Skripsi

PERBANDINGAN VGG19 DAN RESNET50V2 UNTUK KLASIFIKASI PNEUMONIA PADA CITRA CHEST X-RAY

---

Pneumonia is a lung infection caused by various pathogens and poses a global health threat with a high mortality rate. The World Health Organization (WHO) reports that pneumonia caused approximately 740,180 deaths among children under five years of age in 2019, making early detection essential. Pneumonia is generally diagnosed using chest X-ray images because they are inexpensive, easily accessible, and have low radiation doses. Therefore, in this study, the author developed a web-based application to classify chest X-ray images into pneumonia and normal categories using the Convolutional Neural Network (CNN) method with the VGG19 and ResNet50V2 architectures. The dataset used consisted of 5,840 chest X-ray images, which were divided into 4,173 training images, 1,043 validation images, and 624 testing images, and underwent preprocessing stages of resizing, normalization, data augmentation, and class imbalance handling. Model performance was evaluated using a confusion matrix with accuracy, precision, recall, and F1-score metrics. The results showed that ResNet50V2 provided the best performance with an accuracy of 95.67%, precision of 94.16%, recall of 99.23%, and F1-score of 96.63%, while VGG19 obtained an accuracy of 91.99%, precision of 92.08%, recall of 95.38%, and an F1-score of 93.70%.

---

Availability

Detail Information

Series Title

-

Call Number

T1897712025

Publisher

Indralaya : Prodi Teknik Informatika, Fakultas Ilmu Komputer Universitas Sriwijaya., 2025

Collation

xv, 111 hlm.; ilus.; tab.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

006.370 7

Content Type

Text

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Prodi Teknik Informatika
Computer Vision--Pemrosesan Citra

Specific Detail Info

-

Statement of Responsibility

MI

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment