Research on algorithm of attribute reduction based on concept with introducer

Abstract

As the size of data table grows, the concepts generated become larger in number. Making sure the set of extent remaining unchanged, the purpose of attribute reduction of concept lattice is to find out minimum subsets of attributes and make knowledge presented by concept lattice simpler, decision problem simplified as well. This paper introduced the definition of introducer which was minimum closure set of certain attribute; reduced attributes from the perspective of concept with introducer for the first time: if a concept with introducer with regard to certain attribute was degenerate then this attribute was core; otherwise this attribute was unnecessary or relative necessary; proved that if a concept with introducer of certain attribute was non-degenerate(degenerate), then the concepts on the path containing this attribute were non-degenerate(degenerate) simultaneously. Afterwards, this paper put forward an algorithm of attribute reduction and discussed the time complexity. Experimental results showed that algorithm proposed in this paper achieved excellent runtime.