Klasifikasi Penyakit Paru-Paru Dengan Citra X-Ray Menggunakan Metode Convolutional Neural Network

Kusuma, Daniel
Rarasati, Dionisia Bhisetya

Jurnal Ilmiah Sains dan Teknologi
Vol. 9 No. 2 (2025): Jurnal Ilmiah Sains dan Teknologi

This research explores the utilization of Convolutional Neural Network (CNN) methods to classify lung diseases, including COVID-19, Tuberculosis, and Pneumonia. The focus is on developing a CNN model for lung disease classification using a dataset that has undergone augmentation. Data augmentation is performed through various transformations such as rotation, horizontal_flip, vertical_flip, shear_range, and zoom_range. The dataset is divided into 70% for training, 20% for validation, and 10% for testing, totaling 2200 data points. The results indicate that the constructed model successfully achieved an accuracy of 96.49% in the training process and 95% on the testing data. This research demonstrates the potential of CNN in classifying lung diseases quite effectively after model training.