Intelligent agents in a goal finding application for homeland security

Orderly and efficient evacuations are the key in saving lives and are of considerable interest to homeland security. There has been a considerable interest in simulation of intelligent agent behavior in the context of agent based modeling. This paper combines Genetic Algorithm (GA) with Neural Networks (NN) to explore how intelligent agents can look for exits during an evacuation. The agents have the capability to adapt their behavior in the environment and formulate their response by learning from the environment. Our approach focuses on modeling individual behavior as well as group behavior. Individuals constantly adjust their behavior according to the dynamic factors in the environment. We are developing crowd-modeling and emergency behavior modeling capability in a goal finding application. This paper examines an intelligent agent-based evacuation that can help plan emergency evacuations, run numerous event-driven evacuation scenarios, support research in the areas of human behavior, and model the movement of responders and security personnel. The result of this simulation was very promising as we are able to observe the agents use GA and NN to learn how to find the various exits.