Short-term Prediction of Traffic Dynamics With Real-time Recurrent Learning Algorithms

Short-term prediction of dynamic traffic states remains critical in the field of advanced traffic management systems and related areas. In this article, a novel real-time recurrent learning (RTRL) algorithm is proposed to address the above issue. The authors dabble in comparing pair predictability of linear method vs. RTRL algorithms and simple non-linear method vs. RTRL algorithms individually using a first-order autoregressive time-series AR(1) and a deterministic function. A field study tested with flow, speed, and occupancy series data collected directly from dual-loop detectors on a freeway is conducted. The numerical results reveal that the performance of RTRL algorithms in predicting short-term traffic dynamics is satisfactorily accepted. Furthermore, it is found that the dynamics of short-term traffic states characterized in different time intervals, collected in diverse time lags and times of day may have significant effects on the prediction accuracy of the proposed algorithms.

  • Availability:
  • Supplemental Notes:
    • Abstract reprinted with permission from Taylor and Francis
  • Authors:
    • Sheu, Jiuh-Biing
    • Lan, Lawrence W
    • Huang, Yi-San
  • Publication Date: 2009-1


  • English

Media Info

Subject/Index Terms

Filing Info

  • Accession Number: 01148074
  • Record Type: Publication
  • Files: TRIS
  • Created Date: Jan 21 2010 3:29PM