An optimization framework using sequential approximation model and multimodal evolution strategy

Hong Kyu Kim, Chang-Hwan Im, David A. Lowther

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

Abstract

This paper presents an optimization methodology which employs a Kriging model together with a restricted evolution strategy (ES). The global and local optima are found using the restricted ES. Of these optima, some points are selected to enter the sample data set and the Kriging model is reconstructed using the updated sample data set. The numerical tests show that the proposed method is quite efficient for a surrogate-assisted optimization framework.

Original languageEnglish
Title of host publication12th Biennial IEEE Conference on Electromagnetic Field Computation, CEFC 2006
DOIs
StatePublished - 2006 Nov 21
Event12th Biennial IEEE Conference on Electromagnetic Field Computation, CEFC 2006 - Miami, FL, United States
Duration: 2006 Apr 302006 May 3

Other

Other12th Biennial IEEE Conference on Electromagnetic Field Computation, CEFC 2006
CountryUnited States
CityMiami, FL
Period06/04/3006/05/3

Cite this

Kim, H. K., Im, C-H., & Lowther, D. A. (2006). An optimization framework using sequential approximation model and multimodal evolution strategy. In 12th Biennial IEEE Conference on Electromagnetic Field Computation, CEFC 2006 [1632919] https://doi.org/10.1109/CEFC-06.2006.1632919
Kim, Hong Kyu ; Im, Chang-Hwan ; Lowther, David A. / An optimization framework using sequential approximation model and multimodal evolution strategy. 12th Biennial IEEE Conference on Electromagnetic Field Computation, CEFC 2006. 2006.
@inproceedings{4aa41b4b66e04273988d703f04aee632,
title = "An optimization framework using sequential approximation model and multimodal evolution strategy",
abstract = "This paper presents an optimization methodology which employs a Kriging model together with a restricted evolution strategy (ES). The global and local optima are found using the restricted ES. Of these optima, some points are selected to enter the sample data set and the Kriging model is reconstructed using the updated sample data set. The numerical tests show that the proposed method is quite efficient for a surrogate-assisted optimization framework.",
author = "Kim, {Hong Kyu} and Chang-Hwan Im and Lowther, {David A.}",
year = "2006",
month = "11",
day = "21",
doi = "10.1109/CEFC-06.2006.1632919",
language = "English",
isbn = "1424403200",
booktitle = "12th Biennial IEEE Conference on Electromagnetic Field Computation, CEFC 2006",

}

Kim, HK, Im, C-H & Lowther, DA 2006, An optimization framework using sequential approximation model and multimodal evolution strategy. in 12th Biennial IEEE Conference on Electromagnetic Field Computation, CEFC 2006., 1632919, 12th Biennial IEEE Conference on Electromagnetic Field Computation, CEFC 2006, Miami, FL, United States, 06/04/30. https://doi.org/10.1109/CEFC-06.2006.1632919

An optimization framework using sequential approximation model and multimodal evolution strategy. / Kim, Hong Kyu; Im, Chang-Hwan; Lowther, David A.

12th Biennial IEEE Conference on Electromagnetic Field Computation, CEFC 2006. 2006. 1632919.

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

TY - GEN

T1 - An optimization framework using sequential approximation model and multimodal evolution strategy

AU - Kim, Hong Kyu

AU - Im, Chang-Hwan

AU - Lowther, David A.

PY - 2006/11/21

Y1 - 2006/11/21

N2 - This paper presents an optimization methodology which employs a Kriging model together with a restricted evolution strategy (ES). The global and local optima are found using the restricted ES. Of these optima, some points are selected to enter the sample data set and the Kriging model is reconstructed using the updated sample data set. The numerical tests show that the proposed method is quite efficient for a surrogate-assisted optimization framework.

AB - This paper presents an optimization methodology which employs a Kriging model together with a restricted evolution strategy (ES). The global and local optima are found using the restricted ES. Of these optima, some points are selected to enter the sample data set and the Kriging model is reconstructed using the updated sample data set. The numerical tests show that the proposed method is quite efficient for a surrogate-assisted optimization framework.

UR - http://www.scopus.com/inward/record.url?scp=42749099832&partnerID=8YFLogxK

U2 - 10.1109/CEFC-06.2006.1632919

DO - 10.1109/CEFC-06.2006.1632919

M3 - Conference contribution

AN - SCOPUS:42749099832

SN - 1424403200

SN - 9781424403202

BT - 12th Biennial IEEE Conference on Electromagnetic Field Computation, CEFC 2006

ER -

Kim HK, Im C-H, Lowther DA. An optimization framework using sequential approximation model and multimodal evolution strategy. In 12th Biennial IEEE Conference on Electromagnetic Field Computation, CEFC 2006. 2006. 1632919 https://doi.org/10.1109/CEFC-06.2006.1632919