EUVIMEDEUVIMED entdecken
Crossref

Classification of ECG Signals Using CNNs: An Improved Model for Cardiac Disease Diagnosis

Diyar Qader Zeebaree

Journal of Al-Farabi for Engineering Sciences · 23.03.2026 · 5 (1) · 1-13

DOI: 10.59746/kxbg0r45 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Al-Farabi for Engineering Sciences, online erschienen am 23.03.2026. Verfasst von Diyar Qader Zeebaree.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The analysis of ECG signals poses significant challenges as a result of the complex electrical patterns of the heart and issues related to the imbalanced data. Addressing such challenges requires having advanced methods and models for the purpose of ensuring accurate diagnoses and improving the results of the treatments. The combination of the ECG analysis with the approaches of artificial intelligence (AI) became a priority for the health-care improvement, especially as the prevalence of heart diseases keeps rising worldwide. In the present study, Convolutional Neural Networks (CNNs) have been used for creating a classification model for the ECG signals, tested across the balanced as well as the imbalanced data structures from MIT-BIH Arrhythmia data-sets. Results have shown consistently high accuracy of classification, which exceeds 98% in all of the cases. For example, the model has been able to achieve 98.36% accuracy with the unbalanced data after 20 cycles (epochs) of training with the use of the early stopping. When the number of the cycles has been increased to 104, with extended patience setting of 25, accuracy has been increased to 98.76%. Balanced data had produced outcomes that are slightly better, with the model reaching an accuracy level of 98.88% in 25 cycles and 98.45% in 20 cycles. These findings have highlighted the importance of the training cycle count as well as the data balance in increasing the accuracy of the model. Moreover, early stopping proved beneficial in maintaining high performance and training efficiency in ECG signal classification.

Zitieren

APA

Zeebaree, D. Q. (2026). Classification of ECG Signals Using CNNs: An Improved Model for Cardiac Disease Diagnosis. Journal of Al-Farabi for Engineering Sciences, 5(1), 1-13. https://doi.org/10.59746/kxbg0r45

Vancouver

Zeebaree DQ. Classification of ECG Signals Using CNNs: An Improved Model for Cardiac Disease Diagnosis. Journal of Al-Farabi for Engineering Sciences. 2026;5(1):1-13. doi:10.59746/kxbg0r45

BibTeX
@article{Zeebaree2026,
  author = {Zeebaree, Diyar Qader},
  title = {Classification of ECG Signals Using CNNs: An Improved Model for Cardiac Disease Diagnosis},
  journal = {Journal of Al-Farabi for Engineering Sciences},
  year = {2026},
  volume = {5},
  number = {1},
  pages = {1--13},
  doi = {10.59746/kxbg0r45}
}
Kostenlos starten →