Journal of Korean Society of Transportation (대한교통학회지)

Korean Society of Transportation (대한교통학회)
권호 표지

Trip Generation Model Using Backpropagation Neural Networks in Comparison with linear/nonlinear Regression Analysis

신경망 이론을 이용한 통행발생 모형연구 (선형/비선형 회귀모형과의 비교)

  • 장수은 (서울대학교 환경대학원) ;
  • 김대현 (한국도로공사 도로연구소 책임연구원) ;
  • 임강원 (서울대학교 환경대학원)
  • Published : 2000.08.01
Download PDF
⟨ Previous Next ⟩

Abstract

The Purpose of this study is to present a new Trip Generation Model using Backpropagation Neural Networks. For this purpose, it is compared the performance between existing linear/nonlinear Regression models and a new TriP Generation model using Neural Networks. The study was performed according to the below. First, it is analyzed the limits of conventional Regression models, next Proved the superiority of Neural Networks model in theoretical and empirical aspects, and lastly Presented a new approach of Trip Generation methodology. The results show that Backpropagation Neural Networks model is predominant in estimation and Prediction comparable to Regression analysis. Such results mean the possibility of Neural Networks\` application in Trip Generation modeling. Specially under the circumstances of the chancing transportation situations and unstable transportation on vironments, its application in transportation fields will be extended.

본 연구의 목적은 기존의 대표적 통행발생모형인 회귀모형과 신경망 이론에 의한 통행발생모형을 비교.분석하여 통행발생모형에 대한 새로운 방법을 제시하고자 하는 것이다. 이를 위해 모형의 검정력과 안정성을 현재적 설명력과 장래 예측력의 결합으로 전제하고, 시나리오에 따른 모형의 검정력 변화를 통한 안정성 평가를 수행하였다. 연구결과 역전파 신경망 모형(Backpropagation Neural Networks)은 회귀모형의 검정력과 안정성을 상회하는 우수한 결과를 보여 주었으며, 이는 향후 통행발생 모형으로 역전파 신경망 모형의 적용 가능성을 의미하는 것으로 해석된다. 특히 복잡해진 교통현상과 다양한 수집자료를 고려할 때 교통분야에서의 신경망 모형의 적용은 더욱 확대될 전망이다.

Keywords

References

  1. Journal of the Royal Statistical Society An Analysis of Transformations Box;Cox
  2. Regression Analysis by Example(2nd) Chatterjee S.;B. Price
  3. Transportation Research v.13 no.B.2 The Dogit Model Gaudry, M. J. I.;M. G. Degenais
  4. Transportation and Traffic Theory The Use of Neural Networks For Short-Term Prediction Of Traffic Demand J. Barcelo;J. Casas
  5. Fundamentals of Neural Network Laurene Fausett
  6. Fundamentals of Neural Network Mark Dougherty
  7. Transportation Research-B v.28B no.2 Linear or Nonlinear Utility Functions in Logit Models? The Impacts on German High-Speed Rail demand Forecasts Mandel B.(et al.)
  8. Bulletin of Mathematical Biophysics, 5th A logical calculus of the ideas immanent nervous activity McCulloch, W. S.;Pitts, W.
  9. JTEP Alternative Demand Models and Their Elasticity Estimates Oum T. H.
  10. Transportation Research-E v.34 no.1 Exploration of a Box-Cox Logit Model of Intercity Freight Mode Choice Picard G.;M. Gaudry
  11. Neurocomputing:Foun-dations of Research J. A. Anderson;E. Rosenfeld(ed.)
  12. Parallel Distributed Processing:Exploration in the Microstructure of Cognition v.1 & 2 Rumelhart, D. E.;McClelland, J. L.;the PDP Research Group(ed.)
  13. Nerual Networks in Transport Application Velihimanen(et al.)
  14. Transportation Research Board 72nd Annual Meeting Exploration of Driver Route Choice with Advanced Traveler Information Using Neural Network Concepts Yang H.(et al.)