KLASIFIKASI DAN VISUALISASI ENAM KELAS ABNORMALITAS JANTUNG JANIN MENGGUNAKAN CONVOLUTIONAL NEURAL NETWORK DAN GRAD-CAM

LESTARI, YUNI TRI and Nurmaini, Siti (2023) KLASIFIKASI DAN VISUALISASI ENAM KELAS ABNORMALITAS JANTUNG JANIN MENGGUNAKAN CONVOLUTIONAL NEURAL NETWORK DAN GRAD-CAM. Undergraduate thesis, Sriwijaya University.

	Text RAMA_56201_09011181924154.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (4MB) | Request a copy
	Text RAMA_56201_09011181924154_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (10MB) | Request a copy
	Text RAMA_56201_09011181924154_0002085908_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (1MB)
	Text RAMA_56201_09011181924154_0002085908_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (803kB) | Request a copy
	Text RAMA_56201_09011181924154_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_09011181924154_0002085908_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (952kB) | Request a copy
	Text RAMA_56201_09011181924154_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_09011181924154_0002085908_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (728kB) | Request a copy
	Text RAMA_56201_09011181924154_0002085908_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy

Abstract

The use of Artificial Intelligence (AI) technology in healthcare has brought significant changes in recent years, particularly in disease diagnosis. Deep learning is a popular AI technique used in various fields, including healthcare, due to its ability to process complex data and recognize patterns that are difficult for humans to identify, potentially aiding in disease diagnosis. The methods used in this study were Convolutional Neural Network methods such as MobileNetV2, ResNet50, ResNet101, DenseNet101, and DenseNet201, as well as Explainable Artificial Intelligence method Grad-Cam. The dataset used was fetal echo image data from Dr. Mohammad Hoesin Central General Hospital. The study focused on finding the best Convolutional Neural Network model for classifying fetal heart disease abnormalities. After classification using the Convolutional Neural Network architecture, image visualization was applied using Grad-Cam. The main parameters used in this study were accuracy, sensitivity, and specificity. The results of the classification process showed that the DenseNet101 architecture had the best evaluation values, with an accuracy of 88.5%, sensitivity of 60%, and specificity of 93.3%. For the Grad-Cam implementation, the model was effective in visualizing abnormal images, but not as effective in normal images as the heatmap was still detected.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Kecerdasan Buatan, Citra
Subjects:	T Technology > T Technology (General) > T1-995 Technology (General) > T18 Modern
Divisions:	09-Faculty of Computer Science > 56201-Computer Systems (S1)
Depositing User:	Yuni Tri Lestari
Date Deposited:	23 May 2023 06:23
Last Modified:	23 May 2023 06:23
URI:	http://repository.unsri.ac.id/id/eprint/103521

Actions (login required)

View Item