Penerapan Metode Vision Transformer untuk Proses Klasifikasi Penyakit Pneumonia melalui Citra Chest X-Ray

Maulana, Raihan Thobie Nabil (2024) Penerapan Metode Vision Transformer untuk Proses Klasifikasi Penyakit Pneumonia melalui Citra Chest X-Ray. Undergraduate thesis, UPN Veteran Jawa Timur.

	Text (Cover) COVER_SKRIPSI.pdf Download (3MB)
	Text (Bab I) BAB I_SKRIPSI.pdf Download (1MB)
	Text (Bab II) BAB II_SKRIPSI.pdf Restricted to Repository staff only until 16 December 2026. Download (6MB)
	Text (Bab III) BAB III_SKRIPSI.pdf Restricted to Repository staff only until 16 December 2026. Download (7MB)
	Text (Bab IV) BAB IV_SKRIPSI.pdf Restricted to Repository staff only until 16 December 2026. Download (8MB)
	Text (Bab V) BAB V_SKRIPSI.pdf Download (388kB)
	Text (Daftar Pustaka) DAFPUS_SKRIPSI.pdf Download (1MB)

Abstract

Pneumonia is a type of acute respiratory infection that is often caused by viruses or bacteria. Poor air quality in Jakarta's urban areas increases people's risk of pneumonia, acute respiratory infections (ARI) and asthma. In 2019, more than 740,180 children under the age of 5 died from pneumonia, accounting for 14% of all early childhood deaths. Medical researchers have conducted many studies related to early diagnosis of pneumonia. One of the techniques to detect pneumonia is through Chest X-Rays, which have been widely developed for classification. Vision Transformer (ViT) is one of the Deep Learning architectures developed specifically for image processing. The purpose of this research is to implement a pneumonia classification task with ViT that is expected to help detect pneumonia early so that it can be treated faster and better. The results of the research indicated that the ViT Model performed well after applying several augmentation variations, and was stable in both training and testing. at a small Learning Rate of 0.00001 with a Batch Size of 64, it produced 84% accuracy for pneumonia cases. But by implementing the ViT-Base16 Pretrained Model, it can help the model improve its accuracy to a value of 87%.

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	Via, Yisti Vita	NIDN19860425 2021212 001	yistivia.if@upnjatim.ac.id
Thesis advisor	Mandyartha, Eka Prakarsa	NIDN19880525 2018031 001	eka_prakarsa.fik@upnjatim.ac.id

Subjects:

Q Science > QA Mathematics > QA76.6 Computer Programming

Divisions:

Faculty of Computer Science > Departemen of Informatics

Depositing User:

Thobie RTNM Aa

Date Deposited:

16 Dec 2024 06:07

Last Modified:

16 Dec 2024 06:07

URI:

https://repository.upnjatim.ac.id/id/eprint/33459