Short-term travel time forecasting in Hong Kong

K. S. Chan, Hing Keung William Lam, G. Xu

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

Abstract

This paper presents a traffic flow simulator (TFS) for short-term travel time forecasting. The forecasted travel time information is useful for the pre-trip planning of the drivers. The drivers can decide their departure time and mode choice based on the forecasted travel time. A case study has been carried out in the Hong Kong Island during the AM peak period. The stochastic deviation coefficient is introduced in the case study to simulate the variation of traffic flows within the peak hour period. The purposes of the case study are: 1) to show the applicability of the TFS for real road network; and 2) to illustrate the short-term forecasting of link travel times. The results of the case study show that the TFS can be applied for real network effectively. The TFS forecasted travel times and the observed travel times are compared. The findings show that the observed travel times fall in the 90% confidence interval of the TFS forecasted travel times.
Original languageEnglish
Title of host publicationProceedings of the International Conference on Applications of Advanced Technologies in Transportation Engineering
Pages13-17
Number of pages5
Publication statusPublished - 1 Dec 2004
EventProceedings of the Eighth International Conference on Applications of Advanced Technologies in Transportaion Engineering - Beijing, China
Duration: 26 May 200428 May 2004

Conference

ConferenceProceedings of the Eighth International Conference on Applications of Advanced Technologies in Transportaion Engineering
Country/TerritoryChina
CityBeijing
Period26/05/0428/05/04

Keywords

  • Short-term travel time forecasting and traffic flow simulator

ASJC Scopus subject areas

  • General Engineering

Fingerprint

Dive into the research topics of 'Short-term travel time forecasting in Hong Kong'. Together they form a unique fingerprint.

Cite this