Fuzzy Entropy Based Fuzzy c-Means Clustering with Deterministic and Simulated Annealing Methods

Makoto YASUDA  Takeshi FURUHASHI 

Publication
IEICE TRANSACTIONS on Information and Systems  Vol.E92-D  No.6  pp.1232-1239
Publication Date: 2009/06/01
Online ISSN: 1745-1361
Print ISSN: 0916-8532
Type of Manuscript: PAPER
Category: Computation and Computational Models
Keyword: 
fuzzy c-means clustering,  fuzzy entropy,  Fermi-Dirac distribution,  deterministic annealing,  simulated annealing, 

Full Text: PDF(1.1MB)

Summary: 
This article explains how to apply the deterministic annealing (DA) and simulated annealing (SA) methods to fuzzy entropy based fuzzy c-means clustering. By regularizing the fuzzy c-means method with fuzzy entropy, a membership function similar to the Fermi-Dirac distribution function, well known in statistical mechanics, is obtained, and, while optimizing its parameters by SA, the minimum of the Helmholtz free energy for fuzzy c-means clustering is searched by DA. Numerical experiments are performed and the obtained results indicate that this combinatorial algorithm of SA and DA can represent various cluster shapes and divide data more properly and stably than the standard single DA algorithm.