Skripsi

KLASIFIKASI RHEUMATOLOGI MENGGUNAKAN VISION TRANSFORMER

---

Penilaian

---

The development of Artificial Intelligence (AI) has made significant contributions to the medical field, particularly in image-based diagnosis. Rheumatology diseases are often difficult to diagnose due to the complexity of medical image analysis. To address this challenge, this study proposes the use of the Vision Transformer (ViT) for classifying medical images related to rheumatology conditions. ViT was chosen for its ability to capture complex spatial patterns through the self-attention mechanism, which has been shown to outperform CNNs in certain image classification tasks. Data augmentation techniques were also applied to overcome dataset limitations and improve model generalization. Two architectures, ViT-B16 and ViT-B32, were fine-tuned, and their performance was evaluated using accuracy, precision, and recall metrics. The experimental results indicate that ViT-based models can deliver competitive performance in rheumatology medical image classification. ViT-B16 demonstrated the most consistent results among the tested variants, reaffirming the effectiveness of this architecture in supporting more accurate image-based diagnoses.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2507006185	T185426	T1854262025	Central Library (Reference)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T1854262025

Publisher

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

Collation

xvii, 92 hlm.; ilus.; tab.; 29 cm.

Language

Indonesia

ISBN/ISSN

-

Classification

006.307

Content Type

Text

Media Type

unmediated

Carrier Type

other (computer)

Edition

-

Subject(s)

Kecerdasan Buatan
Prodi Sistem Komputer

Specific Detail Info

-

Statement of Responsibility

MI

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment