Abstract: Machine learning is a set of algorithms and statistical models that computers use to perform required tasks. Machine learning can be used in many applications such as face detection, voice recognition, medical diagnosis, mathematical reasoning, traffic prediction, etc. The traffic area includes everything that can affect the traffic on the road, whether it is a traffic light, an accident, an assembly or even a road repair that can lead to a traffic stop. If we first get information close to all of the above and many daily situations that can affect the road, the driver or passenger can make a smart decision. It also contributes to the future of cars. In recent decades, traffic data has been generated extensively and we have moved to a big data concept for transportation. Brilliant visitor forecasting uses a few types of site visitor forecasting and they are still not good enough to meet real world applications. It is tedious to understand the correct direction of the road because the information available for the transport system is very complex. In this work, we have planned to use machine learning, genetics, soft computing and deep learning algorithms to analyze the big data of transportation system with a big reduction of complexity. In addition, image processing algorithms participate in traffic sign recognition, which helps in the proper training of autonomous vehicles. In the economic years, GPS Mobility has become popular in large cities to determine the percentage of traffic that uses central traffic management - distribution. The collected data can be used to build an idea that shows the current traffic in the city and can be used in the future to predict the traffic and the summary can be done.

Keywords: Traffic Environment, Deep Learning, Machine Learning, Genetic Algorithms, Soft Computing, Big Data, Image Processing.

| DOI: 10.17148/IARJSET.2023.10121