Skip to main navigation Skip to search Skip to main content

A sequential latin hypercube sampling method for metamodeling

  • Harbin Institute of Technology

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

For utilizing the original sampling points and improving budget allocation efficiency, we propose a sequential Latin Hypercube Sampling (LHS) method for metamodeling. The sequential method starts with an original LHS of size n and constructs a new LHS of size kn that has the original points as more as possible. The sampling points of LHS are described by some matrixes and it is proved that there is no need to delete original points for the new LHS. A subtraction rule is applied for adding new sampling points. The original and addition sampling points are proved to be a strict LHS. The method is applied for metamodeling to demonstrate the effectiveness.

Original languageEnglish
Title of host publicationTheory, Methodology, Tools and Applications for Modeling and Simulation of Complex Systems - 16th Asia Simulation Conference and SCS Autumn Simulation Multi-Conference, AsiaSim/SCS AutumnSim 2016, Proceedings
EditorsLin Zhang, Xiao Song, Yunjie Wu
PublisherSpringer Verlag
Pages176-185
Number of pages10
ISBN (Print)9789811026621
DOIs
StatePublished - 2016
Event16th Asia Simulation Conference and SCS Autumn Simulation Multi-Conference, AsiaSim/SCS AutumnSim 2016 - Beijing, China
Duration: 8 Oct 201611 Oct 2016

Publication series

NameCommunications in Computer and Information Science
Volume643
ISSN (Print)1865-0929

Conference

Conference16th Asia Simulation Conference and SCS Autumn Simulation Multi-Conference, AsiaSim/SCS AutumnSim 2016
Country/TerritoryChina
CityBeijing
Period8/10/1611/10/16

Keywords

  • Latin hypercube sampling
  • Metamodel
  • Sequential method

Fingerprint

Dive into the research topics of 'A sequential latin hypercube sampling method for metamodeling'. Together they form a unique fingerprint.

Cite this