Impact of data augmentation techniques on deep transfer learning for heart sound classification
Biomedical Physics & Engineering Express · 2026
DOI: 10.1088/2057-1976/aeb4bf ↗Kurz gefasst
Fachartikel in der Zeitschrift Biomedical Physics & Engineering Express, 2026. Verfasst von Nour El Houda Gorine und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, CSTL Lab, University of Mostaganem-Abdelhamid Ibn Badis, Mostaganem, Algeria. Hauptthemen laut MEDLINE: Heart Sounds, Deep Learning, Signal Processing, Computer-Assisted, Cardiovascular Diseases. Die Arbeit nennt 26 Literaturangaben.
Abstract (Originalsprache)
Cardiovascular diseases remain one of the primary causes of death worldwide, highlighting the importance of early detection. PhonoCardioGraphy (PCG) provides a non-invasive approach to identify cardiac abnormalities. However, its effectiveness is limited by scarce datasets and signal variability. Deep learning (DL) models have shown promising results, but their performance strongly depends on the availability of sufficient training data. In this study, PCG signals were converted into spectrogram representations, and four data augmentation techniques were applied individually and in combination, followed by a systematic evaluation. A baseline convolutional neural network (CNN) and several transfer learning models were trained on both original and augmented datasets. The results demonstrate that combining augmentation techniques yields the best performance. The proposed CNN achieved an accuracy of 94%, representing a 5.6% improvement over its performance without data augmentation. In contrast, transfer learning such as VGG16, ResNet50, and DenseNet121 showed improvements of 3.4%, 3.4%, and 2.2%, respectively. These findings indicate that the proposed augmentation strategy effectively improves the classification performance and generalization capability of DL models for heart sound classification.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Computer Science, CSTL Lab, University of Mostaganem-Abdelhamid Ibn Badis, Mostaganem, Algeria.
ORCID-Profile: Nour El Houda Gorine, Mohammed Elamine Moumene, Saliha Benkerdagh
Zitieren
APA
Gorine, N. E. H., Moumene, M. E., & Benkerdagh, S. (2026). Impact of data augmentation techniques on deep transfer learning for heart sound classification. Biomedical Physics & Engineering Express. https://doi.org/10.1088/2057-1976/aeb4bf
Vancouver
Gorine NEH, Moumene ME, Benkerdagh S. Impact of data augmentation techniques on deep transfer learning for heart sound classification. Biomedical Physics & Engineering Express. 2026. doi:10.1088/2057-1976/aeb4bf
BibTeX
@article{Gorine2026,
author = {Gorine, Nour El Houda and Moumene, Mohammed Elamine and Benkerdagh, Saliha},
title = {Impact of data augmentation techniques on deep transfer learning for heart sound classification},
journal = {Biomedical Physics & Engineering Express},
year = {2026},
doi = {10.1088/2057-1976/aeb4bf}
}
EUVIMED