Agent-Based Modeling of the Human Behavior with Genetic Algorithm

The article deals with the implementation of the genetic algorithm for training and optimization of the neural network and its application to the tasks related to agent-based modeling of human behavior. After the analysis of existing agent-based modeling programs, several drawbacks were noticed. The main problem of other systems for crowd modeling was the missing of information about the psychoemotional state of people, who are in crowd. According to the other sources, moods in crowd influence its behavior the most. Therefore, we decided to propose another methodic of creating more realistic crowd behavior. The system that implements training of agents by selecting the most effective strategies of behavior from the existing set of strategies using the genetic algorithm was proposed. In addition, this article highlights the detailed development of one agent behavior module based on the neural network, which help the agent to navigate in the environment on condition of being trained enough. Due to created training methodic, it was mentioned, that training environment affects whole training process, so several surveys were made at different environment configurations. The main goal and mission of such approach implementation is using trained agents to develop a system for crowd behavior modeling in the building, which was set on fire.