基于K-Means的软子空间聚类算法研究综述

Summaryof Soft Subspace Clustering Algorithm Based on K-Means

随着数据挖掘技术的发展,聚类分析算法越来越多,由于分析高维数据有时会陷入所谓维灾难,传统的聚类算法在聚类高维数据时性能会降低很多。针对这种情况,提出了子空间聚类算法,极大地改善了这个问题。K-Means算法是一种应用很广泛的聚类算法,与子空间聚类算法结合可以应用于高维数据聚类。介绍了三类基于K-Means的软子空间聚类算法,并对每种算法进行了描述和分析,最后指出了进一步的研究方向。

With the development of data mining,clustering algorithm is becoming more and more.The difficulties associated with analyzing high-dimensional data are sometimes referred to as the curse of dimensionality.So the performance of traditional clustering algorithm in high-dimensional data clustering will reduce a lot.For this situation,subspace clustering algorithm greatly improves the problem.K-Means algorithm is a widely used clustering algorithm.Combined with subspace clustering algorithm it can be applied to high-dimensional data clustering.This paper introduces three kinds of soft subspace clustering algorithm based on K-Means,then each algorithm is summarized and analyzed.Finally it points out the future research direction.