Text

TEKNIK AUGMENTASI DAN MODIFIKASI ARSITEKTUR XCEPTION DENSE LAYER PADA CITRA RETINA UNTUK KLASIFIKASI PENYAKIT GLAUCOMA

---

Penilaian

---

The application of CNN is widely used in image data, one of which is in the classification of glaucoma using retinal images. CNN architecture has been widely used in classification problems. The advantage of CNN is that it is able to recognize digital image objects with a high level of accuracy, but CNN requires a lot of data. The technique that can be used to reproduce data is Augmentation. CNN has an architecture that improves computational efficiency, namely Xception, but Xception utilizes the skip connection feature which causes a lot of important information from the previous layer to be missed or lost. The addition of a solid layer at the end of the model will allow the Xception architecture to store past and current information for a long time. . This study applies the augmentation and modification of the Xception Dense Layer architecture to meet data needs and obtain a CNN architecture that is able to improve the performance of the Xception architecture. The stages of research carried out include other data collection, data preprocessing, training, testing, evaluation, analysis and interpretation of the results, and drawing conclusions. Augmentation technique is able to increase the amount of data with a total of 7300 retinal image data. The results of accuracy, sensitivity, specificity, and F1-score obtained results of 87.58%, 81.43%, 90.73%, and 81.37%, respectively. These results indicate that the application of augmentation and modification of the Xception Dense Layer architecture works well in the classification of glaucoma using retinal images.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2207004294	T80481	T804812022	Central Library (Referens)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T804812022

Publisher

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

Collation

xii, 68 hlm.; ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

519.07

Content Type

-

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Matematika Terapan
Jurusan Matematika

Specific Detail Info

-

Statement of Responsibility

SEPTA

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment