Systems Engineering and Electronics ›› 2018, Vol. 40 ›› Issue (3): 704-709.doi: 10.3969/j.issn.1001-506X.2018.03.33

Previous Articles     Next Articles

Evolving reweighted sparse subspace clustering algorithm

ZHAO Xiaoxiao, ZHOU Zhiping, JIA Xuan   

  1. Engineering Research Center of Internet of Things Technology Applications Ministry of Education, Jiangnan University, Wuxi 214122, China
  • Online:2018-02-26 Published:2018-02-26

PDF (PC)

Abstract:

As a state-of-the-art subspace clustering algorithm, sparse subspace clustering (SSC) not only can effectively handle high-dimensional data, but also can deal with data nuisances directly, such as noise, sparse outlying entries. However, none of the modified SSC could satisfy the property of sparseness between clusters and consistency within the cluster perfectly. To solve this problem, an evolving iterative weighting (reweighted) l 1 minimization framework is proposed, which contains the characteristic of arctan and logarithmic function at the same time. The evolving reweighted l 1 minimization framework could simultaneously satisfy the two main features of the l 0 minimization framework, which makes a better approximation than the original reweighted l 1 minimization. Based on the evolving reweighted l 1 minimization framework, a new subspace clustering algorithm is proposed, namely, evolving reweighted SSC. The experiments show that the proposed algorithm could achieve better performance than other subspace clustering algorithms.

[an error occurred while processing this directive]