Enhanced soft subspace clustering integrating within-cluster and between-cluster information

While within-cluster information is commonly utilized in most soft subspace clustering approaches in order to develop the algorithms, other important information such as between-cluster information is seldom considered for soft subspace clustering. In this study, a novel clustering technique called enhanced soft subspace clustering (ESSC) is proposed by employing both within-cluster and between-class information. First, a new optimization objective function is developed by integrating the within-class compactness and the between-cluster separation in the subspace. Based on this objective function, the corresponding update rules for clustering are then derived, followed by the development of the novel ESSC algorithm. The properties of this algorithm are investigated and the performance is evaluated experimentally using real and synthetic datasets, including synthetic high dimensional datasets, UCI benchmarking datasets, high dimensional cancer gene expression datasets and texture image datasets. The experimental studies demonstrate that the accuracy of the proposed ESSC algorithm outperforms most existing state-of-the-art soft subspace clustering algorithms.