Muhammad Ilham Robbani, . (2025) PERBANDINGAN PERFORMA METODE TRANSFER LEARNING DALAM DETEKSI PENYAKIT MATA MENGGUNAKAN RESNET-50 DAN VGG16. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![]() |
Text
ABSTRAK.pdf Download (103kB) |
![]() |
Text
AWAL.pdf Download (566kB) |
![]() |
Text
BAB 1.pdf Restricted to Repository UPNVJ Only Download (302kB) |
![]() |
Text
BAB 2.pdf Restricted to Repository UPNVJ Only Download (756kB) |
![]() |
Text
BAB 3.pdf Restricted to Repository UPNVJ Only Download (590kB) |
![]() |
Text
BAB 4.pdf Restricted to Repository UPNVJ Only Download (6MB) |
![]() |
Text
BAB 5.pdf Download (172kB) |
![]() |
Text
DAFTAR PUSTAKA.pdf Download (250kB) |
![]() |
Text
RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (144kB) |
![]() |
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (24MB) |
![]() |
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (30MB) |
![]() |
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (439kB) |
Abstract
The eyes are vital organs that allow humans to acquire most of the information from their surroundings. Diseases such as Age-related Macular Degeneration (AMD), cataracts, diabetic retinopathy, glaucoma, ocular hypertension, and myopia can cause serious vision impairment if not detected and treated early. This study developed an eye disease classification model based on Convolutional Neural Networks (CNN) using the VGG16 and ResNet50 architectures. The dataset used was obtained from the ODIR repository and consists of data from 5,000 patients, divided into 70% for training, 20% for validation, and 10% for testing. The use of transfer learning proved effective in accelerating the training process and enabling more efficient feature extraction, while data augmentation enhanced image diversity and improved the model’s generalization capability. The combination of these two techniques significantly improved classification performance, resulting in higher accuracy and lower loss values. In the best-case scenario, the VGG16 model achieved a validation accuracy of 83.95% with a loss value of 0.5442, while the ResNet50 model achieved an accuracy of 84.90% with a loss of 0.6014. These findings demonstrate that integrating transfer learning and data augmentation plays a crucial role in enhancing the effectiveness of fundus image classification models.
Item Type: | Thesis (Skripsi) |
---|---|
Additional Information: | [No.Panggil: 2010511117] [Pembimbing 1: Jayanta] [Pembimbing 2: Nurul Afifah Ariffudin] [Penguji 1: Ridwan Raafi’udin] [Penguji 2: Muhammad Adrezo] |
Uncontrolled Keywords: | Eye Disease Classification, Fundus Images, Transfer Learning, Data Augmentation, VGG16, ResNet50 |
Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software R Medicine > R Medicine (General) |
Divisions: | Fakultas Ilmu Komputer > Program Studi Informatika (S1) |
Depositing User: | MUHAMMAD ILHAM ROBBANI |
Date Deposited: | 26 Aug 2025 01:19 |
Last Modified: | 26 Aug 2025 01:19 |
URI: | http://repository.upnvj.ac.id/id/eprint/37461 |
Actions (login required)
![]() |
View Item |