Classifier System in Traffic Management

  • Giorgio Casadei
  • Aldopaolo Palareti
  • Gianluca Proli
Conference paper


The systems of controlling and improving traffic movement have been studied for several years now. The usefulness of these systems is that they can modify and change the lights signals of traffic lights. It is not enough to intervene when the situation has reached a critical point such as a traffic jam. The system has to work out how the traffic will flow. The ideal solution would be a system that works out and foresees the situation on the roads based on a model of motorists’ behaviour. This research shows how to best utilise the classifier systems so that it would be possible to create a model that is similar to that of the real world.


Genetic Algorithm Road Network Classifier System Traffic Light Random Performance 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Booker L.B. (1982) Intelligent behaviour as an adaptation to the task environment (Doctoral dissertation, Departement of computer and communication sciences, University of Michigan, Ann Arbor).Google Scholar
  2. Booker L.B. (1987) Improving search in genetic algorithms (In L. Davis, Genetic algoritms and simulated annealing, p. 61-73).Google Scholar
  3. Booker L.B. & Goldberg D.E. & Holland J.H. (1987) Classifier system and genetic algorithms (tecnical report 8, University of Michigan).Google Scholar
  4. Booker L.B. (1988) Classifier System that learn internal world models (Machine learning, 3: 161–192).Google Scholar
  5. Booker L.B. & Goldberg D.E. & Holland J.H. (1989) Classifiers systems and genetic algorithms (Artificial Intelligence p. 235-282).Google Scholar
  6. Booker L.B. (1989) Triggered rule discovery in classifier systems (ICGA pp. 265-274).Google Scholar
  7. Buchanam C. (1963) Traffic in towns.Google Scholar
  8. Colorni A. & Dorigo M. & Maniezzo V. (1990) On the use of genetic algorithms to solve the timetable problem (Internal report 90-060).Google Scholar
  9. Cox L.A. & Davis L. & Qiu Y. (1990) Dynamic anticipatory routing in circuit-switched telecomunications networks (Handbook of genetic algoritms, p. 124-143).Google Scholar
  10. Davis L. & Ritter F. (1987) Schedule optimization with probabilistic search (proceedings of the 3rd IEEE conference on artificial intelligence applications).Google Scholar
  11. Dipartimento ambiente-territorio-trasporti (1982) I problemi della viabilità in Emilia Romagna.Google Scholar
  12. Dorigo M. (1989) Genetic algorithms: the state of the art and some research proposal (Internal report 89–058, Dipartimento di elettronica, Politecnico di Milano).Google Scholar
  13. Dorigo M. (1990) Machine learning: an approach based on classifier systems and evolutionary algorithms (Internal report 90-043).Google Scholar
  14. Dorigo M. (1991) New perspectives about default hierarchies formation in learning classifier systems (Internal report 91-002).Google Scholar
  15. Dorigo M. (1991) Message based bucket brigade: an algorithm for the apportionment of credit problem (Proceedings of the European working section on learning 91).Google Scholar
  16. Dorigo M. & Schnepf U. (1991) Organization of robot behaviour trough genetic learning processes (to appear in the procedings of the fifth IEEE International conference on advanced robotics).Google Scholar
  17. Filippi F. (1985) [Fil85] Piano del traffico e dei trasporti del comune di Forlì.Google Scholar
  18. Grefenstette J.J. (1985) Proceedings of the first International conference on genetic algorithms.Google Scholar
  19. Grefenstette J.J. & Ramsey C.L. & Schultz A.C. (1990) Learning sequential decision rules using simulation models and competition (Machine learning, 5: p: 355–381).Google Scholar
  20. Goldberg D.E. (1981) Robust learning and decision algorithms for pipeline operations (dissertation proposal, University of Michigan, Ann Arbor).Google Scholar
  21. Goldber D.E. & Lingle R. (1985) Alleles, loci, and the traveling salesman problem (proceedings of an International conference on genetic algorithms and their applications, p. 154-159).Google Scholar
  22. Goldberg D.E. & Samtani M.P. (1986) Enginering optimization via genetic algorithm (procedings of the ninth conference on electronic computation, p. 471-482).Google Scholar
  23. Goldberg D.E. (1987) Genetic algorithms in search, optimalization, and machine learning (Addison — Wesley).Google Scholar
  24. Goldberg D.E. & Kuo C.H. (1987) Genetic algorithms in pipeline optimalization (Journal of computers in civil engineering, 1(2), p. 128–141).CrossRefGoogle Scholar
  25. Goldberd D.E. (1987) Genetic algorithms in pipeline optimalization (Engineering with computers, 3, p: 35–45).Google Scholar
  26. Goldberg D.E. & Smith R.E. (1987) Non stationary function optimalization using genetic algorithms with dominance and diploidy (genetic algorithms and their applications:proceedings od the 2nd International conference on genetic algorithms).Google Scholar
  27. Goldberg D.E. & Richardson J. (1987) Genetic algorithm with sharing for multimodal function optimalization (proceedings of the second international conference on genetic algorithm, p. 41-49).Google Scholar
  28. Goldberg D.E. & Wilson S.W. (1989) A critical review of classifier systems. (ICGA pp.244-255).Google Scholar
  29. Goldberg D.E. (1990) Probability matching, the magnitude of reinforcement and classifier system bidding (Machine learning, 5, p. 407–425).Google Scholar
  30. Matson & Smith & Hurd (1961) [MSH61] Tecnica del traffico stradale (Padova Cedam).Google Scholar
  31. Michalewicz Z. & Kazemi M. & Janikow C. (1990) On dynamic control problem (29th IEEE conference on decision and control, Honolulu).Google Scholar
  32. Michalewicz Z. & Vignaux G.A. & Hobbs M. (1990) A genetic algoritm for the nonlinear transportation problem.Google Scholar
  33. Michalewicz Z. & Shell J. (1990) Data structures + genetic operators = evolution programs (proceedings of the International conference on tools for AI).Google Scholar
  34. Microsoft corporation (1990) Microsoft C version 6.00 reference manual.Google Scholar
  35. Montana D.J. (1990) Empirical learning using rule threshold optimization for detection of events in synthetic images (Machine learning, 5, p. 427–450).Google Scholar
  36. National Research Council (1985) [NRC85] Highway Capacity Manual (Special report 209, Transportation research board, Washington D.C.)Google Scholar
  37. Orlandi A. (1974) [Orl74] Tecnica della circolazione (Patron editore Bologna).Google Scholar
  38. Proli G. (1992) I classifier systems (Internal report, Università di Bologna).Google Scholar
  39. Regione Emilia Romagna (1982) Piano Regionale Integrato dei Trasporti.Google Scholar
  40. Vose M.D. (1990) Generaliziong the notion of schema in genetic algorithm (Atificial intelligence 50 p: 385-396).Google Scholar
  41. Wilson S.W. & Goldberg D.E. (1990) A critical review of classifier systems. (ICGA pp.244-255).Google Scholar
  42. Zhou H.H. (1990) CSM: computational model of cumulative learning (Machine learning 5, p.383–406).Google Scholar

Copyright information

© Springer-Verlag/Wien 1993

Authors and Affiliations

  • Giorgio Casadei
    • 1
  • Aldopaolo Palareti
    • 1
  • Gianluca Proli
    • 1
  1. 1.Dipartimento di statistica “P. Fortunati”Università di BolognaItaly

Personalised recommendations