Application of Adaptive Neuro-Fuzzy Inference System to Analysis of Travel Behavior

A relatively new method for data analysis called the adaptive neuro-fuzzy inference system (ANFIS) is illustrated with an example from travel behavior modeling. The options offered by this data analysis technique are illustrated by using data from Australia. In addition, an experiment was performed...

Full description

Saved in:
Bibliographic Details
Published in:Transportation research record 2003, Vol.1854 (1), p.180-188
Main Authors: Prˇibyl, Ondrˇej, Goulias, Konstadinos G.
Format: Article
Language:English
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:A relatively new method for data analysis called the adaptive neuro-fuzzy inference system (ANFIS) is illustrated with an example from travel behavior modeling. The options offered by this data analysis technique are illustrated by using data from Australia. In addition, an experiment was performed to identify the optimal split of data into an estimation sample and a validation sample. Comparisons of ANFIS and the more traditional regression methods such as ordinary least-squares linear regression and negative binomial regression were performed by using the mean square error and correlation coefficients. ANFIS is shown to be a useful tool, and its further use in travel behavior research and applications in transportation planning is recommended. However, many additional issues require further scrutiny and experimentation, which are discussed.
ISSN:0361-1981
2169-4052
DOI:10.3141/1854-20