Paper:
Views over last 60 days: 398
A Sequential Method for Combining Random Utility Model and Fuzzy Inference Model
Backjin Lee*, Akimasa Fujiwara*, Yoriyasu Sugie*, and Moon Namgung**
*Graduate School for International Development and Cooperation, Hiroshima University, 1-5-1 Kagamiyama, Higashi-Hiroshima, 739-8529, Japan
**Department of Civil and Environmental Engineering, Wonkwang University, 344-2 Shinyongdong, Iksanshi, Chollabukdo, 570-7491, Korea
Received:February 1, 2003Accepted:February 24, 2003Published:June 20, 2003
Keywords:combined model, uncertainty, randomness, vagueness, fuzzy inference, latent class multinomial logit
Abstract
In the analysis of choice behavior problem, uncertainty can be divided into two different types: randomness and vagueness. Random utility model and fuzzy inference model have been widely used to consider the randomness and the vagueness, respectively. Despite the necessity of simultaneously considering both uncertainties in choice behavior analysis, few literatures have tried to combine the two types of choice behavior models. Therefore, the aim of this paper is to suggest a model combining the randomness and the vagueness in the context of driver’s route choice behavior under traffic information. To estimate the combined model, a sequential method is suggested as follows: First, a latent class multinomial logit model (LCML) is developed to consider the randomness of route choice behaviors and to analyze the heterogeneity among drivers. Second, a fuzzy inference model is developed to consider the vagueness. Finally, the combined model is established by combining the estimation results of the LCML and the fuzzy inference models. The empirical results in this paper show that the combined model can contribute to enhance the explanatory power of the LCML model by effectively incorporating the randomness and the vagueness uncertainty in the choice behavior model.
Cite this article as:B. Lee, A. Fujiwara, Y. Sugie, and M. Namgung, “A Sequential Method for Combining Random Utility Model and Fuzzy Inference Model,” J. Adv. Comput. Intell. Intell. Inform., Vol.7 No.2, pp. 200-206, 2003.Data files:
