Discernibility-matrix method based on the hybrid of equivalence and dominance relations. (English)
Kuznetsov, Sergei O. (ed.) et al., Rough sets, fuzzy sets, data mining and granular computing. 13th international conference, RSFDGrC 2011, Moscow, Russia, June 25‒27, 2011. Proceedings. Berlin: Springer (ISBN 978-3-642-21880-4/pbk). Lecture Notes in Computer Science 6743. Lecture Notes in Artificial Intelligence, 231-239 (2011).
Summary: The attribute set of some information systems is composed of both regular attributes and criteria. In order to obtain information reduction of this type of information systems, equivalence relation should be defined on the regular attributes and dominance relation on the criteria. Firstly, suppose condition attributes are criteria and decision attributes are regular attributes, dominance-equivalence relation is introduced,and the Discernibility-Matrix (DM) method of reduct generation is developed and compared with the attribute significance method. Secondly, when condition attributes are the hybrid of regular attributes and criteria, equivalence-dominance relation is then defined and Discernibility-Matrix approach of reduction generation is also provided.The effectiveness of this method is shown by both theoretical proof and illustrative example.
Start
Contact
Print
General Help
