Feature selection with genetic algorithms for accident duration forecasting on freeway

Ying Lee, Chien Hung Wei

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This study develops two Artificial Neural Network-based models to provide a sequential forecast of accident duration from the accident notification to the accident site clearance. With these two models, the estimated duration time can be provided by plugging in relevant traffic data as soon as an accident is notified. To select suitable data features, Genetic Algorithm is employed to decrease the number of model inputs while preserving relevant traffic characteristics with fewer inputs. This study shows the proposed models are feasible ones in the Intelligent Transportation Systems (ITS) context.

Original languageEnglish
Title of host publication14th World Congress on Intelligent Transport Systems, ITS 2007
PublisherIntelligent Transportation Society of Japan (ITS Japan)
Pages3773-3780
Number of pages8
ISBN (Print)9781617387777
Publication statusPublished - 2007
Event14th World Congress on Intelligent Transport Systems, ITS 2007 - Beijing, China
Duration: 2007 Oct 92007 Oct 13

Publication series

Name14th World Congress on Intelligent Transport Systems, ITS 2007
Volume5

Other

Other14th World Congress on Intelligent Transport Systems, ITS 2007
Country/TerritoryChina
CityBeijing
Period07-10-0907-10-13

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Mechanical Engineering
  • Electrical and Electronic Engineering
  • Control and Systems Engineering
  • Computer Networks and Communications
  • Transportation
  • Computer Science Applications
  • Automotive Engineering

Fingerprint

Dive into the research topics of 'Feature selection with genetic algorithms for accident duration forecasting on freeway'. Together they form a unique fingerprint.

Cite this