Combining Spectral Analysis with Artificial Intelligence in Heart Sound Study

• Autorzy: Kucharski Dariusz , Kajor Marcin , Grochala Dominik , Iwaniec Marek , Iwaniec Joanna

Identyfikatory

DOI

10.12913/22998624/108447

• Języki publikacji: EN

Abstrakty

EN

The auscultation technique has been widely used in medicine as a screening examination for ages. Nowadays, advanced electronics and effective computational methods aim to support the healthcare sector by providing dedicated solutions which help physicians and support diagnostic process. In this paper, we propose a machine learning approach for the analysis of heart sounds. We used the spectral analysis of acoustic signal to calculate feature vectors and tested a set of machine learning approaches to provide the most effective detection of cardiac disorders. Finally, we achieved 91% of sensitivity and 99% of positive predictivity for a designed algorithm based on convolutional neural network.

Słowa kluczowe

EN

deep learning; heart sound classification; convolutional neural network; machine learning; signal processing

PL

uczenie głębokie; klasyfikacja dźwięku serca; splotowa sieć neuronowa; uczenie maszynowe; przetwarzanie sygnałów

• Wydawca: Lublin University of Technology ; Polish Society of Ecological Engineering (PTIE), Branch of PTIE in Lublin
• Czasopismo: Advances in Science and Technology. Research Journal
• Rocznik: 2019
• Tom: Vol. 13, no 2
• Strony: 112--118
• Opis fizyczny: Bibliogr. 9 poz., fig., tab.

Twórcy

autor

Kucharski Dariusz

• Faculty of Electrical Engineering, Automatics, Computer Science and Biomedical Engineering, AGH University of Science and Technology, Al. Mickiewicza 30, 30-059 Kraków, Poland

autor

Kajor Marcin

• Faculty of Electrical Engineering, Automatics, Computer Science and Biomedical Engineering, AGH University of Science and Technology, Al. Mickiewicza 30, 30-059 Kraków, Poland

autor

Grochala Dominik

• Faculty of Electrical Engineering, Automatics, Computer Science and Biomedical Engineering, AGH University of Science and Technology, Al. Mickiewicza 30, 30-059 Kraków, Poland

autor

Iwaniec Marek

• Faculty of Mechanical Engineering and Robotics AGH University of Science and Technology, Al. Mickiewicza 30, 30-059 Kraków, Poland

autor

Iwaniec Joanna

• Faculty of Mechanical Engineering and Robotics AGH University of Science and Technology, Al. Mickiewicza 30, 30-059 Kraków, Poland

Bibliografia

• 1. Amodei, D., Ananthanarayanan, S., Anubhai, R., Bai, J., Battenberg, E., Case, C., et al. (2016). Deep speech 2: End-to-end speech recognition in english and mandarin. In: International Conference on Machine Learning, pp. 173–182.
• 2. Azra’ai, R.A., bin Taib, M.N., Tahir, N.M. (2008). Artificial neural network for identification of heart problem. Signal Processing and Communication Systems, 2008. In: ICSPCS IEEE 2nd International Conference on, pp. 1–6.
• 3. Dey, N., Mishra, G., Nandi, B., Pal, M., Das, A., Chaudhuri, S.S. (2012). Wavelet based watermarked normal and abnormal heart sound identification using spectrogram analysis. In: Computational Intelligence & Computing Research (ICCIC), IEEE International Conference on, pp. 1–7. IEEE.
• 4. Grochala, D., Kajor, M., Kucharski, D., Iwaniec, M., Kantoch, E. (2018). A Novel Approach in Auscultation Technology-New Sensors and Algorithms. In: IEEE 11th International Conference on Human System Interaction (HSI), pp. 240–244..
• 5. Kajor, M., Grochala, D., Iwaniec, M., Kantoch, E., Kucharski, D. (2018). A prototype of the mobile stethoscope for telemedical application. In: IEEE XIV-th International Conference on Perspective Technologies and Methods in MEMS Design (MEMSTECH), pp. 5–8.
• 6. Kucharski, D., Grochala, D., Kajor, M., Kańtoch, E. (2017). A Deep Learning Approach for Valve Defect Recognition in Heart Acoustic Signal. In: International Conference on Information Systems Architecture and Technology, pp. 3–14, Springer, Cham.
• 7. Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., et al. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12(Oct), 2825–2830.
• 8. Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R. (2014). Dropout: a simple way to prevent neural networks from overfitting. The Journal of Machine Learning Research, 15(1), 1929–1958.
• 9. Yang, T.C.I., Hsieh, H. (2016). Classification of acoustic physiological signals based on deep learning neural networks with augmented features. In: 2016 IEEE Computing in Cardiology Conference (CinC), pp. 569–572.

Uwagi

Opracowanie rekordu w ramach umowy 509/P-DUN/2018 ze środków MNiSW przeznaczonych na działalność upowszechniającą naukę (2019).