Abstract:

The evaluation of the relationships between conceptual clusters is important to identify vital unknown information in many reallife applications, such as crime detection, evolution trees, metallurgical industry, biology engraftment and so forth. A method called "mode pattern plus mutual information" is proposed to rank the interrelationship between clusters. Mode pattern is used to find the outstanding objects from each cluster, while mutual information criterion measures the close proximity of cluster pairs. The proposed method is different from conventional algorithms of classifying and clustering due to focusing on ranking the interrelationship between clusters.Experiments are carried out on a wide range of reallife datasets, including image data and cancer diagnosis data.The experimental results demonstrate the effectiveness of the  proposed algorithm.

Key words: relationship tree;conceptual clusters;mode pattern;mutual information