科研之友
微信
新浪微博
Facebook
分享链接
摘要
We propose a novel framework for association discovery from relational data. The framework is a specialized version of the general framework intended for mining relational data and is defined in granular computing theory. In the framework proposed in this paper we define a method for deriving information granules from relational data. Such granules are the basis for association discovery. Our framework, unlike others, unifies not only the way the data and patterns to be derived are expressed and specified, but also partially the process of discovering patterns from the data. Namely, the patterns can be directly obtained from the information granules or constructed based on them. Moreover, the information granule-based relational data representation, defined in the framework, can be treated as the search space for association discovery. Thanks to this the size of the search space may significantly be limited. Furthermore, we apply in our approach the granular computing idea of switching between different levels of granularity of the universe. Thanks to this relational data representation can easily be replaced by another one and thereby adjusted to a given data mining task, e.g., association discovery. The results of preliminary experiments show that granular representation of relational data can be powerful enough to generate essential patterns.
- 出版日期2013-6-10
