Incomplete System Extension Model Of Rough Set And Data Mining Algorithm Research

Modern society is a society of highly expanded information, data in various fields have increased dramatically with the development of the times, causing explosive growth of information. In addition, uncertainties in data and information systems has increased significantly due to human involvement. How to get potentially valuable information from a large number of complex, strong interference, incompleteness database, has become an important topic of scientific research.Rough set theory is a new mathematical tool proposed by a Polish professor named Z.Pawlak in the early 1980 s to deal with uncertainty and incomplete information. The information not included in the data set is not required in the theory. The essential characteristics and inherent laws of the issues is justfrom the given problem. Has been successfully applied to machine learning, control algorithms available, intelligent data analysis, data mining and other fields, Become an important method for intelligent information processing knowledge acquired in uncertain environments available.Firstly, in this paper an expand rough set model based on tolerance relation of conditions priori probability is put forward, which is improved from the existing one. The related properties and theorem were analyzed and explained with some examples; Secondly, several dominating knowledge reduction algorithms in the extended mode were analyzed; Finally introducing the rules acquisition in incomplete decision systems, with emphasis on application of conditions prior probability tolerance relation and extraction algorithm based on the consistency of the rules binding, and gives a detailed description of the algorithm.