Title :
A Vibrating Method Based Cluster Reducing Strategy
Author :
Hsu, Daniel ; Johnson, Shardrom
Author_Institution :
Sch. of Comput. Eng. & Sci., Shanghai Univ., Shanghai
Abstract :
Clustering is the hot spot in the study of data mining. This paper proposed a cluster reducing strategy based on so called "vibrating method". The "vibrating method" synthesizes the merits of the "distance based method" and the "density based method" of traditional clustering algorithm. It first finds out the "core" of each cluster and then "vibrating" cores to lower the difference between the clusters and tight the relationship among the clusters. Therefore, it can be used as a cluster reducing strategy to reduce or compose the clusters after clustering.
Keywords :
data mining; cluster reducing strategy; data mining; density based method; distance based method; vibrating method; Clustering algorithms; Clustering methods; Data engineering; Data mining; Data warehouses; Fuzzy systems; Knowledge engineering; Noise shaping; Organizing; Shape; core based; reducing strategy; vibrating;
Conference_Titel :
Fuzzy Systems and Knowledge Discovery, 2008. FSKD '08. Fifth International Conference on
Conference_Location :
Shandong
Print_ISBN :
978-0-7695-3305-6
DOI :
10.1109/FSKD.2008.425