Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Internet of Things and Artificial Intelligence Journal
Hendarawaty, Hendarawaty
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Engineering

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

Found 1 Documents
Search

 1 
Implementation of the Convolutional Neural Network Method in Highway Traffic Monitoring Systems Atthariq, Atthariq; Azhar, Azhar; Hendarawaty, Hendarawaty; Parenreng, Jumadi Mabe
Internet of Things and Artificial Intelligence Journal Vol. 5 No. 1 (2025): Volume 5 Issue 1, 2025 [February]
Publisher : Association for Scientific Computing, Electronics, and Engineering (ASCEE)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31763/iota.v5i1.862

Abstract

Traffic Flow Calculation is one of the first steps in urban planning and road infrastructure management, for monitoring traffic flow on a road is very important. To do traffic planning, the Department of Transportation must count every passing vehicle where later the data will be used as material for analysis. Currently, the Department of Transportation calculates vehicles that pass on a road by calculating it with manual tools, so it requires large operational costs and takes a long time. Based on the problems faced, the researcher offers a solution for an intelligent traffic flow monitoring system that can count the number of vehicles that pass by using a closed circuit television camera (CCTV) installed at every city traffic light. Here we propose a high-performance algorithm model You Only Look Once (YOLO), which is based on the TensorFlow framework, to improve real-time vehicle monitoring. From the results of testing the system was built using the Python programming language using the YOLOv4 method, the Tensorflow library, and the PyQT5 library. The accuracy of reading the number of passing vehicles is 97%.
Co-Authors Atthariq, Atthariq Azhar Azhar Jumadi Mabe Parenreng