Classification rule induction based on relevant, irredundant attributes and rule expansion

George Lashkia; Laurence Anthony; Hiroyasu Koshimizu

Classification rule induction based on relevant, irredundant attributes and rule expansion

George Lashkia^*, Laurence Anthony, Hiroyasu Koshimizu

^*Corresponding author for this work

School of Creative Science and Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

In this paper we focus on the induction of classification rules from examples. Conventional algorithms fail in discovering effective knowledge when the database contains irrelevant information. We present a new rule extraction method, RGT, which tackles this problem by employing only relevant and irredundant attributes. Simplicity of rules is also our major concern. In order to create only simple rules, we estimate the purity of patterns and propose a rule merging and expending procedures. In this paper, we describe the methodology for the RGT algorithm, discuss its properties, and compare it with conventional methods.

Original language	English
Title of host publication	WMSCI 2005 - The 9th World Multi-Conference on Systemics, Cybernetics and Informatics, Proceedings
Pages	191-196
Number of pages	6
Publication status	Published - 2005
Event	9th World Multi-Conference on Systemics, Cybernetics and Informatics, WMSCI 2005 - Orlando, FL, United States Duration: 2005 Jul 10 → 2005 Jul 13

Publication series

Name	WMSCI 2005 - The 9th World Multi-Conference on Systemics, Cybernetics and Informatics, Proceedings
Volume	8

Conference

Conference	9th World Multi-Conference on Systemics, Cybernetics and Informatics, WMSCI 2005
Country/Territory	United States
City	Orlando, FL
Period	05/7/10 → 05/7/13

Keywords

Classification rules
Inductive learning
Prime test

ASJC Scopus subject areas

Artificial Intelligence
Computer Networks and Communications
Information Systems

Cite this

Classification rule induction based on relevant, irredundant attributes and rule expansion. / Lashkia, George; Anthony, Laurence; Koshimizu, Hiroyasu.
WMSCI 2005 - The 9th World Multi-Conference on Systemics, Cybernetics and Informatics, Proceedings. 2005. p. 191-196 (WMSCI 2005 - The 9th World Multi-Conference on Systemics, Cybernetics and Informatics, Proceedings; Vol. 8).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Lashkia, G, Anthony, L & Koshimizu, H 2005, Classification rule induction based on relevant, irredundant attributes and rule expansion. in WMSCI 2005 - The 9th World Multi-Conference on Systemics, Cybernetics and Informatics, Proceedings. WMSCI 2005 - The 9th World Multi-Conference on Systemics, Cybernetics and Informatics, Proceedings, vol. 8, pp. 191-196, 9th World Multi-Conference on Systemics, Cybernetics and Informatics, WMSCI 2005, Orlando, FL, United States, 05/7/10.

Lashkia, George ; Anthony, Laurence ; Koshimizu, Hiroyasu. / Classification rule induction based on relevant, irredundant attributes and rule expansion. WMSCI 2005 - The 9th World Multi-Conference on Systemics, Cybernetics and Informatics, Proceedings. 2005. pp. 191-196 (WMSCI 2005 - The 9th World Multi-Conference on Systemics, Cybernetics and Informatics, Proceedings).

@inproceedings{8e47ea472aa5469e8a57609c68b0a9d5,

title = "Classification rule induction based on relevant, irredundant attributes and rule expansion",

abstract = "In this paper we focus on the induction of classification rules from examples. Conventional algorithms fail in discovering effective knowledge when the database contains irrelevant information. We present a new rule extraction method, RGT, which tackles this problem by employing only relevant and irredundant attributes. Simplicity of rules is also our major concern. In order to create only simple rules, we estimate the purity of patterns and propose a rule merging and expending procedures. In this paper, we describe the methodology for the RGT algorithm, discuss its properties, and compare it with conventional methods.",

keywords = "Classification rules, Inductive learning, Prime test",

author = "George Lashkia and Laurence Anthony and Hiroyasu Koshimizu",

year = "2005",

language = "English",

isbn = "9806560604",

series = "WMSCI 2005 - The 9th World Multi-Conference on Systemics, Cybernetics and Informatics, Proceedings",

pages = "191--196",

booktitle = "WMSCI 2005 - The 9th World Multi-Conference on Systemics, Cybernetics and Informatics, Proceedings",

note = "9th World Multi-Conference on Systemics, Cybernetics and Informatics, WMSCI 2005 ; Conference date: 10-07-2005 Through 13-07-2005",

}

TY - GEN

T1 - Classification rule induction based on relevant, irredundant attributes and rule expansion

AU - Lashkia, George

AU - Anthony, Laurence

AU - Koshimizu, Hiroyasu

PY - 2005

Y1 - 2005

N2 - In this paper we focus on the induction of classification rules from examples. Conventional algorithms fail in discovering effective knowledge when the database contains irrelevant information. We present a new rule extraction method, RGT, which tackles this problem by employing only relevant and irredundant attributes. Simplicity of rules is also our major concern. In order to create only simple rules, we estimate the purity of patterns and propose a rule merging and expending procedures. In this paper, we describe the methodology for the RGT algorithm, discuss its properties, and compare it with conventional methods.

AB - In this paper we focus on the induction of classification rules from examples. Conventional algorithms fail in discovering effective knowledge when the database contains irrelevant information. We present a new rule extraction method, RGT, which tackles this problem by employing only relevant and irredundant attributes. Simplicity of rules is also our major concern. In order to create only simple rules, we estimate the purity of patterns and propose a rule merging and expending procedures. In this paper, we describe the methodology for the RGT algorithm, discuss its properties, and compare it with conventional methods.

KW - Classification rules

KW - Inductive learning

KW - Prime test

UR - http://www.scopus.com/inward/record.url?scp=84867364261&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84867364261&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84867364261

SN - 9806560604

SN - 9789806560604

T3 - WMSCI 2005 - The 9th World Multi-Conference on Systemics, Cybernetics and Informatics, Proceedings

SP - 191

EP - 196

BT - WMSCI 2005 - The 9th World Multi-Conference on Systemics, Cybernetics and Informatics, Proceedings

T2 - 9th World Multi-Conference on Systemics, Cybernetics and Informatics, WMSCI 2005

Y2 - 10 July 2005 through 13 July 2005

ER -

Classification rule induction based on relevant, irredundant attributes and rule expansion

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this