원문정보
초록
영어
Traditional association rule mining method has the high redundancy of computation.
Therefore, this paper proposes a kind of association rule algorithm of minimum single
constraint based on post-processing closure operator. Firstly, it proposes association rule
mining method of equivalence relation set based on closure operator constraint rule. It
can meet the above minimum single constraint, maximum support and confidence
coefficient threshold value effectively. In addition, it can divide constraint rule set into
disjointed equivalence rule class. Secondly, it gives answers to questions and necessary
and sufficient conditions of specific rule class existence. It can reduces redundant
computation effectively and improve computation efficiency. At last, it verifies the validity
of proposed algorithm through experimental contrast of standard test set.
목차
1. Introduction
2. Question Description
3. Association Rules of Minimum Single Constraint
3.1. Rough Classification
3.2. Constraint Rule Non-Empty Sufficient and Necessary Condition
3.3. Minimum Single Constraint Smooth Partition
4. Equivalence Class Association Rules
4.1. Expansion Class Structure
5. Experiment and Analysis
6. Conclusion
References