Article Per Year (5 Year)
p-Index From 2021 - 2026
1.931
P-Index
This Author published in this journals
All Journal Jurnal ULTIMA Computing Edsence: Jurnal Pendidikan Multimedia Bantenese Jurnal Pengabdian Masyarakat Indonesian Journal of Electrical Engineering and Computer Science Journal of Computer Networks, Architecture and High Performance Computing REKA ELKOMIKA: Jurnal Pengabdian kepada Masyarakat Journal of Intelligent Systems Technology and Informatics
Fauzan, Mochamad Rizal
Unknown Affiliation
Humanities Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Engineering Industrial & Manufacturing Engineering Social Sciences Other

Published : 13 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 13 Documents
Search

 1   2 
Air Filtration System Utilizing Biomimetic Technology and IoT for Air Quality Improvement Fauzan, Mochamad Rizal; Al Azhima, Silmi Ath Thahirah; Pramudita, Resa; Hakim, Dadang Lukman; Rahmawati, Hanifah Indah; Azmi, Mutiara Nabila; Fauzi, Rafi Rahman; Somantri, Maman; Rahayu, Sri
ULTIMA Computing Vol 16 No 2 (2024): Ultima Computing : Jurnal Sistem Komputer
Publisher : Faculty of Engineering and Informatics, Universitas Multimedia Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31937/sk.v16i2.3871

Abstract

The "Hepix" smart air filtration system, developed with biomimetic and Internet of Things (IoT) technology, aims to address the urgent issue of poor indoor air quality, particularly in high-mobility urban areas. This system integrates advanced sensors (MQ135 and BME680) and biomimetic filtration inspired by leaf stomata to monitor and filter air pollutants. Tested across three locations”Cilame, Jatinangor, and Cibiru”the system achieved an approximate 24.4% reduction in pollutant levels, as well as stable control of humidity and air pressure. Real-time data is continuously monitored through a mobile and web interface, supported by Google Assistant integration for voice commands. The results demonstrate that "Hepix" effectively improves air quality, offering a practical solution for healthier indoor environments in urban areas.
Rethinking Efficiency: A Comparative Study of Lightweight CNN Architectures for Image Classification Fauzan, Mochamad Rizal; Naufal Nadhif Rabbani Iskandar; Rafi Zahran Fauzi
Journal of Intelligent Systems Technology and Informatics Vol 2 No 1 (2026): JISTICS, March 2026
Publisher : Aliansi Peneliti Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64878/jistics.v2i1.167

Abstract

Lightweight convolutional neural networks (CNNs) are increasingly required for image classification in resource-constrained environments; however, their comparative behavior under unified training conditions remains insufficiently explored, particularly when accuracy, parameter efficiency, inference latency, and augmentation sensitivity are evaluated simultaneously. This study presents a systematic benchmark of five lightweight CNN architectures, namely MobileNetV2, EfficientNet-B0, ShuffleNetV2, SqueezeNet, and ResNet18, on the CIFAR-100 dataset using a consistent experimental pipeline. All models were trained for 40 epochs with an input resolution of 128 × 128, AdamW optimization, cosine annealing, mixed-precision training, and identical preprocessing settings. Two augmentation strategies, namely basic and advanced augmentation, were evaluated to examine their influence on model generalization. The results show that EfficientNet-B0 achieved the best classification performance with 82.75% Top-1 accuracy and 96.46% Top-5 accuracy, while SqueezeNet achieved the fastest inference latency of 1.52 ms and the smallest parameter size, indicating its suitability for highly constrained deployment scenarios. Across all evaluated models, the average Top-1 and Top-5 accuracies reached 76.6% and 94.16%, respectively. In addition, the effect of advanced augmentation was found to be architecture-dependent rather than uniformly beneficial. On average, it resulted in a Top-1 accuracy change of −0.66 percentage points, with only ResNet18 showing a modest improvement. The main contribution of this study is to provide a unified, practically oriented benchmark that highlights how architectural design, rather than parameter count alone, determines the balance between accuracy and computational efficiency. These findings provide clearer guidance for selecting lightweight CNN models for real-world image classification tasks under varying deployment constraints.
Hyperparameter Sensitivity of Vanilla Knowledge Distillation for Compact CNNs on CIFAR-100 Fauzan, Mochamad Rizal; Rachman, Raden Muhammad Rafi; Saputra, Shifa Rangga; Nugraha, Daffa Irsyad
Journal of Computer Networks, Architecture and High Performance Computing Vol. 8 No. 2 (2026): Research Paper April 2026
Publisher : Information Technology and Science (ITScience)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/cnahpc.v8i2.8239

Abstract

Knowledge distillation has become an effective strategy for improving compact convolutional neural networks, yet the performance of vanilla knowledge distillation in lightweight image classification is still often reported using default hyperparameter settings without systematic justification. This study addresses the limited empirical understanding of how two core vanilla knowledge distillation hyperparameters, temperature scaling (T) and loss balancing (?), affect compact convolutional neural networks under a unified experimental setting. Using CIFAR-100 as the benchmark dataset, a ResNet-50 teacher was employed to distill knowledge into two lightweight student models, MobileNetV2 and ShuffleNetV2 ×1.0. Performance was evaluated using top-1 accuracy, top-5 accuracy, parameter count, and inference latency. The teacher achieved 81.24% top-1 accuracy and 96.05% top-5 accuracy. Under the default distillation setting, MobileNetV2 improved from 79.18% to 80.83% top-1 accuracy and from 95.77% to 96.40% top-5 accuracy, while reducing latency from 3.98 ms to 3.44 ms. ShuffleNetV2 ×1.0 improved from 77.00% to 78.36% top-1 accuracy and from 94.81% to 95.45% top-5 accuracy, with only a marginal latency increase from 4.23 ms to 4.29 ms. To examine hyperparameter sensitivity, an ablation study was conducted on MobileNetV2 with T = 2, 4, and 6, and ? = 0.3, 0.5, and 0.7. The best configuration was obtained at T = 4 and ? = 0.3, yielding 80.88% top-1 accuracy and 96.51% top-5 accuracy. These results show that vanilla knowledge distillation consistently improves compact convolutional neural networks, but its effectiveness depends strongly on careful hyperparameter selection rather than inherited default settings.
Co-Authors Al Azhima, Silmi Ath Thahirah Al Qibtiya, Mariya Al Qibtya, Mariya Ath Thahirah Al Azhima, Silmi Azmi, Mutiara Nabila Budi, Agus Heri Setya Dadang Lukman Hakim Dedi Rohendi Dedy Suryadi Fauzi, Rafi Rahman Iwa Kuntadi Iwan Kustiawan Jaja Kustija, Jaja Juanda, Endang Akhmad Kaniarudi, Neneng Puspita Khairi, Saiqa Fatur Maman Somantri Muhammad Adli Rizqulloh Naufal Nadhif Rabbani Iskandar Neris Peri Ardiansyah Nugraha, Daffa Irsyad Nurul Fahmi Arief Hakim Pramudita, Resa Rachman, Raden Muhammad Rafi Rafi Zahran Fauzi Rahmawati, Hanifah Indah Roer Eka Pawinanto, Roer Eka Saputra, Shifa Rangga Saripudin Saripudin Siscka Elvyanti, Siscka SRI RAHAYU Surya, Irgi Tuti Suartini Wasimudin Surya Saputra Wawan Purnama