• Refine Query
  • Source
  • Publication year
  • to
  • Language
  • 1
  • Tagged with
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • About
  • The Global ETD Search service is a free service for researchers to find electronic theses and dissertations. This service is provided by the Networked Digital Library of Theses and Dissertations.
    Our metadata is collected from universities around the world. If you manage a university/consortium/country archive and want to be added, details can be found on the NDLTD website.
1

Modelo de estima??o de multid?es pra cen?rios de emerg?ncia

Testa, Estev?o Smania 15 March 2018 (has links)
Submitted by PPG Ci?ncia da Computa??o (ppgcc@pucrs.br) on 2018-09-13T13:02:14Z No. of bitstreams: 1 ESTEVAO SMANIA TESTA_DIS.pdf: 3237172 bytes, checksum: d5aadd66e71bcae6b9ef00c5c31e0e5a (MD5) / Approved for entry into archive by Sheila Dias (sheila.dias@pucrs.br) on 2018-09-14T19:04:09Z (GMT) No. of bitstreams: 1 ESTEVAO SMANIA TESTA_DIS.pdf: 3237172 bytes, checksum: d5aadd66e71bcae6b9ef00c5c31e0e5a (MD5) / Made available in DSpace on 2018-09-14T19:26:34Z (GMT). No. of bitstreams: 1 ESTEVAO SMANIA TESTA_DIS.pdf: 3237172 bytes, checksum: d5aadd66e71bcae6b9ef00c5c31e0e5a (MD5) Previous issue date: 2018-03-15 / Planos de evacua??o t?m sido historicamente usados como uma medida de seguran?a para a constru??o de edif?cios. Os simuladores existentes requerem ambientes 3D totalmente modelados e tempo suficiente para preparar e simular cen?rios. Uma vez que a quantidade de pessoas pode mudar ao longo do tempo, v?rias simula??es s?o frequentemente necess?rias para gerar um plano de evacua??o otimizado. Neste documento ? apresentado uma nova abordagem para estimar os dados resultantes de um dado cen?rio de evacua??o sem simula-lo de fato. Para tal o ambiente ? dividido o ambiente em salas modulares com configura??es diferentes, em um estilo divis?o e conquista. Em seguida, uma rede neural artificial ? treinada para estimar os dados desejados de uma sala sozinha. Ap?s coletar os dados estimados de cada sala, uma heur?stica capaz de agregar informa??es por sala ? desenvolvida para que o ambiente completo possa ser devidamente estimado. Esse m?todo apresenta erros dentro da margem de 30% quando comparado o tempo de evacua??o em um ambiente real e complexo. Al?m disso, n?o ? necess?rio modelar o ambiente 3D, aprender como configurar um simulador de multid?es e o tempo computacional para estimar ? instant?neo quando comparado ao melhor caso de um simulador de multid?es. / Evacuation plans have been historically used as a safety measure for the construction of buildings. The existing simulators require fully-modeled 3D environments and enough time to prepare and simulate scenarios. Since the amount of people in a given simulated scenario can change over time, several simulations are often required in order to generate an optimal evacuation plan. With that in mind, we present in this paper a novel approach to estimate the resulting data of a given evacuation scenario without actually simulating it. For such, we divide the environment into modular rooms with different configurations, in a divide-and-conquer fashion. Next, we train an artificial neural network to estimate all required data regarding the evacuation of a single room. After collecting the estimated data from each room, we developed a heuristic capable of aggregating per room information so the full environment can be properly evaluated. Our method presents errors within the 30% margin when compared to evacuation time in a real and complex environment. In addition, it is not necessary to model the 3D environment, learn how to use and configure a crowd simulator, and the computational time to estimate is instantaneous when compared to a best case real-time crowd simulator.

Page generated in 0.0962 seconds