Neural Agent (Neugent) Models of Driver Behavior for Supporting ITS Simulations

  • Hussein Dia
  • Sakda Panwai


This paper presents an agent-based neuro-fuzzy approach for modeling drivers’ compliance with travel advice under the influence of real-time traffic information. Fuzzy logic is combined with neural networks to capture the variability of drivers’ appraisal of the different route attributes as well as the variability in their perceptions of the various attribute levels. The accuracy of the models, in terms of predicting the categories of drivers likely to comply with traffic advice, was found to exceed 90%. A comparative evaluation with discrete choice models showed higher accuracies ranging between (91 and 96) percent compared to (50–73) percent for the binary choice models.


Neural networks Fuzzy logic Traffic simulation Driver behavior Intelligent transport systems 



At the time of undertaking this research, both authors were with the ITS Research Laboratory at the University of Queensland, Australia. The work reported in this paper was part of the second author’s PhD work. An earlier version of this paper was presented at the 10th Intelligent Transport Systems Asia-Pacific Forum, in Bangkok, Thailand (2009).


  1. 1.
    U.S. Department of Transportation. Intelligent Transport Systems Benefits, Costs and Lessons Learned., Accessed 30–12-2009 (2009)
  2. 2.
    Hawas, Y.E.: Development and calibration of route choice utility model: factorial experimental design approach. Transp. Eng ASCE 130(2), 159–170 (2004)CrossRefMathSciNetGoogle Scholar
  3. 3.
    Hawas, Y.E.: Development and calibration of route choice utility models: neuro-fuzzy approach. J. Transp. Eng ASCE 130(2), 171–182 (2004)CrossRefMathSciNetGoogle Scholar
  4. 4.
    Kuri, I., Pursula, M.: Modeling Car Route Choice with Non-Dynamic Stated Preference Data: A Comparison Between Fuzzy Similarity and Random Utility Models, Annual Meeting of the Transportation Research Board, Washington, DC (2001)Google Scholar
  5. 5.
    Henn, V.: Fuzzy route choice model for traffic assignment. Fuzzy Sets Syst. 116, 77–101 (2000)zbMATHCrossRefGoogle Scholar
  6. 6.
    Teodorovic, D., Vukanovic, S., Obradovic, K.: Modeling route choice with advanced traveler information by fuzzy logic. Transp. Plann. Technol. 22(1), 1–25 (1998)CrossRefGoogle Scholar
  7. 7.
    Chen, T.-Y., Chang, H.-L., Tzeng, G.-H.: Using a weight-assessing model to identify route choice criteria and information effects. Transp. Res. A Policy Pract. 35, 197–224 (2001)CrossRefGoogle Scholar
  8. 8.
    Chen, W.-H., Jovanis, P.P.: Analysis of driver en-route guidance compliance and driver learning with ATIS using a travel simulation experiment. Transportation Research Board Annual Meeting, January 2003, Washington DC (2003)Google Scholar
  9. 9.
    Dia, H.: An agent-based approach to modelling driver route choice behaviour under the influence of real-time information. Transp. Res. C Emerg. Technol. 10, 331–349 (2002)CrossRefGoogle Scholar
  10. 10.
    Shoham, Y.: Agent-oriented programming. Artif. Intell. 60(1), 51–92 (1993)CrossRefMathSciNetGoogle Scholar
  11. 11.
    Thomas, S.R. PLACA, Agent Oriented Programming Language, Stanford University (1993)Google Scholar
  12. 12.
    Peeta, S., Yu, J.W.: Adaptability of a hybrid route choice model to incorporating driver behavior dynamics under information provision. IEEE Transections Syst. Man Ctbernetics A Syst. Hum. 4(2), 243–256 (2004)CrossRefGoogle Scholar
  13. 13.
    Khattak, A., Polydoropoulou, A., Ben-Akiva, M.: Modeling revealed and stated pretrip travel response to advanced traveler information systems. Transp. Res. Rec. 46–54 (1996)Google Scholar
  14. 14.
    Dia, H., Panwai, S.: Modelling drivers’ compliance and route choice behaviour in response to travel information. Special issue on Modelling and Control of Intelligent Transportation Systems. J. Nonlinear Dyn. 49(40), 493–509 (2007). SpringerzbMATHCrossRefGoogle Scholar
  15. 15.
    Dia, H.: An object-oriented neural network approach to short-term traffic forecasting. Eur. J. Oper. Res. 131, 253–261 (2001)zbMATHCrossRefGoogle Scholar
  16. 16.
    Furusawa, H.: A study of route choice behaviour in response to content of variable message signs in Adelaide. University of SA, Adelaide (2004)Google Scholar
  17. 17.
