Text

PENERAPAN AUGMENTASI DATA DAN PRINCIPAL COMPONENT ANALYSIS PADA PENENTUAN PENYAKIT DIABETIC RETINOPATHY MENGGUNAKAN ALGORITMA RECURRENT CONVOLUTIONAL NEURAL NETWOR

---

Penilaian

---

Diabetic Retinopathy (DR) is one of the biggest health problems in the world. DR disease classification process needs to be done early to prevent the occurrence of DR. Recurrent Convolutional Neural Network (RCNN) is a deep learning-based classification algorithm that can classify image data accurately but requires a large amount of image data. Data augmentation can be applied to increase the amount of image data so that training data, validation data, and testing data are obtained as many as 15.000 images, 2.000 images, and 2.000 images. In addition, the large data dimensions make the classification performance not very efficient. Principal Component Analysis (PCA) is a method that can operate dimension reduction in image data so that the cumulative proportion of variance is approximately 99% with the number of principal components is 70. The purpose of this research is to apply data augmentation and PCA method to retinal image data for classifying DR disease using RCNN algorithm. The research methods used are data collection, image enhancement, data augmentation, implementation of PCA and RCNN algorithm, data training, data testing, evaluation, and analysis of results. Classification results were measured by calculating the values of accuracy, sensitivity, specificity, F1-Score, and Cohens Kappa with the values obtained as many as 94,55%, 89,1%, 100%, 94,23%, and 0,891. Based on the classification results obtained, it can be concluded that application of data augmentation and PCA can still provide good classification performance to classify DR disease using RCNN on retinal images.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2207000917	T68494	T684942022	Central Library (Referens)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T684942022

Publisher

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

Collation

xii, 80 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