The artificial neural network combined predictor (ANNCP) is proposed for short term traffic flow forecasting based on the combination of an artificial neural network (ANN) predictor and an autoregressive integrated moving average (ARIMA) model based predictor. The method is tested using traffic flow data collected on Guangshen freeway in Guangdong, China. Statistical analysis of prediction errors reveals that the two singular predictors perform differently depending on different time and different prediction horizons. The combined prediction is a weighted sum of the ANN and ARIMA prediction. According to different time and the forecasting results of the two singular predictor, the weights are decided by ANN dynamically. The proposed method outperforms both singular ANN predictor and singular ARIMA predictor.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Short Term Traffic Flow Forecasting Based on Artificial Neural Network Combined Predictor


    Contributors:
    Nie, Peilin (author) / Yu, Zhi (author) / He, Zhaocheng (author)

    Conference:

    First International Conference on Transportation Engineering ; 2007 ; Southwest Jiaotong University, Chengdu, China



    Publication date :

    2007-07-09




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English




    Short Term Traffic Flow Forecasting Based on Artificial Neural Network Combined Predictor

    Nie, P. / Yu, Z. / He, Z. et al. | British Library Conference Proceedings | 2007


    Short-term traffic flow forecasting based on wavelet transform and neural network

    Ouyang, Liwei / Zhu, Fenghua / Xiong, Gang et al. | IEEE | 2017



    Short-Term Traffic Flow Prediction Based on EMD and Artificial Neural Network

    Luo, Xianglong / Niu, Guohong / Wu, Qianjiao | ASCE | 2009


    Short-Term Traffic Flow Prediction Based on EMD and Artificial Neural Network

    Luo, X. / Niu, G. / Wu, Q. | British Library Conference Proceedings | 2009