Ontology Enhanced Mining of Multidimensional Association Rules from Data Cubes

Abstract

Many approaches have provided applicable solutions to explain associations within data cubes. Nevertheless, there are still many issues causing users extra time to get real knowledge or even failing to obtain the useful knowledge they need. In this paper, we introduce an ontology based approach for multidimensional association rule mining that incorporates a domain ontology to help users in reducing the system resource consumption and improving the efficiency of the mining process. The structure of this ontology is illustrated and how it would be of benefit to the mining process is also demonstrated. Our experimental results prove that a significant improvement and efficiency is achieved using our suggested approach in comparison with those fitting in the same trend.