Research on the Method of Warfare Simulation Data Analysis Based on BP Neural Network and RoughSet

Abstract

Preliminary exploration on simulation data mining with BP network and rough set method is made in advance.Then data mining method based on rough set theory and BP neural network is put up. Firstly, the redundant attributes in the decision-making table with rough set method is reduced, and the noise is filtered by BP neural network. Finally, rule set is generated by rough set from the reduction decision table. This method not only avoid the complexity of the rules extracted from training the neural network, but also improve the classification accuracy effectively. At last,the mining data by the experimental data of the troops marching warfare simulation system and the result with the actual reference value is obtained.