The Research And The Application Of Data Reduction Based On Rough Set Theory

In recent years, with the quick development of the database technology and theextensive application of the database management system, the data of backlog in thedatabase of business enterprise are more and more. However the data explosionconceal many important information, If we want to carry on the analysis to allinformation and carry on knowledge excavation, it is unwise and unnecessary. It isimportant for us to find out suitable methods,reduce redundant knowledge and refineimportant datas.Rough sets theory, initialized by Professor Pawlak in early 1980's hasbeen proved to be an excellent mathematical tool dealing with uncertain and vaguedescription of objects,whose basic idea is to derive classification rules of conceptionby knowledge reduction with the ability of clsssification unchanged. It may find thehiding and potential rules, which is knowledge, from the data without any preliminaryor additional information.And rough sets theory has played an important role in softcomputing.The main procedures of this paper are listed as follows:First, the paper introduced the things about the Rough set theory, the basicconcepts of Rough set theory and the expansion of the Rough set model.Second,thearticle has made the further research on data reduction, we present a dividing methodfor inconsistent decision table; As well as we bring forward a way to combine themethods of Rough set theory and statistics in the course of inconsistent decision rulesextraction and the resulting-rules are sifted by support,certainty and coverage, whichcan improve the accuracy and rationality in decision -making.And combined with thefeatures of teaching work, this paper puts forward the method of the comprehensiveevaluation of teaching quality, which reduces the evaluation indexes of teachingquality and ascertains the weight of evaluation indexes based on the theory of RoughSets. This method reduces the scale of index system and weakens the subjectivity inweight assignment. Finally,by integrating Rough set's reduction theory with neuralnetwork,the article advances rough neural network reduction model and the applicationof that model.