clustering, data mining, object-oriented modeling, persistent objects, BETA

This paper concerns the problem of the interactive hierarchical clustering in cluster analysis. Proper design and object-oriented approach bring new possibilities of various combination of the strategies in numerical clustering. One of these possibilities enables interactive clustering, which means adding new clusters to the current ones and continue with hierarchical clustering from the reached level of the hierarchical clustering. Actual state of clustering is stored and retrieved by using persistent store and persistent objects. Moreover object-oriented perspective enables modeling different hierarchical clustering methods with the benefit of exploiting virtual procedure mechanism. Described approach was tested on medical data. The whole application is developed using the Mjolner BETA System and the BETA language for its rich facilities of the conceptual modeling.

This paper concerns the problem of the interactive hierarchical clustering in cluster analysis. Proper design and object-oriented approach bring new possibilities of various combination of the strategies in numerical clustering. One of these possibilities enables interactive clustering, which means adding new clusters to the current ones and continue with hierarchical clustering from the reached level of the hierarchical clustering. Actual state of clustering is stored and retrieved by using persistent store and persistent objects. Moreover object-oriented perspective enables modeling different hierarchical clustering methods with the benefit of exploiting virtual procedure mechanism. Described approach was tested on medical data. The whole application is developed using the Mjolner BETA System and the BETA language for its rich facilities of the conceptual modeling.