Artificial Neural Networks for microscopic evacuation system

The need to safely evacuate a large number of people from public facilities is a challenging problem. Therefore, the analysis of evacuation process has attracted an increasing interest over the last decades. Models for evacuating people can be divided into two main subcategories: macroscopic and microscopic models. The aim of this paper is to design and develop an intelligent system which is able to simulate the behavior of an evacuee during an emergency situation, for microscopic models. In view of the stochastic nature of evacuee behavior, Artificial Neural Networks (ANN) could be an interesting alternative to design such kind of problem.