RDCNET: CONVOLUTIONAL NEURAL NETWORKS FOR CLASSIFICATION OF RETINOPATHY DISEASE IN UNBALANCED DATA CASES
| Main Authors: | Edi Abdurachman, Boy Subirosa Sabarguna, Bambang Krismono Triwijoyo, Widodo Budiharto |
|---|---|
| Format: | electronic file |
| Bahasa: | eng |
| Terbitan: |
ICIC Express Letters
, 2020
|
| Subjects: | |
| Online Access: |
http://library.itltrisakti.ac.id/catalog/index.php?p=show_detail&id=1840 |
Daftar Isi:
- Retinopathy disease is a type of retinal disorder, which often occurs, including hypertensive retinopathy and diabetic hypertension. Detection of retinopathy can beby analyzing the retinal image, using a deep learning approach, but the problem that isoften faced is unbalanced data. In this study, a convolutional neural network architecture is proposed for the classification of retinopathy using the MESSIDOR database thathas been labeled, by duplicating and augmentation of sample images in classes with lownumbers of samples using a data generator to overcome the problem of unbalanced data.The experimental results show that the validation and testing accuracy performance onthe model with two output classes are 100%, and 87.50%, while on the model with fouroutput classes are 99.38%, and 76.47%.