Dynamic fuzzy c-means (dFCM) clustering for continuously varying data environments

Many real world applications require online analysis of streaming data, making an adaptive clustering technique desirable. Most adaptive variations of available clustering techniques are application-specific, and do not apply to the applications of clustering as a whole. With this in mind, a generalized algorithm is proposed which is a modification of the fuzzy c-means clustering technique, so that dynamic data environments in differing fields can be addressed and analyzed. We demonstrate the capabilities of the dynamic fuzzy c-means (dFCM) algorithm with the aid of synthetic data sets, and discuss a possible application of the dFCM algorithm in associative memories, through preliminary experiments.

[1]  David G. Stork,et al.  Pattern Classification , 1973 .

[2]  Ming Yu,et al.  A new adaptive clustering technique for large-scale sensor networks , 2005, 2005 13th IEEE International Conference on Networks Jointly held with the 2005 IEEE 7th Malaysia International Conf on Communic.

[3]  Shigeo Abe DrEng.  Pattern Classification , 2001, Springer London.

[4]  James C. Bezdek,et al.  Pattern Recognition with Fuzzy Objective Function Algorithms , 1981, Advanced Applications in Pattern Recognition.

[5]  Thrasyvoulos N. Pappas.  An adaptive clustering algorithm for image segmentation , 1992, IEEE Trans. Signal Process..

[6]  Bart Kosko,et al.  Neural networks and fuzzy systems: a dynamical systems approach to machine intelligence , 1991 .

[7]  Ebrahim Bagheri,et al.  FACT: A New Fuzzy Adaptive Clustering Technique , 2006, ISCC.

[8]  James C. Bezdek,et al.  On cluster validity for the fuzzy c-means model , 1995, IEEE Trans. Fuzzy Syst..

[9]  Bart Kosko,et al.  Fuzzy Engineering , 1996 .

[10]  Cheng Jin.  A statistical image retrieval method using color invariant , 2009, CIRA.