Abstract:
Clusterization is one of the most widespread problems in data analysis. There are many approaches and methods for its solution. However, the result of clusterization strongly depends on the choice of the feature space, on the object proximity measures, and on the method used to formalize the concepts of the object and cluster equivalence. As a result, different solutions can be far apart from each other; they can be degenerate or be quite different from the actually existing groupings. In this paper, clusterization obtained by groups of algorithms is considered; these methods make it possible to construct consistent solutions that best match the actually existing groupings.
Fulltext:
PDF file (2058 kB)