EUVIMEDEUVIMED entdecken
Crossref

Innovative ECG Classification Approach Utilizing aTransfer Learning-Driven Ensemble Architecture

HMLS Kumari

International Journal of Research in Computing · 2024

DOI: 10.64701/ijrc/345/8903 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Research in Computing, 2024. Verfasst von HMLS Kumari.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

An electrocardiogram (ECG/EKG) is a vital methodology that is used for the diagnosis and monitoring ofheart diseases by recording the electrical activity of the heart. However, manual analysis of ECGs shows limitations suchas noise sensitivity, visual interpretation constraints and data imbalance. The proposed study a deep learning ensemblemodel combining DenseNet121, InceptionV3, and ResNet50 are implement to classify ECG images to improve diagnosticaccuracy. The model is trained on two datasets: the National Heart Foundation 2023 ECG dataset and the ECG Dataset forHeart Condition Classification, focusing the main cardiac conditions such as abnormal heartbeat, myocardial infarction.The preprocessing techniques include background removal of ECG signal images, grayscale conversion, and dataaugmentation to enhance image quality and overfitting reduction. Stratified 5-Fold cross-validation was employed todemonstrate the generalization abilities of the proposed models. Early stopping and performance plots demonstrated thatproposed model is not overfitting and two proposed models show consistent accuracy which suggests the model is notbiased toward a specific dataset. While the ensemble models, as demonstrated in this study, produce better results thansingle models. The proposed study demonstrates validation accuracies of 98.62% and 96.75% for the National HeartFoundation 2023 dataset and the ECG dataset for heart condition classification, respectively, using 5-fold stratified cross-validation. There are still some limitations, such as the proposed ensemble models not being evaluated using ExplainableAI, which reduces clinical trust. Additionally, small datasets can limit the model's generalizability. Therefore, this studydemonstrates the potential of deep ensemble models with advanced preprocessing for ECG classification, but it alsohighlights the importance of greater transparency, better dataset diversity, and real-world validation in future researchstudies. KEYWORDS: Data Augmentation, ECG (electrocardiogram), Ensemble Architectures, Preprocessing techniques,Transfer learning

Zitieren

APA

Kumari, H. (2024). Innovative ECG Classification Approach Utilizing aTransfer Learning-Driven Ensemble Architecture. International Journal of Research in Computing. https://doi.org/10.64701/ijrc/345/8903

Vancouver

Kumari H. Innovative ECG Classification Approach Utilizing aTransfer Learning-Driven Ensemble Architecture. International Journal of Research in Computing. 2024. doi:10.64701/ijrc/345/8903

BibTeX
@article{Kumari2024,
  author = {Kumari, HMLS},
  title = {Innovative ECG Classification Approach Utilizing aTransfer Learning-Driven Ensemble Architecture},
  journal = {International Journal of Research in Computing},
  year = {2024},
  doi = {10.64701/ijrc/345/8903}
}
Kostenlos starten →