一种基于密度的增量式网格聚类算法

An Incremental Grid Density - Based Clustering Algorithm

增量算法的要求是聚类特征一般是可加的、非迭代的。文中提出了一种基于密度的网格聚类算法GDCLUS,并在此 基础上提出了增量式算法IGDCLUS,它可发现任意形状的聚类,具有高效、易实现的特点,适用于数据库周期性地增量环境下的 数据批量更新。

Incremental clustering algorithm featured normally in addable and non-iterative. This paper introduces a grid density-based clustering algorithm-GDCLUS,and an incremental algorithm-IGDCLUS, which can find high effectively arbitrary shape clusters,and is applicable in periodically incremental environment.