Traffic Congestion Report

Transportation has been a vital side of human civilization at all the times, however it is just in the last half of the recent century that the phenomenon of traffic congestion has become more important because of the fast increase in the number of vehicles and in the transportation demand in almost all transportation modes. Traffic congestion leads to extra delays, reduced safety, and enhanced environmental pollution. Right now, traffic congestion is a critical social problem, and traditional road construction is restricted by the land and capital. So that, to solve the traffic related issues, intelligent transportation systems (ITS) are widely used all over the world. Many subsystems of ITS such as Advanced Traffic Management System (ATMS)

Since then, a great variety of models for traffic flow forecasting have been suggested by researchers from different areas, such as transportation engineering, statistics, machine learning, control engineering, and economics. Previous prediction approaches can be classified into three classes, i.e., parametric techniques, nonparametric methods, and simulations. Parametric models consist of time-series models, Kalman filtering models, etc. Nonparametric models consist of k-nearest neighbor (k-NN) methods, artificial neural networks (ANNs), etc. Simulation approaches utilize traffic simulation tools for traffic flow

Levin and Tsao used Box–Jenkins time-series analyses for predicting expressway traffic flow and found that the ARIMA (0, 1, 1) model was the most statistically significant for all prediction [6]. Hamed et al. applied an ARIMA model for traffic flow prediction in urban arterial roads [7]. Many variants of ARIMA were presented to enhance prediction accuracy, such as Kohonen- ARIMA (KARIMA) [8], subset ARIMA [9], ARIMA with explanatory variables (ARIMAX) [10], vector autoregressive moving average (ARMA) and space–time ARIMA [11], and seasonal ARIMA (SARIMA) [12]. Besides the ARIMA-like time-series models, other types of time-series models were also used for traffic flow forecasting