Systems Engineering and Electronics

• SOFTWARE ALGORITHM AND SIMULATION • Previous Articles     Next Articles

Partition region-based suppressed fuzzy C-means algorithm

Kun Zhang1,*, Weiren Kong1, Peipei Liu1, Jiao Shi1, Yu Lei1, Jie Zou2, and Min Liu2   

  1. 1. School of Electronics and Information, Northwestern Polytechnical University, Xi’an 710072, China;
    2. Science and Technology on Electro-Optic Control Laboratory, Luoyang 471009, China
  • Online:2017-10-25 Published:2010-01-03

Abstract:

Aimed at the problem that the traditional suppressed fuzzy C-means clustering algorithms ignore the real needs of different objects, applying the same suppressed parameter for modifying membership degrees of all the objects, a novel partition region-based suppressed fuzzy C-means clustering algorithm with better capacity of adaptability and robustness is proposed in this paper. The model based on the real needs of different objects is built, making it clear to decide whether to proceed with further determination; in addition, the external user-defined suppressed parameter is automatically selected according to the intrinsic structural characteristic of each dataset, making the proposed method become robust to the fluctuations in the incoming dataset and initial conditions. Experimental results show that the proposed method is more robust than its counterparts and overcomes the weakness of the original suppressed clustering algorithm in most cases.