Title :
The Canonical Basis of Implicational System
Author :
Shi, Hui-feng ; Hua, Qiang ; Zhang, Bo
Author_Institution :
Coll. of Appl. Math., & Phys., North China Electr. Power Univ., Baoding
Abstract :
In this paper, using the closure of the Galois connection, two algorithm are proposed for computing all closed itemsets and their generators of a formal context. The canonical implications basis is a minimal no-redundant implication set from which all implications can be inferred by the Armstrong rules. The canonical basis relies on the particular sort itemsets called pseudo-closed itemsets of formal context are presented
Keywords :
Boolean algebra; Galois fields; data mining; inference mechanisms; set theory; sorting; Armstrong rule inference; Galois connection closure; canonical implication basis; closed itemset computing algorithm; formal concept analysis; minimal nonredundant implication set; pseudo-closed itemset sorting; Association rules; Computer science; Cybernetics; Data mining; Databases; Educational institutions; Itemsets; Knowledge acquisition; Lattices; Machine learning; Mathematics; Power generation; Formal context; closed itemset; closure operator; implicational system; pseudo-closed;
Conference_Titel :
Machine Learning and Cybernetics, 2006 International Conference on
Conference_Location :
Dalian, China
Print_ISBN :
1-4244-0061-9
DOI :
10.1109/ICMLC.2006.258563
