Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal Sinkron : Jurnal dan Penelitian Teknik Informatika Nusantara Computer and Design Review
Ulumuddin, Mochammad Fatih
Unknown Affiliation
Computer Science & IT

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

Found 2 Documents
Search

 1 
Quality of Service (QoS) Jaringan Internet di PT Penyedia Instalasi Fiber Optik Berbasis Wireshark Ulumuddin, Mochammad Fatih; Alamin, Mochammad Machlul; Farizki, Daniel Achmad; Rasyidin, Mukhammad Hafid; Firmansyah, Muhammad; Mauliddin, Rizky Akbar; Haq, Ahmad Khoir Al
Nusantara Computer and Design Review Vol. 3 No. 2 (2025): Nusantara Computer and Design Review
Publisher : LPPM UNUSIDA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55732/hfmd1f24

Abstract

Penelitian ini menganalisis kualitas layanan (Quality of Service) jaringan internet di PT Quantum Nusatama, perusahaan yang bergerak di bidang instalasi jaringan fiber optik. Penggunaan perangkat lunak wireshark memungkinkan analisis terhadap parameter QoS seperti throughput, delay, jitter, dan packet loss sesuai standar TIPHON. Hasilnya menunjukkan bahwa performa jaringan tergolong baik yakni throughput rata-rata 85% dari kapasitas, delay 25–35 ms, jitter 5–10 ms, dan packet loss di bawah 2%. Kesimpulannya, jaringan internet di perusahaan tersebut memenuhi standar layanan yang dibutuhkan untuk mendukung operasional bisnis. This study analyzes the quality of service (Quality of Service) of the internet network at PT Quantum Nusatama, a company engaged in fiber optic network installation. The use of Wireshark software allows analysis of QoS parameters such as throughput, delay, jitter, and packet loss according to TIPHON standards. The results show that the network performance is quite good, with an average throughput of 85% of capacity, a delay of 25–35 ms, jitter of 5–10 ms, and packet loss below 2%. In conclusion, the internet network at the company meets the service standards required to support business operations.
Cross-Architecture Performance Evaluation of Transfer Learning Models for Multi-Class Vehicle Damage Severity Classification Ulumuddin, Mochammad Fatih; Pramana, Anggay Luri
Sinkron : jurnal dan penelitian teknik informatika Vol. 10 No. 2 (2026): Article Research April, 2026
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/sinkron.v10i2.15939

Abstract

Automated vehicle damage classification supports objectivity and scalability in insurance claim processing and digital inspection systems; however, prior studies often report performance improvements without controlled experimental settings or statistical validation, limiting methodological reliability. This study establishes a statistically controlled cross-architecture evaluation framework to determine whether pretrained convolutional neural networks significantly outperform a custom baseline model in multi-class vehicle damage classification. A dataset of 891 labeled vehicle images categorized into heavy, medium, light, and normal damage was partitioned using stratified sampling (70% training, 15% validation, 15% testing). Four architectures Baseline (CustomCNN), VGG16, ResNet50, and MobileNetV2 were trained under identical preprocessing and optimization settings with two training durations (30 and 50 epochs). Five-fold cross-validation and paired t-test analysis were applied to assess statistical significance. At 30 epochs, MobileNetV2 achieved the highest accuracy (75.76%), while at 50 epochs VGG16 obtained the best performance (78.03%). Extending training duration did not produce statistically significant improvement (p > 0.05). Pretrained architectures significantly outperformed the baseline model, whereas ResNet50 did not demonstrate superior performance. The novelty of this study lies in its statistically validated comparative framework. Although limited by moderate dataset size and single-source imagery, the findings provide practical guidance for selecting efficient convolutional neural networks in vehicle damage classification systems.
Co-Authors Anggay Luri Pramana Farizki, Daniel Achmad Haq, Ahmad Khoir Al Mauliddin, Rizky Akbar Mochammad Machlul Alamin Muhammad Firmansyah, Muhammad Rasyidin, Mukhammad Hafid