一种基于密度栅格的快速聚类算法
首发时间:2015-11-30
摘要:针对已有网格算法和密度算法存在的效率和质量问题,给出了一种结合栅格和密度的聚类算法,即基于密度和栅格的聚类算法DGBCA(density and grid based clustering algorithm)。该算法首先将数据空间划分为栅格单元,根据栅格单元内所含数据点数,筛选出密集栅格,并划分过渡栅格,利用并查集方法对密集栅格进行连通合并,再根据栅格合并结果以及过渡栅格,处理数据得到聚类结果。实验表明,本算法在保证聚类质量的前提下提高了聚类效率。
For information in English, please click here
A fast clustering algorithm based on grid and density
Abstract: In view of the efficiency and quality issues existed in both the grid and density clustering algorithms, this paper proposed the combination of density and grid clustering algorithm, that was DGBCA(density and grid based clustering algorithm) which based on density and grid. The given algorithm firstly divided data space into grids, followed by selecting dense grids according to the number of points in the grids, dividing transition grids, and then combined the dense grids with Union-Find algorithm, finally, it carried on handling data based on merged dense grids and transition grids, and maps the local clustering results to the global clustering results. The experiment shows that the algorithm gained enhance on time efficiency under the premise of clustering quality.
Keywords: grid clustering Union-Find density clustering
基金:
论文图表:
引用
No.4658692109669514****
同行评议
共计0人参与
勘误表
一种基于密度栅格的快速聚类算法
评论
全部评论0/1000