Skripsi

ANALISIS AKURASI MODEL MOBILENETV2 DALAM KLASIFIKASI CITRA X-RAY UNTUK DETEKSI KONDISI PARU-PARU

---

Penilaian

---

This study aims to analyze the accuracy of the MobileNetV2 model in classifying chest X-ray images for detecting four pulmonary conditions: Normal, Pneumonia, Cardiomegaly, and Pneumothorax. The dataset consists of 12.539 X-ray images obtained from public repositories and has undergone preprocessing, augmentation, and class weighting to address data imbalance. The model was developed using transfer learning and fine-tuning on the final layers of MobileNetV2. Testing results indicate that the proposed model achieves an accuracy of 99,42%, precision of 98,87%, recall of 98,88%, and F1-score of 98,86%. All evaluation metrics exceed the minimum standard ≥90% for clinical application. These findings confirm that MobileNetV2 has strong potential as an automatic diagnostic tool based on X-ray images, thereby improving the effectiveness of early detection of lung diseases in clinical settings.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2507003904	T177882	T1778822025	Central Library (Reference)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T1778822025

Publisher

Indralaya : Prodi Magister Fisika, Fakultas Matematika dan Ilmu Pengetahuan Alam Universitas Sriwijaya., 2025

Collation

xvii, 66 hlm.; ilus.; tab.; 29 cm.

Language

Indonesia

ISBN/ISSN

-

Classification

538.07

Content Type

Text

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Ilmu Fisika

Specific Detail Info

-

Statement of Responsibility

MI

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment