Article Per Year (5 Year)
p-Index From 2021 - 2026
0.61
P-Index
This Author published in this journals
All Journal Sebatik TEPIAN
Septian, M Ridwan Dwi
Unknown Affiliation
Computer Science & IT

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
A Real-Time Helmet Detection System Based on YOLOv8 to Support Traffic Law Enforcement Puspita, Tiara; Swedia, Ericks Rachmat; Cahyanti, Margi; Septian, M Ridwan Dwi
Sebatik Vol. 29 No. 1 (2025): June 2025
Publisher : STMIK Widya Cipta Dharma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46984/sebatik.v29i1.2585

Abstract

Helmet use is a critical safety measure for motorcycle riders, yet non-compliance remains high in Indonesia. This study introduces a real-time helmet detection system using the YOLOv8 architecture, deployed on Android devices with the Kotlin programming language. A dataset of 1,197 digital images was collected and annotated using Roboflow Annotate, containing two classes: helmet users (True) and non-users (False). To improve model generalization, data augmentation techniques such as rotation and shear were applied. The model was trained using the pretrained yolov8n.pt weights and evaluated based on mAP and Intersection over Union (IoU). During training, the model achieved a mAP50 of 98% and a mAP50–95 of 59.6%. In testing, the mAP50 reached 98.3% and mAP50–95 reached 61%, with an average IoU of 0.73. The trained model was then converted into TensorFlow Lite format and integrated into an Android application. Real-time testing showed a detection accuracy of 93.3%. These results demonstrate that YOLOv8 is effective for mobile-based real-time helmet detection and has strong potential to support traffic law enforcement systems, especially in urban environments where manual monitoring is inefficient. The system contributes to enhancing public safety through smart technology integration.
Implementation of Deep Learning Algorithm for Vehicle Count Monitoring System Septian, M Ridwan Dwi; Masitoh, Agustine Hana; Sari, Intan Meutia
TEPIAN Vol. 5 No. 4 (2024): December 2024
Publisher : Politeknik Pertanian Negeri Samarinda

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51967/tepian.v5i4.3213

Abstract

Vehicle detection plays a crucial role in various applications such as traffic surveillance, license plate recognition, and the development of autonomous vehicles. The You Only Look Once (YOLO) object detection method is renowned for its high-speed real-time object detection capabilities. In this study, YOLO is employed to detect vehicles in images and videos. YOLO treats object detection as a direct regression problem for bounding boxes and class predictions. The aim of this research is to develop a vehicle counting system using the YOLO method. The Midpoint algorithm is utilized to calculate the midpoint between two points in a coordinate plane. Another objective is to analyze the strengths and weaknesses of the method and algorithm in the context of vehicle detection while identifying related research trends. The test results indicate that the system is capable of detecting vehicles with an average accuracy of 92.42% across four different time periods. In the morning, the system detected 156 vehicles (manual count: 147, accuracy: 94.23%); at midday, it detected 246 vehicles (manual count: 225, accuracy: 91.46%); in the evening, 377 vehicles were detected (manual count: 351, accuracy: 93.10%); and at night, the system identified 526 vehicles (manual count: 225, accuracy: 92.58%). This study contributes to the development of a more effective vehicle counting system for smart city applications while also paving the way for further research on vehicle detection under varying lighting and environmental conditions.
Deep Learning Architecture of VGG16 and VGG19 for Eyeglasses Face Classification Fatah, Muhammad Faiz Abrar; Swedia, Ericks Rachmat; Cahyanti, Margi; Septian, M Ridwan Dwi
Sebatik Vol. 29 No. 2 (2025): December 2025
Publisher : STMIK Widya Cipta Dharma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46984/sebatik.v29i2.2688

Abstract

This study aims to conduct a comparative analysis of the performance of two popular Convolutional Neural Network (CNN) architectures, namely Visual Geometry Group (VGG16 and VGG19), in classifying facial images with glasses using the “Glasses or No Glasses” dataset. Both models were developed through a transfer learning approach by utilizing pre-trained ImageNet weights to accelerate convergence and improve classification accuracy. The training process employed the Adam optimizer with binary crossentropy as the loss function. The dataset was divided into two subsets 80% for training and 20% for validation while testing was performed on 50 unseen images excluded from both subsets. Experimental results show that the VGG16 architecture achieved 87.86% training accuracy and 89.11% validation accuracy, whereas VGG19 achieved 86.86% training accuracy and 87.89% validation accuracy. On the testing dataset, VGG16 correctly classified 47 out of 50 images (94%), while VGG19 correctly classified 48 images (96%). Although the performance gap is relatively small, VGG19 demonstrated better computational efficiency with a shorter training duration (2 hours and 41 minutes) compared to VGG16 (2 hours and 59 minutes). Furthermore, the trained models were successfully implemented in an Android application using TensorFlow Lite, enabling real-time eyeglasses detection. These findings indicate that the VGG19 architecture offers superior efficiency and accuracy for deep learning–based eyeglass face classification tasks.
Co-Authors Cahyanti, Margi Ericks Rachmat Swedia Fatah, Muhammad Faiz Abrar Masitoh, Agustine Hana Puspita, Tiara Sari, Intan Meutia