Abstract Views :251 |
PDF Views:2
Authors
Affiliations
1 SVS Institute of Computer Applications, Coimbatore-109, Tamil Nadu, IN
2 Dr. NGP Arts & Science College, Coimbatore-48, Tamil Nadu, IN
3 Dr. GRD College of Science, Coimbatore-14, Tamil Nadu, IN
Source
Data Mining and Knowledge Engineering, Vol 3, No 12 (2011), Pagination: 731-736
Abstract
Association rule mining is considered as one of the most important tasks in Knowledge Discovery in Databases. Among sets of items in transaction databases, it aims at discovering implicative tendencies that can be valuable information for the decision-maker. In Data Mining, the usefulness of association rules is strongly limited by the huge amount of delivered rules. To overcome this drawback, several methods were proposed in the literature such as itemset concise representations, redundancy reduction, and post processing. However, being generally based on statistical information, most of these methods do not guarantee that the extracted rules are interesting for the user. Thus, it is crucial to help the decision-maker with an efficient post processing step in order to reduce the number of rules. This thesis proposes a new interactive approach to prune and filter discovered rules. First, we propose to use ontologies in order to improve the integration of user knowledge in the post processing task. Second, we propose the Rule Schema formalism extending the specification language proposed by Liu et al. for user expectations. Furthermore, an interactive framework is designed to assist the user throughout the analyzing task. Applying our new approach over voluminous sets of rules, we were able, by integrating domain expert knowledge in the post processing step, to reduce the number of rules to several dozens or less. Moreover, the quality of the filtered rules was validated by the domain expert at various points in the interactive process. Further we enhance this approach with Fuzzy Ontology based on the fuzzy concepts and fuzzy relations. The Fuzzy ontology T2FSs provide us with more design degrees of freedom and has the potential to outperform the system using especially when dealing with an environment with high interuser uncertainty levels, such as decision-maker with an efficient post processing, where we have several experts and where each expert has a different opinion.
Keywords
Clustering, Association Rules, Interactive Data Exploration.