Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal RABIT: Jurnal Teknologi dan Sistem Informasi Univrab
Anindya Novia Ramadani
Universitas Amikom Purwokerto
Computer Science & IT Engineering

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

Found 1 Documents
Search

 1 
DETEKSI DINI KATARAK BERBASIS CITRA MATA MENGGUNAKAN METODE DEEP LEARNING CONVOLUTIONAL NEURAL NETWORK (CNN): EARLY DETECTION OF CATARACT BASED ON EYE IMAGES USING DEEP LEARNING METHOD: CONVOLUTIONAL NEURAL NETWORK (CNN) Anindya Novia Ramadani; Rujianto Eko Saputro
Rabit : Jurnal Teknologi dan Sistem Informasi Univrab Vol 11 No 2 (2026): Juli
Publisher : LPPM Universitas Abdurrab

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36341/rabit.v11i2.7914

Abstract

Cataract is one of the leading causes of visual impairment that requires early detection to prevent more severe conditions. This study aims to develop an image classification model based on Convolutional Neural Network (CNN) using the EfficientNetB0 architecture with a transfer learning approach and progressive training strategy to distinguish between normal and cataract eye images. The dataset used was obtained from Kaggle, consisting of two classes, namely normal and cataract eye images, which were then processed through preprocessing stages including resizing, normalization, and data augmentation. The dataset was divided into training and validation data with a ratio of 80:20. The model was trained in two stages, where Stage 1 involved freezing the entire EfficientNetB0 base model, and Stage 2 applied fine-tuning on selected layers to improve performance. The experimental results show that the model achieved a validation accuracy of 87.60% with a loss value of 0.3742. Evaluation using precision, recall, and F1-score indicates that the model performs relatively balanced, but shows better performance in recognizing normal eye images compared to cataract images. This is reflected in the higher recall value for the normal class and the relatively high false negative rate in the cataract class. In conclusion, the proposed CNN model based on EfficientNetB0 is capable of classifying cataract and normal eye images; however, further improvements in dataset size, model architecture, and training strategy are required to achieve better performance for reliable medical-based early detection systems.
Co-Authors Rujianto Eko Saputro