Title :
A Novel Fuzzy Positive and Negative Association Rules Algorithm
Author_Institution :
China Ship Dev. & Design Center, Wuhan, China
Abstract :
According to the existing mining algorithm of fuzzy association rules, a novel fuzzy positive and negative association rules algorithm will be proposed in this paper. We focus on the membership function of fuzzy set and minimum support parameters of positive and negative association rules and adopt a method that selects parameters automatically which is based on the k-means clustering. Besides, multi-level fuzzy support and correlation coefficient are chosen to restrain the quantity and quality of rules generated by the algorithm. Finally the validity and accuracy of the algorithm are proved by an experiment.
Keywords :
data mining; fuzzy set theory; pattern clustering; correlation coefficient; fuzzy negative association rules algorithm; fuzzy positive association rules algorithm; fuzzy set membership function; k-means clustering; mining algorithm; multilevel fuzzy support; Algorithm design and analysis; Association rules; Clustering algorithms; Correlation; Fuzzy sets; Itemsets;
Conference_Titel :
Distributed Computing and Applications to Business Engineering and Science (DCABES), 2010 Ninth International Symposium on
Conference_Location :
Hong Kong
Print_ISBN :
978-1-4244-7539-1
DOI :
10.1109/DCABES.2010.163
