基于特征加权距离的双指数模糊子空间聚类算法

Double-indices fuzzy subspace clustering algorithm based on feature weighted distance

传统的模糊聚类算法(FCM)使用欧氏距离计算数据点之间的差异时,对于高维数据集聚类效果不够理想.对此,以FCM算法的目标函数为基础,用特征加权距离代替传统的欧氏距离,同时向约束条件中引入指数γ和β,提出了一种基于特征加权距离的双指数模糊子空间聚类算法,并讨论了该算法的收敛性.实验表明,所提出算法可以有效提取高维数据集各类别的相关特征,在真实数据集上有较好的聚类效果.

The conventional fuzzy clustering algorithms（FCM） fall short when clustering is performed in high dimensional spaces, because they use the Euclidean metric to compute the distance between data points. In this paper, a fuzzy subspace clustering algorithm is proposed by introducing the feature weighted distance and the power exponent γ and β into the objective function of FCM. The global convergence property of the proposed algorithm is discussed. The experimental results on real dataset show the effectiveness of the algorithm.