A comparison of classification strategies in rule-based classifiers. (25th September 2017)

• Record Type: Journal Article
• Authors: Wojciechowski, Szymon
• Is Part Of: Logic journal of the IGPL. Volume 26:Number 1(2018:Feb.)
• Page Start: 29
• Page End: 46
• Publication Date: 2017-09-25
• Subjects: Classification -- rule induction -- rule-based classifiers -- classification strategies; Logic, Symbolic and mathematical -- Periodicals; 511.3
• DOI: 10.1093/jigpal/jzx053
• Languages: English
• ISSNs: 1367-0751

Abstract

Abstract: This article discusses classification strategies in rule-based classifiers, reveals how often induced rules did not lead to unambiguous classification and emphasizes a major role that classification strategies play in classification of unknown examples. Five selected popular classification strategies proposed by Michalski $et al$, Grzymała-Busse and Zou, An, Stefanowski, Sulzmann and Fürnkranz are reviewed and compared experimentally. Additionally, a new strategy that exploits $\chi^{2}$ statistic to measure the association between the rule coverage and the indicated class is proposed. The experiment was conducted on 30 UCI datasets using MODLEM and modified RIPPER classifiers.