Skripsi

KLASIFIKASI PENYAKIT MATA MENGGUNAKAN CONVOLUTIONAL NEURAL NETWORK (CNN) : PERBANDINGAN METODE RESNET-101 DAN EFFICIENTNET-B4

---

This study examines the use of the Convolutional Neural Network (CNN) algorithm for eye disease classification based on retinal images. The research methodology involves collecting a dataset from the Kaggle website, named eye_disease_classification, which includes four main categories: normal, cataract, diabetic retinopathy, and glaucoma, with a total of 4,233 images before augmentation. The dataset undergoes preprocessing steps such as normalization, augmentation, and splitting into training, validation, and testing subsets. Two CNN architectures, namely ResNet-101 and EfficientNet-B4, are employed for model training and evaluation. The process utilizes the Adam optimizer, categorical cross-entropy loss function, and performance metrics including accuracy, precision, recall, and F1-score. The results indicate that ResNet-101 achieves a better balance between accuracy and processing time, while EfficientNet-B4 demonstrates higher performance in recall and F1-score under certain configurations. This study provides insights into the effectiveness of both models for medical image classification tasks, particularly in the classification of retinal eye diseases. Keywords: Convolutional Neural Network (CNN), retina, image classification, ResNet-101, EfficientNet-B4, cataract, diabetic retinopathy, glaucoma, deep learning.

---

Availability

Detail Information

Series Title

-

Call Number

T1894082025

Publisher

Indralaya : Prodi Sistem Komputer, Fakultas Ilmu Komputer Universitas Sriwijaya., 2025

Collation

xiv, 62 hlm.; ilus.; tab, 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

617.7150 7

Content Type

Text

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Prodi Sistem Komputer
Diagnosis Penyakit Mata

Specific Detail Info

-

Statement of Responsibility

MI

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment