Generalized noise clustering as a robust fuzzy c-M-estimators model

Document Type

Conference Proceeding

Publication Date

1-1-1998

Abstract

R.N. Dave's (1991) noise clustering (NC) algorithm has been generalized in an earlier work where the noise distance δ is allowed to take different values for different feature vectors. Based on that, it was shown that the membership generated by the NC algorithm is a product of two terms, one is the original fuzzy c-means (FCM) membership responsible for data partitioning and the other is a generalized possibilistic membership that achieves a mode seeking effect, and imparts robustness. It is shown that a variety of robust M-estimators can be incorporated into the generalized NC algorithm, for example Huber, Hampel, Cauchy, Tukey biweight, and Andrew's sine. The generalized NC algorithm is also compared with the recently introduced mixed c-means and a noise resistant FCM technique.

Identifier

0344006411 (Scopus)

ISBN

[0780344537]

Publication Title

Annual Conference of the North American Fuzzy Information Processing Society NAFIPS

External Full Text Location

https://doi.org/10.1109/NAFIPS.1998.715576

First Page

256

Last Page

260

This document is currently not available here.

Share

COinS