Pribadi, Argo Galih (2021) DETEKSI COVID-19 BERBASIS CITRA CT-SCAN MENGGUNAKAN METODE EFFICIENTNET. Undergraduate thesis, Institut Teknologi Sepuluh Nopember.
Text
05111740000150-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2023. Download (1MB) | Request a copy |
Abstract
Pendeteksian awal COVID-19 adalah hal yang sangat penting untuk mengetahui sejak dini dan pencegahan penyebarannya. Deteksi COVID-19 dapat menggunakan citra CT-Scan paru-paru. Kendala menggunakan CT-Scan mempunyai kualitas citra yang berbeda-beda tergantung jenis mesin CT.
Beberapa metode telah diusulkan untuk deteksi COVID-19 berbasis citra CT-Scan. Sebagai contoh menggunakan ResNet dan VGG16 yang sudah dilakukan oleh banyak peneliti. Tugas Akhir ini bertujuan untuk mengimplementasikan metode EfficientNet untuk mendeteksi COVID-19 pada citra CT-Scan. Dataset yang digunakan untuk tugas akhir ini terdiri dari data COVID seebanyak 1252 dan Non-COVID 1229. Dari hasil uji coba menunjukkan tingkat akurasi sebesar 85% dan presisi sebesar 92% dengan menggunakan Adam Optimizer.
========================================================================================================
Early detection of COVID-19 is very important to know early and prevent its spread. Detection of COVID-19 can use CT-Scan images of the lungs. Constraints using CT-Scan have different image quality depending on the type of CT machine.
Several methods have been proposed to detect COVID-19 based on CT-Scan images. For example the use of ResNet and VGG16 which has been done by many people. This final project aims to implement the EfficientNet method to detect COVID-19 on CT-Scan images. The dataset used for this final project consists of 1252 COVID and 1229 Non-COVID data. The test results show an accuracy rate of 85% and precision of 92% using the Adam Optimizer.
Item Type: | Thesis (Undergraduate) |
---|---|
Uncontrolled Keywords: | COVID-19, CT-Scan, ResNet, VGG16, EfficientNet |
Subjects: | R Medicine > R Medicine (General) |
Divisions: | Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Informatics Engineering > 55201-(S1) Undergraduate Thesis |
Depositing User: | Argo Galih Pribadi |
Date Deposited: | 23 Aug 2021 07:43 |
Last Modified: | 23 Aug 2021 07:43 |
URI: | http://repository.its.ac.id/id/eprint/89980 |
Actions (login required)
View Item |