The feasible solution algorithm for fuzzy least trimmed squares clustering
Document Type
Conference Proceeding
Publication Date
1-1-2004
Abstract
The issue of sensitivity to noise and outliers of LS minimization based clustering techniques, is addressed In this paper. A novel and robust clustering scheme based on the feasible solution algorithm that implements the Least Trimmed Squares (LTS) estimator, is developed, implemented and the results presented. The LTS estimator is known to be resistant to noise and has a high breakdown point. The feasible solution algorithm approach also guarantees convergence of the solution set to a global optima. Our experiments show the practicability of the proposed scheme in terms of computational requirements and in the attractiveness of its simplistic framework.
Identifier
4544332099 (Scopus)
Publication Title
Annual Conference of the North American Fuzzy Information Processing Society NAFIPS
External Full Text Location
https://doi.org/10.1109/nafips.2004.1336281
First Page
222
Last Page
227
Volume
1
Recommended Citation
Banerjee, Amit and Davé, Rajesh N., "The feasible solution algorithm for fuzzy least trimmed squares clustering" (2004). Faculty Publications. 20543.
https://digitalcommons.njit.edu/fac_pubs/20543
