology (2018): 431-436
  49. Powers, David Martin. "Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation." (2011)
  50. WHO.2017 world statistics on cardiovascular disease. URL
  51. Arslan, Ayse, and Oktay Yildiz. "Automated Auscultative Diagnosis System for Evaluation of Phonocardiogram Signals Associated with Heart Murmur Diseases." Gazi University Journal of Science 31.1 (2018): 112-124
  52. Thompson, W. Reid, et al. "Artificial intelligence-assisted auscultation of heart murmurs: validation by virtual clinical trial." Pediatric cardiology 40.3 (2019): 623-629
  53. Delgado-Trejos, Edilson, et al. "Digital auscultation analysis for heart murmur detection." Annals of biomedical engineering 37.2 (2009): 337-353
  54. El-Segaier, Milad, et al. "Computer-based detection and analysis of heart sound and murmur." Annals of Biomedical Engineering 33.7 (2005): 937-942
  55. Balili CC, Sobrepena M, Naval PC, Classification of heart sounds using discrete and continuous wavelet transform and random forests. In 3rd IAPR Asian Conference on Pattern Recognition, Kuala Lumpur, 2015
  56. Potes, Cristhian, et al. "Ensemble of feature-based and deep learning-based classifiers for detection of abnormal heart sounds." 2016 Computing in Cardiology Conference (CinC). IEEE, 2016
  57. Zabihi, Morteza, et al. "Heart sound anomaly and quality detection using ensemble of neural networks without segmentation." 2016 Computing in Cardiology Conference (CinC). IEEE, 2016
  58. Kay, Edmund, and Anurag Agarwal. "Dropconnected neural network trained with diverse features for classifying heart sounds." 2016 Computing in Cardiology Conference (CinC). IEEE, 2016
  59. Clifford, Gari D., et al. "Classification of normal/abnormal heart sound recordings: The PhysioNet/Computing in Cardiology Challenge 2016." 2016 Computing in Cardiology Conference (CinC). IEEE, 2016
  60. Quiceno-Manrique, A. F., et al. "Selection of dynamic features based on time{frequency representations for heart murmur detection from phonocardiographic signals." Annals of biomedical engineering 38.1 (2010): 118-137
  61. Dokur, Zümray, and Tamer Olmez. "Feature determination for heart sounds based on divergence analysis." Digital Signal Processing 19.3 (2009): 521-531
  62. Chakrabarti, Tamal, et al. "Phonocardiogram signal analysis-practices, trends and challenges: A critical review." 2015 International conference and workshop on computing and communication (IEMCON). IEEE, 2015
  63. Silverman, Mark E., and Charles F. Wooley. "Samuel A. Levine and the history of grading systolic murmurs." The American journal of cardiology 102.8 (2008): 1107-1110
  64. Bozkurt, Baris, Ioannis Germanakis, and Yannis Stylianou. "A study of time-frequency features for CNN-based automatic heart sound classification for pathology detection." Computers in biology and medicine 100 (2018): 132-143
  65. Hanbay, Davut. "An expert system based on least square support vector machines for diagnosis of the valvular heart disease." Expert Systems with Applications 36.3 (2009): 4232-4238
  66. Munia, Tamanna TK, et al. "Heart sound classification from wavelet decomposed signal using morphological and statistical features." 2016 Computing in Cardiology Conference (CinC). IEEE, 2016
  67. Koçyiğit, Yücel. "Heart sound signal classification using fast independent component analysis." Turkish Journal of Electrical Engineering & Computer Sciences 24.4 (2016): 2949-2960
  68. Uzunhisarcikli, Esma. "Nonlinear dynamic analysis of mitral valve doppler signals: surrogate data analysis." Turkish Journal of Electrical Engineering & Computer Sciences 18.2 (2010): 327-337
  69. Das, Sangita, Saurabh Pal, and Madhuchhanda Mitra. "Supervised model for Cochleagram feature based fundamental heart sound identification." Biomedical Signal Processing and Control 52 (2019): 32-40
  70. Springer DB, Tarassenko L, Clifford GD. Logistic regression-HSMM-based heart sound segmentation. IEEE Transactions on Biomedical Engineering 2016;63(4):822{832
  71. Zhang D, He J, Jiang Y, Du M. Analysis and classification of heart sounds with mechanical prosthetic heart valves based on Hilbert-Huang transform. International Journal of Cardiology2011;151(1):126{127
  72. Kao WC, Wei CC. Automatic phonocardiograph signal analysis for detecting heart valve disorders. Expert Systems with Applications 2011;38(6):6458{68
  73. Yuenyong S, Nishihara A, Kongprawechnon W, Tungpimolrut K. A framework for automatic heart sound analysis without segmentation. In BioMedical Engineering OnLine, 2011; 10-13
