Based On Rough Data Mining Algorithm For Attribute Reduction Research

Rough set theory is provided by Z.Pawlak in 1982. It is a math theory that process the non-accurate after probability theory, fuzzy theory and Dempster-Shafer. Not needing other information or Previous knowledge this theory can analyze and process the non-accurate, non-integrity data and then mine latent knowledge. Data mining and knowledge discovery in databases is drawing knowledge from the database, data warehouse or other databases. Rough set theory is a new data mining technology. After thorough research of rough set and its application in data mining. The paper mainly research expansion model of rough set: rough set model based on continuous attribute and algorithm of reduction; model and algorithm for reduction of knowledge under incomplete information systems; rough set model and reduction based multivalued information system. The main research include:1. An survey on rough set and relative technology of data mining.2. Thorough research all kinds of rough set model. provided the method to show diverse information system.3. The attribute reduction of Information system is the main topic in rough set theory. But, it is proved that getting the best reduction or all reduction is a NP problem. There is putting forward some valid algorithm currently, however complexity is all higher. The paper give improved general form algorithm of attribute reduction based on algebra and the information theories.4. Researching the rough set model in incomplete information system and providing the reduction algorithm based on limited tolerance relation. putting forward multivalued information system and attribute reduction based on it. give algorithm of attribute reduction based on information about continuous attribute. The Lastly, the paper give complete solid example to prove that all model and algorithm given previously is usefulness and validity in application.