An Aggregation Approach to Short-Term Traffic Flow Prediction

In this paper, the authors propose an aggregation approach for traffic flow prediction that is based on the moving average (MA), exponential smoothing (ES), autoregressive MA (ARIMA), and neural network (NN) models. The aggregation approach assembles information from weekly, daily, and hourly time series. The MA, ES, and ARIMA models are selected to give predictions of the three relevant time series. The predictions resulting from the different models are used as the basis of the NN in the aggregation stage, and the output of the trained NN serves as the final prediction.

  • Availability:
  • Authors:
    • Tan, Man-chun
    • Wong, S C
    • Xu, Jian-Min
    • Guan, Zhan-Rong
    • Zhang, Peng
  • Publication Date: 2009-3


  • English

Media Info

Subject/Index Terms

Filing Info

  • Accession Number: 01142750
  • Record Type: Publication
  • Source Agency: UC Berkeley Transportation Library
  • Files: BTRIS, TRIS
  • Created Date: Oct 5 2009 5:14PM