Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Algoritme Jurnal Mahasiswa Teknik Informatika
Martin, Nicolas
Unknown Affiliation
Computer Science & IT

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Klasifikasi Kanker Kulit Pada Citra Dermatoskopi Menggunakan CNN Martin, Nicolas; Udjulawa, Daniel
Jurnal Algoritme Vol 5 No 1 (2024): Oktober 2024 || Algoritme Jurnal Mahasiswa Teknik Informatika
Publisher : Program Studi Teknik Informatika Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/algoritme.v5i1.9034

Abstract

Skin health is an important aspect of human well-being that is often overlooked because it is considered trivial. There are various types of skin diseases, ranging from allergies, fungal infections, to skin cancer which causes high mortality rates according to WHO. Early diagnosis is essential to improve skin cancer recovery, but often requires sophisticated medical devices and biopsies, where doctors remove a patient's skin lesion through minor surgery to detect cancer cells. This study uses the Convolutional Neural Network (CNN) method with the AlexNet architecture to classify skin cancer types. Convolutional Neural Network was chosen because of its ability to extract complex features from images for accurate classification. The dataset used came from Kaggle, consisting of 24,839 images, with testing using all data and 3,000 data, 500 images each for 6 types of skin cancer. The data is divided into 80% for training and 20% for testing. The best results were achieved using 24.839 data, a learning rate of 0.0001, Adamax Optimizer, batch size 16, and epoch 40, resulting in an accuracy value of 72%, a recall value of 72%, a precision value of 70%, and an F1 score of 69%.
Co-Authors Daniel Udjulawa