AN IMPROVED CLUSTERING ALGORITHM

摘要：

For the time being, traditional clustering algorithms have some common problems, such as the sensitivity to initializing parameters, difficulty of finding out the optimal clustering result and the validity of clustering. In this paper, Grid-Based Clustering Method and K-means Clustering Method are combined skillfully together, and on the another side,propose an improved method in the idiographic detail of clustering process. Devise a new clustering method-GBKM clustering method. The validity of this method has been proved though the theoretical analysis and the contrast of experiment results.

关键词： Clustering algorithm Grid-Based Clustering K-means clustering

作者: XU LIANG DAN JIANG MING HUANG

作者单位: Software Technology Institute, Dalian Jiao Tong University, Dalian 116028

会议类型: 国际会议

会议名称: The Second International Conference on Information & Systems Sciences(ICISS2008)(第二届信息与系统科学国际会议)

会议地点: 大连

会议语种:英文

页码: 469-473

在线出版日期: 2008-12-18（万方平台首次上网日期，不代表论文的发表时间）