其他摘要：Human stampedes occur frequently because of abnormal events (e.g., a fire or explosion) produced in collective events (e.g., religious pilgrimages, music concerts and sportive events). These events provoke panic and when people are agglomerated they try to escape pushing each other without realizin g that others are being crushed. Since crowds can consist of individuals with diverse physical and social characteristics determined by cultural diversity, it is difficult to configure the space in advance and find solutions in real - time to save people and reduce catastrophe. This paper proposes an approach to explore the impact of anthropometry and cultural diversity in the behaviour of crowds in panic situations. Our approach includes techniques for reproducing and simulating the behaviour of the crowd to generate models that can help decision making to control such situations. The main contribution of our work is to use computational science, data processing and visualization techniques to perform our simulation and study, for eventually support ing critic al decision making.
其他关键词：Crowd simulation; efficient data management; multi-agent systems.
