GARS: An improved genetic algorithm with reserve selection for global optimization

Yang Chen, Takayuki Furuzuki, Kotaro Hirasawa, Songnian Yu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

12 Citations (Scopus)

Abstract

This paper investigates how genetic algorithms (GAs) can be improved to solve large-scale and complex problems more efficiently. First of all, we review premature convergence, one of the challenges confronted with when applying GAs to real-world problems. Next, some of the methods now available to prevent premature convergence and their intrinsic defects are discussed. A qualitative analysis is then done on the cause of premature convergence that is the loss of building blocks hosted in less-fit individuals during the course of evolution. Thus, we propose a new improver - GAs with Reserve Selection (GARS), where a reserved area is set up to save potential building blocks and a selection mechanism based on individual uniqueness is employed to activate the potentials. Finally, case studies are done in a few standard problems well known in the literature, where the experimental results demonstrate the effectiveness and robustness of GARS in suppressing premature convergence, and also an enhancement is found in global optimization capacity.

Original languageEnglish
Title of host publicationProceedings of GECCO 2007: Genetic and Evolutionary Computation Conference
Pages1173-1178
Number of pages6
DOIs
Publication statusPublished - 2007
Event9th Annual Genetic and Evolutionary Computation Conference, GECCO 2007 - London
Duration: 2007 Jul 72007 Jul 11

Other

Other9th Annual Genetic and Evolutionary Computation Conference, GECCO 2007
CityLondon
Period07/7/707/7/11

Fingerprint

Premature Convergence
Global optimization
Global Optimization
Genetic algorithms
Genetic Algorithm
Building Blocks
Qualitative Analysis
Defects
Uniqueness
Enhancement
Robustness
Gas
Experimental Results
Demonstrate

Keywords

  • Building block hypothesis
  • Evolutionary computation
  • Genetic algorithms
  • Population diversity
  • Premature convergence
  • Reserve selection

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software
  • Theoretical Computer Science

Cite this

Chen, Y., Furuzuki, T., Hirasawa, K., & Yu, S. (2007). GARS: An improved genetic algorithm with reserve selection for global optimization. In Proceedings of GECCO 2007: Genetic and Evolutionary Computation Conference (pp. 1173-1178) https://doi.org/10.1145/1276958.1277188

GARS : An improved genetic algorithm with reserve selection for global optimization. / Chen, Yang; Furuzuki, Takayuki; Hirasawa, Kotaro; Yu, Songnian.

Proceedings of GECCO 2007: Genetic and Evolutionary Computation Conference. 2007. p. 1173-1178.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Chen, Y, Furuzuki, T, Hirasawa, K & Yu, S 2007, GARS: An improved genetic algorithm with reserve selection for global optimization. in Proceedings of GECCO 2007: Genetic and Evolutionary Computation Conference. pp. 1173-1178, 9th Annual Genetic and Evolutionary Computation Conference, GECCO 2007, London, 07/7/7. https://doi.org/10.1145/1276958.1277188
Chen Y, Furuzuki T, Hirasawa K, Yu S. GARS: An improved genetic algorithm with reserve selection for global optimization. In Proceedings of GECCO 2007: Genetic and Evolutionary Computation Conference. 2007. p. 1173-1178 https://doi.org/10.1145/1276958.1277188
Chen, Yang ; Furuzuki, Takayuki ; Hirasawa, Kotaro ; Yu, Songnian. / GARS : An improved genetic algorithm with reserve selection for global optimization. Proceedings of GECCO 2007: Genetic and Evolutionary Computation Conference. 2007. pp. 1173-1178
@inproceedings{3e0ec105933d4826b451d09a9e006970,
title = "GARS: An improved genetic algorithm with reserve selection for global optimization",
abstract = "This paper investigates how genetic algorithms (GAs) can be improved to solve large-scale and complex problems more efficiently. First of all, we review premature convergence, one of the challenges confronted with when applying GAs to real-world problems. Next, some of the methods now available to prevent premature convergence and their intrinsic defects are discussed. A qualitative analysis is then done on the cause of premature convergence that is the loss of building blocks hosted in less-fit individuals during the course of evolution. Thus, we propose a new improver - GAs with Reserve Selection (GARS), where a reserved area is set up to save potential building blocks and a selection mechanism based on individual uniqueness is employed to activate the potentials. Finally, case studies are done in a few standard problems well known in the literature, where the experimental results demonstrate the effectiveness and robustness of GARS in suppressing premature convergence, and also an enhancement is found in global optimization capacity.",
keywords = "Building block hypothesis, Evolutionary computation, Genetic algorithms, Population diversity, Premature convergence, Reserve selection",
author = "Yang Chen and Takayuki Furuzuki and Kotaro Hirasawa and Songnian Yu",
year = "2007",
doi = "10.1145/1276958.1277188",
language = "English",
isbn = "1595936971",
pages = "1173--1178",
booktitle = "Proceedings of GECCO 2007: Genetic and Evolutionary Computation Conference",

}

TY - GEN

T1 - GARS

T2 - An improved genetic algorithm with reserve selection for global optimization

AU - Chen, Yang

AU - Furuzuki, Takayuki

AU - Hirasawa, Kotaro

AU - Yu, Songnian

PY - 2007

Y1 - 2007

N2 - This paper investigates how genetic algorithms (GAs) can be improved to solve large-scale and complex problems more efficiently. First of all, we review premature convergence, one of the challenges confronted with when applying GAs to real-world problems. Next, some of the methods now available to prevent premature convergence and their intrinsic defects are discussed. A qualitative analysis is then done on the cause of premature convergence that is the loss of building blocks hosted in less-fit individuals during the course of evolution. Thus, we propose a new improver - GAs with Reserve Selection (GARS), where a reserved area is set up to save potential building blocks and a selection mechanism based on individual uniqueness is employed to activate the potentials. Finally, case studies are done in a few standard problems well known in the literature, where the experimental results demonstrate the effectiveness and robustness of GARS in suppressing premature convergence, and also an enhancement is found in global optimization capacity.

AB - This paper investigates how genetic algorithms (GAs) can be improved to solve large-scale and complex problems more efficiently. First of all, we review premature convergence, one of the challenges confronted with when applying GAs to real-world problems. Next, some of the methods now available to prevent premature convergence and their intrinsic defects are discussed. A qualitative analysis is then done on the cause of premature convergence that is the loss of building blocks hosted in less-fit individuals during the course of evolution. Thus, we propose a new improver - GAs with Reserve Selection (GARS), where a reserved area is set up to save potential building blocks and a selection mechanism based on individual uniqueness is employed to activate the potentials. Finally, case studies are done in a few standard problems well known in the literature, where the experimental results demonstrate the effectiveness and robustness of GARS in suppressing premature convergence, and also an enhancement is found in global optimization capacity.

KW - Building block hypothesis

KW - Evolutionary computation

KW - Genetic algorithms

KW - Population diversity

KW - Premature convergence

KW - Reserve selection

UR - http://www.scopus.com/inward/record.url?scp=34548089212&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34548089212&partnerID=8YFLogxK

U2 - 10.1145/1276958.1277188

DO - 10.1145/1276958.1277188

M3 - Conference contribution

AN - SCOPUS:34548089212

SN - 1595936971

SN - 9781595936974

SP - 1173

EP - 1178

BT - Proceedings of GECCO 2007: Genetic and Evolutionary Computation Conference

ER -