Research on Temporal and Spatial Short-Term Traffic Flow Forecasting Model based on Multi-Sensing Data

The intelligent transportation system mainly includes freeway ramp control, active shift limit and active accident management system. Traffic flow prediction is the key input of active traffic control systems. Accurately predicting road traffic flow is the basic guarantee for the realization of intelligent transportation. In order to improve the prediction accuracy of road traffic flow, this paper proposes a short-term traffic flow prediction method based on the space-time fusion framework. This method uses traffic flow rate, occupancy rate and weather factors to make short-term predictions of traffic flow. Under the framework of space-time fusion, four traffic flow prediction methods are studied: deep neural networks, distributed random forests, gradient propulsion machines and the related performance of generalized linear models. The experiment uses traffic data from Shangtang Elevated Road in Hangzhou City for calibration and evaluation. The results show that under the framework of space-time fusion, the results obtained by the above four prediction models are very similar and can accurately predict road traffic flow. Among them, the accuracy of the distributed random forest model is better than the other three methods.