Comparison of shallow and deep learning methods of ECG signals classification for arrhythmia detection

• Autorzy: Nugrahadi Dodon Turianto , Herteno Rudy , Kartini Dwi , Haekal Muhammad , Faisal Mohammad Reza

Identyfikatory

DOI

10.35784/jcsi.3273

Warianty tytułu

PL

Porównanie metod płytkiego i głębokiego uczenia do klasyfikacji sygnałów EKG zastosowanych do wykrywania arytmii

• Języki publikacji: EN

Abstrakty

EN

The research aimed to compare the classification performance of arrhythmia classification from the ECG signal dataset from the Massachusetts Institute of Technology–Beth Israel Hospital (MIT-BIH) database. Shallow learning methods that were used in this study are Support Vector Machine, Naïve Bayes, and Random Forest. 1D Convolutional Neural Network (1D CNN), Long Short Term Memory (LSTM), and Gated Recurrent Unit (GRU) were deep learning methods that were used for the study. The models were tested on a dataset with 140 samples that were grouped into four class labels, and each sample has 2160 features. Those models were tested for classification performance. This research shows Random Forest and 1D CNN have the best performance.

PL

Badanie ma na celu porównanie wydajności klasyfikacji arytmii na podstawie zestawu danych sygnału EKG z bazy danych Massachusetts Institute of Technology – Beth Israel Hospital (MIT-BIH). W pracy zastosowano następujące metody: Support Vector Machine, Naïve Bayes i Random Forest. Ponadto wykorzystano następujące metody głębokiego uczenia: 1D Convolutional Neural Network (1D CNN), Long Short Term Memory (LSTM) oraz Gated Recurrent Unit (GRU). Modele zostały przetestowane na zbiorze danych zawierającym 140 próbek pogrupowanych w cztery etykiety klas. Każda próbka zawierała 2160 cech. Przeprowadzone testy wydajności klasyfikacji wskazały, że Random Forest i 1D CNN wykazują najwyższą wydajność.

Słowa kluczowe

EN

ECG signals; arrhythmia classification; shallow learning; deep learning

PL

sygnał EKG; klasyfikacja arytmii; płytkie uczenie; głębokie uczenie

• Wydawca: Wydawnictwo Politechniki Lubelskiej
• Czasopismo: Journal of Computer Sciences Institute
• Rocznik: 2023
• Tom: Vol. 27
• Strony: 132--137
• Opis fizyczny: Bibliogr. 15 poz., fig., tab.

Twórcy

autor

Nugrahadi Dodon Turianto

• Lambung Mangkurat University (Indonesia

• https://orcid.org/0000-0001-7746-2658

autor

Herteno Rudy

• Lambung Mangkurat University (Indonesia)

