Location:Home > Engineering science > Information and Communication Engineering > Research of Redundant Knowledge Model Integration Based on Rough Set

Research of Redundant Knowledge Model Integration Based on Rough Set

Downloads: []
Tutor: WangJiaYang
School: Central South University
Course: Information and Communication Engineering
Keywords: rough set,redundant knowledge,rule evaluation,model net,model integration
Type: Master's thesis
Year:  2013
Facebook Google+ Email Gmail Evernote LinkedIn Twitter Addthis

not access Image Error Other errors

Rough Set Theory, introduced by Pawlak Z. in early1980¡¯s, is a new mathematical tool dealing with vagueness and uncertainty. The basic idea is to derive classification rules of conception by knowledge reduction with the ability of unchanged classification. In recent years, it has been widely used in the area of data mining, machine learning, pattern recognition, artificial intelligence, fault diagnosis, etc.The research works in the thesis is generating redundant knowledge using rough set and fusion problem of decision rule. Through research the basic principle of generating redundant knowledge using rough set, the thesis provides the formalization definition of multiple knowledge bases. The article describes many metrics of decision rules and analyzes the properties for these metrics. Then it presents the metrics for rule set which shows the properties of a rule set in general. All of them play an important role for decision of redundant knowledge.Based on basic theory of model integration, each knowledge-base can be viewed as a single decision model. The thesis proposes the concept of model net and model integration method. Each knowledge-base can be viewed as a single decision model, then decision fusion is realized by model integration. It achieves acomprehensive decision at model level. Firstly, We give the formal definition of the concept of model net. Then a construction algorithm of the model net is introduced. Algorithms of model net simplification according to the different categories of decision problems are also worked out. And proposed the model integration approach based on the algorithms. However, the model net simplification and model integration algorithms may work improperly in practical applications for the reason that a model net constructed based on the concept of generalized data type matching may contain cycles. So, the article worked out a method to eliminating the cycles existing in a model net.
Related Dissertations
Last updated
Sponsored Links
Home |About Us| Contact Us| Feedback| Privacy | copyright | Back to top