Road congestion condition analysis method



The invention discloses a road congestion condition analysis method, and aims at analyzing the road congestion condition of the next moment. The method specifically comprises the following steps of: establishing a road congestion prediction model, wherein the road congestion prediction model fuses a BP neural network model and an SVM (support vector machine) model; acquiring traffic flow data and preprocessing the traffic flow data; and inputting the traffic flow data into the road congestion prediction model so as to obtain a predicted road congestion condition: firstly predicting a traffic congestion condition through the BP neural network model and the SVM (support vector machine) model, and then weighting output results of the two models to solve an average value and taking the average value as a final result. According to the method disclosed by the invention, traffic flow prediction can be carried out by utilizing a traffic flow related to the current moment and traffic flows related to history moments and adopting an improved neural network model, so that the prediction efficiency and correctness are improved.




Download Full PDF Version (Non-Commercial Use)

Patent Citations (0)

    Publication numberPublication dateAssigneeTitle

NO-Patent Citations (0)


Cited By (0)

    Publication numberPublication dateAssigneeTitle