The research of vessel traffic flow prediction is important basis of waterway planning, design and vessel navigation management. Vessel traffic model is a nonlinear, uncertain and complex dynamics system, which hardly can be expressed using some precise mathematical models. Forecasting models all have limitations to reflect the overall traffic flow situations. This article introduces three single forecasting models of vessel traffic flow with RBF neural network, Grey forecasting and auto-regression. And then combining the three models with the support vector machine (SVM) is to make the combination forecasting. Based on the vessel traffic flow dates of the Yangtze River, the result of combination forecasting is as the final predicted value. Kinds of forecasting method fusion which are fit with the vessel traffic flow forecasting, can reduce the uncertainty of single prediction methods and increase the accuracy and robustness of the prediction.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Vessel traffic flow forecasting with the combined model based on support vector machine


    Contributors:


    Publication date :

    2015-06-01


    Size :

    205624 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English