作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2011, Vol. 37 ›› Issue (19): 65-67. doi: 10.3969/j.issn.1000-3428.2011.19.020

• 软件技术与数据库 • 上一篇    下一篇

空间数据聚类中的网格粒度求解方法

陈 曦,马一峰   

  1. (长沙理工大学计算机与通信工程学院,长沙 410114)
  • 收稿日期:2011-03-22 出版日期:2011-10-05 发布日期:2011-10-05
  • 作者简介:陈 曦(1963-),男,教授,主研方向:数据挖掘,人工智能;马一峰,硕士研究生
  • 基金资助:
    国家自然科学基金资助项目(60973113)

Solving Method of Grid Granularity in Spatial Data Clustering

CHEN Xi, MA Yi-feng   

  1. (College of Computer and Communication Engineering, Changsha University of Science and Technology, Changsha 410114, China)
  • Received:2011-03-22 Online:2011-10-05 Published:2011-10-05

摘要: 提出一种空间数据聚类中的网格粒度求解方法。在网格动态划分过程中,根据密网格和稀疏网格的产生情况,确定最佳网格粒度与密度阈值。在给定一组密度阈值的条件下,利用该方法可以确定一个最佳的密度阈值及相应的网格粒度。给出该求解方法的聚类算法描述及算法时间复杂度分析。实验结果表明证明了该算法的有效性。

关键词: 空间数据聚类, 网格粒度, 密度阈值, 网格划分

Abstract: This paper proposes a solving method of grid granularity in spatial data clustering. It ascertains the optimum grid granularity and density threshold on the basis of the situation in which dense and sparse grid is generated during the procedure of grid dynamical partitioning. Using an optimum density threshold and corresponding grid granularity can be ascertained with a set of given density thresholds. It gives the algorithm based on the proposed method and the time complexity analysis. Experimental results show the validity of the algorithm.

Key words: spatial data clustering, grid granularity, density threshold, grid partition

中图分类号: