Traffic Flow Forecasting in Intelligent Transportation Systems Prediction Using Machine Learning
Mohammad Naveed Hossain, Nafim Ahmed, S. M. Wazid Ullah
Abstract
Globally, intelligent transportation systems utilize traffic predictions. Traffic congestion, route planning, and vehicle dispatching all benefit from accurate traffic forecasts. The road system’s changing geographical and temporal dependencies complicate the problem. In recent years, traffic forecasting has improved thanks to research, particularly deep learning. We investigate traffic predictions for Dhaka based on machine learning and deep learning techniques. The classification of existing traffic prediction methods comes first. To enable academics, we aggregate and arrange commonly used public datasets. We undertake comprehensive experiments on a publicly accessible real-world dataset to compare and contrast diverse methodologies. The contribution of the third section is automated approaches for traffic forecasting. In closing, we discuss some of the outstanding questions.