Detail publikace

Calibrating Traffic Simulation Model using Vehicle Travel Times

Originální název

Calibrating Traffic Simulation Model using Vehicle Travel Times

Anglický název

Calibrating Traffic Simulation Model using Vehicle Travel Times

Jazyk

en

Originální abstrakt

In this paper, we propose an effective calibration method of the cellular automaton based microscopic traffic simulation model. We have shown that by utilizing a genetic algorithm it is possible to optimize various model parameters much better than a human expert. Quality of the new model has been shown in task of travel time estimation. We increased precision by more than 25 % with regard to a manually tuned model. Moreover, we were able to calibrate some model parameters such as driver sensitivity that are extremely difficult to calibrate as relevant data can not be measured using standard monitoring technologies.

Anglický abstrakt

In this paper, we propose an effective calibration method of the cellular automaton based microscopic traffic simulation model. We have shown that by utilizing a genetic algorithm it is possible to optimize various model parameters much better than a human expert. Quality of the new model has been shown in task of travel time estimation. We increased precision by more than 25 % with regard to a manually tuned model. Moreover, we were able to calibrate some model parameters such as driver sensitivity that are extremely difficult to calibrate as relevant data can not be measured using standard monitoring technologies.

BibTex


@article{BUT96950,
  author="Pavol {Korček} and Lukáš {Sekanina} and Otto {Fučík}",
  title="Calibrating Traffic Simulation Model using Vehicle Travel Times",
  annote="In this paper, we propose an effective calibration method of the cellular
automaton based microscopic traffic simulation model. We have shown that by
utilizing a genetic algorithm it is possible to optimize various model parameters
much better than a human expert. Quality of the new model has been shown in task
of travel time estimation. We increased precision by more than 25 % with regard
to a manually tuned model. Moreover, we were able to calibrate some model
parameters such as driver sensitivity that are extremely difficult to calibrate
as relevant data can not be measured using standard monitoring technologies.",
  address="NEUVEDEN",
  chapter="96950",
  doi="10.1007/978-3-642-33350-7_84",
  edition="NEUVEDEN",
  howpublished="print",
  institution="NEUVEDEN",
  number="7495",
  volume="2012",
  year="2012",
  month="september",
  pages="807--816",
  publisher="NEUVEDEN",
  type="journal article - other"
}