Study about Rule Mining for Multiple Tables with Fuzzy Data

Abstract

The research takes the track of mining association rules in databases with many tables and fuzzy data along with its taxonomy. Many data mining algorithms have been developed to deal with databases that are made up of a single table with fuzzy taxonomic structures constructed on top of it. This study uses fuzzy data from several tables, which were created using ER models, and each entity table maintains information on all attributes connected with a certain object, while the relationship table represents relationships between distinct entities. The study's major goal is to handle many tables at multiple levels. The study's objective is to create a new algorithm by combining the previously published algorithms Extended Apriori and Apriori star. The research will aid in the identification of relevant outcomes from database tables containing ambiguous data.