期刊名称：International Journal of Advanced Research in Computer Engineering & Technology (IJARCET)
印刷版ISSN：2278-1323
出版年度：2014
卷号：3
期号：2
页码：372-378
出版社：Shri Pannalal Research Institute of Technolgy
摘要：Traditional clustering algorithms like K-means, CLARANS, BIRCH, DBSCAN etc. are not able to handle higher dimensional data because of the many issues occurred in high dimensional data e.g. "curse of dimensionality", "irrelevant dimensions", "distance problem" etc. To cluster higher dimensional data, density and grid based, both traditional clustering algorithms combined and let to a step ahead to the traditional clustering i.e. called subspace clustering. This paper presents an important subspace clustering algorithm called CLIQUE, which deals with all the problems ensued in clustering high dimensional data. CLIQUE find clusters of arbitrary shape in large dimensional data by taking grid size and a density threshold value as a user input. It starts process of finding clusters at a single dimension and then proceeds upward to the higher dimensions. In this paper, CLIQUE is compared with the other traditional clustering algorithms to measure its performance in terms of accuracy and time taken, in high dimensional space.
关键词：CLIQUE; Apriori approach; Subspace ; Clustering; Alternative Subspace Clustering
