NIS-Apriori-based rule generation with three-way decisions and its application system in SQL

• Main Authors: Sakai, H., Nakata, M., Watada, J.
• Format: Article
• Published: Elsevier Inc. 2020
• Online Access: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85053220091&doi=10.1016%2fj.ins.2018.09.008&partnerID=40&md5=0004babaf102eeabfaf7ae50cbb8ad58; http://eprints.utp.edu.my/23343/
• Institution: Universiti Teknologi Petronas

In the study, non-deterministic information systems-Apriori-based (NIS-Apriori-based) rule generation from table data sets with incomplete information, SQL implementation, and the unique characteristics of the new framework are presented. Additionally, a few unsolved new research topics are proposed based on the framework. We follow the framework of NISs and propose certain rules and possible rules based on possible world semantics. Although each rule � depends on a large number of possible tables, we prove that each rule � is determined by examining only two �-dependent possible tables. The NIS-Apriori algorithm is an adjusted Apriori algorithm that can handle such tables. Furthermore, it is logically sound and complete with regard to the rules. Subsequently, the implementation of the NIS-Apriori algorithm in SQL is described and a few new topics induced by effects of NIS-Apriori-based rule generation are confirmed. One of the topics that are considered is the possibility of estimating missing values via the obtained certain rules. The proposed methodology and the environment yielded by NIS-Apriori-based rule generation in SQL are useful for table data analysis with three-way decisions. © 2018 Elsevier Inc.