SISTEM DETEKSI KEBOCORAN JANTUNG MENGGUNAKAN METODE FASTER R-CNN

AL AZDI, FARANSI and Nurmaini, Siti (2022) SISTEM DETEKSI KEBOCORAN JANTUNG MENGGUNAKAN METODE FASTER R-CNN. Undergraduate thesis, Sriwijaya University.

	Text RAMA_ 56201_09011181621029.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (4MB) | Request a copy
	Text RAMA_ 56201_09011181621029_0002085908_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (20MB) | Request a copy
Preview	Text RAMA_ 56201_09011181621029_0002085908_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (832kB) | Preview
	Text RAMA_ 56201_09011181621029_0002085908_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (583kB) | Request a copy
	Text RAMA_ 56201_09011181621029_0002085908_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (753kB) | Request a copy
	Text RAMA_ 56201_09011181621029_0002085908_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy
	Text RAMA_ 56201_09011181621029_0002085908_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (55kB) | Request a copy
	Text RAMA_ 56201_09011181621029_0002085908_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (142kB) | Request a copy
	Text RAMA_ 56201_09011181621029_0002085908_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (274kB) | Request a copy

Abstract

Leaky heart disease is a disease of heart valve abnormalities. Diseases called congenital heart defects, are abnormalities in the structure of the heart from birth. This method of examining congenital heart disease can be done with the help of echocardiography. Echocardiography is a tool used for medical examination methods by utilizing high-frequency sound waves to capture the structure of the heart. From the data recorded by the echocardiographic device, the expert can diagnose a leak in the fetal heart valve. This study limits the problem of the location of the leak in the heart valve into three types of heart leakage, namely atrial septal defect (ASD), ventricular septal defect (VSD), and atrioventricular septal defect (AVSD). This heart valve leak detection research method uses faster R-CNN with input and output data in the form of image data that are labeled before and after prediction. The architectures used in this research are VGG16, MobileNetV1 and Resnet50. The final result of the study based on the MAP value, loss value and the number of objects detected correctly is the VGG16 architecture with a MAP value of 89%.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Jantung Kongenital, ekokardiografi, atrium septal defect (ASD), ventricle septal defect (VSD), atrioventricular septal defect (AVSD), VGG16, Mobilenetv1, Resnet50, faster R-CNN, MAP
Subjects:	T Technology > TA Engineering (General). Civil engineering (General) > TA164 Bioengineering
Divisions:	09-Faculty of Computer Science > 56201-Computer Systems (S1)
Depositing User:	Faransi Al-azdi
Date Deposited:	16 Mar 2022 01:40
Last Modified:	16 Mar 2022 01:40
URI:	http://repository.unsri.ac.id/id/eprint/66189

Actions (login required)

View Item