KOMBINASI ARSITEKTUR DENSENET BOTTLENECK LAYER DAN GATE RECURRENT UNITS (GRU) PADA KLASIFIKASI PENYAKIT GLAUKOMA MENGGUNAKAN CITRA RETINA

KARINA, KARINA and Desiani, Anita and Dewi, Novi Rustiana (2024) KOMBINASI ARSITEKTUR DENSENET BOTTLENECK LAYER DAN GATE RECURRENT UNITS (GRU) PADA KLASIFIKASI PENYAKIT GLAUKOMA MENGGUNAKAN CITRA RETINA. Undergraduate thesis, Sriwijaya University.

	Text RAMA_44021_08011182025007.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy
	Text RAMA_44021_08011182025007_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (9MB) | Request a copy
	Text RAMA_44021_08011182025007_0011127702_0013117004_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (1MB)
	Text RAMA_44021_08011182025007_0011127702_0013117004_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (834kB) | Request a copy
	Text RAMA_44021_08011182025007_0011127702_0013117004_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (280kB) | Request a copy
	Text RAMA_44021_08011182025007_0011127702_0013117004_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (790kB) | Request a copy
	Text RAMA_44021_08011182025007_0011127702_0013117004_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (107kB) | Request a copy
	Text RAMA_44021_08011182025007_0011127702_0013117004_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (146kB) | Request a copy

Abstract

Glaucoma is a chronic eye disease that can lead to blindness. Glaucoma detection can be done by classification using the DenseNet architecture. DenseNet provides good model performance, but often suffers from overfitting. Bottleneck layers can be used to prevent overfitting by reducing the feature dimensions before entering deeper layers. However, reducing the feature dimension may lead to the loss of useful features. Another method that can reach features that have been skipped is the Gate Recurrent Units (GRU) architecture. GRU can update features in the input data by involving information about the overall state of the network. This research applies DenseNet architecture combined with bottleneck layer and GRU architecture. The results of research with retinal image datasets consisting of 3 classes obtained an accuracy value of 98.181%, sensitivity 97.32%, specificity 98.65%, f1-score 97.25%, and cohen's cappa 95.88%. The training graph of the method used proves that this study is able to overcome overfitting. Based on these results, it shows that the combination of DenseNet Bottleneck layer architecture and GRU is able to perform the classification task very well. Keyword : Glaucoma, Classification, retinal image, DenseNet, Bottleneck layers, GRU

Item Type:	Thesis (Undergraduate)
Subjects:	Q Science > QA Mathematics > QA75-76.95 Calculating machines > QA76.9.B45 Big data. Machine learning. Quantitative research. Metaheuristics.
Divisions:	08-Faculty of Mathematics and Natural Science > 44201-Mathematics (S1)
Depositing User:	Karina Karina
Date Deposited:	19 Sep 2024 02:31
Last Modified:	19 Sep 2024 02:31
URI:	http://repository.unsri.ac.id/id/eprint/156666

Actions (login required)

View Item