Research Article
BibTex RIS Cite

Spektral Özellikler ve MFCC Tabanlı Özellikleri Kullanan Klasik Makine Öğrenmesi Metotlarıyla PCG Parça Sınıflandırması

Year 2022, Issue: 42, 77 - 82, 31.10.2022
https://doi.org/10.31590/ejosat.1188483

Abstract

Günümüzde en sık rastlanan hastalıklardan birisi kalp damar rahatsızlıklarıdır. Doğuştan gelen anormallikler, kalp ritminin bozulmasıyla çıkan hastalıklar, damar tıkanıklığı, ameliyat sonrası ortaya çıkan aritmiler, kalp krizleri ve kalp kapacıklarındaki düzensizlikler çeşitli kardiyovasküler hastalıklardan bazılarıdır. Bunların erken fark edilmesi tedavide olumlu sonuçlar almak için oldukça önemlidir. Bu amaçla kalpten gelen sesler dinlenerek kardiyovasküler rahatsızlıkların teşhis ve tanısı yapılmaya çalışılmaktadır. Kalbin ritmik çalışması esnasında kalp odacıklarının kasılıp gevşemesi, kanının kalpten damarlara dolup boşalması kalple özdeşleşen sesleri meydana çıkarır. Kalbin karakteristik seslerinin içinde ise patolojik durumların bir göstergesi olarak hışırtıya benzer sesler duyulur. Hışırtıya benzeyen beklenmedik bu sesler kalp üfürümü olarak adlandırılır. Bu mekanik sesleri mikrofon vasıtasıyla kaydetmek için Fonokardiyograf cihazı kullanılır. Kalpten gelen seslerin alındığı kayıtlarda da fonokardiyogram denilmektedir. Değişken uzunlukta olabilen bu kayıtlardan üfürümü uzman hekimler dinleyerek tespit etmektedir. Ortam gürültüsü, mikrofonun cızırtısı, hastanın nefes alış/veriş sesleri ise bu görevi zorlaştıran etmenlerdir. Makine öğrenmesi, sinyal işleme ve yapay zeka algoritmalarıyla elde edilen bilgisayar destekli sistemler bu konuda uzman hekimlere yardımcı olacak çözümler sunmaktadır. Bu çalışmada PCG kayıtlarının 1 saniye uzunluğunda kesitlere parçalanmasıyla elde edilen eşit uzunluktaki segmentlerinin makine öğrenmesi yöntemleriyle normal veya üfürüm içeren şeklinde sınıflandırılması amaçlandı. Bu amaçla yaygın olarak kullanılan ve meşhur olan C4.5 karar ağacı, Naive Bayes, Destek Vektör Makinaları ve k-en yakın komşu sınıflayıcıları kullanıldı. Özellik olarak da PCG sinyallerinin spektral değerleri, MFCC değerlerinin ortalamaları ve MFCC değerlerinden derin öğrenme ile elde edilen özellikler kullanıldı. Farklı makine öğrenmesi yöntemlerinin performansları doğruluk değerlerine göre karşılaştırıldı.

Supporting Institution

YOK

Project Number

YOK

Thanks

Doktora tez danışmanıma ve ICEANS 2. konferansını düzenlemede emeği geçen herkes teşekkürler

