Identifikasi Penyakit Autoimun Kulit Menggunakan Metode Convolutional Neural Network

Zahra, Annisa Lusyani (2025) Identifikasi Penyakit Autoimun Kulit Menggunakan Metode Convolutional Neural Network. Undergraduate thesis, UPN Veteran Jawa Timur.

	Text (COVER) 20082010153_ANNISA_LUSYANI_ZAHRA_LAPORAN_SKRIPSI_CETAK2_COVER fix.pdf Download (4MB)
	Text (BAB I) 20082010153_ANNISA_LUSYANI_ZAHRA_LAPORAN_SKRIPSI_CETAK2_BAB I.pdf Download (3MB)
	Text (BAB 2) 20082010153_ANNISA_LUSYANI_ZAHRA_LAPORAN_SKRIPSI_CETAK2_BAB II.pdf Restricted to Repository staff only until May 2027. Download (3MB)
	Text (BAB 3) 20082010153_ANNISA_LUSYANI_ZAHRA_LAPORAN_SKRIPSI_CETAK2_BAB III.pdf Restricted to Repository staff only until May 2027. Download (3MB)
	Text (BAB 4) 20082010153_ANNISA_LUSYANI_ZAHRA_LAPORAN_SKRIPSI_CETAK2_BAB IV.pdf Restricted to Repository staff only until May 2027. Download (3MB)
	Text (BAB 5) 20082010153_ANNISA_LUSYANI_ZAHRA_LAPORAN_SKRIPSI_CETAK2_BAB V.pdf Download (3MB)
	Text (DAFTAR PUSTAKA) 20082010153_ANNISA_LUSYANI_ZAHRA_LAPORAN_SKRIPSI_CETAK2_DAPUS.pdf Download (3MB)
	Text (LAMPIRAN) 20082010153_ANNISA_LUSYANI_ZAHRA_LAPORAN_SKRIPSI_CETAK2_LAMPIRAN.pdf Restricted to Repository staff only Download (3MB)

Abstract

Autoimmune diseases are conditions in which the immune system, which is supposed to protect the body from infections, instead attacks healthy cells and tissues. One form of this is autoimmune skin diseases, which include various dermatological conditions such as psoriasis, lichen planus, vitiligo, dermatomyositis, and hidradenitis. These diseases present a range of symptoms, including rashes, skin discoloration, lesions, inflammation, and pain. Therefore, this study aims to develop a digital image-based method to improve the accuracy of autoimmune skin disease identification. This research applies deep learning using Convolutional Neural Network (CNN) architectures by comparing ResNet50, DenseNet121, and EfficientNetB0. Evaluations were conducted on both the original dataset and an augmented dataset to assess the impact of augmentation on model performance. Experimental results showed that the DenseNet121 architecture with a batch size of 32 and 60 epochs achieved the best accuracy at 92.43%. This model also demonstrated stability across various batch size and epoch configurations. As an implementation, the optimal model was deployed as a web-based application using Flask, which can serve as a tool to assist in the identification of autoimmune skin diseases.

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	Arifiyanti, Amalia Anjani	NIDN0712089201	amalia_anjani.fik@upnjatim.ac.id
Thesis advisor	Sugata, Tri Luhur Indayanti	NIDN	tri.luhur.fasilkom@upnjatim.ac.id

Subjects:

T Technology > T Technology (General)

Divisions:

Faculty of Computer Science > Departemen of Information Systems

Depositing User:

Annisa Lusyani Zahra

Date Deposited:

27 May 2025 05:39

Last Modified:

27 May 2025 05:39

URI:

https://repository.upnjatim.ac.id/id/eprint/36525