Triple and quadruple comparison-based interactive differential evolution and differential evolution

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

17 Citations (Scopus)

Abstract

We propose a triple comparison and a quadruple comparison based mechanism for enhancing differential evolution (DE), especially for interactive DE (IDE) where the method can be used to reduce IDE user fatigue. Besides the target vector and trial vector from normal DE, opposition vectors generated by opposition-based learning are used to determine offspring, and the best vector from among these three or four vectors becomes offspring for the next generation. We evaluate the proposed methods by comparing them with conventional IDE and conventional opposition-based IDE using a simulated IDE modeled using a four dimensional Gaussian mixture model. We also evaluate them in DE using 24 benchmark functions. The experiments show that our proposed methods can enhance IDE and DE search efficiently according to several evaluation indices. These include the converged fitness values after the same number of generations, converged fitness values after the same number of fitness calculations, fitness calculation cost, convergence success rates and acceleration rates.

Original languageEnglish
Title of host publicationFOGA 2013 - Proceedings of the 12th ACM Workshop on Foundations of Genetic Algorithms
Pages173-182
Number of pages10
DOIs
Publication statusPublished - Apr 15 2013
Event12th ACM Workshop on Foundations of Genetic Algorithms, FOGA 2013 - Adelaide, SA, Australia
Duration: Jan 16 2013Jan 20 2013

Publication series

NameFOGA 2013 - Proceedings of the 12th ACM Workshop on Foundations of Genetic Algorithms

Other

Other12th ACM Workshop on Foundations of Genetic Algorithms, FOGA 2013
CountryAustralia
CityAdelaide, SA
Period1/16/131/20/13

Fingerprint

Quadruple
Differential Evolution
Fitness
Evaluate
Gaussian Mixture Model
Fatigue
Benchmark
Target
Evaluation
Costs
Experiment

All Science Journal Classification (ASJC) codes

  • Discrete Mathematics and Combinatorics

Cite this

Pei, Y., & Takagi, H. (2013). Triple and quadruple comparison-based interactive differential evolution and differential evolution. In FOGA 2013 - Proceedings of the 12th ACM Workshop on Foundations of Genetic Algorithms (pp. 173-182). (FOGA 2013 - Proceedings of the 12th ACM Workshop on Foundations of Genetic Algorithms). https://doi.org/10.1145/2460239.2460255

Triple and quadruple comparison-based interactive differential evolution and differential evolution. / Pei, Yan; Takagi, Hideyuki.

FOGA 2013 - Proceedings of the 12th ACM Workshop on Foundations of Genetic Algorithms. 2013. p. 173-182 (FOGA 2013 - Proceedings of the 12th ACM Workshop on Foundations of Genetic Algorithms).

