SEASONAL EGYPTIAN ROAD TRAFFIC VOLUME VARIATIONS USING MACHINE LEARNING

Document Type : Original Article

Authors

1 , Department of Civil Engineering, Faculty of Engineering, Shoubra – Banha University, Cairo, Egypt.

2 Department of Building and Construction, Faculty of Engineering, October 6 University, Giza, Egypt.

Abstract

Seasonal factors Weather, holidays, and school schedules all contribute to traffic. Seasonal factors have a significant influence on annual average daily traffic (AADT). Traffic volume is measured and predicted using AADT. To make intelligent transportation planning and finance decisions, seasonal factors must be included while examining AADT data since there has been no Egyptian traffic flow research. Machine learning approaches include regression analysis and artificial neural networks (ANNs) to predict seasonal variations. Since 2018, the General Authority for Roads, Bridges, and Land Transport (GARBLT) has not kept traffic records. Seasonal factors were employed to generate a more accurate and understandable AADT figure from 11 stationary monitoring stations monitored from 2013 to 2018. These stations collected socioeconomic data as well as information about the roads, such as lanes and station locations. The artificial neural network (ANN) model seasonal factors were far more precise and reliable when compared to the real values.

Keywords

Main Subjects

Journal of Al-Azhar University Engineering Sector
Volume 19, Issue 71
April 2024
Pages 475-494

Files

Share

How to cite

Statistics