Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Jurnal Teknologi Terpadu
Adi Karawinata Sataynegara
Universitas Adhirajasa Reswara Sanjaya
Computer Science & IT Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Penerapan CNN dengan Arsitektur EfficientNet-B4 untuk Deteksi Penyakit Glaukoma Berbasis Web Rizal Rachman; Adi Karawinata Sataynegara
Jurnal Teknologi Terpadu Vol 12 No 1 (2026): Juli, 2026
Publisher : LPPM STT Terpadu Nurul Fikri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54914/jtt.v12i1.2623

Abstract

Glaucoma is a leading cause of irreversible blindness and frequently goes undetected in its early stages due to its slow and silent progression. Many individuals remain unaware of the disease until significant optic nerve damage has occurred. Early screening is limited by low public awareness, insufficient access to eye-care facilities, and the need for specialists to interpret retinal images. Automated detection is further complicated by inconsistent image quality, illumination variations, and the subtle differences between healthy and glaucomatous retinas. This study develops a web-based early detection system using the EfficientNet-B4 Convolutional Neural Network. A total of 9,540 retinal images from the EyePACS dataset were utilised, including 8,000 for training, 770 for validation, and 770 for testing. Classification was performed using two expert-annotated categories: normal and glaucomatous. The model was trained for 30 epochs through transfer learning and fine-tuning to achieve stable performance. The results show validation accuracy between 90% and 92%, with well-converging loss. The final model was integrated into an interactive web platform that allows users to upload retinal images and receive preliminary predictions accompanied by basic glaucoma information. This system offers potential as an accessible tool for early community-level screening.
Co-Authors Rizal Rachman, Rizal