References

  • Khan, M. U., Samer, S., Alshehri, M. D., Baloch, N. K., Khan, H., Hussain, F., ... & Zikria, Y. B. (2022). Artificial neural network-based cardiovascular disease prediction using spectral features. Computers and Electrical Engineering, 101, 108094.
  • Ismail, S., Ismail, B., Siddiqi, I., & Akram, U. (2023). PCG classification through spectrogram using transfer learning. Biomedical Signal Processing and Control, 79, 104075.
  • Arslan, Ö., & Karhan, M. (2022). Effect of Hilbert-Huang transform on classification of PCG signals using machine learning. Journal of King Saud University-Computer and Information Sciences.
  • Chen, Y., Wei, S., & Zhang, Y. (2020). Classification of heart sounds based on the combination of the modified frequency wavelet transform and convolutional neural network. Medical & Biological Engineering & Computing, 58(9), 2039-2047.
  • Varghees, V. N., & Ramachandran, K. I. (2014). A novel heart sound activity detection framework for automated heart sound analysis. Biomedical Signal Processing and Control, 13, 174-188.
  • Goldberger, A. L., Amaral, L. A., Glass, L., Hausdorff, J. M., Ivanov, P. C., Mark, R. G., ... & Stanley, H. E. (2000). PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals. circulation, 101(23), e215-e220.
  • P.C. heart sounds challenge, Peter Bentley, et al., 2011.
  • Potes, C., Parvaneh, S., Rahman, A., & Conroy, B. (2016, September). Ensemble of feature-based and deep learning-based classifiers for detection of abnormal heart sounds. In 2016 computing in cardiology conference (CinC) (pp. 621-624). IEEE.
  • Rath, A., Mishra, D., Panda, G., & Pal, M. (2022). Development and assessment of machine learning based heart disease detection using imbalanced heart sound signal. Biomedical Signal Processing and Control, 76, 103730.
  • Noman, F., Ting, C. M., Salleh, S. H., & Ombao, H. (2019, May). Short-segment heart sound classification using an ensemble of deep convolutional neural networks. In ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 1318-1322). IEEE.
  • Das, S., Pal, S., & Mitra, M. (2022). Deep learning approach of murmur detection using Cochleagram. Biomedical Signal Processing and Control, 77, 103747.
  • Arslan, Ö. (2022). Automated detection of heart valve disorders with time-frequency and deep features on PCG signals. Biomedical Signal Processing and Control, 78, 103929.
  • Chowdhury, T. H., Poudel, K. N., & Hu, Y. (2020). Time-frequency analysis, denoising, compression, segmentation, and classification of PCG signals. IEEE Access, 8, 160882-160890.
  • Langley, P., & Murray, A. (2017). Heart sound classification from unsegmented phonocardiograms. Physiological measurement, 38(8), 1658.
  • Liu, C., Springer, D., Li, Q., Moody, B., Juan, R. A., Chorro, F. J., ... & Clifford, G. D. (2016). An open access database for the evaluation of heart sound algorithms. Physiological measurement, 37(12), 2181.
  • Oliveira, J., Renna, F., Costa, P., Nogueira, M., Oliveira, A. C., Elola, A., ... & Coimbra, M. The CirCor DigiScope Phonocardiogram Dataset.
  • Ismail, S., Siddiqi, I., & Akram, U. (2018). Localization and classification of heart beats in phonocardiography signals—a comprehensive review. EURASIP Journal on Advances in Signal Processing, 2018(1), 1-27.
  • Witten, I. H., Frank, E., Hall, M. A., Pal, C. J., & DATA, M. (2005, June). Practical machine learning tools and techniques. In Data Mining (Vol. 2, No. 4).

PCG Frame Classification by Classical Machine Learning Methods Using Spectral Features and MFCC Based Features

Year 2022, Issue: 42, 77 - 82, 31.10.2022
https://doi.org/10.31590/ejosat.1188483

Abstract

Cardiovascular diseases are some of the most common diseases today. Congenital abnormalities, diseases caused by impaired heart rhythm, vascular occlusion, post-operation arrhythmias, heart attacks and irregularities in heart valves are some of the various cardiovascular diseases. Early recognition of them is very important for obtaining positive results in treatment. For this purpose, it is tried to diagnose and detect cardiovascular diseases by listening to the sounds coming from the heart. During the rhythmic work of the heart, the contraction and relaxation of the heart chambers and the filling and discharge of blood from the heart into the veins create the sounds that are identified with the heart. Among the characteristic sounds of the heart, there can be some sounds similar to rustling which are indicators of pathological conditions. These unexpected sounds, similar to rustling, are called heart murmurs. Phonocardiograph device is used to record these mechanical sounds via microphone. Heart sounds recordings captured by a phonocardiograph device are called phonocardiograms (PCGs). Expert physicians try to detect the heart murmurs by listening to the heart sounds and examining PCGs. Ambient noise, the squeak of the microphone, and the patient's breathing sounds are the factors that make this task more difficult and challenging. Computer-aided systems supported with machine learning, signal processing and artificial intelligence algorithms offer solutions to help physicians in this regard. In this study, detection of heart murmur from PCG frames was examined. PCG frames of equal length, obtained by fragmenting the PCG recordings into 1-second-long frames, were classified by widely used machine learning methods namely C4.5 decision tree, Naive Bayes, Support Vector Machines and k-nearest neighbor. To train those classifiers we used spectral features of PCG signals, averages of MFCC values and some refined features obtained from a deep learning model which was inputted MFCC values. At the end of this manuscript the accuracies of those machine learning methods were compared.

