IMPLEMENTASI CONVOLUTIONAL NEURAL NETWORKS (CNN) MENGGUNAKAN ARSITEKTUR RESNET-50 UNTUK KLASIFIKASI PENYAKIT KUKU BERDASARKAN CITRA KUKU

Irmaya Salsabila, . (2025) IMPLEMENTASI CONVOLUTIONAL NEURAL NETWORKS (CNN) MENGGUNAKAN ARSITEKTUR RESNET-50 UNTUK KLASIFIKASI PENYAKIT KUKU BERDASARKAN CITRA KUKU. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.

[img] Text
ABSTRAK.pdf
Download (254kB)
[img] Text
AWAL.pdf
Download (563kB)
[img] Text
BAB 1.pdf
Restricted to Repository UPNVJ Only
Download (328kB)
[img] Text
BAB 2.pdf
Restricted to Repository UPNVJ Only
Download (1MB)
[img] Text
BAB 3.pdf
Restricted to Repository UPNVJ Only
Download (745kB)
[img] Text
BAB 4.pdf
Restricted to Repository UPNVJ Only
Download (1MB)
[img] Text
BAB 5.pdf
Download (311kB)
[img] Text
DAFTAR PUSTAKA.pdf
Download (286kB)
[img] Text
RIWAYAT HIDUP.pdf
Restricted to Repository UPNVJ Only
Download (191kB)
[img] Text
LAMPIRAN.pdf
Restricted to Repository UPNVJ Only
Download (5MB)
[img] Text
HASIL PLAGIARISME.pdf
Restricted to Repository staff only
Download (17MB)
[img] Text
ARTIKEL KI.pdf
Restricted to Repository staff only
Download (737kB)

Abstract

Nail diseases are often underestimated because they do not directly show clinical symptoms that disrupt health. However, changes in the color, texture, or shape of nails can be early indicators of various medical disorders, such as infections, metabolic disorders, and autoimmune diseases. Common nail diseases such as Koilonychia, Onychomycosis, and Psoriasis not only affect physical health but also impact aesthetics and quality of life. This study proposes a nail disease classification method by combining feature extraction from the Convolutional Neural Network (CNN) architecture ResNet-50 and traditional texture feature extraction using Local Binary Pattern (LBP). The dataset consists of 2,000 images divided into 80% training data, 10% validation, and 10% testing. The testing results show that the fusion model ResNet-50 + LBP can classify four classes of nail diseases with an accuracy of 98.50%, and precision, recall, and F1-score values of 98.50%, 98.50%, and 98.49%, respectively. This approach effectively captures local texture features and complex visual patterns simultaneously, making it suitable for accurate and efficient image-based nail disease classification.

Item Type: Thesis (Skripsi)
Additional Information: [No.Panggil: 2110511080] [Pembimbing 1: Neny Rosmawarni] [Pembimbing 2: Nurul Afifah Arifuddin] [Penguji 1: Musthofa Galih Pradana] [Penguji 2: Hamonangan Kinantan Prabu]
Uncontrolled Keywords: Convolutional Neural Network, Nail Disease Classification, Local Binary Pattern (LBP), ResNet-50
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: Fakultas Ilmu Komputer > Program Studi Informatika (S1)
Depositing User: IRMAYA SALSABILA
Date Deposited: 13 Jul 2025 21:10
Last Modified: 18 Jul 2025 08:10
URI: http://repository.upnvj.ac.id/id/eprint/37395

Actions (login required)

View Item View Item