by Gehrke, Jan D. and Wojtusiak, Janusz
Abstract:
This paper describes a methodology and initial results of predicting traffic by autonomous agents within a vehicle route planning system. The traffic predictions are made using AQ21, a natural induction system that learns and applies attributional rules. The presented methodology is implemented and experimentally evaluated within PlaSMA multiagent-based simulation system. Initial results obtained by simulation indicate advantage of agents using AQ21 predictions when compared to naive agents that make no predictions and agents that use only weather-related information.
Reference:
Gehrke, Jan D. and Wojtusiak, Janusz, "Traffic Prediction for Agent Route Planning", In International Conference on Computational Science 2008, Springer, vol. 3, no. 5103, Krak\ó\w, Poland, pp. 692–701, 2008.
Bibtex Entry:
@inproceedings{Gehrke2008a,
abstract = {This paper describes a methodology and initial results of predicting traffic by autonomous agents within a vehicle route planning system. The traffic predictions are made using AQ21, a natural induction system that learns and applies attributional rules. The presented methodology is implemented and experimentally evaluated within PlaSMA multiagent-based simulation system. Initial results obtained by simulation indicate advantage of agents using AQ21 predictions when compared to naive agents that make no predictions and agents that use only weather-related information.},
address = {Krak\{\'{o}\}w, Poland},
author = {Gehrke, Jan D. and Wojtusiak, Janusz},
booktitle = {International Conference on Computational Science 2008},
doi = {10.1007/978-3-540-69389-5\{\_\}77},
editor = {Bubak, Marian and van Albada, Dick and Dongarra, Jack and Sloot, Peter M A},
keywords = {ISPL,Agents,Logistics},
number = {5103},
pages = {692--701},
publisher = {Springer},
series = {LNCS},
title = {{Traffic Prediction for Agent Route Planning}},
volume = {3},
year = {2008}
}