The connected vehicles contribute to diminish traffic densities at metro cities using a Vehicular Ad Hoc Network (VANET) by deployment of On-Board Units (OBU) at Vehicles as the recent vehicles are equipped with complex sensors for knowing the pressure, speed, direction of vehicle and profoundly transmit it to other vehicles, which is available in VANET. Furthermore, these sensors are already versatile with Internet. This paper identifies prerequisites of predicting the vehicular traffic during busy hours at urban areas using a machine learning algorithm. In addition, with Vehicle-to-Vehicle (V2V) correspondence systems that are basically intended to reduce mishaps and traffic, particularly with the worse traffic conditions. Thus, the VANET has been risen with a refined source of flexible option to reduce the traffic caused by vehicles. There are various machine learning algorithms may predict the traffic, but only few can manage the traffic by providing automated alerts like Convolutional Neural Networks CNN and K nearest neighbor KNN to vehicles according to the speed of vehicles in an urban areas or congested areas to avoid collision, these algorithms assist in diverting the vehicles with another shortest path for destination.
Machine Learning Algorithms for Predication of Traffic Control Systems on VANET’s
Algorithms for Intelligent Systems
Proceedings of International Conference on Communication and Computational Technologies ; Chapter : 32 ; 393-404
2021-08-24
12 pages
Article/Chapter (Book)
Electronic Resource
English
Congestion Control in Vehicular Ad-Hoc Networks (VANET’s): A Review
Springer Verlag | 2020
|BAHG: Back-Bone-Assisted Hop Greedy Routing for VANET's City Environments
Online Contents | 2013
|Aircraft track predication method of air traffic control system
European Patent Office | 2015
|