A classification method of fuzzy association rules

Author

Lu, Jianjiang ; Xu, Baowen ; Yang, Ongji

Author_Institution

Dept. of Comput. Sci. & Eng., Southeast Univ., Nanjing

fYear

2003

fDate

8-10 Sept. 2003

Firstpage

248

Lastpage

251

Abstract

Partition method of interval is adopted in current classification based on associations (CBA), but this method cannot reflect the actual distribution of data and exists the problem of sharp boundary. Quantitative attributes are partitioned into several fuzzy sets by fuzzy c-means algorithm, and search technology of Apriori algorithm is improved to discover interesting fuzzy association rules, which are used to build classification system. Because fuzzy c-means algorithm can embody the actual distribution of the data and fuzzy sets can soften partition boundary, the classification system of the fuzzy association rules can obtain better classification accuracy than two popular classification methods: C4.5 and CBA

Keywords

data mining; deductive databases; fuzzy set theory; Apriori algorithm; CBA; classification based on associations; classification system; data mining; deductive databases; fuzzy association rules; fuzzy c-means algorithm; fuzzy sets; search technology; Association rules; Classification tree analysis; Computer science; Data mining; Fuzzy sets; Fuzzy systems; Partitioning algorithms; Programmable logic arrays; Relational databases; Software quality;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications, 2003. Proceedings of the Second IEEE International Workshop on

Conference_Location

Lviv

Print_ISBN

0-7803-8138-6

Type

conf

DOI

10.1109/IDAACS.2003.1249560

Filename

1249560