Klasifikasi Citra Penyakit Monkeypox Dengan Random Forest Serta Ekstraksi Fitur GLCM Dan VGG19

Zaki, Muhammad Azka (2026) Klasifikasi Citra Penyakit Monkeypox Dengan Random Forest Serta Ekstraksi Fitur GLCM Dan VGG19. Undergraduate thesis, UPN Veteran Jawa Timur.

	Text (cover) 21081010132.-cover.pdf Download (1MB)
	Text (bab 1) 21081010132.-bab1.pdf Download (253kB)
	Text (bab 2) 21081010132.-bab2.pdf Restricted to Repository staff only until 20 January 2029. Download (682kB)
	Text (bab 3) 21081010132.-bab3.pdf Restricted to Repository staff only until 20 January 2029. Download (780kB)
	Text (bab 4) 21081010132.-bab4.pdf Restricted to Repository staff only until 20 January 2029. Download (1MB)
	Text (bab 5) 21081010132.-bab5.pdf Download (243kB)
	Text (daftar pustaka) 21081010132.-daftarpustaka.pdf Download (190kB)
	Text (lampiran) 21081010132.-lampiran.pdf Restricted to Repository staff only until 20 January 2029. Download (364kB)

Abstract

Monkeypox is a contagious skin disease that can spread through both direct infection and indirect infection via household objects. Manual detection can increase the risk of disease transmission, therefore innovations in the form of mobile applications can serve as supportive tools, as mobile applications can be used individually without the risk of disease transmission. A fast and accurate diagnostic method is required to classify Monkeypox. This study aims to classify Monkeypox images using the Random Forest algorithm, with GLCM and VGG19 feature extraction methods performed in parallel and then combined. The dataset consists of 770 original images, which were subsequently expanded to 5,860 images through geometric transformation-based augmentation. A total of 24 training scenarios were conducted and divided into two groups: 8 scenarios for Random Forest classification with GLCM feature extraction, and 16 scenarios for Random Forest classification with a combination of GLCM and VGG19 feature extraction. The results show that the combination of GLCM and VGG19 feature extraction with Random Forest classification achieved an accuracy of 95.5%, while the Random Forest and GLCM method achieved an accuracy of only 79.1%, indicating that the use of VGG19 as a feature extraction method can improve the accuracy of Random Forest classification with GLCM feature extraction in the case of Monkeypox images. These findings demonstrate the potential of this method as a machine learning approach for detecting Monkeypox and can be further developed using other artificial intelligence approaches.

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	Mandyartha, Eka Prakarsa	NIDN0725058805	eka_prakarsa.fik@upnjatim.ac.id
Thesis advisor	Junaidi, Achmad	NIDN0710117803	achmadjunaidi.if@upnjatim.ac.id

Subjects:

Q Science > QA Mathematics > QA75 Electronic computers. Computer science

Divisions:

Faculty of Computer Science > Departemen of Informatics

Depositing User:

Muhammad Azka Zaki

Date Deposited:

20 Jan 2026 02:05

Last Modified:

20 Jan 2026 02:05

URI:

https://repository.upnjatim.ac.id/id/eprint/48884