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

Pei, Y & Takagi, H 2013, Triple and quadruple comparison-based interactive differential evolution and differential evolution. in FOGA 2013 - Proceedings of the 12th ACM Workshop on Foundations of Genetic Algorithms. FOGA 2013 - Proceedings of the 12th ACM Workshop on Foundations of Genetic Algorithms, pp. 173-182, 12th ACM Workshop on Foundations of Genetic Algorithms, FOGA 2013, Adelaide, SA, Australia, 1/16/13. https://doi.org/10.1145/2460239.2460255
Pei Y, Takagi H. Triple and quadruple comparison-based interactive differential evolution and differential evolution. In FOGA 2013 - Proceedings of the 12th ACM Workshop on Foundations of Genetic Algorithms. 2013. p. 173-182. (FOGA 2013 - Proceedings of the 12th ACM Workshop on Foundations of Genetic Algorithms). https://doi.org/10.1145/2460239.2460255
Pei, Yan ; Takagi, Hideyuki. / Triple and quadruple comparison-based interactive differential evolution and differential evolution. FOGA 2013 - Proceedings of the 12th ACM Workshop on Foundations of Genetic Algorithms. 2013. pp. 173-182 (FOGA 2013 - Proceedings of the 12th ACM Workshop on Foundations of Genetic Algorithms).
@inproceedings{b3bb23018e7146b1b305001e19ca8c94,
title = "Triple and quadruple comparison-based interactive differential evolution and differential evolution",
abstract = "We propose a triple comparison and a quadruple comparison based mechanism for enhancing differential evolution (DE), especially for interactive DE (IDE) where the method can be used to reduce IDE user fatigue. Besides the target vector and trial vector from normal DE, opposition vectors generated by opposition-based learning are used to determine offspring, and the best vector from among these three or four vectors becomes offspring for the next generation. We evaluate the proposed methods by comparing them with conventional IDE and conventional opposition-based IDE using a simulated IDE modeled using a four dimensional Gaussian mixture model. We also evaluate them in DE using 24 benchmark functions. The experiments show that our proposed methods can enhance IDE and DE search efficiently according to several evaluation indices. These include the converged fitness values after the same number of generations, converged fitness values after the same number of fitness calculations, fitness calculation cost, convergence success rates and acceleration rates.",
author = "Yan Pei and Hideyuki Takagi",
year = "2013",
month = "4",
day = "15",
doi = "10.1145/2460239.2460255",
language = "English",
isbn = "9781450319904",
series = "FOGA 2013 - Proceedings of the 12th ACM Workshop on Foundations of Genetic Algorithms",
pages = "173--182",
booktitle = "FOGA 2013 - Proceedings of the 12th ACM Workshop on Foundations of Genetic Algorithms",

}

TY - GEN

T1 - Triple and quadruple comparison-based interactive differential evolution and differential evolution

AU - Pei, Yan

AU - Takagi, Hideyuki

PY - 2013/4/15

Y1 - 2013/4/15

N2 - We propose a triple comparison and a quadruple comparison based mechanism for enhancing differential evolution (DE), especially for interactive DE (IDE) where the method can be used to reduce IDE user fatigue. Besides the target vector and trial vector from normal DE, opposition vectors generated by opposition-based learning are used to determine offspring, and the best vector from among these three or four vectors becomes offspring for the next generation. We evaluate the proposed methods by comparing them with conventional IDE and conventional opposition-based IDE using a simulated IDE modeled using a four dimensional Gaussian mixture model. We also evaluate them in DE using 24 benchmark functions. The experiments show that our proposed methods can enhance IDE and DE search efficiently according to several evaluation indices. These include the converged fitness values after the same number of generations, converged fitness values after the same number of fitness calculations, fitness calculation cost, convergence success rates and acceleration rates.

AB - We propose a triple comparison and a quadruple comparison based mechanism for enhancing differential evolution (DE), especially for interactive DE (IDE) where the method can be used to reduce IDE user fatigue. Besides the target vector and trial vector from normal DE, opposition vectors generated by opposition-based learning are used to determine offspring, and the best vector from among these three or four vectors becomes offspring for the next generation. We evaluate the proposed methods by comparing them with conventional IDE and conventional opposition-based IDE using a simulated IDE modeled using a four dimensional Gaussian mixture model. We also evaluate them in DE using 24 benchmark functions. The experiments show that our proposed methods can enhance IDE and DE search efficiently according to several evaluation indices. These include the converged fitness values after the same number of generations, converged fitness values after the same number of fitness calculations, fitness calculation cost, convergence success rates and acceleration rates.

UR - http://www.scopus.com/inward/record.url?scp=84876008275&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84876008275&partnerID=8YFLogxK

U2 - 10.1145/2460239.2460255

DO - 10.1145/2460239.2460255

M3 - Conference contribution

AN - SCOPUS:84876008275

SN - 9781450319904

T3 - FOGA 2013 - Proceedings of the 12th ACM Workshop on Foundations of Genetic Algorithms

SP - 173

EP - 182

BT - FOGA 2013 - Proceedings of the 12th ACM Workshop on Foundations of Genetic Algorithms

ER -