| With the extensive application of massive databases and fast development of Internet, the storage in databases is increasing rapidly in the world. So it is one of the major research subjects to mine potential and valuable information from vast and various data (namely Data Mining) in knowledge discovery in these days. The rough set theory, introduced by Pawlak in 1982, is a new mathematical tool to deal with vagueness and uncertainty. Knowledge reduction is one of the important contents in the research on rough set theory. Reduction is used to decrease the dimension of structured data and the various compact degrees of data sets are obtained. It is one of important tasks in the research on Data Mining. Because of general phenomena of indefinite data or even imperfect existing, information systems that are presented to user are mostly incomplete. Simultaneously, the classical rough set theory is based on complete information systems. Therefore, it is most significant to investigate how to obtain knowledge from incomplete information systems. In this paper, Knowledge Discovery based the rough set theory under incomplete information systems is studied. The main contents are presented as following:(1) It is given an overview of the current situation of researches on Data Mining and Rough Set.(2) Based on the tolerance relation, distribution reduction, maximum distribution reduction and assignment reduction are introduced into the incomplete information systems. It is also defined a new knowledge reduction-assignment order reduction. On this condition it presents algorithms for assignment reduction, maximum distribution reduction and assignment order reduction and analyzes their time complexes.(3) Algorithms for reduction are validated by experiments. It shows that these algorithms can find corresponding reduction results.(4) A system for Knowledge Discovery is established. By knowledge reduction, we discover knowledge. Functions of the system are achieved mostly. |
PDF Full Text Request