Advertisement

Towards Optimal Police Patrol Routes with Genetic Algorithms

  • Danilo Reis
  • Adriano Melo
  • André L. V. Coelho
  • Vasco Furtado
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3975)

Abstract

It is quite consensual that police patrolling can be regarded as one of the best well-known practices for implementing public-safety preventive policies towards the combat of an assortment of urban crimes. However, the specification of successful police patrol routes is by no means a trivial task to pursue, mainly when one considers large demographic areas. In this work, we present the first results achieved with GAPatrol, a novel evolutionary multiagent-based simulation tool devised to assist police managers in the design of effective police patrol route strategies. One particular aspect investigated here relates to the GAPatrol’s facility to automatically discover crime hotspots, that is, high-crime-density regions (or targets) that deserve to be better covered by routine patrol surveillance. In order to testify the potentialities of the novel approach in such regard, simulation results related to two scenarios of study over the same artificial urban territory are presented and discussed here.

Keywords

Genetic Algorithm Multiagent System Crime Prevention Police Resource Urban Crime 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Bäck, T., Fogel, D., Michalewicz, Z.: The Handbook of Evolutionary Computation. Oxford University Press, New York (1997)CrossRefGoogle Scholar
  2. 2.
    Collier, N.: Repast: An extensible framework for agent simulation (2003), Available in, http://repast.sourceforge.net
  3. 3.
    Sherman, L., Gartin, P., Buerger, M.: Hot spots of predatory crime: routine activities and the criminology of place. Criminology 27, 27–56 (1989)CrossRefGoogle Scholar
  4. 4.
    Drogoul, A., Vanbergue, D., Meurisse, T.: Multi-agent based simulation: Where are the agents? In: Sichman, J.S., Bousquet, F., Davidsson, P. (eds.) MABS 2002. LNCS (LNAI), vol. 2581, pp. 1–15. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  5. 5.
    Smith, R., Bonacina, C.: Evolutionary computation as a paradigm for engineering emergent behaviour in multi-agent systems. In: Plekhanova, V. (ed.) Intelligent Agent Software Engineering, Idea Group, pp. 118–136 (2002)Google Scholar
  6. 6.
    Weisburd, D., Maher, L., Sherman, L.: Contrasting crime general and crime specific theory: the case of hot spots of crime. In: Advances in Criminological Theory, vol. 4. Transaction Press, New Brunswick (1992)Google Scholar
  7. 7.
    Weiss, G. (ed.): Multiagent Systems: a Modern Approach to Distributed Artificial Intelligence. The MIT Press, Cambridge (1999)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Danilo Reis
    • 1
  • Adriano Melo
    • 1
  • André L. V. Coelho
    • 1
  • Vasco Furtado
    • 1
  1. 1.Master Program in Applied Informatics (MIA), Center of Technological Sciences (CCT)UNIFOR – University of FortalezaFortalezaBrazil

Personalised recommendations