Support Vector Machine Based Traffic Congestion in Intelligent Transportation System

Abstract

Traffic congestion is one of the most significant obstacles that municipal managers must surmount to be successful in their work. This paper focuses on the use of intelligent transportation systems (ITS) and smart environmental monitoring in smart cities to improve the accuracy and efficiency with which they track and respond to environmental threats such as pollution, traffic jams, and more. The goal of this paper is to classify the traffic congestion using machine learning algorithm and to offer a better congestion management. To make an accurate prediction of congestion using a Support Vector Machine, a pre-processing layer that can manage incomplete values and improve the quality of the incoming data is required. The results of simulation show that the proposed method achieves higher accuracy in detecting the traffic congestion and smartly manages to reduce it.