    Hensher, D.A., Ton, T.T.: A comparison of the predictive potential of artificial neural networks and nested logit models for commuter mode choice. Transp. Res. E Logistics Transp. Rev. 36, 155–172 (2000)CrossRefGoogle Scholar
  18. 18.
    Haykin, S.: Neural networks: A comprehensive foundation, 3rd edn. Prentice Hall, NJ (2007)Google Scholar
  19. 19.
    Smith, L.: An Introduction to Neural Networks., Accessed 20-Jan-2010, (2003)
  20. 20.
    Panwai, S., Dia, H.: Neural agent car-following models. IEEE Trans. Intell. Transp. Syst. 8(1), 60–70 (2007)CrossRefGoogle Scholar
  21. 21.
    Zhao, S., Muromachi, Y., Harata, K., Ohta, A.: SP model for route choice behavior in response to travel time information with marginal errors. Proceedings 7th World Conference Transport Research, Australia (1995)Google Scholar
  22. 22.
    Lotan, T.: On effects of familiarity on route choice behaviour in response of information. Proceedings 7th World Conference on Transport Research, Australia (1995)Google Scholar
  23. 23.
    Abdel-Aty, M., Kitamura, R., Jovanis, P.: Using stated preference data for studying the effect of advanced traffic information on drivers’ route choice. Transp. Res. C 5(1), 39–50 (1997)CrossRefGoogle Scholar
  24. 24.
    Wardman, M., Bonsall, P., Shires, J.: Driver response to variable message signs: a stated preference investigation. Transp. Res. C Emerg. Technol. 5(6, 1), 389–405 (1997)CrossRefGoogle Scholar
  25. 25.
    Bonsall, P., Firmin, P., Anderson, M., Palmer, I., Balmforth, P.: Validating the results of a route choice simulator. Transp. Res. C Emerg. Technol. 5(6), 371–387 (1997)CrossRefGoogle Scholar
  26. 26.
    Peeta, S., Poonuru, K., Sinha, K.: Evaluation of mobility impacts of advanced information systems. J. Transp. Eng. Am. Soc. Civ. Eng. 126, 212–220 (2000)Google Scholar
  27. 27.
    Mizoue, S., Kakimoto, R., Shibaki, M.: Experimental analysis on dynamic route choice behavior under providing travel information. Traffic Eng. 35(3), 9–19 (2000)Google Scholar
  28. 28.
    Lai, K-h, Wong, W-g: SP approach toward driver comprehension of message formats on VMS. J. Transp. Eng. Am. Soc. Civ. Eng. 126, 221–227 (2000)Google Scholar
  29. 29.
    Adler, J.L.: Investigating the learning effects of route guidance and traffic advisories on route choice behavior. Transp. Res. C Emerg. Technol. 9(1), 1–14 (2001)CrossRefGoogle Scholar
  30. 30.
    Hidas, P., Awadalla, E.: Investigation of route choice in response to variable message signs J. East. Asia Soc. Transp. Stud. (EASTS), Behavioral Analysis and Traffic Models 4(3):39–54. ISSN 1341-8521.Google Scholar
  31. 31.
    Dia, H., Harney, D., Boyle, A.: Dynamics of drivers’ route choice decisions under advanced traveler information systems. Roads and Transport Research. Vol. 10, No. 4, ARRB Transport Research Ltd, Vermont South, Victoria, Australia. pp. 2–12 (2001)Google Scholar
  32. 32.
    Dia, H., Rose, G.: Development and evaluation of neural network freeway incident detection models using field data. Transp. Res. C Emerg. Technol. 5, 313–331 (1997)CrossRefGoogle Scholar
  33. 33.
    NeuralWare: NeuralWorks professional II/PLUS: Getting started—a tutorial for microsoft windows computers. CARNEGIE, PA (2006)Google Scholar
  34. 34.
    Kohonen, T.: Self-organization and associative memory. Springer-Verlag, New York (1988)zbMATHGoogle Scholar
  35. 35.
    Palacharla, P.V., Nelson, P.C.: Application of fuzzy logic and neural networks for dynamic travel time estimation. Int. Trans. Oper. Res. 6(1), 145–160 (1999)CrossRefGoogle Scholar
  36. 36.
    Pedrycz, W.: Fuzzy neural networks and neurocomputations. Fuzzy Sets Syst. 56, 1–28 (1993)CrossRefGoogle Scholar
  37. 37.
    Peeta, S., Yu, J.W.: A data-consistent fuzzy approach for on-line driver behavior under information provision. Transp. Res. Rec. 1803, 76–86 (2002)CrossRefGoogle Scholar
  38. 38.
    TSS: AIMSUN 6.1 Microsimulator user manual. Version 6.1. Transport Simulation Systems, Barcelona (2010)Google Scholar
  39. 39.
    Panwai, S., Dia, H.: Comparative evaluation of microscopic car-following behavior. IEEE Trans. Intell. Transp. Syst. 6(3), 314–325 (2005)CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2010

Authors and Affiliations

  1. 1.AECOMBrisbaneAustralia
  2. 2.Expressway Authority of ThailandBangkokThailand

Personalised recommendations