At present, the number of motor vehicles in many big cities has exceeded the capacity of the road network, resulting in frequent traffic congestion. As a region with rapid economic development, county towns face a challenge of avoiding the problem of "urban disease". Therefore, it is particularly important to predict motor vehicle ownership in county towns reasonably to make effective traffic management measures in advance. In this paper, a variety of prediction models are analyzed, and support vector machine model is used to predict motor vehicle ownership in Changxing County, Zhejiang Province, China. The predicted values were compared with those of BP Neural Network and Polynomial Regression. The result shows that the accuracy of support vector machine model is higher, the relative errors between the predicted values and the true values are controlled within 2%, and the model has strong stability. Motor vehicle ownership is the basic data for traffic management departments to coordinate traffic demand and carbon control demand in combination with road network capacity. The prediction results will provide theoretical basis for the rational allocation of traffic facilities in county towns.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Prediction of Motor Vehicle Ownership in County Towns Based on Support Vector Machine


    Contributors:
    Zhang, Xu hua (author) / qi Hu, Min (author) / Peng, Xian yue (author) / Gan, Jing (author) / Xiang, Qiao jun (author)


    Publication date :

    2019-09-01


    Size :

    3670545 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English




    Predicting motor vehicle crashes using Support Vector Machine models

    Li, Xiugang / Lord, Dominique / Zhang, Yunlong et al. | Elsevier | 2008



    Household Vehicle Ownership Prediction Using Machine Learning Approach

    S, Manjushree N / G H, Samyama Gunjal / Swamy, Samarth C et al. | IEEE | 2022