Efficient use of pure component and interferent spectra in multivariate calibration

Sandeep Sharma, Mohammad Goodarzi, Laure Wynants, Herman Ramon, Wouter Saeys

Research output: Contribution to journalArticle

13 Citations (Scopus)

Abstract

Partial Least Squares (PLS) is by far the most popular regression method for building multivariate calibration models for spectroscopic data. However, the success of the conventional PLS approach depends on the availability of a 'representative data set' as the model needs to be trained for all expected variation at the prediction stage. When the concentration of the known interferents and their correlation with the analyte of interest change in a fashion which is not covered in the calibration set, the predictive performance of inverse calibration approaches such as conventional PLS can deteriorate. This underscores the need for calibration methods that are capable of building multivariate calibration models which can be robustified against the unexpected variation in the concentrations and the correlations of the known interferents in the test set. Several methods incorporating 'a priori' information such as pure component spectra of the analyte of interest and/or the known interferents have been proposed to build more robust calibration models. In the present study, four such calibration techniques have been benchmarked on two data sets with respect to their predictive ability and robustness: Net Analyte Preprocessing (NAP), Improved Direct Calibration (IDC), Science Based Calibration (SBC) and Augmented Classical Least Squares (ACLS) Calibration. For both data sets, the alternative calibration techniques were found to give good prediction performance even when the interferent structure in the test set was different from the one in the calibration set. The best results were obtained by the ACLS model incorporating both the pure component spectra of the analyte of interest and the interferents, resulting in a reduction of the RMSEP by a factor 3 compared to conventional PLS for the situation when the test set had a different interferent structure than the one in the calibration set.

Original languageEnglish (US)
Pages (from-to)15-23
Number of pages9
JournalAnalytica Chimica Acta
Volume778
DOIs
StatePublished - May 17 2013

Fingerprint

Calibration
calibration
Least-Squares Analysis
prediction
Availability

Keywords

  • Augmented Classical Least Squares
  • Glucose
  • Improved Direct Calibration
  • Net Analyte Preprocessing
  • Robust calibration
  • Science Based Calibration

ASJC Scopus subject areas

  • Analytical Chemistry
  • Biochemistry
  • Environmental Chemistry
  • Spectroscopy

Cite this

Efficient use of pure component and interferent spectra in multivariate calibration. / Sharma, Sandeep; Goodarzi, Mohammad; Wynants, Laure; Ramon, Herman; Saeys, Wouter.

In: Analytica Chimica Acta, Vol. 778, 17.05.2013, p. 15-23.

Research output: Contribution to journalArticle

Sharma, Sandeep ; Goodarzi, Mohammad ; Wynants, Laure ; Ramon, Herman ; Saeys, Wouter. / Efficient use of pure component and interferent spectra in multivariate calibration. In: Analytica Chimica Acta. 2013 ; Vol. 778. pp. 15-23.
@article{2e440b0a4a674d8db97c0dac45ef48de,
title = "Efficient use of pure component and interferent spectra in multivariate calibration",
abstract = "Partial Least Squares (PLS) is by far the most popular regression method for building multivariate calibration models for spectroscopic data. However, the success of the conventional PLS approach depends on the availability of a 'representative data set' as the model needs to be trained for all expected variation at the prediction stage. When the concentration of the known interferents and their correlation with the analyte of interest change in a fashion which is not covered in the calibration set, the predictive performance of inverse calibration approaches such as conventional PLS can deteriorate. This underscores the need for calibration methods that are capable of building multivariate calibration models which can be robustified against the unexpected variation in the concentrations and the correlations of the known interferents in the test set. Several methods incorporating 'a priori' information such as pure component spectra of the analyte of interest and/or the known interferents have been proposed to build more robust calibration models. In the present study, four such calibration techniques have been benchmarked on two data sets with respect to their predictive ability and robustness: Net Analyte Preprocessing (NAP), Improved Direct Calibration (IDC), Science Based Calibration (SBC) and Augmented Classical Least Squares (ACLS) Calibration. For both data sets, the alternative calibration techniques were found to give good prediction performance even when the interferent structure in the test set was different from the one in the calibration set. The best results were obtained by the ACLS model incorporating both the pure component spectra of the analyte of interest and the interferents, resulting in a reduction of the RMSEP by a factor 3 compared to conventional PLS for the situation when the test set had a different interferent structure than the one in the calibration set.",
keywords = "Augmented Classical Least Squares, Glucose, Improved Direct Calibration, Net Analyte Preprocessing, Robust calibration, Science Based Calibration",
author = "Sandeep Sharma and Mohammad Goodarzi and Laure Wynants and Herman Ramon and Wouter Saeys",
year = "2013",
month = "5",
day = "17",
doi = "10.1016/j.aca.2013.03.045",
language = "English (US)",
volume = "778",
pages = "15--23",
journal = "Analytica Chimica Acta",
issn = "0003-2670",
publisher = "Elsevier",

