<![CDATA[The lungs are one of the important organs for humans. One of the lung diseases that can potentially cause death is pneumonia. This study compares the performance of the Convolutional Neural Network (CNN), ResNet-50, and MobileNetV2 models in detecting pneumonia using chest X-ray images. The dataset used was obtained from Kaggle with a total of 2,000 chest X-ray images, which were divided into 70% training data, 15% validation data, and 15% test data. All images were resized to 256×256 pixels. The experiment was carried out 10 times with 20 training epochs and a batch size of 32. The results showed that the CNN model obtained an average accuracy of 95.76%, precision of 95.39%, recall of 96.20%, and F1-score of 95.77%. The ResNet-50 model produced an average accuracy of 96.99%, precision of 99.79%, recall of 94.20%, and F1-score of 96.90%. Meanwhile, MobileNetV2 achieved an average accuracy of 97.33%, precision of 97.23%, recall of 98.13%, and F1-score of 97.66%. ResNet-50 was better at minimizing False Positives, while MobileNetV2 was better at minimizing False Negatives. Overall, all three models performed well in detecting pneumonia, although there were variations in the confusion matrix results across experiments.]]>
Copyrights © 2026
