Development of a neural-based model for forecating link travel times

신경망 이론에 의한 링크 통행시간 예측모형의 개발

  • 박병규 (서울시정개발연구원 , 위촉연구원) ;
  • 노정현 (한양대 도시공학과) ;
  • 정하욱 (한양대 도시공학과)
  • Published : 1995.02.01

Abstract

n this research neural -based model was developed to forecast link travel times , And it is also compared wiht other time series forecasting models such as Box-Jenkins model, Kalman filter model. These models are validated to evaluate the accuracy of models with real time series data gathered by the license plate method. Neural network's convergency and generalization were investigated by modifying learning rate, momentum term and the number of hidden layer units. Through this experiment, the optimum configuration of the nerual network architecture was determined. Optimumlearining rate, momentum term and the number of hidden layer units hsow 0.3, 0.5, 13 respectively. It may be applied to DRGS(dynamic route guidance system) with a minor modification. The methods are suggested at the condlusion of this paper, And there is no doubt that this neural -based model can be applied to many other itme series forecating problem such as populationforecasting vehicel volume forecasting et .

Keywords

References

  1. 신경망 이론과 응용(Ⅰ) 김대수
  2. 시계열분석 김원경
  3. 한양대학교 대학원 석사학위논문 신경망이론에 의한 링크통행시간 예측모형의 개발 박병규
  4. IVHS 국내개발방향에 관한 연구 하동익(외 2인)
  5. Neural Computation First and Second order method for learning between steepest descent and newton's method Battiti,Roberto
  6. Introduction to random signals and applied Kalman flitering(2nd ed.) Brown,R.G.;Hwang,P.Y.C.
  7. Proceedings of Two Parallel Conference: Infrastructure Planning and Management A Short-Term Demand Forecasting Model from Real-Time Traffic Data C.Kim;A.G.Hobeika
  8. 72nd Transportation Research Board Annual Meeting An Artifical Neural Network Approach for Estimating Multiperiod Travel Times in Transportation Networks Chien-Hung Wei;Paul M.Schonfeld
  9. Kalman Filtering with Real-Time Applications(2nd ed.) Chui,C.K.;Chen,G.
  10. Proceedings of the 1988 Connectionist Models Summer School Faster-learning variations of Backpropagation; An empirical study Fahlman,Scott;David Touretzky(ed.);Geoffrey Hinton(ed.);Terrence Sejnowski(ed.)
  11. 72nd Transportation Research Board Annual Meeting Exploration of Driver Route Choice with Advanced Traveller Information Using Neural Network Concepts Hai Yang;Ryuichi Kitamura;Paul P. Jovanis;Kenneth M. Vaughn;Mohamed A. Abel-Aty;Prasuna DVG Reddy
  12. Micro TSO User's Manual Hall,R.E.;Johnston,J.;Lilien,D.M.
  13. 72nd Transportation Research Board Annual Meeing Macroscopie Modeling of Freeway Traffic Using an Artificial Neural Network Hongjun Zhang;Stephen G. Ritchie;Zhen-Ping Lo
  14. Transpn. Res.-C v.2 no.4 Modelling Dual Carriageway Lane Changing Using Neural Networks J.G.Hunt;G.D.Lyons
  15. Transportation Research Record v.722 Analysis of Freeway Traffic Time Series Data Using Box and Jenkins Techniques M.Ahmed;A.Cook
  16. 72nd Transportation Research Board Annual Meeting Prediction of Discrete Choice Via Neural Networks Michael G. McNally;Zhen-Ping Lo
  17. Proceedings of the 1988 Connectionist Models Summer School Learning with localized receptive fields Moody;Jaha;Christian Darken;David Touretzky(ed.);Geoffrey Hinton(ed.);Terrence Sejnowski(ed.)
  18. Transportation v.9 Use of the Box and Jenkins Time Series Technique in Traffic Forecasting N.L.Nihan;K.O.Holmesland
  19. Neural network for statistical modeling Smith;Murray
  20. 73nd Transportation Research Board Annual Meeting A Simulation-Neural Network Model for Evaluating Dilemma Zone Problems X.Peter Huang;Prahlad D. Pant