Simulation Based Multiple Regression Analysis of Fuzzy Logic Crowd Injury Model

Realistic predictions for the future supply the decision makers to take important precautions especially for the public events to save the public peace in advance. Agent based simulations supported by well defined models can produce large amount of data for the analyzers to analyze that data and gather valuable information for the decision makers. In this work, we conducted a multiple regression analysis with a full factorial design to check the reliability and accuracy of the fuzzy logic based crowd injury model which is implemented in our previous works. Repast Simphony toolkit and its parameter sweep feature are in bath run mode to produce data for the analysis. The data gathered from the simulation are analyzed by using Minitab statistics software, and results showed that the injury model is acceptable and reliable with a high confidence level.