基于KP CA的作战仿真实验数据特征提取方法

摘要

For the complexity and nonlinearity of various combat elements in combat simulation analysis, a feature extraction method for combat simulation data based on KPCA is proposed. The principle and algorithm of KPCA feature extraction are described. Then KPCA method is applied to the dimension reduction of combat simulation data. The number of new features is determined by the cumulative contribution rate. Simulation results show that compared with PCA, the proposed method has the advantages of obvious principal component feature and concentrated contribution rate. It can effectively integrate the non-linear characteristics, and reduce the dimension of the original data.%针对作战仿真分析过程中各作战要素的复杂性与非线性，研究了一种基于KPCA的作战仿真实验数据特征提取方法。该方法描述了KPCA特征提取的原理和算法，并将其应用于作战仿真实验数据的空间降维，根据累积贡献率确定新特征的数量。仿真结果表明，该方法与PCA相比具有主成份特征明显、贡献率集中等优点，能够有效综合原始数据的非线性特征，降低原始数据的维数。