一种基于改进K-means算法的空间群划分方法

A Space Group Division Method Based on Improved K-means Algorithm

空间群划分是兵力分群的重要环节,其关键在于确定“距离”度量函数、分群数目和初始分群中心。传统算法的初始聚类中心和聚类数目不固定,直接用于空间群划分将使得划分结果不稳定。为此,提出了一种基于改进算法的空间群划分方法。利用了现有空间群划分方法中的距离函数改进策略计算敌方作战单元两两之间的“距离”,引入一种快速搜寻高密度点的方法,确定了初始分群中心和分群数目,通过仿真实验验证了该方法的有效性。

Space grouping is an important part of military force grouping.The key is to determine the“distance”measurement function,the initial clustering center and the number of groups.The initial clustering center and number of clusters of traditional algorithms are not fixed and cannot be directly used for space group partitioning.For this reason,a space group partition method based on improved algorithm is proposed.Firstly,the distance function improvement strategy in the existing space group partitioning method is used to calculate the distance between two enemy entities.Then a method for quickly searching for high density points is introduced to determine the initial clustering center and the number of clusters;finally,The effectiveness of the method was verified by simulation experiments.