Short-term traffic flow prediction based on deep circulation neural network

Abstract

The difficulty of traffic flow prediction in intelligent transportation system is its non-linearity and correlation, There are many factors affecting the short-term traffic flow, but the prediction of the traffic flow at the next moment is closely related to the information of the historical moment.In this paper, a prediction model based on deep cyclic network (RNN) is proposed. The feature data are extracted from the data of the relevant time as the reference standard to predict the traffic at the future time. The simulation results show that the prediction effect of this algorithm is obviously improved.