Construction of the Ensemble of Logical Models in Cluster Analysis

摘要

In this paper, the algorithm of cluster analysis based on the ensemble of tree-like logical models (decision trees) is proposed. During the construction of the ensemble, the algorithm takes into account distances between logical statements describing clusters. Besides, we consider some properties of the Bayes model of classification. These properties are used at the motivation of information-probabilistic criterion of clustering quality. The results of experimental studies demonstrate the effectiveness of the suggested algorithm.