A SHORT TERM PREDICTION OF TRAFFIC FLUCTUATIONS USING PSEUDO-TRAFFIC PATTERNS
This paper shows a short term prediction scheme of travel time on a long section of a motorway using psuedo-traffic patterns. The auto-regressive method was introduced as a prediction model, and parameters of the model were identified adapting an extended Kalman Filtering method. Time lags in predicted fluctuations which appeared in many studies presented earlier were almost eliminated using the proposed method here. The prediction errors, the relative mean error in this paper, were almost less than 10%. That was significantly smaller than the results of many earlier studies.
-
Supplemental Notes:
- Full conference proceedings available only on CD.
-
Corporate Authors:
1100 17th Street, NW, 12th Floor
Washington, DC United States 20036 -
Authors:
- Iwasaki, M
- Shirao, K
-
Conference:
- Intelligent Transportation: Realizing the Future. Abstracts of the Third World Congress on Intelligent Transport Systems
- Location: Orlando, Florida
- Date: 1996-10-14 to 1996-10-18
- Publication Date: 1996
Language
- English
Media Info
- Pagination: n.p.
Subject/Index Terms
- TRT Terms: Forecasting; Mathematical models; Time duration; Traffic flow rate; Travel time
- Uncontrolled Terms: Models; Short term; Traffic fluctuation
- Subject Areas: Highways; Operations and Traffic Management; Planning and Forecasting; I72: Traffic and Transport Planning;
Filing Info
- Accession Number: 00741482
- Record Type: Publication
- Files: TRIS
- Created Date: Aug 28 1997 12:00AM