Key points are not available for this paper at this time.
A class of fuzzy ISODATA clustering algorithms has been developed previously which includes fuzzy means. This class of algorithms is generalized to include fuzzy covariances. The resulting algorithm closely resembles maximum likelihood estimation of mixture densities. It is argued that use of fuzzy covariances is a natural approach to fuzzy clustering. Experimental results are presented which indicate that more accurate clustering may be obtained by using fuzzy covariances.
Gustafson et al. (Sun,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: