Development  of  trip  generation  models  has  been  conducted  mainly  using  the  traditional  Multiple  Linear  Regression approach, which sometimes might not necessarily result in appropriate models, especially with existence of many interrelated and complex relationships  among  several  related  socioeconomic  variables.  This study  investigates  the  feasibility  of  using  a  relatively new approach, the Adaptive Neuro-Fuzzy Inference System, and compares the results with those using the traditional approach. This  is  conducted  by  developing  a  home-based  general  trip  generation  model  for  one  of  the  Palestinian  urban  areas.  The comparison between the two methods outcome and the associated validation results is done using the R-squared, RMSE, and MAE measures.  The  Adaptive  Neuro-Fuzzy  Inference  System was  found  to  be  a  useful  tool  and  a  promising  technique  for  modelling household  trip  generation,  which  is  shown  to  outperform  the  traditional  approach,  with  more  accurate  results  and  closer predictions to actual values. Further exploration of the new approach in transportation studies is recommended. 

Title

International Journal of Simulation: Systems, Science & Technology

Publisher

United Kingdom Simulation Society

Publisher Country

United Kingdom

Publication Type

Online only

Volume

21

Year

2020

Pages

17.1-17.6