Research On Data Mining Technique Based On Granular Computing

Data mining represents extracting a sequence of unknown,valid and operable knowledge from a great deal of datum.It is playing an important step in knowledge discovering procedure.On one hand the availability of data mining results lies in its correctness and reasoning;on the other hand the operability lies in its usage in decision supporting.Based on data mining,methods have emerged,such as Decision Tree Classification,Statistical Classification,Bayesian Classification and Neural Networks recent years.The diversity observed from studies on the interpretations of rules and algorithms for mining rules,on the one hand shows the richness of the field, and on the other hand suggests the need for a unified framework in which different algorithms and methodologies can be examined and analyzed.Granular computing (GrC) is a label of theories,methodologies,techniques,and tools that make use of granules in the process of problem solving.The basic ideas and principles of granular computing have been studied explicitly and implicitly in many fields in isolation such as evidence theory,clusteririg analysis,database system,machine learning,data mining and so on,but the principal focus in the Special Issue is data mining.Though data mining is viewed as a form of summarization of very large datasets,granular computing may be viewed as a scheme of summarizing small datasets in a hierarchy.This thesis introduces data mining technique and the soft computing—Granular Computing in details and then proposes the method on Data Mining using Granular Computing.The Quotient space theory model is established the hierarchical chain structure by natural projection,which is fused to the grain of granular computing's main feature.This paper utilizes the granular computing of the quotient space theory method on the Yuemachang tunnel's data warehouse mining to chooses the suitable granularity solution according to the tunnel data warehouse's requirement.Then this paper makes the Granular Computing further extended application of the data mining, and used prediction method based on Granular Computing to predict and analyze pile bearing capacity of large bridges.