Application of the least trimmed squares technique to prototype-based clustering

Authors:
Jongwoo Kim;Raghu Krishnapuram;Rajesh Davé
Affiliations:
Department of Electrical and Computer Engineering, University of Missouri, Columbia, MO 65203, USA;Department of Electrical and Computer Engineering, University of Missouri, Columbia, MO 65203, USA;Department of Mechanical and Industrial Engineering, New Jersey Institute of Technology, Newark, NJ 07102, USA
Venue:
Pattern Recognition Letters - Special issue on fuzzy set technology in pattern recognition
Year:
1996

Citing 3
Cited 6

Unsupervised Optimal Fuzzy Clustering

IEEE Transactions on Pattern Analysis and Machine Intelligence
The fuzzy median and the fuzzy MAD

ISUMA '95 Proceedings of the 3rd International Symposium on Uncertainty Modelling and Analysis
Optimization of clustering criteria by reformulation

IEEE Transactions on Fuzzy Systems

Enhanced neural gas network for prototype-based clustering

Pattern Recognition
The fuzzy mega-cluster: robustifying FCM by scaling down memberships

FSKD'05 Proceedings of the Second international conference on Fuzzy Systems and Knowledge Discovery - Volume Part I
Objective function-based clustering

Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery
Fuzzy clustering of human activity patterns

Fuzzy Sets and Systems
Multi-Objective Genetic Algorithm for Robust Clustering with Unknown Number of Clusters

International Journal of Applied Evolutionary Computation
Robust constrained fuzzy clustering

Information Sciences: an International Journal

Quantified Score

Hi-index	0.01

Visualization

Abstract

Prototype-based clustering algorithms such as the K-means and the Fuzzy C-Means algorithms are sensitive to noise and outliers. This paper shows how the Least Trimmed Squares technique can be incorporated into prototype-based clustering algorithms to make them robust.