Application of global optimization in data clustering analisys

Abstract

On the basis of global optimization methods in the system of computer mathematics «Matlab» algorithms of clear and fuzzy data clustering had developed to determine the parameters of prototypes of clusters. A method of finding the clusters boundaries was proposed. On simulated data it had been show that the cluster centers derived by algorithms based on «patternsearch» and «K-means» are the same. Applied to the processing of geological data, the developed algorithms simplify the analysis of rocks, for example, allow on the image of the rocks assess their mineral composition.

Keywords

• algorithms of global optimization
• clear and fuzzy clustering data
• centers
• boundaries
• shape of clusters
• areas of clustering data.