Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal IKRA-ITH Informatika : Jurnal Komputer dan Informatika
Tjoargen Christoper Redja
Universitas Singaperbangsa Karawang
Computer Science & IT

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Implementasi Implementasi Model YOLO11 untuk Deteksi Alat Pelindung Diri Berbasis Citra Statis Tjoargen Christoper Redja; Rini Mayasari; Riza Ibnu Adam
IKRA-ITH Informatika : Jurnal Komputer dan Informatika Vol. 10 No. 2 (2026): IKRAITH-INFORMATIKA Vol 10 No 2 Juli 2026
Publisher : Fakultas Teknik Universitas Persada Indonesia YAI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37817/ikraith-informatika.v10i2.7211

Abstract

The use of Personal Protective Equipment (PPE) is a fundamental requirement in ensuring workplace safety, especially in chemical industry environments such as PT Mustika Dipa Lestari. However, manual PPE monitoring systems have significant limitations in consistency, efficiency, and coverage of large work areas. This research aims to develop an automatic detection system using the YOLO11 (You Only Look Once version 11) model based on static images to detect PPE usage among workers in industrial environments. The dataset consists of 406 images collected directly from PT Mustika Dipa Lestari with PPE objects including bouffant caps, laboratory coats, masks, and gloves. Data is divided with a 70:20:10 ratio for training, validation, and testing. Annotation was conducted using the Roboflow platform and the model was trained using the PyTorch framework with Adam optimizer over 150 epochs. Evaluation uses Mean Average Precision (mAP@50), mAP@0.5:0.95, precision, recall, and F1-score metrics. Results show that YOLO11 achieves optimal performance with mAP@50 of 96.91%, mAP@0.5:0.95 of 86.68%, precision of 98.30%, recall of 97.05%, and F1-score of 97.67%, surpassing the minimum business target of 85%. Comparison with YOLOv4 (mAP@50 = 66.47%) and YOLOv5 (mAP@50 = 95.75%) demonstrates YOLO11's superiority on a specialized chemical industry domain dataset.
Co-Authors Rini Mayasari Riza Ibnu Adam