Article Per Year (5 Year)
p-Index From 2021 - 2026
3.018
P-Index
This Author published in this journals
All Journal Elkom: Jurnal Elektronika dan Komputer Intuisi Jurnal Transformatika Jurnal Informatika Upgris AKSIOMA Fountain of Informatics Journal IJISTECH (International Journal Of Information System & Technology) Jurnal Informatika dan Rekayasa Perangkat Lunak Jurnal Teknologi Informasi dan Komunikasi Community Empowerment IJISTECH Jurnal Program Kemitraan dan Pengabdian Kepada Masyarakat ALMUJTAMAE: Jurnal Pengabdian Masyarakat TECHSI - Jurnal Teknik Informatika Paradigma J-ABDIPAMAS (Jurnal Pengabdian Kepada Masyarakat) Jurnal Informatika: Jurnal Pengembangan IT SWAGATI: Journal of Community Service Advance Sustainable Science, Engineering and Technology (ASSET) Sekolah Dasar: Kajian Teori dan Praktik Pendidikan
Febrian Murti Dewanto
Universitas PGRI Semarang
Arts Humanities Chemistry Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Library & Information Science Mathematics Mechanical Engineering Public Health Social Sciences Other

Published : 33 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 33 Documents
Search

 1   2   3   4 
Facial Skin Disease Classification Using Swin Transformer V2 and ResNet-50 in a Flask-Based System Shinta Arum Imaniyah; Febrian Murti Dewanto; Nur Latifah Dwi Mutiara Sari
Paradigma - Jurnal Komputer dan Informatika Vol. 28 No. 1 (2026): March 2026 Period
Publisher : LPPM Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/p.v28i1.12381

Abstract

Facial skin diseases are common health conditions that can significantly affect both physical and psychological well-being. Early identification is essential to minimize the risk of disease progression. However, in many areas, there is still a lack of access to dermatological care. Although deep learning algorithms have been widely used in medical image categorization, few studies offer a direct comparison between convolutional neural networks (CNN) and transformer-based architectures within a cohesive experimental framework, especially concerning the classification of facial skin diseases. This study compares the effectiveness of ResNet-50 with Swin Transformer V2 and develops a deep learning system to classify six different types of skin problems on the face. The models were evaluated using accuracy, precision, recall, and F1-score after the dataset was divided into subsets for testing, validation, and training. According to the trial results, Swin Transformer V2 achieves an astounding accuracy of 97.54%, outperforming ResNet-50, which achieves 94.44%. The training curves indicate stable learning behavior with minimal overfitting. Grad-CAM visualization is applied to improve interpretability by highlighting relevant regions in the images. The best-performing model is implemented in a Flask-based web application as a prototype system for early detection. These results demonstrate how transformer-based architectures can improve classification performance and highlight their potential applications in practical diagnostic support systems
Development of Counseling Sites with Digital Accessibility Features for the Blind and Visually Impaired Students Dini Rakhmawati; Venty; Febrian Murti Dewanto
Advance Sustainable Science Engineering and Technology Vol. 7 No. 1 (2025): November-January
Publisher : Science and Technology Research Centre Universitas PGRI Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26877/asset.v7i1.1157

Abstract

Current counseling services, such as those available through sikons.upgris.ac.id, lack full accessibility for students with disabilities, particularly those who are blind and visually impaired. Studies reveal significant accessibility barriers across educational websites, impeding equal access for users with disabilities. This study addresses these gaps by developing an accessible counseling platform aligned with Web Content Accessibility Guidelines (WCAG) to ensure inclusive access for all students. Using the ADDIE model's structured stages of Analysis, Design, Development, Implementation, and Evaluation, this study aims to create a technically advanced, user-centered application that enhances usability and independence for students with disabilities. Results from user acceptance testing with 11 participants indicated a high satisfaction rate of 89,33%, demonstrating that the platform effectively meets users' needs, significantly improving accessibility and usability in educational counseling services. This outcome underscores the importance of integrating accessibility standards to foster inclusivity and equitable participation in digital educational resources.
Pelatihan Desain Produk Digital Kreatif sebagai Peluang Kerja Remote bagi Remaja Panti Asuhan Al Jannah Kota Semarang Aditiya Pratama Nugroho; Prianka Ratri Nastiti; Febrian Murti Dewanto
ALMUJTAMAE: Jurnal Pengabdian Masyarakat Vol. 6 No. 2 (2026): Agustus
Publisher : Universitas Djuanda Bogor

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30997/almujtamae.v6i2.25001

Abstract

Perkembangan ekonomi digital telah membuka berbagai peluang kerja baru yang dapat dilakukan secara fleksibel melalui pemanfaatan teknologi digital. Namun, remaja panti asuhan masih memiliki keterbatasan dalam memperoleh keterampilan produktif berbasis digital yang relevan dengan perkembangan dunia kerja saat ini. Kegiatan pengabdian kepada masyarakat ini bertujuan untuk meningkatkan keterampilan desain produk digital kreatif serta pemahaman kerja remote bagi remaja Panti Asuhan Al Jannah Kota Semarang melalui pelatihan berbasis praktik menggunakan Canva dan Lynk.id. Metode pelaksanaan dilakukan melalui tahapan observasi, sosialisasi, pelatihan, pendampingan, dan evaluasi kegiatan. Materi pelatihan meliputi pengenalan peluang ekonomi digital, pembuatan produk digital sederhana, penggunaan Canva untuk desain visual, serta simulasi monetisasi produk digital melalui platform Lynk.id. Evaluasi kegiatan dilakukan menggunakan metode pre-test dan post-test untuk mengukur peningkatan pemahaman peserta sebelum dan sesudah pelatihan. Hasil evaluasi menunjukkan adanya peningkatan pada seluruh indikator pelatihan, yaitu pemahaman desain dasar dari 40% menjadi 85%, kemampuan penggunaan Canva dari 38% menjadi 88%, pemahaman kerja remote dari 44% menjadi 82%, literasi kewirausahaan digital dari 46% menjadi 80%, serta kemampuan membuat desain sederhana dari 42% menjadi 86%. Hasil tersebut menunjukkan bahwa pelatihan berbasis praktik mampu meningkatkan keterampilan dan literasi digital peserta secara efektif. Selain itu, seluruh peserta berhasil menghasilkan produk digital sederhana sebagai portofolio awal dan mulai memahami peluang income tambahan melalui kerja remote berbasis digital.
Co-Authors Achmad Buchori Achmad Buchori Aditiya Pratama Nugroho Ari Tri Jaka Harjanta Aris Tri Jaka Harjanta, Aris Tri Aris Tri Joko Harjanto Bambang Agus Herlambang, Bambang Desi Maulia Desi Purwaningsih Dini Rakhmawati Dini Rakhmawati Fitria, Alfina Haryo Kusumo Husni Wakhyudin Irfan Nur Ridwan Khoiriya Latifah, Khoiriya Khoirul Junianto Kusumo, Haryo Lia Ayu Kusumaningrum Lukman Harun Marlina, Dian Mega Novita Mega Novita Mudzanatun Mudzanatun Noora Qotrun Nada, Noora Qotrun Nur Latifah Dwi Mutiara Sari Prianka Ratri Nastiti Ridwan, Irfan Nur Setyoningsih Wibowo Setyoningsih Wibowo Shinta Arum Imaniyah Venty Venty Vilda Ana Veria Setyawati Waliyansyah, Rahmat Robi Wobowo, Setyoningsih Yayuk Wahyuningsih