SHIDQI, MUHAMMAD AKMAL and Andriani, Yuli and Desiani, Anita (2023) KOMBINASI ARSITEKTUR VGG DAN XCEPTION DALAM KLASIFIKASI CITRA CT-SCANS TIGA DIMENSI PADA PENYAKIT COVID-19. Undergraduate thesis, Sriwijaya University.
Text
RAMA_44201_08011281924020.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy |
|
Text
RAMA_44201_08011281924020_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (6MB) | Request a copy |
|
Text
RAMA_44201_08011281924020_0002077202_0011127702_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (599kB) |
|
Text
RAMA_44201_08011281924020_0002077202_0011127702_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (384kB) | Request a copy |
|
Text
RAMA_44201_08011281924020_0002077202_0011127702_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (82kB) | Request a copy |
|
Text
RAMA_44201_08011281924020_0002077202_0011127702_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (770kB) | Request a copy |
|
Text
RAMA_44201_08011281924020_0002077202_0011127702_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (11kB) | Request a copy |
|
Text
RAMA_44201_08011281924020_0002077202_0011127702_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (160kB) | Request a copy |
Abstract
Detection in CT-Scans images can be done by applying image classification using methods found in Convolutional Neural Network (CNN). The CNN architectures commonly used in classification are VGG and Xception. In this study, a combination of VGG and Xception architectures is applied for the classification of COVID-19 disease using CT-Scans images. The combination involves using VGG architecture with 13 convolutional layers, followed by Xception architecture with 2 depthwise separable convolution layers and 2 fully connected layers to determine the classification results. The research stages conducted include data collection, preprocessing, training, testing, evaluation, analysis and interpretation of results, and conclusion drawing. The results of the CT-Scans image classification research using the MosMed dataset with VGG and Xception architectures yielded an accuracy of 95.57%, sensitivity of 93.89%, specificity of 97.36%, F1-Score of 95.64%, and Cohen's Kappa of 91.14%. Based on the obtained results, the combination of VGG and Xception architectures is capable of performing excellent classification on CT-Scans images.
Item Type: | Thesis (Undergraduate) |
---|---|
Subjects: | Q Science > QA Mathematics > QA75-76.95 Calculating machines > QA76.9.B45 Big data. Machine learning. Quantitative research. Metaheuristics. |
Divisions: | 08-Faculty of Mathematics and Natural Science > 44201-Mathematics (S1) |
Depositing User: | MUHAMMAD AKMAL SHIDQI |
Date Deposited: | 10 Aug 2023 02:01 |
Last Modified: | 10 Aug 2023 02:01 |
URI: | http://repository.unsri.ac.id/id/eprint/126830 |
Actions (login required)
View Item |