Predicting Short-time Traffic Flow Using Volterra Adaptive Model

DOI

10.2991/iske.2007.123How to use a DOI?

Keywords

Volterra series, adaptive prediction, phase space reconstruction, traffic flow, chaos

Abstract

An adaptive method for predicting short-time traffic flow, which is based on phase space reconstruction and Volterra series, was proposed. We first employed Lyapunav exponent method based small data sets to validate that chaos exists in traffic flow. Then, phase space reconstruction for traffic flow data was performed. And we constructed Volterra adaptive prediction model, which coefficients were updated by LMS adaptive algorithm. We finally applied this model to execute simulations for chaotic time series and real measured traffic flow data. Experimental results show that Volterra adaptive model can effectively predict chaotic time series and traffic flow.

Copyright

© 2007, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Yumei Zhang
AU  - Shiru Qu
AU  - Kaige Wen
PY  - 2007/10
DA  - 2007/10
TI  - Predicting Short-time Traffic Flow Using Volterra Adaptive Model
BT  - Proceedings of the 2007 International Conference on Intelligent Systems and Knowledge Engineering (ISKE 2007)
PB  - Atlantis Press
SP  - 719
EP  - 724
SN  - 1951-6851
UR  - https://doi.org/10.2991/iske.2007.123
DO  - 10.2991/iske.2007.123
ID  - Zhang2007/10
ER  -