Freeway traffic flow modeling is the basis of control, analysis, design, and decision-making in intelligent transportation system. A traffic flow dynamic model using radial basis function neural network with feedback is studied. The fuzzy c-mean clustering algorithm was used to determine the position of centers of the hidden layer. A gradient descent method was used to obtain the weights from the hidden layer to the output layer. A freeway with four segments of same length, an on-ramp at the first segment, and an off-ramp at the third segment is discussed. The training data for traffic flow modeling were generated using a well-known macroscopic traffic flow model at different densities and average velocities. The simulation result proves the practicability of this algorithm.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Freeway traffic flow modeling based on neural network


    Contributors:


    Publication date :

    2003-01-01


    Size :

    230652 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Freeway Traffic Flow Modeling Based on Neural Network

    Xiao, J.-M. / Wang, X.-H. / IEEE | British Library Conference Proceedings | 2003



    Freeway Traffic Flow Modeling Based on Recurrent Neural Network and Wavelet Transform

    Liang, X.R. / Wei, Y.X. / China Communications and Transportation Association; Transportation & Development Institute (American Society of Civil Engineers) | British Library Conference Proceedings | 2007



    Macroscopic Modeling of Freeway Traffic Using an Artificial Neural Network

    Zhang, H. / Ritchie, S. G. / Lo, Z.-P. et al. | British Library Conference Proceedings | 1997