Article Per Year (5 Year)
p-Index From 2021 - 2026
2.552
P-Index
This Author published in this journals
All Journal SISFO JURNAL TEKNOLOGI DAN OPEN SOURCE AMALIAH: JURNAL PENGABDIAN KEPADA MASYARAKAT Jurnal Ilmu Komputer dan Desain Komunikasi Visual Jutisi: Jurnal Ilmiah Teknik Informatika dan Sistem Informasi Aviation Electronics, Information Technology, Telecommunications, Electricals, Controls (AVITEC) INTEGRITAS : Jurnal Pengabdian JATI (Jurnal Mahasiswa Teknik Informatika) JITU : Journal Informatic Technology And Communication Jurnal Pendidikan dan Teknologi Indonesia Jurnal Pengabdian dan Pemberdayaan Nusantara (JPPNu) Jurnal Ilmu Komunikasi Jurnal Komputer Teknologi Informasi Sistem Komputer (JUKTISI) Al-Kharaj: Jurnal Ekonomi, Keuangan & Bisnis Syariah Computing Insight: Journal of Computer Science Jurnal Teknik Informatika dan Teknologi Informasi
Sembilu, Nambi
Universitas Pembangunan Nasional Veteran, Jawa Timur, Indonesia
Aerospace Engineering Agriculture, Biological Sciences & Forestry Arts Humanities 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 Law, Crime, Criminology & Criminal Justice Library & Information Science Public Health Social Sciences

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

Found 1 Documents
Search
Journal : JITU : Journal Informatic Technology And Communication

 1 
Meningkatkan Efisiensi Energi Perangkat Edge melalui Optimasi Pruning dan Kuantisasi Model Sembilu, Nambi; Mukhlis, Iqbal Ramadhani; Satibi, Iswanda Fauzan
JITU Vol 10 No 1 (2026)
Publisher : Universitas Boyolali

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36596/jitu.v10i1.2324

Abstract

Edge computing devices are increasingly tasked with performing artificial intelligence inference under strict constraints on processing capacity and power consumption. This study evaluates magnitude-based weight pruning and dynamic quantization as practical model compression techniques for energy-efficient edge AI deployment. MobileNetV2, pretrained on ImageNet, was adapted to the CIFAR-10 classification task and compressed under three configurations: 40% L1 unstructured pruning followed by recovery fine-tuning (Prune40), dynamic INT8 post-training quantization (QuantINT8), and a sequential combination of both (Prune+Quant). All experiments were executed on a physical Intel N150 mini PC with a thermal design power of 6 watts, using PyTorch 2.1 in CPU-only inference mode. Results show that Prune40 reduced inference latency by 17.9% while simultaneously improving classification accuracy by 1.04 percentage points, attributed to the implicit regularisation effect of sparse weight removal and recovery fine-tuning. QuantINT8 yielded moderate latency savings (6.6%) with negligible accuracy loss. The combined pipeline achieved the lowest absolute latency at a marginal energy overhead. These findings establish magnitude pruning with recovery training as the most effective single-step compression strategy for low-power x86 edge platforms.
Co-Authors Ahmad Ramsi, Dhiya’ Ulhaq Amalia Anjani Arifiyanti Anindo Saka Fitri Aprilia, Eka Fahira Ariyana, Denny Arnando, Rasi Andante Caesaria, Vica Ayu Cahyo Wibowo, Nur Dwi Shahita Febriliyan Samopa Iqbal Ramadhani Mukhlis Isnandar, Ahmad Yazid Iswanda F. Satibi Iswanda F. Satibi Kartika, Annisa Dita Putri Khoirul Ngibad Khotmil Ula Mahendrawathi ER Mohammad Syarrafah Muhamad Agung Laksono Ngibad, Khoirul Permatasari, Reisa Prasasti Karunia Farista Ananto Putri, Intan Syahrani Rafika Rahmawati Rafika Rahmawati Rafika Rahmawati Ridwandono, Doddy Satibi, Iswanda Fauzan Setiawan Setiawan Subagyo Subagyo Thomas Aquino Berno Doduk Tri Luhur Indayanti Sugata Tri Puspa Rinjeni Virdha Rahma Aulia Wahyuni, Eka Dyar