@MASTERSTHESIS{ 2018:1035364136,
 	title = {Modelo de estimação de multidões pra cenários de emergência},
 	year = {2018},
 	url = "http://tede2.pucrs.br/tede2/handle/tede/8285",
 	abstract = "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.",
 	publisher = {Pontifícia Universidade Católica do Rio Grande do Sul},
 	scholl = {Programa de Pós-Graduação em Ciência da Computação},
 	note = {Escola Politécnica}
}