2 results for Andrade, K.

  • Investigating the temporal transferability of transport modal choice models: an approach based on GIS database

    Andrade, K.; Kagaya, S.; Uchida, K.; Dantas, A.; Nicholson, A. (2007)

    Conference Contributions - Published
    University of Canterbury Library

    Developing precise travel behavior models and testing its forecasting capability are essential when planning transportation systems. However, emphasis is observed in estimating while forecasting still needs to be better understood. This study examines the temporal transferability of a Multinomial Logit Model and a hybrid Neuro-Fuzzy Multinomial Logit model, which differ primarily by including linear and non-linear utilities. Geographic Information System is successfully used during the forecasting process. Overall, the hybrid model presents better performance, even though both models do not show satisfactory behavior when directly transferred to the application context. Small sample model results show good behavior of the hybrid model. Accordingly, a sensitivity analysis suggests this model is able to capture travelers’ sensitivity to parking cost variations, which is not well described by the classical model. Travelers’ behavior could be better explained by the hybrid model rather than by the classical Multinomial Logit structure.

    View record details
  • A GA-based transport modal choice model

    Andrade, K.; Uchida, K.; Kagaya, S.; Dantas, A.; Nicholson, A. (2006)

    Conference Contributions - Published
    University of Canterbury Library

    This paper presents a hybrid transport modal choice model in which the genetic algorithm is applied for estimating parameters of a Multinomial Logit Model. The model has a simple decision structure which requires relatively modest computational capabilities and time to be estimated. Linear Utility Functions are defined for the transport modes which are included in the model structure as the fitness function. The objective function seeks to reduce the errors in the modal choice process. Moreover, the hybrid model incorporates distance as a spatial attribute variable for explaining commuters’ modal choices among automobile, bus, bicycle and walk modes. After this introduction section, a brief review on GA’s is presented. Section 3 introduces the Hybrid Transport Modal Choice Model structure, which is followed by the modeling results. Finally, Section 5 discusses this work’s findings and makes recommendations to further research.

    View record details