Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal Information System Journal (INFOS) Journal of Information Technology (JINTECH)
Ahmad , Nazaruddin
Unknown Affiliation
Computer Science & IT Other

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
PERANCANGAN DAN PEMBUATAN SISTEM INFORMASI CAÉ ACEH BERBASIS WEBSITE Bustami; Khairul Ammar , Muhammad; Mursyidin; Ahmad , Nazaruddin
Journal of Information Technology (JINTECH) Vol. 4 No. 2 (2023): Agustus 2023
Publisher : Prodi Teknologi Informasi UIN Ar-Raniry Bekerjasama dengan Pusat Penelitian dan Penerbitan LP2M Universitas Islam Negeri Ar-Raniry Banda Aceh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22373/jintech.v4i2.3265

Abstract

This research is spurred by the absence of a dedicated website to showcase caé, coupled with the significant number of young Acehnese individuals in the information age who lack awareness about caé. Leveraging existing technology, the aim of this study is to develop a website-based centralized information system exclusively devoted to caé Aceh. This system not only offers public access to view the caé present in the database but also encourages users to suggest any caé that might not have been included yet. The primary objective of this system is to serve as a platform for preserving the nation's cultural heritage, with a specific emphasis on caé. Furthermore, it seeks to enhance the understanding of caé among the general public, particularly the younger generation in Aceh, and foster increased interest in studying Aceh caé through the website. The development process employed the prototype methodology, with experts conducting black box testing—a method where the system's internal workings are not disclosed—to ensure thorough evaluation. The testing results for this system yielded a perfect score of 100%, indicating its high suitability and effectiveness.
DETEKSI PENYAKIT KULIT DENGAN MENGGUNAKAN MODEL PRETRAINED DAN HYBRID KNOWLEDGE DISTILLATION Sasongko , Theopilus Bayu; Hadinegoro, Arifiyanto; Pujastuti, Eli; Agastya , I Made Artha; Ahmad , Nazaruddin
Information System Journal Vol. 8 No. 02 (2025): Information System Journal (INFOS)
Publisher : Universitas Amikom Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24076/infosjournal.2025v8i02.2585

Abstract

Knowledge Distillation (KD) merupakan paradigma efektif untuk mentransfer pengetahuan dari model teacher berkapasitas tinggi ke model student yang ringan melalui kombinasi soft label dan hard label. Meskipun KD Hinton mampu menangkap kesamaan antar kelas, pendekatan ini masih terbatas dalam mentransfer representasi fitur mendalam yang krusial pada tugas pencitraan medis, seperti klasifikasi lesi kulit, di mana fitur halus sering hilang jika hanya mengandalkan keluaran akhir model. Untuk mengatasi keterbatasan tersebut, penelitian ini mengembangkan tiga varian KD, yaitu KD Hinton dengan supervisi hard label, KD dengan penyelarasan fitur, dan Hybrid KD yang mengombinasikan keduanya. Pendekatan ini memungkinkan student meniru distribusi semantik dan representasi fitur internal teacher sekaligus mempertahankan informasi diskriminatif dari ground truth. Eksperimen pada berbagai pasangan teacher–student menunjukkan adanya trade-off antara akurasi dan biaya komputasi. Hasilnya, metode Hybrid KD memberikan peningkatan kinerja tertinggi, mencapai akurasi Top-1 sebesar 82,07% pada MobileNetV2 tanpa menambah kompleksitas model, sehingga efektif untuk aplikasi pencitraan medis real-time berbasis sumber daya terbatas.
Co-Authors Agastya , I Made Artha Arifiyanto Hadinegoro, Arifiyanto Bustami Eli Pujastuti, Eli Khairul Ammar , Muhammad Mursyidin Sasongko , Theopilus Bayu