Frequent patterns-based subspace clustering

Clustering in high dimensional data is an important task. Subspace clustering has emerged as a possible solution to the challenges associated with high dimensional clustering. A subspace cluster is a subset of points together with a subset of attributes, such that some category of value of cluster points has great aggregation in these attributes. This paper proposes a subspace clustering algorithm which follows the bottom-up strategy, evaluating each dimension separately and then using only those dimensions with great aggregation in further steps. Experimental results on synthetic data show that presented algorithm scales linearly with the number of the attributes and has good scalability as the size of the data objects is increased.