Incorporação de múltiplos representantes auxiliares em processos de detecção de agrupamentos semi-supervisionados

Abstract

The incorporation of semi-supervision in the cluster detection process has proved especially useful when one wants to get a high consistency between the data partitioning and the knowledge the user has about the data domain. In recent years, several strategies for semi-supervised clustering have been proposed. The approaches adopted by these strategies aim at guiding the process of cluster detection by using constraints with the following purposes: to interfere with the allocation of instances to the most appropriate cluster at each iteration of the algorithm; or to modify the objective function employed. This dissertation presents a novel approach for incorporating semi-supervision in the wellknown k-means algorithm. This semi-supervised clustering method employs constraint information in the definition of multiple assistant representatives for the centroids used at each iteration of k-means and generating new types of constraints acting on prototype level. A refinement process is designed to reduce the number of assistant representatives considered for each centroid without losing the clustering quality. The experimental results show the potential of the proposed approach for dealing with clustering composed by clusters of different shapes, sizes and densities.