LESCA: An Algorithm for Subspace Data Clustering Through Approximations

摘要：

Subspace data clustering is comparatively a new off spring of the conventional data clustering. A novel subspace data clustering algorithm is presented here. It addresses the issue of high dimensional subspace. It computes subspaces on the basis of dimensional numerical analysis and extract subspace cluster approximation with help of user defined two parameters. Within the approximation, clusters are detected and finally base clusters of all approximations of the subspace are merged to obtain final subspace clustering of the data set We tested the algorithm on two real life data sets. It demonstrated good results.

关键词： algorithms subspace subspace data clustering

作者: Ariflqbal Umar Yunhong WANG Ejaz Hussain Sadique Ahmad

作者单位: School of Computer Science & Engineering, BeiHang University Beijing China School of Computer Science & engineering BeiHang University Beijing China

会议类型: 国际会议

会议名称: 2010 International Conference on Software and Computing Technology(2010年软件与计算机技术国际会议 ICSCT 2010)

会议地点: 昆明

会议语种:英文

页码: 292-296

在线出版日期: 2010-10-17（万方平台首次上网日期，不代表论文的发表时间）