Text

KLASIFIKASI CITRA RETINA DALAM MENENTUKAN PENYAKIT GLAUKOMA MENGGUNAKAN ARSITEKTUR VISION TRANSFORMER

---

Penilaian

---

Glaucoma is the second leading cause of blindness in the world. Early detection of glaucoma needs to be done to reduce the risk of blindness. So, we need a technology to predict and classify glaucoma. Therefore, this study performed retinal image classification to determine glaucoma. Glaucoma can be classified to 3 classes, there are advanced glaucoma, early glaucoma, and normal control. Deep learning is often used to perform various tasks in machine learning such as classification. One of the learning methods in classification is Vision Transformer (ViT). The advantage of ViT is its small memory usage with excellent results in performing classification tasks. In this study, retinal image classification was performed to determine glaucoma disease using the ViT architecture. The research stages are data collection, data pre-processing, training, testing, and performance evaluation as well as analysis and interpretation. The study used retinal image data sourced from the Harvard Dataverse with the performance evaluation values for accuracy, sensitivity, specificity, F1-score, and Cohen's kappa were 96.74%, 95.10%, 97.57%, 95.10%, and 92.46%, respectively. Based on the results obtained, it can be concluded that the Vision Transformer architecture is very good in performing the task of classifying retinal images to determine glaucoma disease.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2207003583	T77816	T778162022	Central Library (Referens)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T778162022

Publisher

Inderalaya : Jurusan Matematika, Fakultas Matematika Dan Ilmu Pengetahuan Alam Universitas Sriwijaya., 2022

Collation

xii, 70 hlm.; ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

519.507

Content Type

-

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Jurusan Matematika
Matematika Statistikal

Specific Detail Info

-

Statement of Responsibility

SEPTA

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment