• DocumentCode
    2642566
  • Title

    The Application of Evolutionary Computation in Evacuation Planning

  • Author

    Muhdi, Rani ; Garrett, Aaron ; Agarwal, Ravikant ; Davis, Jerry ; Dozier, Gerry ; Umphress, David

  • Author_Institution
    Dept. of Ind. & Syst. Eng., Auburn Univ., AL
  • fYear
    2006
  • fDate
    17-20 Sept. 2006
  • Firstpage
    600
  • Lastpage
    605
  • Abstract
    Evacuation planning plays a significant role in building evacuation. The purpose of this paper is to demonstrate how an evolutionary computation technique in the form of an estimation of distribution algorithm can be used in evacuation planning. This technique is used to evolve the number and location of exits in order to minimize overall evacuation time and reduce the number of casualties and injuries. The algorithm is applied to three day-care layouts, classified as playroom, lunchroom, and classroom settings. The algorithm generates an optimal or near-optimal configuration, and results across several trials can be used to determine the probability that an exit is needed for each possible location. The best exit configurations are presented for each of the three layouts, and a brief analysis is discussed. Although evacuation planning presented in this paper is focused on room layouts, evolutionary computation techniques have the potential to be implemented in large-scale evacuation planning
  • Keywords
    emergency services; evolutionary computation; probability; traffic engineering computing; building evacuation; distribution algorithm estimation; evacuation planning; evolutionary computation; probability; room layouts; Buildings; Computational modeling; Computer simulation; Design automation; Evolutionary computation; Humans; Injuries; Large-scale systems; Predictive models; Safety;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Intelligent Transportation Systems Conference, 2006. ITSC '06. IEEE
  • Conference_Location
    Toronto, Ont.
  • Print_ISBN
    1-4244-0093-7
  • Electronic_ISBN
    1-4244-0094-5
  • Type

    conf

  • DOI
    10.1109/ITSC.2006.1706807
  • Filename
    1706807