BulDML at Institute of Mathematics and Informatics >
IMI Periodicals >
Serdica Journal of Computing >
2013 >
Volume 7 Number 2 >

Please use this identifier to cite or link to this item:

Title: Classifier PGN: Classification with High Confidence Rules
Authors: Mitov, Iliya
Depaire, Benoit
Ivanova, Krassimira
Vanhoof, Koen
Keywords: Association Rules
High Confidence Rules
Issue Date: 2013
Publisher: Institute of Mathematics and Informatics Bulgarian Academy of Sciences
Citation: Serdica Journal of Computing, Vol. 7, No 2, (2013), 143p-164p
Abstract: Associative classifiers use a set of class association rules, generated from a given training set, to classify new instances. Typically, these techniques set a minimal support to make a first selection of appropriate rules and discriminate subsequently between high and low quality rules by means of a quality measure such as confidence. As a result, the final set of class association rules have a support equal or greater than a predefined threshold, but many of them have confidence levels below 100%. PGN is a novel associative classifier which turns the traditional approach around and uses a confidence level of 100% as a first selection criterion, prior to maximizing the support. This article introduces PGN and evaluates the strength and limitations of PGN empirically. The results are promising and show that PGN is competitive with other well-known classifiers.
Description: ACM Computing Classification System (1998): H.2.8, H.3.3.
ISSN: 1312-6555
Appears in Collections:Volume 7 Number 2

Files in This Item:

File Description SizeFormat
sjc-vol7-num2-2013-p143-p164.pdf410.97 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.


Valid XHTML 1.0!   Creative Commons License