Computer Engineering and Applications ›› 2007, Vol. 43 ›› Issue (23): 177-180.

• 数据库与信息处理 • Previous Articles     Next Articles

Novel semi-supervised clustering:collaborating primary space with auxiliary space

LUO Xiao-qing,WANG Shi-tong,XU Hong-lin   

  1. School of Information Technology,Southern Yangtze University,Wuxi,Jiangsu 214122,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2007-08-11 Published:2007-08-11
  • Contact: LUO Xiao-qing

基于辅助空间与主空间合作的半监督聚类方法

罗晓清,王士同,徐红林   

  1. 江南大学 信息工程学院,江苏 无锡 214122
  • 通讯作者: 罗晓清

Abstract: In general,unsupervised clustering is only based on primary space.If auxiliary space is considered to incorporate with primary space,unsupervised clustering will become semi-supervised clustering.In this paper,auxiliary space combined with primary space is introduced to the design of the corresponding cost function.And accordingly a novel semi-supervised clustering algorithm APMSC based on both auxiliary space and primary space is proposed.This algorithm realizes the efficient clustering by minimizing the corresponding cost function iteratively.Our experimental results demonstrate its validity and superiority.

Key words: auxiliary space, primary space, cost function, semi-supervised clustering

摘要: 无监督聚类仅仅基于主空间,当辅助空间被引入聚类过程时,无监督聚类成为半监督聚类。代价函数的设计既考虑到主空间又考虑到辅助空间,从而一个新颖的基于辅助空间与主空间合作的半监督聚类方法APMSC被提出。该算法通过迭代优化,使得相应的代价函数最小化,最终得到有效的聚类结果。通过实验证实了APMSC的有效性和优越性。

关键词: 辅助空间, 主空间, 代价函数, 半监督聚类