Robust calibration using orthogonal projection and experimental design. Application to the correction of the light scattering effect on turbid NIR spectra

Preys, Sébastien; Roger, Jean‐Michel; Boulet, Jean Claude

doi:10.1016/j.chemolab.2007.10.007

Cited by 33 publications

(11 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In general, those methods do not require identical samples measured on both spectrometers. Common transforms include the multiplicative scatter correction , standard normal variate , orthogonal signal correction (OSC) , and finite impulse response (FIR) filtering . These methods correct for changes in baselines and signal‐to‐noise ratios that invariably occur.…”

Section: Introductionmentioning

confidence: 99%

Application of orthogonal space regression to calibration transfer without standards

Lin

et al. 2013

Journal of Chemometrics

View full text Add to dashboard Cite

To transfer a calibration model in cases where the standardization samples are rare or unstable, a method based on orthogonal space regression (OSR) is proposed. It uses virtual standardization spectra to account for response changes between instruments or batches. A comparative study of the proposed OSR, piecewise direct standardization, finite impulse response, orthogonal signal correction, and model updating (MU) was conducted on both pharmaceutical tablet data and chlorogenic acid data. The results of these studies suggest that both the OSR and the MU are superior to the other transfer techniques in terms of root‐mean‐squared error of prediction and ratio of performance to interquartile distance. Moreover, OSR requires no identical standard samples, and it avoids re‐optimizing the transfer models. In conclusion, both the differences among spectra measured on different spectrometers and the differences between different batches can be corrected successfully using the OSR method. Copyright © 2013 John Wiley & Sons, Ltd.

show abstract

Section: Introductionmentioning

confidence: 99%

Application of orthogonal space regression to calibration transfer without standards

Lin

et al. 2013

Journal of Chemometrics

View full text Add to dashboard Cite

show abstract

“…During the past decades, the use of spectroscopic information1–19 has received much attention and begun to emerge as an important technique, which is being heavily encouraged and practiced for different purposes. Predicting a dependent variable from the spectra measurement is a frequently encountered problem in chemometrics.…”

Section: Introductionmentioning

confidence: 99%

Spectra data analysis and calibration modeling method using spectra subspace separation and multiblock independent component regression strategy

2011

View full text Add to dashboard Cite

In this article, a spectra data analysis and calibration modeling approach is proposed for the estimation of the concentration of sources species in chemical mixture. Based on the multiplicity of underlying spectra characteristics, it designs spectra subspace separation and multiblock independent component regression modeling strategy. It is performed in two steps: The first step aims at an automatic partition of the original wavelength space into different spectra subspaces to reveal the changes of underlying spectra information. In different spectra subspaces, each being well fitted by one independent component analysis (ICA) model, it better explores the existing chemical constituent species of interest. In the second step, multiblock regression system is designed for concentration estimation. The advantage is mainly to allow for easier interpretation and enhanced understanding by zooming into different smaller specific segments and thus well tracking the wavelength-varying effects on qualities. It is theoretically and experimentally illustrated that the proposed method can result in better predictive power compared with standard ICR (SICR) modeling focusing on the full-range wavelength.

show abstract

“…Therefore, it is a common practice to apply a pretreatment before calibration modeling to remove those disturbing factors. To address the above problems, various strategies have been developed, in which, variable selection (Xu and Zhang, 2001;Abrahamsson et al, 2003;Gusnanto et al, 2003;Chu et al, 2004;Cai et al, 2008;Galvão et al, 2008;Ye et al, 2008) and orthogonal signal correction (OSC) (Sjöblom et al, 1998;Wold et al, 1998;Fearn, 2000;Ghorbani et al, 2006;Zarei et al, 2006;Boulet et al, 2007;Nizai and Yazdanipour, 2007;Preys et al, 2008) are the popular preprocessing means. Several variable selection methods have been suggested to choose a subset of descriptors that produce the most correlated relationship with qualities.…”

mentioning

confidence: 99%

Covariance‐oriented qualitative and quantitative calibration analysis for multistage batch processes

2009

View full text Add to dashboard Cite

An improved stage-specific multivariate calibration scheme is developed for multistage batch processes based on the covariance analysis unit. First, the process duration is automatically and properly divided into different stages, which reveals the changes of quality-related process correlation characteristics. The concept of stage-representative average process behaviour is then introduced, which is comprehensibly realized by averaging all covariance patterns within the same stage based on different weights. In this way, it stacks the cumulative effects of process variations on quality within each stage and meanwhile considers their time-varying characteristics. Subsequently, covariance-oriented OSC and variable selection are effectively combined, which can simplify the calibration model structure and enhance the causal relationship between predictors and quality by excluding the redundant latent factors and input variables. Finally, stage-representative PLS regression models are developed focusing on the critical-to-quality stages for online quality prediction. It shows that a complete multistage calibration solution is readily achieved from an "overall" stage perspective by smartly making use of covariance. The illustration study to injection molding shows the effectiveness of the proposed method for improving process comprehension and quality prediction.On a mis au point un schéma amélioré d'étalonnage multivarié pour des procédés discontinus multi-étapes, spécifiqueà chaqueétape, basé sur l'analyse des covariances sans tenir compte de chaque variable de procédé. En premier lieu, la durée de procédé est automatiquement et correctement divisée en quatreétapes différentes, révélant le changement des caractéristiques de corrélation de procédé liéà la qualité. Le concept de comportement de procédé moyen représentatif d'uneétape est alors introduit, ce qui se réalise de façon complète en moyennant tous les profils de covariance d'uneétape donnée avec différentes pondérations. De cette façon, on tient compte dans la qualité des effets cumulatifs des variations de procédé spécifiquesà chaqueétape et considère de ce fait leurs caractéristiquesévolutives. Par conséquent, l'OSC orienté vers la covariance et la technique de sélection des variables sont combinés efficacement afin de simplifier la structure du modèle d'étalonnage et améliorer la relation causale en excluant les facteurs latents redondants ou les variables d'entrée. Enfin, des modèles de régression de type PLS représentatifs desétapes sont mis au point, mettant l'accent sur lesétapes critiques en terme de qualité pour la prédiction de la qualité en ligne. Cela montre qu'une solution complète d'étalonnage multi-étapes peut se réaliser parfaitement en utilisant bien la covariance. L'illustration dans le cas du moulage par injection montre l'efficacité de la méthode proposée pour la compréhension du procédé et l'amélioration des prédictions.

show abstract

Robust calibration using orthogonal projection and experimental design. Application to the correction of the light scattering effect on turbid NIR spectra

Cited by 33 publications

References 14 publications

Application of orthogonal space regression to calibration transfer without standards

Application of orthogonal space regression to calibration transfer without standards

Spectra data analysis and calibration modeling method using spectra subspace separation and multiblock independent component regression strategy

Covariance‐oriented qualitative and quantitative calibration analysis for multistage batch processes

Contact Info

Product

Resources

About