DETEKSI RUANG JANTUNG ANAK PADA PANDANGAN 4 CHAMBER MENGGUNAKAN ARSITEKTUR FASTER R-CNN

ESTIYANI, LENI and Nurmaini, Siti (2021) DETEKSI RUANG JANTUNG ANAK PADA PANDANGAN 4 CHAMBER MENGGUNAKAN ARSITEKTUR FASTER R-CNN. Undergraduate thesis, Sriwijaya University.

	Text RAMA_56201_09011181722004.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (3MB) | Request a copy
	Text RAMA_56201_09011181722004_0002085908_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (2MB)
	Text RAMA_56201_09011181722004_0002085908_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (547kB) | Request a copy
	Text RAMA_56201_09011181722004_0002085908_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (572kB) | Request a copy
	Text RAMA_56201_09011181722004_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_09011181722004_0002085908_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (369kB) | Request a copy
	Text RAMA_56201_09011181722004_0002085908_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (347kB) | Request a copy
	Text RAMA_56201_09011181722004_0002085908_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (652kB) | Request a copy
	Text RAMA_56201_09011181722004_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (7MB) | Request a copy

Abstract

The heart is a vital human organ that sometimes has dangerous abnormal conditions, such as: atrioventricular septal defect (AVSD), atrial septal defect (ASD), and ventricular septal defect (VSD). In this final project, we propose a Faster R-CNN architecture method using several backbones such as VGG16, Resnet50 and mobilenetv1 as heart detectors. The dataset used is a dataset in the form of an abnormal child's heart frame with a 4-chamber point of view. This research focuses on the level of accuracy generated from the data frame to build a Faster R-CNN model that is effective in detecting abnormal heart chambers in children such as the right atrium, left atrium, right ventricle, left ventricle and holes. Parameter assessment using mean average precision (mAP) is a benchmark to determine the level of success of the method in detecting objects, especially in abnormal children's heart. The best results were obtained in the model using the VGG16 backbone with a learning rate of 0.001 with an average mAP value of 92.32% and in the unseen data the best results were obtained in the model using the VGG16 backbone learning rate of 0.001 with an average mAP value of 71.49%.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Jantung Anak, Atrioventricular Septal Defect (AVSD), Atrial Septal Defect (ASD), Ventricular Septal Defect (VSD), Faster R-CNN, VGG16, 4 Chamber View, Deteksi Ruang Jantung Anak Abnormal.
Subjects:	Q Science > Q Science (General) > Q334-342 Computer science. Artificial intelligence. Algorithms. Robotics. Automation.
Divisions:	09-Faculty of Computer Science > 56201-Computer Systems (S1)
Depositing User:	Leni Estiyani
Date Deposited:	13 Sep 2021 07:33
Last Modified:	13 Sep 2021 07:33
URI:	http://repository.unsri.ac.id/id/eprint/53886

Actions (login required)

View Item