Latest revision as of 19:07, 28 January 2021

Abstract

In recent years, distinction and prediction of urban traffic congestion has become an important part of Intelligent Transportation System (ITS), hence attracting more and more attentions. Road congestion can be predicted by analyzing traffic flow data collected by various data acquisition equipment primarily. However, existing methods not only need to store large amount of historical information, but has not enough suitability for large-scaled and changing traffic flows. Therefore, an online prediction method based on Random Forest (RF) is put forward in this paper and the prediction on congestions is made by real-time data instead of digging the historical data. Simulation and experiment results show that the design presented in this paper improves accuracy of predictions and it has a certain use value.

Original document

The different versions of the original document can be found in:

• http://dx.doi.org/10.2991/icmmcce-15.2015.518 under the license https://creativecommons.org/licenses/by-nc

• https://download.atlantis-press.com/article/25845064.pdf

• https://www.atlantis-press.com/proceedings/icmmcce-15/25845064,

https://academic.microsoft.com/#/detail/2295586473 under the license cc-by-nc