From the past decade the expansion of highways are slow when compared to the growth of transportation, traffic blockage becoming a central transportation issue in a metropolitan cities. Modeling of growth trend and improvement in forecasting techniques for transport population has always been and will continue to be of first importance for any major infrastructure development initiatives in the transportation engineering sector. Although many traditional, as well as some advanced methods, are in vogue for this process of estimation, there has been a continuous quest for improving the accuracy of different methods. A citywide traffic pattern is used in transportation and metropolitan planning. Traditional approaches for the estimation of traffic flow may heavily depend on the road-based sensor, and nowadays the traffic forecasting is done by using data mining techniques, machine learning, artificial intelligence, neural networks, cloud computing. Even social networks also play the vital role in predicting the traffic. Big-data-driven traffic flow prediction systems are accessible when the big data concept emerged into the field. In this area, the robustness of prediction performance depends on accuracy and timeliness. In this paper, we have studied various research works, and we are analyzed the different methods and techniques which are used to forecasting the traffic flow estimation.
A survey on citywide traffic estimation techniques
01.08.2017
256448 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Calibrating a Citywide Traffic Model
British Library Conference Proceedings | 1993
|Citywide Traffic Signal Coordination Using Closed-Loop Systems
British Library Conference Proceedings | 1992
|A Citywide Distributed inVANETs-Based Protocol for Managing Traffic
Springer Verlag | 2018
|Kraftfahrwesen | 2015
|Online Contents | 2014