DETEKSI CACAT SEPTUM PADA JANTUNG JANIN SECARA REAL-TIME MENGGUNAKAN ARSITEKTUR MASK-RCNN

JOVANDY, ADITHIA and Nurmaini, Siti (2021) DETEKSI CACAT SEPTUM PADA JANTUNG JANIN SECARA REAL-TIME MENGGUNAKAN ARSITEKTUR MASK-RCNN. Undergraduate thesis, Sriwijaya University.

	Text RAMA_56201_09011181722012.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_56201_09011181722012_TURNITIN.pdf - Accepted Version Restricted to Registered users only Available under License Creative Commons Public Domain Dedication. Download (5MB) | Request a copy
Preview	Text RAMA_56201_09011181722012_0002085908_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (393kB) | Preview
	Text RAMA_56201_09011181722012_0002085908_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (802kB) | Request a copy
	Text RAMA_56201_09011181722012_0002085908_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_56201_09011181722012_0002085908_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_56201_09011181722012_0002085908_06_ref.pdf - Bibliography Restricted to Repository staff only Download (411kB) | Request a copy
	Text RAMA_56201_09011181722012_0002085908_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (183kB) | Request a copy
	Text RAMA_56201_09011181722012_0002085908_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (802kB) | Request a copy

Abstract

Congenital heart disease (CHD) or often referred to as congenital heart disease is a disease that causes the most common morbidity of death in developing and developed countries. Congenital heart defects have a mortality prevalence of between 5 and 9 in 1000 births, heart defects often occur in the first year of birth. In the medical world, the state of the heart can be detected through Ultrasonography (USG). The position of the hole in the heart in this study focused on the hole in each class, the atrial septal defect (ASD), the hole that is between the right and left atria. Furthermore, the ventricular septal defect (VSD) is the hole between the right and left ventricles, and the hole between the ASD and VSD is an atrioventricular septal defect (AVSD). The method used is object detection and segmentation of the Mask-RCNN architecture with a convolutional Neural network (CNN). The backbone used in this research is Resnet50 and Resnet101. The best model is obtained by adjusting the learning rate, epoch and batch size which has been increased, from the best model is obtained by using the resnet50 backbone with a Map value of 47%, IoU of 65%, Dsc of 71% and FPS of 10

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Real-Time detection, Fetus heart, Convolutional Neural Network, Mask�RCNN.
Subjects:	T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK7885-7895 Computer engineering. Computer hardware
Divisions:	09-Faculty of Computer Science > 56201-Computer Systems (S1)
Depositing User:	mr Adithia Jovandy jovandy
Date Deposited:	03 Jun 2021 07:14
Last Modified:	03 Jun 2021 07:14
URI:	http://repository.unsri.ac.id/id/eprint/46710

Actions (login required)

View Item