Project Number

YOK

References

  • Khan, M. U., Samer, S., Alshehri, M. D., Baloch, N. K., Khan, H., Hussain, F., ... & Zikria, Y. B. (2022). Artificial neural network-based cardiovascular disease prediction using spectral features. Computers and Electrical Engineering, 101, 108094.
  • Ismail, S., Ismail, B., Siddiqi, I., & Akram, U. (2023). PCG classification through spectrogram using transfer learning. Biomedical Signal Processing and Control, 79, 104075.
  • Arslan, Ö., & Karhan, M. (2022). Effect of Hilbert-Huang transform on classification of PCG signals using machine learning. Journal of King Saud University-Computer and Information Sciences.
  • Chen, Y., Wei, S., & Zhang, Y. (2020). Classification of heart sounds based on the combination of the modified frequency wavelet transform and convolutional neural network. Medical & Biological Engineering & Computing, 58(9), 2039-2047.
  • Varghees, V. N., & Ramachandran, K. I. (2014). A novel heart sound activity detection framework for automated heart sound analysis. Biomedical Signal Processing and Control, 13, 174-188.
  • Goldberger, A. L., Amaral, L. A., Glass, L., Hausdorff, J. M., Ivanov, P. C., Mark, R. G., ... & Stanley, H. E. (2000). PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals. circulation, 101(23), e215-e220.
  • P.C. heart sounds challenge, Peter Bentley, et al., 2011.
  • Potes, C., Parvaneh, S., Rahman, A., & Conroy, B. (2016, September). Ensemble of feature-based and deep learning-based classifiers for detection of abnormal heart sounds. In 2016 computing in cardiology conference (CinC) (pp. 621-624). IEEE.
  • Rath, A., Mishra, D., Panda, G., & Pal, M. (2022). Development and assessment of machine learning based heart disease detection using imbalanced heart sound signal. Biomedical Signal Processing and Control, 76, 103730.
  • Noman, F., Ting, C. M., Salleh, S. H., & Ombao, H. (2019, May). Short-segment heart sound classification using an ensemble of deep convolutional neural networks. In ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 1318-1322). IEEE.
  • Das, S., Pal, S., & Mitra, M. (2022). Deep learning approach of murmur detection using Cochleagram. Biomedical Signal Processing and Control, 77, 103747.
  • Arslan, Ö. (2022). Automated detection of heart valve disorders with time-frequency and deep features on PCG signals. Biomedical Signal Processing and Control, 78, 103929.
  • Chowdhury, T. H., Poudel, K. N., & Hu, Y. (2020). Time-frequency analysis, denoising, compression, segmentation, and classification of PCG signals. IEEE Access, 8, 160882-160890.
  • Langley, P., & Murray, A. (2017). Heart sound classification from unsegmented phonocardiograms. Physiological measurement, 38(8), 1658.
  • Liu, C., Springer, D., Li, Q., Moody, B., Juan, R. A., Chorro, F. J., ... & Clifford, G. D. (2016). An open access database for the evaluation of heart sound algorithms. Physiological measurement, 37(12), 2181.
  • Oliveira, J., Renna, F., Costa, P., Nogueira, M., Oliveira, A. C., Elola, A., ... & Coimbra, M. The CirCor DigiScope Phonocardiogram Dataset.
  • Ismail, S., Siddiqi, I., & Akram, U. (2018). Localization and classification of heart beats in phonocardiography signals—a comprehensive review. EURASIP Journal on Advances in Signal Processing, 2018(1), 1-27.
  • Witten, I. H., Frank, E., Hall, M. A., Pal, C. J., & DATA, M. (2005, June). Practical machine learning tools and techniques. In Data Mining (Vol. 2, No. 4).
There are 18 citations in total.

Details

Primary Language English
Subjects Engineering
Journal Section Articles
Authors

Ali Fatih Gündüz 0000-0002-3838-6813

Fatih Talu 0000-0003-1166-8404

Project Number YOK
Early Pub Date October 25, 2022
Publication Date October 31, 2022
Published in Issue Year 2022 Issue: 42

Cite

APA Gündüz, A. F., & Talu, F. (2022). PCG Frame Classification by Classical Machine Learning Methods Using Spectral Features and MFCC Based Features. Avrupa Bilim Ve Teknoloji Dergisi(42), 77-82. https://doi.org/10.31590/ejosat.1188483