Research Article
BibTex RIS Cite

Derin Öğrenme ve Chroma Spektrogramlarına Dayalı EKG Sinyallerinin Sınıflandırılması

Year 2024, , 164 - 175, 31.12.2024
https://doi.org/10.46578/humder.1540437

Abstract

Elektrokardiyografi (EKG), kalbin elektriksel aktivitesini izleyerek ritim ve fonksiyon bozukluklarını tespit etmekte kullanılan, invazif olmayan bir tanı yöntemidir. EKG sinyalleri genellikle düşük genlikli ve karmaşık yapıda olup, bu sinyallerdeki küçük değişiklikler gözle fark edilemeyebilir. Aritmiler, her zaman ciddi olmasa da, kalp hastalığı semptomlarına ve potansiyel olarak tehlikeli durumlara yol açabilir. Yapay zeka, EKG verilerini analiz ederek bu tür kalp hastalıklarının daha hızlı ve doğru bir şekilde tespit edilmesine olanak sağlar, böylece klinik kararların desteklenmesine katkıda bulunur. Bu çalışmada, PhysioNet/CinC Challenge 2016 veri seti kullanılarak, Chroma spektrogramları oluşturulmuş ve bu veriler üzerinde altı farklı önceden eğitilmiş ağ modeli test edilmiştir. Modeller, üç farklı doğrulama yöntemi ve altı farklı sınıflandırıcı ile değerlendirilmiştir. Sonuçlar, MobileNet V2 modeli ile Q-DVM sınıflandırıcısının en iyi performansı sergilediğini göstermiştir. Modelimiz, doğruluk (%87,6), duyarlılık (%96,1), kesinlik (%88,9) ve F1 skoru (%92,4) açısından güçlü ve iyi bir performans sergilemiştir.

Supporting Institution

Harran Üniversitesi Bilimsel Araştırma Projeleri Koordinatörlüğü (HÜBAK)

Project Number

22219

Thanks

Bu çalışma 22219 no’lu proje olarak HÜBAK tarafından desteklenmiştir. Not: Bu makale, yüksek lisans tez çalışmasından elde edilen bulgulara dayanmaktadır.

