Skripsi

PENERAPAN HYBRID CNN DAN VISION TRANSFORMER UNTUK KLASIFIKASI PENYAKIT MATA PADA CITRA RETINA

---

Retinal diseases require early detection to improve the effectiveness of medical treatment. This study aims to classify retinal diseases based on fundus images using a hybrid architecture of CNN and Transformer Encoder based on Vision Transformer. The research stages include preparing and dividing the dataset into training, validation, and test data, as well as preprocessing in the form of resizing, normalization, data augmentation, and handling class imbalance using oversampling and artificial sampling techniques based on Weighted Random Sampler. The model is then trained end-to-end and evaluated on the test data to measure multi-class classification performance. The best model was obtained in the artificial sampling scenario, achieving an accuracy of 79.29%, a precision of 78.75%, a recall of 78.78%, and an F1-score of 78.62%. The results show that the hybrid architecture combined with an appropriate data balancing strategy can improve the classification performance of retinal diseases in medical images

---

Availability

Detail Information

Series Title

-

Call Number

T1965692026

Publisher

Indralaya : Prodi Sistem Komputer, Fakultas Ilmu Komputer Universitas Sriwijaya., 2026

Collation

xiv, 62 hlm.; ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

006.607

Content Type

Text

Media Type

unmediated

Carrier Type

-

Edition

-

Subject(s)

Pengolahan Citra Digital
Prodi Sistem Komputer

Specific Detail Info

-

Statement of Responsibility

KA

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment