KLASIFIKASI COVID-19 DENGAN CITRA X-RAY PARU-PARU MENGGUNAKAN MODEL DEEP BELIEF NETWORK (DBN)

INDRIANI, ASTRI and Suprapto, Bhakti Yudho (2023) KLASIFIKASI COVID-19 DENGAN CITRA X-RAY PARU-PARU MENGGUNAKAN MODEL DEEP BELIEF NETWORK (DBN). Undergraduate thesis, Sriwijaya University.

	Text RAMA_20201_03041381924094.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (4MB) | Request a copy
	Text RAMA_20201_03041381924094_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy
	Text RAMA_20201_03041381924094_0011027503_01_font_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (1MB)
	Text RAMA_20201_03041381924094_0011027503_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (749kB) | Request a copy
	Text RAMA_20201_03041381924094_0011027503_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (493kB) | Request a copy
	Text RAMA_20201_03041381924094_0011027503_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_20201_03041381924094_0011027503_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (190kB) | Request a copy
	Text RAMA_20201_03041381924094_0011027503_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (310kB) | Request a copy
	Text RAMA_20201_03041381924094_0011027503_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy

Abstract

Corona Virus Disease 2019 or also known as COVID-19 is a disease or virus that has spread around the world in recent years. This virus has claimed many victims. Therefore, the initial examination can be carried out using a chest X-Ray because the costs incurred for chest x-rays are cheaper compared to PCR tests and swab tests. In this study, the data used were chest X-Ray image data. In this study, x-ray images were taken from Dr. Rivai Abdullah Palembang (Covid-19, Normal, and TBC) and kaggle (Covid-19, Normal, TBC, and Pneumonia). For the training process, 10,000 images are used in 4 classes. Meanwhile, for the testing process, 400 x-ray images of the lungs (Covid-19, Normal, TB, and Pneumonia) were taken outside the data for training. Then for the test data using the GUI, 10 new images were taken from the Hospital. This study uses the Deep Belief Network (DBN) model with epochs of 1,000, 5,000, and 10,000, each of which has training accuracy of 72%, 93% and 96%. While the LeNet architecture CNN model as a comparison gets 94% accuracy. The results show that the DBN model with 10,000 epochs and the LeNet architecture CNN model are better than the DBN model with 1,000 and 5,000 epochs. However, the Computational DBN requires less time than the CNN.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Covid-19, klasifikasi, deep belief network, citra x-ray paru-paru
Subjects:	T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK1-9971 Electrical engineering. Electronics. Nuclear engineering > TK1 Electrical engineering--Periodicals. Automatic control--Periodicals. Computer science--Periodicals. Information technology--Periodicals. Automatic control. Computer science. Electrical engineering. Information technology.
Divisions:	03-Faculty of Engineering > 20201-Electrical Engineering (S1)
Depositing User:	Astri Indriani
Date Deposited:	17 Jul 2023 01:32
Last Modified:	17 Jul 2023 01:32
URI:	http://repository.unsri.ac.id/id/eprint/117125

Actions (login required)

View Item