Confidence intervals for real-time freeway travel time prediction

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientific

7 Citations (Scopus)

Abstract

In this paper we demonstrate two ways of assigning confidence intervals to real-time neural network based freeway travel time predictions, which express the uncertainty in our model parameters. Both exploit a bootstrap mechanism, but of different sizes. The non-parameterized bootstrap approach estimates model variance by the variance of the ensemble prediction, while the approximate Bayesian approach utilizes a combination of the ensemble variance and the variance that can be calculated analytically through a Bayesian approach toward neural network training. Both methods yield plausible results, albeit that the Bayesian method requires less (computational) effort. since it suffices with a much smaller ensemble of neural networks. The Bayesian approach, however, does seem to overestimate variance in freeflow conditions. Both methods can be straight forwardly extended to calculate prediction intervals, given that we are able to model the noise inherent to the data.
Original languageUndefined/Unknown
Title of host publicationProceedings of the 2003 IEEE International conference on intelligent transportation systems
Place of PublicationShanghai
PublisherIEEE Society
Pages1-6
Number of pages6
ISBN (Print)0-7803-8126-2
Publication statusPublished - 2003
Event2003 IEEE International Conference on Intelligent Transportation Systems, Shanghai - Shanghai
Duration: 12 Oct 200315 Oct 2003

Publication series

Name
PublisherIEEE

Conference

Conference2003 IEEE International Conference on Intelligent Transportation Systems, Shanghai
Period12/10/0315/10/03

Keywords

  • Civiele techniek
  • conference contrib. refereed
  • Conf.proc. > 3 pag

Cite this

van Lint, JWC. (2003). Confidence intervals for real-time freeway travel time prediction. In Proceedings of the 2003 IEEE International conference on intelligent transportation systems (pp. 1-6). IEEE Society.