Calibration model fusion
Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
Standard
Calibration model fusion. / Halberg, Helene Fog Froriep; Holst, Anette Yde; Kaufmann, Niels; Bro, Rasmus.
I: Journal of Chemometrics, Bind 37, Nr. 3, e3350, 2023.Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - Calibration model fusion
AU - Halberg, Helene Fog Froriep
AU - Holst, Anette Yde
AU - Kaufmann, Niels
AU - Bro, Rasmus
N1 - Publisher Copyright: © 2021 John Wiley & Sons, Ltd.
PY - 2023
Y1 - 2023
N2 - Calibration model maintenance is often overlooked but is a significant part of successful use of multivariate calibration models, for example, in process monitoring and optimization. In some cases, companies are maintaining tens or even hundreds of calibration models. This could be partial least squares (PLS) calibration models pertaining to different recipes or raw materials or neural network based models covering different production sites. Maintaining such a high number of models is cumbersome and expensive. Sometimes, a solution presented for this problem is to merge all the models into one, but this often comes at the expense of significantly higher prediction errors. In this paper, we suggest a new approach for rationally merging calibration models in order to optimally balance the prediction error and maintenance workload. We do this by systematically merging models that lower the error as much as possible and hence provide a sort of optimal clustering or fusion of calibration models. We showcase the new approach on a case based on infrared spectroscopy applied to dairy production.
AB - Calibration model maintenance is often overlooked but is a significant part of successful use of multivariate calibration models, for example, in process monitoring and optimization. In some cases, companies are maintaining tens or even hundreds of calibration models. This could be partial least squares (PLS) calibration models pertaining to different recipes or raw materials or neural network based models covering different production sites. Maintaining such a high number of models is cumbersome and expensive. Sometimes, a solution presented for this problem is to merge all the models into one, but this often comes at the expense of significantly higher prediction errors. In this paper, we suggest a new approach for rationally merging calibration models in order to optimally balance the prediction error and maintenance workload. We do this by systematically merging models that lower the error as much as possible and hence provide a sort of optimal clustering or fusion of calibration models. We showcase the new approach on a case based on infrared spectroscopy applied to dairy production.
U2 - 10.1002/cem.3350
DO - 10.1002/cem.3350
M3 - Journal article
AN - SCOPUS:85105941778
VL - 37
JO - Journal of Chemometrics
JF - Journal of Chemometrics
SN - 0886-9383
IS - 3
M1 - e3350
ER -
ID: 272061892