Developing fuzzy route choice models using neural nets

Author

Hawas, Yaser E.

Author_Institution

Civil Eng. Dept., United Arab Emirates Univ., Al-Ain, United Arab Emirates

Volume

1

fYear

2002

fDate

17-21 June 2002

Firstpage

71

Abstract

The paper discusses the calibration methodology of a neuro-fuzzy logic for route choice behaviour modelling. Neuro-fuzzy refers to the trend of logics that couple the traditional fuzzy logic structure with neural nets training capabilities for knowledge base and parameters settings. The fuzzy logic accounts for the various factors of potential effect on the route choice utility perceived by the traveller. The structure of the fuzzy logic, the calibration of the membership functions, and the composition of the knowledge base are discussed in detail. Logic training is based on data extracted from a factorial experimental design model.

Keywords

behavioural sciences; design of experiments; driver information systems; fuzzy logic; fuzzy set theory; inference mechanisms; learning (artificial intelligence); neural nets; transportation; factorial experimental design model; fuzzy route choice models; membership functions calibration; neural nets; neuro-fuzzy logic; route choice behaviour modelling; training capabilities; Calibration; Data mining; Design for experiments; Distribution functions; Engines; Fuzzy logic; Fuzzy neural networks; Logic design; Neural networks; Uncertainty;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Vehicle Symposium, 2002. IEEE

Print_ISBN

0-7803-7346-4

Type

conf

DOI

10.1109/IVS.2002.1187930

Filename

1187930