Expert system for selecting computer programs

Janice Daniel, Shauna Hallmark

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

Abstract

Computer programs developed for analyzing signalized intersections continue to grow in their popularity and use by many transportation professionals. These programs differ not only in the features or options available, but the programs also differ in certain underlying assumptions of the models used in estimating various measures of effectiveness. These differences make some programs more appropriate than others when the features and underlying assumptions are evaluated for their compatibility to the type of analysis being performed and the type of intersection being analyzed. The selection of the most appropriate program for performing intersection analysis has direct implications on the success of congestion management strategies which rely on results from these programs. This paper describes an expert system that can be used to select the most appropriate intersection analysis model. The system was developed using knowledge or experience obtained from experts in traffic engineering who have a great deal of familiarity with signalized intersection analysis programs and understand their abilities and limitations.

Original languageEnglish (US)
Title of host publicationChallenges, Innovations, and Opportunities
EditorsRahim F. Benekohal
PublisherASCE
Pages83-89
Number of pages7
StatePublished - Jan 1 1997
Externally publishedYes
EventProceedings of the 1997 Conference on Traffic Congestion and Traffic Safety in the 21st Century - Chicago, IL, USA
Duration: Jun 8 1997Jun 11 1997

Other

OtherProceedings of the 1997 Conference on Traffic Congestion and Traffic Safety in the 21st Century
CityChicago, IL, USA
Period6/8/976/11/97

All Science Journal Classification (ASJC) codes

  • Safety, Risk, Reliability and Quality
  • Safety Research

Fingerprint Dive into the research topics of 'Expert system for selecting computer programs'. Together they form a unique fingerprint.

Cite this