Font Size: a A A

The Research On How To Merge Newly Discovered Knowledge With Original Fuzzy Knowledge Base

Posted on:2009-11-08Degree:MasterType:Thesis
Country:ChinaCandidate:D FengFull Text:PDF
GTID:2178360242489064Subject:Computer application technology
Abstract/Summary:PDF Full Text Request
Fuzzy expert system is an important practice field front of artificial intelligence discipline. Various data mining skills will get different forms of knowledge, so it is a key research content of fuzzy expert system to merge newly discovered knowledge with original fuzzy knowledge base effectively.This article has researched on the major theory and technology of the integration of data mining results and fuzzy knowledge bases, and the research results has been applied in aluminum electrolyte. The main researches and contributions are threefold:Propose a general model which could automatically merge newly discovered knowledge with original fuzzy knowledge base. The model automatically checks and merges the newly discovered patterns of KDD process with the original fuzzy knowledge base, thus improves the quality of the knowledge base. The model alleviates people from laborious manual work and enables repetitive automatic procedure of knowledge discovery and knowledge base updating;This article propose a refined method of knowledge checking, which checks the interval ranges of fuzzy sets. Based on the definitions of relations between fuzzy sets expressions and relations between rules, this thesis details the strategies of inconsistency checking and knowledge refinement. This method checks knowledge with a more fine granularity and higher precision, and could find out the same rules, redundant rules, contradict rules and other conflict rules;This paper proposes a mechanisms to automatically merge newly discovered knowledge with original fuzzy knowledge base. This procedure is realized based on user-defined strategies to deal with knowledge inconsistency and unsoundness, along with the rule's support, confidence and the degree of satisfying constraints. This method is different from traditional method which needs engineers and experts in the field of knowledge; At last, realize a system which applied in aluminum electrolyte fuzzy expert system-Feside,and could automatically analyzes the newly discovered knowledge and merge them with original fuzzy knowledge base.
Keywords/Search Tags:data mining, fuzzy expert system, knowledge intergration
PDF Full Text Request
Related items