Article Per Year (5 Year)
p-Index From 2021 - 2026
1.376
P-Index
This Author published in this journals
All Journal IJISTECH (International Journal Of Information System & Technology) International Journal of Informatics and Computation IJISTECH Jurnal Pengabdian dan Kewirausahaan Jurnal Abdimas Indonesia : Jurnal Abdimas Indonesia
Mohamad Yusuf
Mercu Buana University
Religion Agriculture, Biological Sciences & Forestry Arts Humanities Computer Science & IT Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Environmental Science Health Professions Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Library & Information Science Public Health Social Sciences Other

Published : 7 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : International Journal of Informatics and Computation

 1 
Improving Vehicle Detection in Challenging Datasets: YOLOv5s and Frozen Layers Analysis Ahmad Nanda Yuma Rafi; Mohamad Yusuf
International Journal of Informatics and Computation Vol. 5 No. 2 (2023): International Journal of Informatics and Computation
Publisher : University of Respati Yogyakarta, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35842/ijicom.v5i2.64

Abstract

Small datasets and imbalanced classes often cause problems when it used as primary research material. In case of classification and object detection, some researchers proposed Transfer Learning (TF) with several frozen layers. Moreover, YOLO (You Only Look Once) is one of the algorithms that works in real-time object detection. In this research, we focused on evaluating the YOLOv5s version of detecting vehicles in small and imbalanced datasets. The original YOLOv5s were trained and compared with YOLOv5s with freezing layers method (10 and 24 frozen layers). The experimental results of original YOLOv5s were precision score of 0.779, recall value of 0.933, mAP@0.5 of 0.93 and mAP@0.5:0.95 of 0.684 while YOLOv5s with 10 frozen layers where precision score was decreased to 0.639, but the other value increase with recall value of 0.939, mAP@0.5 of 0.951 and mAP@0.5:0.95 of 0.732. Overall, the version with 10 frozen layers demonstrated superior performance in addressing the challenges of small and imbalanced datasets, particularly excelling in recall and mAP metrics.
Line Crossing Detector System for Real-Time Over-Taking Vehicle Detection Ahmad Nanda Yuma Rafi; Mohamad Yusuf
International Journal of Informatics and Computation Vol. 6 No. 1 (2024): International Journal of Informatics and Computation
Publisher : University of Respati Yogyakarta, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35842/ijicom.v6i1.72

Abstract

This study introduces a novel method for detecting overtaking vehicles by integrating Virtual Line Detection with the YOLOv8n algorithm. The objective is to enhance road safety by accurately identifying and tracking vehicles as they overtake, which is crucial for preventing. The research demonstrates the effectiveness of this approach, achieving a detection accuracy rate of 80.95% using line crossing detection techniques. This high level of accuracy underscores the potential of the system to reliably identify overtaking maneuvers in traffic conditions. Furthermore, this innovative method holds promising implications for enhancing safety riding by providing realtime alerts to drivers and preventing infrastructure loss resulting from traffic incidents. Our findings suggest that integrating advanced detection algorithms like YOLOv8n with virtual line detection can be a viable solution for modern traffic safety challenges.
Co-Authors Ahmad Nanda Yuma Rafi Ahmad Nanda Yuma Rafi Hadi Santoso Hakim, Lukman Ifan Prihandi Nungky Awang Candra Roy Mubarak Rushendra, Rushendra Siti Maesaroh