autor

Kartini Dwi

• https://orcid.org/0000-0002-7382-5084

autor

Haekal Muhammad

autor

Faisal Mohammad Reza

• https://orcid.org/0000-0001-5748-7639

Bibliografia

• 1. Shakya, B. Gurung, M. S. Thapa, M. Rai, B. Joshi, Music classification based on genre and mood, International Conference On Computational Intelligence, Communications, and Business Analytics (2017) 168-183, https://doi.org/10.1007/978-981-10-6430-2_14.DOI: https://doi.org/10.1007/978-981-10-6430-2_14
• 2. R. F. R. Junior, F. A. D. Almeida, G. F. Gomes, Fault classification in three-phase motors based on vibration signal analysis and artificial neural networks, Neural Computing and Applications 32(18) (2020) 15171-15189, https://doi.org/10.1007/s00521-020-04868-w.DOI: https://doi.org/10.1007/s00521-020-04868-w
• 3. M. K. Delimayanti, B. Purnama, N.G. Nguyen, M.R. Faisal, K. R. Mahmudah, F. Indriani, M. Kubo, K. Satou, Classification of brainwaves for sleep stages by high-dimensional FFT features from EEG signals, Applied Sciences. 10(5) (2020) 1797-1809, https://doi.org/10.3390/app10051797.DOI: https://doi.org/10.3390/app10051797
• 4. Z. Ebrahimi, M. Loni, M. Daneshtalab, A. Gharehbaghi, A review on deep learning methods for ECG arrhythmia classification, Expert Systems with Applications X 7 (2020), https://doi.org/10.1016/j.eswax.2020.100033.DOI: https://doi.org/10.1016/j.eswax.2020.100033
• 5. M. Kropf, D. Hayn, G. Schreier, ECG classification based on time and frequency domain features using random forests. In 2017 Computing in Cardiology (CinC) (2017) 1-4, https://doi.org/10.22489/CinC.2017.168-168.DOI: https://doi.org/10.22489/CinC.2017.168-168
• 6. O. M. A. Ali; S. W. Kareem, A. S.Mohammed, Evaluation of electrocardiogram signals classification using CNN, SVM, and LSTM algorithm: A review, In 2022 8th International Engineering Conference on Sustainable Technology and Development (IEC) (2022) 185-191, https://doi.org/10.1109/IEC54822.2022.9807511.DOI: https://doi.org/10.1109/IEC54822.2022.9807511
• 7. Venkatesan, P. Karthigaikumar, R. J. M. T. Varatharajan, A novel LMS algorithm for ECG signal preprocessing and KNN classifier based abnormality detection, Multimedia Tools and Applications 77(8) (2018) 10365-10374, https://doi.org/10.1007/s11042-018-5762-6.DOI: https://doi.org/10.1007/s11042-018-5762-6
• 8. Krithiga, P. Sabari, I. Jayasri, I. Anjali, Early detection of coronary heart disease by using naive bayes algorithm, In Journal of Physics: Conference Series Vol. 1717 No. 1 IOP Publishing (2021) 012-040, http://doi.org/10.1088/1742-6596/1717/1/012040.DOI: https://doi.org/10.1088/1742-6596/1717/1/012040
• 9. R. A. Cahya, C. Dewi, B. Rahayudi, Arrhythmia classification from electrocardiogram results using support vector machine with feature selection using genetic algorithms, Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer (2018) 1170 – 1178.
• 10. T. Wang, C. Lu, Y. Sun, M. Yang, C. Liu, C. Ou, Automatic ECG classification using continuous wavelet transform and convolutional neural network, Entropy 23(1) (2021) 119-132, https://doi.org/10.3390/e23010119.DOI: https://doi.org/10.3390/e23010119
• 11. S. I. Dimitriadis, D. Liparas, How random is the random forest? Random forest algorithm on the service of structural imaging biomarkers for Alzheimer's disease, Neural Regeneration Research 13(6) (2018) 962-970, https://doi.org/10.4103%2F1673-5374.233433.DOI: https://doi.org/10.4103/1673-5374.233433
• 12. M. Dovbnych, M. P. Wójcik, A comparison of conventional and deep learning methods of image classification, Journal of Computer Sciences Institute (2021) 303-308, https://doi.org/10.35784/jcsi.2727.DOI: https://doi.org/10.35784/jcsi.2727
• 13. Tabian, H. Fu, Z. S. Khodaei, A convolutional neural network for impact detection and characterization of complex composite structures, Sensors, 19(22) (2019) 4933-4958, https://doi.org/10.3390/s19224933.DOI: https://doi.org/10.3390/s19224933
• 14. Li, J. Zhang, Q. Zhang, X. Wei, Classification of ECG signals based on 1D convolution neural network, 19th International Conference on e-Health Networking Applications and Services (Healthcom) (2017) 1-6, https://doi.org/10.1109/HealthCom.2017.8210784.DOI: https://doi.org/10.1109/HealthCom.2017.8210784
• 15. H. M. Lynn, S. B. Pan, P. Kim, A deep bidirectional GRU network model for biometric electrocardiogram classification based on recurrent neural networks, IEEE Access 7 (2019) 145395-145405, https://doi.org/10.1109/ACCESS.2019.2939947.DOI: https://doi.org/10.1109/ACCESS.2019.2939947

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki (2025).