Dynamic tabu search for dimensionality reduction in rough set

Research output: Contribution to journalArticle

Abstract

This study proposed a Dynamic Tabu Search (DTSAR) that incorporates a dynamic Tabu list to solve an attribute reduction problem in Rough Set Theory. The dynamic Tabu list is used to skip the aspiration criteria and promote faster running times. A number of experiments have been conducted to evaluate the performance of the proposed technique with other published metaheuristic techniques, rough set and decision tree. DTSAR shows promising results on reduct generation time. It ranges between 0.20-22.18 min. For comparisons on the performances that are based on the number of produced reduct, DTSAR is on par with other metaheuristic techniques. DTSAR outperforms some techniques on certain datasets. Quality of classification rules generated by adopting DTSAR is comparable with those generated by Rough Set and Decision Trees Methods.

Original languageEnglish
Pages (from-to)12-19
Number of pages8
JournalInternational Journal of Soft Computing
Volume8
Issue number1
DOIs
Publication statusPublished - 2013

Fingerprint

Tabu search
Dimensionality Reduction
Tabu Search
Rough Set
Reduct
Decision trees
Metaheuristics
Decision tree
Attribute Reduction
Rough set theory
Classification Rules
Rough Set Theory
Evaluate
Range of data
Experiment

Keywords

  • Attribute reduction
  • Computational intelligence
  • Dynamic tabu list
  • Rough set
  • Tabu search

ASJC Scopus subject areas

  • Software
  • Theoretical Computer Science
  • Modelling and Simulation

Cite this

@article{69430f0019964d688120244df1af2bc3,
title = "Dynamic tabu search for dimensionality reduction in rough set",
abstract = "This study proposed a Dynamic Tabu Search (DTSAR) that incorporates a dynamic Tabu list to solve an attribute reduction problem in Rough Set Theory. The dynamic Tabu list is used to skip the aspiration criteria and promote faster running times. A number of experiments have been conducted to evaluate the performance of the proposed technique with other published metaheuristic techniques, rough set and decision tree. DTSAR shows promising results on reduct generation time. It ranges between 0.20-22.18 min. For comparisons on the performances that are based on the number of produced reduct, DTSAR is on par with other metaheuristic techniques. DTSAR outperforms some techniques on certain datasets. Quality of classification rules generated by adopting DTSAR is comparable with those generated by Rough Set and Decision Trees Methods.",
keywords = "Attribute reduction, Computational intelligence, Dynamic tabu list, Rough set, Tabu search",
author = "Zalinda Othman and {Abu Bakar}, Azuraliza and Salwani Abdullah and {Ahmad Nazri}, {Mohd Zakree} and Sengalang, {Nelly Anak}",
year = "2013",
doi = "10.3923/ijscomp.2013.12.19",
language = "English",
volume = "8",
pages = "12--19",
journal = "International Journal of Soft Computing",
issn = "1816-9503",
publisher = "Medwell Publishing",
number = "1",

}

TY - JOUR

T1 - Dynamic tabu search for dimensionality reduction in rough set

AU - Othman, Zalinda

AU - Abu Bakar, Azuraliza

AU - Abdullah, Salwani

AU - Ahmad Nazri, Mohd Zakree

AU - Sengalang, Nelly Anak

PY - 2013

Y1 - 2013

N2 - This study proposed a Dynamic Tabu Search (DTSAR) that incorporates a dynamic Tabu list to solve an attribute reduction problem in Rough Set Theory. The dynamic Tabu list is used to skip the aspiration criteria and promote faster running times. A number of experiments have been conducted to evaluate the performance of the proposed technique with other published metaheuristic techniques, rough set and decision tree. DTSAR shows promising results on reduct generation time. It ranges between 0.20-22.18 min. For comparisons on the performances that are based on the number of produced reduct, DTSAR is on par with other metaheuristic techniques. DTSAR outperforms some techniques on certain datasets. Quality of classification rules generated by adopting DTSAR is comparable with those generated by Rough Set and Decision Trees Methods.

AB - This study proposed a Dynamic Tabu Search (DTSAR) that incorporates a dynamic Tabu list to solve an attribute reduction problem in Rough Set Theory. The dynamic Tabu list is used to skip the aspiration criteria and promote faster running times. A number of experiments have been conducted to evaluate the performance of the proposed technique with other published metaheuristic techniques, rough set and decision tree. DTSAR shows promising results on reduct generation time. It ranges between 0.20-22.18 min. For comparisons on the performances that are based on the number of produced reduct, DTSAR is on par with other metaheuristic techniques. DTSAR outperforms some techniques on certain datasets. Quality of classification rules generated by adopting DTSAR is comparable with those generated by Rough Set and Decision Trees Methods.

KW - Attribute reduction

KW - Computational intelligence

KW - Dynamic tabu list

KW - Rough set

KW - Tabu search

UR - http://www.scopus.com/inward/record.url?scp=84881351435&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84881351435&partnerID=8YFLogxK

U2 - 10.3923/ijscomp.2013.12.19

DO - 10.3923/ijscomp.2013.12.19

M3 - Article

VL - 8

SP - 12

EP - 19

JO - International Journal of Soft Computing

JF - International Journal of Soft Computing

SN - 1816-9503

IS - 1

ER -