}

TY - JOUR

T1 - Efficient use of pure component and interferent spectra in multivariate calibration

AU - Sharma, Sandeep

AU - Goodarzi, Mohammad

AU - Wynants, Laure

AU - Ramon, Herman

AU - Saeys, Wouter

PY - 2013/5/17

Y1 - 2013/5/17

N2 - Partial Least Squares (PLS) is by far the most popular regression method for building multivariate calibration models for spectroscopic data. However, the success of the conventional PLS approach depends on the availability of a 'representative data set' as the model needs to be trained for all expected variation at the prediction stage. When the concentration of the known interferents and their correlation with the analyte of interest change in a fashion which is not covered in the calibration set, the predictive performance of inverse calibration approaches such as conventional PLS can deteriorate. This underscores the need for calibration methods that are capable of building multivariate calibration models which can be robustified against the unexpected variation in the concentrations and the correlations of the known interferents in the test set. Several methods incorporating 'a priori' information such as pure component spectra of the analyte of interest and/or the known interferents have been proposed to build more robust calibration models. In the present study, four such calibration techniques have been benchmarked on two data sets with respect to their predictive ability and robustness: Net Analyte Preprocessing (NAP), Improved Direct Calibration (IDC), Science Based Calibration (SBC) and Augmented Classical Least Squares (ACLS) Calibration. For both data sets, the alternative calibration techniques were found to give good prediction performance even when the interferent structure in the test set was different from the one in the calibration set. The best results were obtained by the ACLS model incorporating both the pure component spectra of the analyte of interest and the interferents, resulting in a reduction of the RMSEP by a factor 3 compared to conventional PLS for the situation when the test set had a different interferent structure than the one in the calibration set.

AB - Partial Least Squares (PLS) is by far the most popular regression method for building multivariate calibration models for spectroscopic data. However, the success of the conventional PLS approach depends on the availability of a 'representative data set' as the model needs to be trained for all expected variation at the prediction stage. When the concentration of the known interferents and their correlation with the analyte of interest change in a fashion which is not covered in the calibration set, the predictive performance of inverse calibration approaches such as conventional PLS can deteriorate. This underscores the need for calibration methods that are capable of building multivariate calibration models which can be robustified against the unexpected variation in the concentrations and the correlations of the known interferents in the test set. Several methods incorporating 'a priori' information such as pure component spectra of the analyte of interest and/or the known interferents have been proposed to build more robust calibration models. In the present study, four such calibration techniques have been benchmarked on two data sets with respect to their predictive ability and robustness: Net Analyte Preprocessing (NAP), Improved Direct Calibration (IDC), Science Based Calibration (SBC) and Augmented Classical Least Squares (ACLS) Calibration. For both data sets, the alternative calibration techniques were found to give good prediction performance even when the interferent structure in the test set was different from the one in the calibration set. The best results were obtained by the ACLS model incorporating both the pure component spectra of the analyte of interest and the interferents, resulting in a reduction of the RMSEP by a factor 3 compared to conventional PLS for the situation when the test set had a different interferent structure than the one in the calibration set.

KW - Augmented Classical Least Squares

KW - Glucose

KW - Improved Direct Calibration

KW - Net Analyte Preprocessing

KW - Robust calibration

KW - Science Based Calibration

UR - http://www.scopus.com/inward/record.url?scp=84876992632&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84876992632&partnerID=8YFLogxK

U2 - 10.1016/j.aca.2013.03.045

DO - 10.1016/j.aca.2013.03.045

M3 - Article

C2 - 23639394

AN - SCOPUS:84876992632

VL - 778

SP - 15

EP - 23

JO - Analytica Chimica Acta

JF - Analytica Chimica Acta

SN - 0003-2670

ER -