References

  • Vikipedi yazarları, "Elektrokardiyografi," Vikipedi, Özgür Ansiklopedi. Erişim tarihi: 29 Mayıs 2024. https://tr.wikipedia.org/wiki/Elektrokardiyografi#:~:text=Elektrokardiyografi%20(EKG)%2C%20kalp%20kas%C4%B1n%C4%B1n,kullan%C4%B1lan%20alete%20de%20elektrokardiyograf%20denir.
  • A. Alpman, "Elektrokardiyogram (EKG)," Ahmet Alpman. Erişim tarihi: 6 Ağustos 2024. https://ahmetalpman.com/elektrokardiyogram-ekg/.
  • Y. Ansari, O. Mourad, K. Qaraqe, ve E. Serpedin, "Deep learning for ECG arrhythmia detection and classification: an overview of progress for period 2017–2023," Frontiers in Physiology, 14 (2023) 1246746.
  • Q. Xiao, K. Lee, S. A. Mokhtar, I. Ismail, A. L. B. M. Pauzi, Q. Zhang, ve P. Y. Lim, "Deep learning-based ECG arrhythmia classification: A systematic review," Applied Sciences, 13:8 (2023) 4964.
  • N. Katal, S. Gupta, P. Verma, ve B. Sharma, "Deep-learning-based arrhythmia detection using ECG signals: A comparative study and performance evaluation," Diagnostics, 13: 24 (2023) 3605.
  • Mohebbanaaz, L. R. Kumar, ve Y. P. Sai, "A new transfer learning approach to detect cardiac arrhythmia from ECG signals," Signal, Image and Video Processing, cilt. 16: 7 (2022) 1945-1953.
  • P. N. Singh ve R. P. Mahapatra, "A novel deep learning approach for arrhythmia prediction on ECG classification using recurrent CNN with GWO," International Journal of Information Technology, 16:1 (2024) 577-585.
  • M. B. Er ve I. B. Aydilek, "Music emotion recognition by using chroma spectrogram and deep visual features," International Journal of Computational Intelligence Systems, 12:2 (2019) 1622–1634. https://doi.org/10.2991/ijcis.d.191216.001.
  • M. B. Er, "A novel approach for classification of speech emotions based on deep and acoustic features," IEEE Access, 8 (2020) 221640-221651. https://doi.org/10.1109/ACCESS.2020.3043201.
  • G. D. Clifford, C. Liu, B. Moody, H. L. Li-wei, I. Silva, Q. Li, ... ve R. G. Mark, "AF classification from a short single lead ECG recording: The PhysioNet/computing in cardiology challenge 2017," 2017 Computing in Cardiology (CinC), ss. 1-4, Eylül 2017.
  • Y. Liang, S. Yin, Q. Tang, Z. Zheng, M. Elgendi, ve Z. Chen, "Deep learning algorithm classifies heartbeat events based on electrocardiogram signals," Frontiers in Physiology, 11 (2020) 569050.
  • S. Śmigiel, K. Pałczyński, ve D. Ledziński, "ECG signal classification using deep learning techniques based on the PTB-XL dataset," Entropy, 23:9 (2021) 1121.
  • M. B. Er, "Heart sounds classification using convolutional neural network with 1D-local binary pattern and 1D-local ternary pattern features," Applied Acoustics, 180 (2021) 108152.
  • S. Sattar, R. Mumtaz, M. Qadir, S. Mumtaz, M. A. Khan, T. De Waele, ... ve A. Shahid, "Cardiac arrhythmia classification using advanced deep learning techniques on digitized ECG datasets," Sensors, 24:8 (2024) 2484.
  • C. Liu, D. Springer, B. Moody, I. Silva, A. Johnson, M. Samieinasab, ... ve G. D. Clifford, "Classification of heart sound recordings-the PhysioNet computing in cardiology challenge 2016," PhysioNet, 2016.
  • G. D. Clifford, C. Liu, B. Moody, D. Springer, I. Silva, Q. Li, ... ve R. G. Mark, "Classification of normal/abnormal heart sound recordings: The PhysioNet/Computing in Cardiology Challenge 2016," 2016 Computing in Cardiology Conference (CinC), ss. 609-612, Eylül 2016.
  • I. Grzegorczyk, M. Soliński, M. Łepek, A. Perka, J. Rosiński, J. Rymko, ... ve J. Gierałtowski, "PCG classification using a neural network approach," 2016 Computing in Cardiology Conference (CinC), ss. 1129-1132, Eylül 2016.
  • J. Rubin, R. Abreu, A. Ganguli, S. Nelaturi, I. Matei, ve K. Sricharan, "Classifying heart sound recordings using deep convolutional neural networks and mel-frequency cepstral coefficients," 2016 Computing in Cardiology Conference (CinC), 813-816, Eylül 2016.
  • T. Nilanon, J. Yao, J. Hao, S. Purushotham, ve Y. Liu, "Normal/abnormal heart sound recordings classification using convolutional neural network," 2016 Computing in Cardiology Conference (CinC), ss. 585-588, Eylül 2016.
  • F. Noman, C. M. Ting, S. H. Salleh, ve H. Ombao, "Short-segment heart sound classification using an ensemble of deep convolutional neural networks," ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), ss. 1318-1322, Mayıs 2019.
  • A. Bouril, D. Aleinikava, M. S. Guillem, ve G. M. Mirsky, "Automated classification of normal and abnormal heart sounds using support vector machines," 2016 Computing in Cardiology Conference (CinC), ss. 549-552, Eylül 2016.
Year 2024, , 164 - 175, 31.12.2024
https://doi.org/10.46578/humder.1540437

