Travel mode choice forecasts receive wide attention in travel behavior analysis. Most traditional mode choice models are based on the principle of random utility maximization. Alternatively, mode choice is a pattern recognition problem, where different human behavior determines the choices among travel mode alternatives. In this study a new artificial intelligence model, support vector machine, is applied to travel mode choice modeling. The support vector machine model is tested and compared with a nested logit model and a multilayer feed forward neural networks model in terms of both fitting and testing results. The analysis of actual investigation data shows that the model has fast convergence and high precision, which is of great importance for travel mode choice prediction.
Travel Mode Choice Analysis Using Support Vector Machines
11th International Conference of Chinese Transportation Professionals (ICCTP) ; 2011 ; Nanjing, China
ICCTP 2011 ; 360-371
2011-07-26
Conference paper
Electronic Resource
English
Travel Mode Choice Modeling with Support Vector Machines
Transportation Research Record | 2008
|Travel Mode Choice Modeling with Support Vector Machines
Online Contents | 2008
|Bus travel time prediction using support vector machines for high variance conditions
DOAJ | 2021
|Travel Demand, Mode Choice, and System Analysis
NTIS | 1974
|European Patent Office | 2023
|