A Modified Particle Swarm Optimization-based Human Behavior Modeling for Emergency Evacuation Simulation System

摘要

A novel emergency evacuation model based on a modified Particle Swarm Optimization was presented. The Linear Weight Decreasing Particle Swarm Optimization was introduced to simulate individual's movement. Compared with social force model and CA model, the new model well performed evacuation result. A prototype system of emergency evacuation simulation was implemented based on Geographic Information System (GIS) application framework. This prototype system simulated human behaviours in multi-exit evacuation environment. The result shows that some typical evacuation behaviors such as avoiding impact, queuing, congesting and herding are well performed and the model based on MPSO has good efficiency and practicability.