Information fusion from multiple databases using meta-association rules

详细信息    查看全文

• 作者：M.D. Ruiz^a ; ^b ; ^{mdruiz@decsai.ugr.es} ; J. Gó ; mez-Romero^a ; ^b ; ^{jgomez@decsai.ugr.es} ; M. Molina-Solana^a ; ^b ; ^{miguems@decsai.ugr.es} ; M. Ros^a ; ^b ; ^{marosiz@decsai.ugr.es} ; M.J. Martin-Bautista^a ; ^b ; ^{mbautis@decsai.ugr.es}
• 关键词：Association rules ; Meta-association rules ; Fuzzy association rules ; Information fusion ; High order mining ; Multiple databases
• 刊名：International Journal of Approximate Reasoning
• 出版年：2017
• 出版时间：January 2017
• 年：2017
• 卷：80
• 期：Complete
• 页码：185-198
• 全文大小：771 K
• 卷排序：80

文摘

We propose a method to fuse information from multiple databases in the form of meta-association rules. Meta-rules express which associations are more frequent in a set of databases. Fuzzy and non-fuzzy approaches are described and compared. The proposed algorithm allows the incorporation of contextual information. The fuzzy approach produces a more manageable set of rules for human inspection. Meta-rules convey new relevant information that cannot be obtained by regular association rules.