An Improved Latin Hypercube Sampling Method to Enhance Numerical Stability Considering the Correlation of Input Variables

An Improved Latin Hypercube Sampling Method to Enhance Numerical Stability Considering the Correlation of Input Variables

Latin hypercube sampling (LHS) method has difficulty in dealing with non-positive definite correlation matrices by traditional Cholesky decomposition, whereas it may often happen with the increasing scale of input variables. In order to improve the numerical stability of LHS, an improved LHS with mo...

Full description

Bibliographic Details
Main Authors: Qingshan Xu, Yang Yang, Yujun Liu, Xudong Wang
Format: Article
Language:English
Published: IEEE 2017-01-01
Series:IEEE Access
Subjects:
Latin hypercube sampling
correlation matrix
non-positive definite matrix
Cholesky decomposition
alternating projections method
Online Access:https://ieeexplore.ieee.org/document/7993009/

Internet

https://ieeexplore.ieee.org/document/7993009/

Similar Items