期刊名称：International Journal of Innovative Research in Science, Engineering and Technology
印刷版ISSN：2347-6710
电子版ISSN：2319-8753
出版年度：2015
卷号：4
期号：7
页码：5179
DOI：10.15680/IJIRSET.2015.0407020
出版社：S&S Publications
摘要：The Data Mining process enables the end users to analyze, understand and use the extracted knowledgein an intelligent system or to support in the decision-making processes Association refers to the data mining task ofuncovering relationships among the data. In Data Mining, the usefulness of association rules is strongly limited by thehuge amount of delivered rules. There are a number of ways to overcome this drawback that depends on the statisticalinformation. But none of them guarantee that the rules extracted are interesting for user. Thus we introduced a newapproach in which the user knowledge I taken into the consideration to extract the rules through user interactivesystem. We propose ontologies to in order to improve the integration of user knowledge in the postprocessing task. Theuser can even edit or validate ontologies. We propose the Rule Schema formalism extending the specification languagefor user expectations. The rules extracted are pruned and filtered. So that, voluminous set of rules were reduced toseveral dozens or less.
关键词：Association rules; knowledge discovery in databases; ontologies; pruning; filters.
