Published Paper Details:

The project's objective is to develop a tool for predicting traffic data accurately and promptly. This encompasses various factors such as trains, accidents, races, and road maintenance that can impact road traffic, potentially causing disruptions. By providing highly accurate predictions in advance for these scenarios and other daily situations affecting traffic, the tool aims to empower drivers and passengers to make informed decisions. Furthermore, this predictive capability is envisioned to contribute to the advancement of autonomous vehicles. As the volume of car data has surged in recent years, there is a transition toward leveraging car data. Although existing traffic prediction methods employ various models, they still face challenges in addressing real-world applications effectively. This challenge underscores the need to investigate traffic issues using advanced data and models. Given the substantial volume of available traffic data, the project proposes the use of machine learning, genetic algorithms, soft computing, and deep learning algorithms to analyze transportation big data with minimal reductions. Additionally, the project incorporates image processing algorithms in the driver recognition process, ultimately enhancing the training of autonomous vehicles.