Optimal input design for reduction of parameter correlations

Ke Wang, Hong Yue, Hui Yu

Research output: Contribution to conferencePaper

Abstract

An new scalarisation criterion is proposed for optimal experiment design (OED) of input intensity so as to obtain the most informative experimental data for parameter estimation with reduced parameter correlations. This criterion is a linear combination of logarithm function of the A-optimality and the modified E (ME)-optimality. It can be used to improve the estimation quality from the A-optimal design, and to reduce parameter correlations from the MEoptimal design. The proposed algorithm has been examined through simulation study of an enzyme reaction system model. The results are compared with A-optimal design, MEoptimal design, and other designs with a focus on reducing parameter correlations such as the C- and the CE- designs.

Conference

ConferenceThe 24th International Conference on Automation and Computing (ICAC'18)
Abbreviated titleICAC'18
CountryUnited Kingdom
CityNewcastle
Period6/09/187/09/18
Internet address

Fingerprint

Design of experiments
Parameter estimation
Enzymes
Optimal design

Keywords

  • parameter estimation
  • optimal experimental design (OED)
  • optimal input design
  • reduction of parameter correlation

Cite this

Wang, K., Yue, H., & Yu, H. (2018). Optimal input design for reduction of parameter correlations. Paper presented at The 24th International Conference on Automation and Computing (ICAC'18), Newcastle, United Kingdom.
Wang, Ke ; Yue, Hong ; Yu, Hui. / Optimal input design for reduction of parameter correlations. Paper presented at The 24th International Conference on Automation and Computing (ICAC'18), Newcastle, United Kingdom.6 p.
@conference{1f2ae6022aaf4bdabc9e19389165d9ab,
title = "Optimal input design for reduction of parameter correlations",
abstract = "An new scalarisation criterion is proposed for optimal experiment design (OED) of input intensity so as to obtain the most informative experimental data for parameter estimation with reduced parameter correlations. This criterion is a linear combination of logarithm function of the A-optimality and the modified E (ME)-optimality. It can be used to improve the estimation quality from the A-optimal design, and to reduce parameter correlations from the MEoptimal design. The proposed algorithm has been examined through simulation study of an enzyme reaction system model. The results are compared with A-optimal design, MEoptimal design, and other designs with a focus on reducing parameter correlations such as the C- and the CE- designs.",
keywords = "parameter estimation, optimal experimental design (OED), optimal input design, reduction of parameter correlation",
author = "Ke Wang and Hong Yue and Hui Yu",
year = "2018",
month = "9",
day = "6",
language = "English",
note = "The 24th International Conference on Automation and Computing (ICAC'18), ICAC'18 ; Conference date: 06-09-2018 Through 07-09-2018",
url = "http://www.cacsuk.co.uk/index.php/conferences",

}

Wang, K, Yue, H & Yu, H 2018, 'Optimal input design for reduction of parameter correlations' Paper presented at The 24th International Conference on Automation and Computing (ICAC'18), Newcastle, United Kingdom, 6/09/18 - 7/09/18, .

Optimal input design for reduction of parameter correlations. / Wang, Ke; Yue, Hong; Yu, Hui.

2018. Paper presented at The 24th International Conference on Automation and Computing (ICAC'18), Newcastle, United Kingdom.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Optimal input design for reduction of parameter correlations

AU - Wang, Ke

AU - Yue, Hong

AU - Yu, Hui

PY - 2018/9/6

Y1 - 2018/9/6

N2 - An new scalarisation criterion is proposed for optimal experiment design (OED) of input intensity so as to obtain the most informative experimental data for parameter estimation with reduced parameter correlations. This criterion is a linear combination of logarithm function of the A-optimality and the modified E (ME)-optimality. It can be used to improve the estimation quality from the A-optimal design, and to reduce parameter correlations from the MEoptimal design. The proposed algorithm has been examined through simulation study of an enzyme reaction system model. The results are compared with A-optimal design, MEoptimal design, and other designs with a focus on reducing parameter correlations such as the C- and the CE- designs.

AB - An new scalarisation criterion is proposed for optimal experiment design (OED) of input intensity so as to obtain the most informative experimental data for parameter estimation with reduced parameter correlations. This criterion is a linear combination of logarithm function of the A-optimality and the modified E (ME)-optimality. It can be used to improve the estimation quality from the A-optimal design, and to reduce parameter correlations from the MEoptimal design. The proposed algorithm has been examined through simulation study of an enzyme reaction system model. The results are compared with A-optimal design, MEoptimal design, and other designs with a focus on reducing parameter correlations such as the C- and the CE- designs.

KW - parameter estimation

KW - optimal experimental design (OED)

KW - optimal input design

KW - reduction of parameter correlation

M3 - Paper

ER -

Wang K, Yue H, Yu H. Optimal input design for reduction of parameter correlations. 2018. Paper presented at The 24th International Conference on Automation and Computing (ICAC'18), Newcastle, United Kingdom.