IMPLEMENTASI TRANSFER LEARNING PADA CONVOLUTIONAL NEURAL NETWORK UNTUK DIAGNOSIS COVID-19 DAN PNEUMONIA PADA CITRA X-RAY

WIJAYA, ALEXANDER ERIC (2021) IMPLEMENTASI TRANSFER LEARNING PADA CONVOLUTIONAL NEURAL NETWORK UNTUK DIAGNOSIS COVID-19 DAN PNEUMONIA PADA CITRA X-RAY. Masters thesis, UNIVERSITAS MA CHUNG.

	Text 05 311710001_ABSTRACT.pdf Download (6kB)
	Text 10 311710001_BAB 1.pdf Download (139kB)
	Text 11 311710001_BAB 2.pdf Download (543kB)
	Text 12 311710001_BAB 3.pdf Restricted to Registered users only Download (685kB)
	Text 13 311710001_BAB 4.pdf Restricted to Registered users only Download (504kB)
	Text 14 311710001_BAB 5.pdf Download (125kB)
	Text 15 311710001_DAFTAR PUSTAKA.pdf Download (16kB)

Abstract

COVID-19 has become one of the big problems for countries in the world since 2020. COVID-19 and Pneumonia have many symptoms such as coughing and shortness of breath. Efforts to diagnose COVID-19 and Pneumonia are carried out by
laboratory examinations and also chest X-rays. The chest x-ray images of COVID-19 patients have similarities with the x-ray results of Pneumonia patients, but radiologists
managed to find that there are differences between the chest x-ray images of COVID�19 patients and the chest x-ray images of Pneumonia patients where there is a glass-like
pattern. pounded on X-ray images of patients with the Corona virus.Diagnosis is on the patient's chest x-ray image using the Deep Learning model. This study will also compare the performance of the Xception model using Transfer
Learning with the performance of the Xception model without Transfer Learning. There are 4 configuration experiments on the Xception model without Transfer, namely
training on the configuration of the base model layer, training on the custom head model, and training on the base model layer and custom head model. There are 2
experiments using Resnet50 and VGG16 models without Transfer Learning.earning has better performance than the
Xception model without Transfer Learning. The four Xception model experiments without Transfer Learning and the second experiment with the Resnet and VGG16 models had accuracy above 85%. However, the model without Transfer Learning was
not able to recognize Pneumonia on the patient's chest x-ray image.Keywords:Transfer Learning, Pneumonia, COVID-19, virus Corona, CNN, X-Ray, Deep Learning

Item Type:	Thesis (Masters)
Additional Information:	TUGAS AKHIR
Subjects:	T Technology > T Technology (General)
Divisions:	Fakultas Teknologi dan Desain > S1 Teknik Informatika
Depositing User:	Surya
Date Deposited:	19 Nov 2024 03:26
Last Modified:	19 Nov 2024 03:26
URI:	http://repository.machung.ac.id/id/eprint/479

Actions (login required)

View Item