This paper proposes a method to predict freeway travel times using a linear model in which the coefficients vary as smooth functions of the departure time. The method uses widely available freeway sensor data and is computationally efficient. To demonstrate the effectiveness of the method, the approach is applied to two field loop detector data sets. The first data set is relatively small in scale, but very high in quality, containing information from probe vehicles and double loop detectors. On this data set, the prediction error ranges from 5% for a trip leaving immediately to 10% for a trip leaving 30 min or more in the future. The method is then applied to a data set on a much larger spatial scale. On this data set, errors range from about 8% at zero lag to 13% at a time lag of 30 min or more. Slightly different versions of the method are compared to enhance understanding of the inner workings of the model. Findings indicate that the quality of the training data used to estimate the model coefficients has significant impact on the prediction accuracy. The potential of a multi-segment version of the model is also demonstrated.


  • English

Media Info

Subject/Index Terms

Filing Info

  • Accession Number: 00961890
  • Record Type: Publication
  • Files: TRIS, ATRI
  • Created Date: Sep 1 2003 12:00AM