Skip to content
SDGs Center UDINUS

Evidence record · UDINUS · SDGs

A high accuracy of deep learning based CNN architecture: classic, VGGNet, and RestNet50 for Covid-19 image classification

Rektorat UDINUS 2024 Published 2026-10-30

Evidence record · UDINUS · SDGs

Unit
Rektorat UDINUS
Period
2024
Goals
Record
440d4ff4-07ec-4fbe-b790-75d5162b550a
Published
2026-10-30

Universitas Dian Nuswantoro conducted research examining convolutional neural network (CNN) structures used for Covid-19 image classification. The activity involved Mulyono, Ibnu Utomo Wahyu; Rachmawanto, Eko Hari; Sari, Christy Atika; and Sarker, Md Kamruzzaman as participants. The study investigated classic CNN, visual geometry group (VGG), and ResNet-50 architectures across a variety of datasets. The evaluation considered accuracy, precision, recall, and F1-Score to examine the efficacy of each architecture in the classification task.

The experimental results showed that the ResNet-50 architecture achieved the highest performance, with an accuracy rate of 96.63%, outperforming both VGG and classic CNN models. The study also examined the combination of ResNet-50 with the Adam optimizer and reported its effectiveness in improving classification accuracy. VGG and ResNet-50 were selected because of their strong feature extraction capabilities, state-of-the-art performance, suitability for transfer learning, and widely available pre-trained models. These characteristics facilitated their usage and experimentation.

The activity relates to health research through its examination of deep learning architectures for Covid-19 image classification. Its findings provide insights into the comparative performance of CNN architectures and emphasize the importance of architectural choices and hyperparameter selection for optimal model performance. Through this research activity, Universitas Dian Nuswantoro frames the evaluation of CNN architectures and hyperparameters as an institutional research contribution concerning Covid-19 image classification.

Reference https://www.scopus.com/pages/publications/85202731097?origin=resultslist