RECURSIVE PREDICTION OF TRAFFIC CONDITIONS WITH NEURAL NETWORK MODELS
This paper presents a recursive traffic flow prediction algorithm using artificial neural networks. The system prediction model is specified based on the understanding of how disturbances in traffic flow are propagated, and the order of the model is determined by correlation analysis. The parameters of the model, on the other hand, can be obtained through nonlinear optimization. Preliminary studies show that this approach can yield reasonably accurate results.
-
Availability:
- Find a library where document is available. Order URL: http://worldcat.org/oclc/8674831
-
Corporate Authors:
American Society of Civil Engineers
1801 Alexander Bell Drive
Reston, VA United States 20191-4400 -
Authors:
- Zhang, H M
- Publication Date: 2000-11
Language
- English
Media Info
- Features: Appendices; Figures; References; Tables;
- Pagination: p. 472-481
-
Serial:
- Journal of Transportation Engineering
- Volume: 126
- Issue Number: 6
- Publisher: American Society of Civil Engineers
- ISSN: 0733-947X
- Serial URL: https://ascelibrary.org/journal/jtepbs
Subject/Index Terms
- TRT Terms: Algorithms; Calibration; Correlation analysis; Feedback control; Mathematical models; Mathematical prediction; Neural networks; Optimization; Traffic flow; Validation
- Subject Areas: Data and Information Technology; Highways; Operations and Traffic Management; I71: Traffic Theory;
Filing Info
- Accession Number: 00802043
- Record Type: Publication
- Files: TRIS, ATRI
- Created Date: Nov 7 2000 12:00AM