Article Per Year (5 Year)
p-Index From 2020 - 2025
2.911
P-Index
This Author published in this journals
All Journal Techno.Com: Jurnal Teknologi Informasi SISFOTENIKA Jutisi: Jurnal Ilmiah Teknik Informatika dan Sistem Informasi Progresif: Jurnal Ilmiah Komputer Jurnal Bumigora Information Technology (BITe) Journal of Soft Computing Exploration International Journal of Computer and Information System (IJCIS) International Research on Big-data and Computer Technology (IRobot) Malcom: Indonesian Journal of Machine Learning and Computer Science Innovative: Journal Of Social Science Research Bulletin of Network Engineer and Informatics (BUFNETS) International Journal of Applied Research and Sustainable Sciences (IJARSS)
Nourman Satya Irjanto
Universitas Sepuluh Nopember Papua
Religion Humanities Chemical Engineering, Chemistry & Bioengineering Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Education Electrical & Electronics Engineering Engineering Law, Crime, Criminology & Criminal Justice Public Health Other

Published : 19 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search
Journal : Journal of Soft Computing Exploration

 1 
Melanoma detection on skin images using deep learning based on convolutional neural network (CNN) Irjanto, Nourman Satya; Hermawan, Ruly
Journal of Soft Computing Exploration Vol. 6 No. 2 (2025): June 2025
Publisher : SHM Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joscex.v6i2.567

Abstract

Melanoma is a life-threatening skin cancer that poses challenges in regions with limited access to specialized medical personnel, such as Papua, Indonesia. Early diagnosis is essential, but accurate detection is hindered by the scarcity of dermatologists. This study develops a melanoma detection system using computer vision, utilizing the VGG16 architecture enhanced with the Convolutional Block Attention Module (CBAM) and fine-tuning via transfer learning. The model was trained on a dataset comprising melanoma and non-melanoma images, with data augmentation to address class imbalance. The model achieved an accuracy of 91.25%, precision of 92.31%, recall of 90%, and an F1-score of 91.13%, demonstrating reliable performance in melanoma classification. High specificity (92.5%) indicates a low false positive rate, while sensitivity (90%) shows effective melanoma detection, though the 10% false negative rate requires improvement. Future enhancements include increasing sensitivity through weighted loss functions, optimizing classification thresholds, and performing external validation. Additionally, Grad-CAM is used for interpretability, and a web-based application is proposed to support healthcare practitioners, offering an accessible diagnostic tool for melanoma screening in resource-limited settings.
Co-Authors Ahmad Farhan Maualana Budi Soepriyanto Bun, Tengadi Boney Elvis Pawan Elvis Pawan Heremba, Ismail Hermawan, Ruly Imbiri, Carolina C.Y. Kiswanto, Rahmat Haryadi Kulwy, Agustinus Lahallo, Jim Maria Sesni Regina Jowey Morib, Yemi Pasaribu, Victor Ramos Pawan, Elvis Radika, Radika Rahman, Fadil Ratih Nurul Aprilianti Ratih Nurul Aprilianti Risman, M. Robaha, Paskalino Melgibson Rully Oktavia Hermawan Sabra, Isacc Samon Sarbel Sitanggang Siburian, Riandyka Sutejo, Heru Syaraswati Syaraswati Tatuhey, Emy Lenora Utari, Yanik Wainggai, Virginia Apriliani Teruko Wakdomi Sapari, Mega Christin E Yosep Menekir