Abstract
In this paper, we study new efficient approaches based on DC (Difference of Convex functions) programming and DCA (DC Algorithm) for MSSC (Minimum Sum-of-Squares Clustering) using weighted dissimilarity measures. Two most widely used models of MSSC that are bilevel program and mixed integer program are studied. It turns out that both optimization problems can be reformulated as a DC program and then efficient DCA schemas are developed. Experimental results on real world datasets have illustrated the efficiency of our proposed algorithms and its superiority with respect to standard algorithms in terms of quality of solution.KeywordsClusteringMSSCFeature WeightingOptimizationDC ProgrammingDCA
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
