Loading...

School trip attraction modeling using neural & fuzzy-neural approaches

Shafahi, Y ; Sharif University of Technology | 2005

172 Viewed
  1. Type of Document: Article
  2. DOI: 10.1109/ITSC.2005.1520199
  3. Publisher: 2005
  4. Abstract:
  5. Trip attraction has long been considered as a major element in trip demand estimation. Many models have been presented for this purpose. Models use socio-economic variables in order to predict trip attraction. Neural networks and neuro-fuzzy systems are suitable approaches to establish proper models. This paper develops neural and fuzzy-neural models to predict school trip attraction. Neural networks are organized in different architectures and the results have been compared in order to determine the best fitting one. Then an adaptive neural fuzzy inference system (ANFIS) is used to estimate number of school trip attraction. Different models were trained, validated and tested with a real database obtained from Shiraz, a large city in Iran, and then compared with regression model made for school trip attraction in Shiraz Comprehensive Transportation Study (SCTS). The results indicate that the neural networks and fuzzy-neural systems performed more accurate than regression models. © 2005 IEEE
  6. Keywords:
  7. Adaptive neural fuzzy inference system (ANFIS) ; Neuro-fuzzy systems ; Real database ; School trip attraction ; Database systems ; Economic and social effects ; Neural networks ; Parameter estimation ; Predictive control systems ; Regression analysis ; Transportation ; Fuzzy sets
  8. Source: 8th International IEEE Conference on Intelligent Transportation Systems, Vienna, 13 September 2005 through 16 September 2005 ; Volume 2005 , 2005 , Pages 1068-1073 ; 0780392159 (ISBN); 9780780392151 (ISBN)
  9. URL: https://ieeexplore.ieee.org/abstract/document/1520199