K-maximin clustering: a maximin correlation approach to partition-based clustering

IEICE Electronics Express

Sungroh Yoon³  Seung Jean Kim¹  Eui-Young Chung²  Taehoon Lee³ 

[1] Electrical Eng., Stanford University;Electrical and Electronic Eng., Yonsei University;Electrical Eng., Korea University

关键词: data mining;    clustering;    maximin correlation;    k-means;   

DOI  :  10.1587/elex.6.1205

学科分类：电子、光学、磁材料

来源: Denshi Jouhou Tsuushin Gakkai

【 摘 要 】

References(4)Cited-By(1)We propose a new clustering algorithm based upon the maximin correlation analysis (MCA), a learning technique that can minimize the maximum misclassification risk. The proposed algorithm resembles conventional partition clustering algorithms such as k-means in that data objects are partitioned into k disjoint partitions. On the other hand, the proposed approach is unique in that an MCA-based approach is used to decide the location of the representative point for each partition. We test the proposed technique with typography data and show our approach outperforms the popular k-means and k-medoids clustering in terms of retrieving the inherent cluster membership.

【 授权许可】

Unknown