  74. Deng SW, Han JQ. Towards heart sound classification without segmentation via autocorrelation feature and diffusion maps. Future Generation Computer Systems 2016;60:13{21
  75. Liu C, Springer D, Li Q, Moody B, Juan RA, Chorro FJ, Castells F, Roig JM, Silva I, Johnson AE, Syed Z, Schmidt SE, Papadaniil CD, Hadjileontiadis L, Naseri H, Moukadem A, Dieterlen A, Brandt C, Tang H, Samieinasab M, Samieinasab MR, Sameni R, Mark RG, Clifford GD. An open access database for the evaluation of heart sound algorithms. Physiological Measurement 2016;37(9)
  76. Naseri, H., and M. R. Homaeinezhad. "Detection and boundary identification of phonocardiogram sounds using an expert frequency-energy based metric." Annals of biomedical engineering 41.2 (2013): 279-292
  77. Gharehbaghi, Arash, et al. "A novel method for discrimination between innocent and pathological heart murmurs." Medical engineering & physics 37.7 (2015): 674-682
  78. Cömert, Zafer, and Adnan Fatih Kocamaz. "Evaluation of fetal distress diagnosis during delivery stages based on linear and nonlinear features of fetal heart rate for neural network community." Int. J. Comput. Appl. 156.4 (2016): 26-31
  79. Ahlstrom, Christer, et al. "Feature extraction for systolic heart murmur classification." Annals of biomedical engineering 34.11 (2006): 1666-1677
  80. PhysioNet. Classification of normal/abnormal heart sound recordings: the PhysioNet/Computing in Cardiology Challenge 2016[internet].PhysioNet; 2016. Available from
  81. Karci, Ali. "Fractional order entropy: New perspectives." Optik 127.20 (2016): 9172-9177
  82. Homsi, Masun Nabhan, et al. "Automatic heart sound recording classification using a nested set of ensemble algorithms." 2016 Computing in Cardiology Conference (CinC). IEEE, 2016
  83. Huang X, Acero A, Hon HW. Spoken Language Processing. A Guide to Theory, Algorithm, and System Development. Prentice Hall, 2001
  84. Antony, Anett, and R. Gopikakumari. "Speaker identification based on combination of MFCC and UMRT based features." Procedia computer science 143 (2018): 250-257
  85. Tuğal, Ihsan, and Ali Karcı. "Comparisons of Karcı and Shannon entropies and their effects on centrality of social networks." Physica A: Statistical Mechanics and its Applications 523 (2019): 352-363
  86. Eibe Frank, Mark A. Hall, and Ian H. Witten (2016). The WEKA Workbench. Online Appendix for "Data Mining: Practical Machine Learning Tools and Techniques", Morgan Kaufmann, Fourth Edition, 2016
  87. J. Kittler, M. Hatef, Robert P.W. Duin, J. Matas (1998). On combining classifiers. IEEE Transactions on Pattern Analysis and Machine Intelligence. 20(3):226-239
  88. Mondejar-Guerra, V., et al. "Heartbeat classification fusing temporal and morphological information of ECGs via ensemble of classifiers." Biomedical Signal Processing and Control 47 (2019): 41-48
  89. Ludmila I. Kuncheva (2004). Combining Pattern Classifiers: Methods and Algorithms. John Wiley and Sons, Inc
  90. Aha, David W., Dennis Kibler, and Marc K. Albert. "Instance-based learning algorithms." Machine learning 6.1 (1991): 37-66
  91. J. C. Platt, Advances in Kernel Methods: Support Vector Machines, B. Schölkopf, C. Burges, and A. Smola, Eds. Cambridge, MA: MIT Press, Dec. 1998. Fast training of support vector machines using sequential minimal optimization
  92. Shevade, Shirish K., et al. "Improvements to the SMO algorithm for SVM regression." IEEE transactions on neural networks 11.5 (2000): 1188-1193
  93. Keerthi, S. Sathiya, et al. "Improvements to Platt’s SMO algorithm for SVM classifier design." Neural computation 13.3 (2001): 637-649
  94. Trevor Hastie, Robert Tibshirani: Classification by Pairwise Coupling. In: Advances in Neural Information Processing Systems, 1998
  95. Hussain, Muhammad, et al. "A comparison of SVM kernel functions for breast cancer detection." 2011 Eighth International Conference Computer Graphics, Imaging and Visualization. IEEE, 2011
  96. J. Davis and M. Goadrich, \The Relationship Between Precision-Recall and ROC Curves," Proceedings of the 23rd International Conference on Machine Learning, Pittsburgh, 2006
  97. Galdi, Paola, and Roberto Tagliaferri. "Data mining: accuracy and error measures for classification and prediction." Encyclopedia of Bioinformatics and Computational Biology (2018): 431-436
  98. Powers, David Martin. "Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation." (2011).