The invention belongs to the field of artificial intelligence of a computer application technology, relates to an application of a swarm intelligence optimization method of an intelligence optimization algorithm, and particularly relates to a traffic flow forecasting method for an intelligent traffic system. A mixed artificial fish swarm optimization support vector regression method is applied to traffic flow forecasting. The construction process of the mixed optimization method is characterized in that a particle swarm algorithm is applied to improve the behavior selection of the artificial fish swarm algorithm aiming at the problem that the effect of a step-length factor in the artificial fish swarm algorithm on the algorithm is insufficient to reduce the step-length effect, then the support vector regression is optimized to conduct parameter selection to further build a mixed artificial fish swarm optimization traffic flow forecasting model. The method has the advantages of being capable of overcoming the shortcomings of the artificial fish swarm algorithm, acquires better combination regression parameters compared with the single swarm intelligence optimization algorithm application, and improves the traffic flow forecasting accuracy accordingly. The mixed optimization method is applicable to actual traffic flow predication and other engineering optimization.


    Access

    Download


    Export, share and cite



    Title :

    Traffic flow forecasting method optimizing support vector regression by mixed artificial fish swarm algorithm


    Contributors:
    YAO WEIHONG (author) / FANG RENXIAO (author) / ZHANG XUDONG (author)

    Publication date :

    2015-05-06


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    English


    Classification :

    IPC:    G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS / G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung