Analysis of ontology based approach for clustering tasks
2012
Grabusts, P., Rezekne Higher Educational Institution (Latvia). Faculty of Engineering
Clustering algorithms are used to group given objects defined by a set of numerical properties in such a way that the objects within a group are more similar than the objects in different groups. All clustering algorithms have common parameters the choice of which characterizes the effectiveness of clustering. The most important parameters characterizing clustering are: metrics, number of clusters k and cluster validity criteria. In classical clustering algorithms semantic knowledge is ignored. This creates difficulties in interpreting the results of clustering. Currently, the possibility to use ontology opportunities is developing rapidly, that provide an explicit model for structuring concepts, together with their interrelationship, that allows to gain knowledge on a specific data model. According to the previously obtained results of clustering study, the author will make a first attempt to create ontology based prototype of clustering concepts from numerical data using similarity measures, cluster numbers, cluster validity and others characteristic features.
Mostrar más [+] Menos [-]Palabras clave de AGROVOC
Información bibliográfica
Este registro bibliográfico ha sido proporcionado por Fundamental Library of Latvia University of Life Sciences and Technologies