Abstract

Project Number

22219

References

  • Vikipedi yazarları, "Elektrokardiyografi," Vikipedi, Özgür Ansiklopedi. Erişim tarihi: 29 Mayıs 2024. https://tr.wikipedia.org/wiki/Elektrokardiyografi#:~:text=Elektrokardiyografi%20(EKG)%2C%20kalp%20kas%C4%B1n%C4%B1n,kullan%C4%B1lan%20alete%20de%20elektrokardiyograf%20denir.
  • A. Alpman, "Elektrokardiyogram (EKG)," Ahmet Alpman. Erişim tarihi: 6 Ağustos 2024. https://ahmetalpman.com/elektrokardiyogram-ekg/.
  • Y. Ansari, O. Mourad, K. Qaraqe, ve E. Serpedin, "Deep learning for ECG arrhythmia detection and classification: an overview of progress for period 2017–2023," Frontiers in Physiology, 14 (2023) 1246746.
  • Q. Xiao, K. Lee, S. A. Mokhtar, I. Ismail, A. L. B. M. Pauzi, Q. Zhang, ve P. Y. Lim, "Deep learning-based ECG arrhythmia classification: A systematic review," Applied Sciences, 13:8 (2023) 4964.
  • N. Katal, S. Gupta, P. Verma, ve B. Sharma, "Deep-learning-based arrhythmia detection using ECG signals: A comparative study and performance evaluation," Diagnostics, 13: 24 (2023) 3605.
  • Mohebbanaaz, L. R. Kumar, ve Y. P. Sai, "A new transfer learning approach to detect cardiac arrhythmia from ECG signals," Signal, Image and Video Processing, cilt. 16: 7 (2022) 1945-1953.
  • P. N. Singh ve R. P. Mahapatra, "A novel deep learning approach for arrhythmia prediction on ECG classification using recurrent CNN with GWO," International Journal of Information Technology, 16:1 (2024) 577-585.
  • M. B. Er ve I. B. Aydilek, "Music emotion recognition by using chroma spectrogram and deep visual features," International Journal of Computational Intelligence Systems, 12:2 (2019) 1622–1634. https://doi.org/10.2991/ijcis.d.191216.001.
  • M. B. Er, "A novel approach for classification of speech emotions based on deep and acoustic features," IEEE Access, 8 (2020) 221640-221651. https://doi.org/10.1109/ACCESS.2020.3043201.
  • G. D. Clifford, C. Liu, B. Moody, H. L. Li-wei, I. Silva, Q. Li, ... ve R. G. Mark, "AF classification from a short single lead ECG recording: The PhysioNet/computing in cardiology challenge 2017," 2017 Computing in Cardiology (CinC), ss. 1-4, Eylül 2017.
  • Y. Liang, S. Yin, Q. Tang, Z. Zheng, M. Elgendi, ve Z. Chen, "Deep learning algorithm classifies heartbeat events based on electrocardiogram signals," Frontiers in Physiology, 11 (2020) 569050.
  • S. Śmigiel, K. Pałczyński, ve D. Ledziński, "ECG signal classification using deep learning techniques based on the PTB-XL dataset," Entropy, 23:9 (2021) 1121.
  • M. B. Er, "Heart sounds classification using convolutional neural network with 1D-local binary pattern and 1D-local ternary pattern features," Applied Acoustics, 180 (2021) 108152.
  • S. Sattar, R. Mumtaz, M. Qadir, S. Mumtaz, M. A. Khan, T. De Waele, ... ve A. Shahid, "Cardiac arrhythmia classification using advanced deep learning techniques on digitized ECG datasets," Sensors, 24:8 (2024) 2484.
  • C. Liu, D. Springer, B. Moody, I. Silva, A. Johnson, M. Samieinasab, ... ve G. D. Clifford, "Classification of heart sound recordings-the PhysioNet computing in cardiology challenge 2016," PhysioNet, 2016.
  • G. D. Clifford, C. Liu, B. Moody, D. Springer, I. Silva, Q. Li, ... ve R. G. Mark, "Classification of normal/abnormal heart sound recordings: The PhysioNet/Computing in Cardiology Challenge 2016," 2016 Computing in Cardiology Conference (CinC), ss. 609-612, Eylül 2016.
  • I. Grzegorczyk, M. Soliński, M. Łepek, A. Perka, J. Rosiński, J. Rymko, ... ve J. Gierałtowski, "PCG classification using a neural network approach," 2016 Computing in Cardiology Conference (CinC), ss. 1129-1132, Eylül 2016.
  • J. Rubin, R. Abreu, A. Ganguli, S. Nelaturi, I. Matei, ve K. Sricharan, "Classifying heart sound recordings using deep convolutional neural networks and mel-frequency cepstral coefficients," 2016 Computing in Cardiology Conference (CinC), 813-816, Eylül 2016.
  • T. Nilanon, J. Yao, J. Hao, S. Purushotham, ve Y. Liu, "Normal/abnormal heart sound recordings classification using convolutional neural network," 2016 Computing in Cardiology Conference (CinC), ss. 585-588, Eylül 2016.
  • F. Noman, C. M. Ting, S. H. Salleh, ve H. Ombao, "Short-segment heart sound classification using an ensemble of deep convolutional neural networks," ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), ss. 1318-1322, Mayıs 2019.
  • A. Bouril, D. Aleinikava, M. S. Guillem, ve G. M. Mirsky, "Automated classification of normal and abnormal heart sounds using support vector machines," 2016 Computing in Cardiology Conference (CinC), ss. 549-552, Eylül 2016.
There are 21 citations in total.

Details

Primary Language Turkish
Subjects Computer Software
Journal Section Research Articles
Authors

Songül Akdağ 0000-0003-2278-4232

Mehmet Bilal Er 0000-0002-2074-1776

Project Number 22219
Early Pub Date December 30, 2024
Publication Date December 31, 2024
Submission Date August 29, 2024
Acceptance Date October 8, 2024
Published in Issue Year 2024

Cite

APA Akdağ, S., & Er, M. B. (2024). Derin Öğrenme ve Chroma Spektrogramlarına Dayalı EKG Sinyallerinin Sınıflandırılması. Harran Üniversitesi Mühendislik Dergisi, 9(3), 164-175. https://doi.org/10.46578/humder.1540437