KLASIFIKASI PENYAKIT MONKEYPOX DENGAN MENGGUNAKAN METODE GLCMLBP DAN ALGORITMA SVM

Hutagaol, LeonHoss (2025) KLASIFIKASI PENYAKIT MONKEYPOX DENGAN MENGGUNAKAN METODE GLCMLBP DAN ALGORITMA SVM. Undergraduate thesis, UPN Veteran Jawa Timur.

[img] Text (Cover)
COVER.pdf

Download (2MB)
[img] Text (Bab 1)
BAB 1.pdf

Download (92kB)
[img] Text
BAB 2.pdf
Restricted to Repository staff only until 4 June 2027.

Download (605kB) | Request a copy
[img] Text (Bab 3)
BAB 3.pdf
Restricted to Repository staff only until 4 June 2027.

Download (587kB) | Request a copy
[img] Text (Bab 4)
BAB 4.pdf
Restricted to Repository staff only until 4 June 2027.

Download (2MB) | Request a copy
[img] Text (Bab 5)
BAB 5.pdf

Download (10kB)
[img] Text (Daftar Pustaka)
DAFTAR PUSTAKA.pdf

Download (140kB)

Abstract

Monkeypox is an infectious disease that requires early detection for effective treatment. This study aims to develop a Monkeypox image classification model with a hybrid approach that combines texture feature extraction using Gray Level Co-occurrence Matrix (GLCM) and Local Binary Pattern (LBP), and classification using the Support Vector Machine (SVM) algorithm. The dataset used consists of 3200 Monkeypox images that have gone through a preprocessing stage including grayscale conversion and median filtering to remove noise. Feature extraction is carried out by combining GLCM (energy, contrast, correlation, homogeneity) and LBP to obtain a more comprehensive texture representation. Classification is carried out by testing various SVM kernels (linear, polynomial, RBF, sigmoid) and manual parameter tuning. Performance evaluation using accuracy, precision, recall, and F1-score metrics shows that the model with combined GLCM-LBP features and RBF kernels achieves the highest accuracy of 94%, with stability and efficient computing time. These results indicate that the hybrid approach of GLCM-LBP and SVM with RBF kernel has great potential in supporting the automatic diagnosis of Monkeypox disease through medical image analysis.

Item Type: Thesis (Undergraduate)
Contributors:
ContributionContributorsNIDN/NIDKEmail
Thesis advisorSwari, Made Hanindia PramiNIDN0805028901madehanindia.fik@upnjatim.ac.id
Thesis advisorAkbar, Fawwas AliNIDN0017039201fawwaz_ali.fik@upnjatim.ac.id
Subjects: Q Science > QA Mathematics > QA76.6 Computer Programming
Q Science > QA Mathematics > QA76.625 Internet Programming
R Medicine > RA Public aspects of medicine > RA0421 Public health. Hygiene. Preventive Medicine
Divisions: Faculty of Computer Science > Departemen of Informatics
Depositing User: Mr LeonHoss Hutagaol
Date Deposited: 08 Jul 2025 07:45
Last Modified: 08 Jul 2025 07:45
URI: https://repository.upnjatim.ac.id/id/eprint/38899

Actions (login required)

View Item View Item