Short-term prediction of traffic flows is an integral component of proactive traffic management systems. Prediction during abnormal conditions, such as incidents, is important for such systems. In this paper, three different models with increasing information in explanatory variables are presented. Time Delay and Recurrent Neural Networks and the k-Nearest Neighbour (kNN) algorithms are chosen as the machine learning tools in these models. The models are tested during both normal and incident conditions. The results indicate that historical patterns provide less predictive information during incidents.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Comparison of modelling approaches for short term traffic prediction under normal and abnormal conditions


    Contributors:
    Fangce Guo, (author) / Polak, J W (author) / Krishnan, R (author)


    Publication date :

    2010-09-01


    Size :

    1686983 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Multi-model ensemble for short-term traffic flow prediction under normal and abnormal conditions

    Chen, Xiqun (Michael) / Zhang, Shuaichao / Li, Li | IET | 2018

    Free access

    Multi‐model ensemble for short‐term traffic flow prediction under normal and abnormal conditions

    Chen, Xiqun (Michael) / Zhang, Shuaichao / Li, Li | Wiley | 2019

    Free access


    Dynamic Procedure for Short-Term Prediction of Traffic Conditions

    Lin, Wei-Hua / Lu, Qingying / Dahlgren, Joy | Transportation Research Record | 2002


    Dynamic Procedure for Short-Term Prediction of Traffic Conditions

    Lin, W.-H. / Lu, Q. / Dahlgren, J. et al. | British Library Conference Proceedings | 2002