Approximate distributed clustering by learning the confidence radius on Fisher discriminant ratio

Abstract

Presented is a new clustering algorithm with approximate distributed clustering over a peer-to-peer (P2P) network. The Fisher discriminant ratio is used to dynamically learn the confidence radius based on the data distribution in every local peer. Experimental results show that the proposed approach can achieve better clustering accuracies than the DFEKM algorithm while preserving much lower bandwidth consumptions. © 2012 The Institution of Engineering and Technology.