Robustness of models developed by multivariate calibration. Part II: The influence of pre-processing methods

Zeaiter, Magida; Roger, Jean‐Michel; Maurel, Véronique Bellon

doi:10.1016/j.trac.2004.11.023

Cited by 137 publications

(81 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…As noted in the literature, wavelength (variable) selection can be viewed as a subset of the more generic process of dimension reduction. 24 Potentially, wavelength selection can enhance the stability of the model to the collinearity in the acquired Raman spectra as well as increase the interpretability of the relationship between the model and the sample compositions by reducing the number of loading vectors to the chemical rank of the system. 25 The important consideration is how many and which of the spectral bands facilitate accurate prediction.…”

Section: Theoretical Background 21 Wavelength Selectionmentioning

confidence: 99%

Wavelength selection-based nonlinear calibration for transcutaneous blood glucose sensing using Raman spectroscopy

et al. 2011

View full text Add to dashboard Cite

Abstract. While Raman spectroscopy provides a powerful tool for noninvasive and real time diagnostics of biological samples, its translation to the clinical setting has been impeded by the lack of robustness of spectroscopic calibration models and the size and cumbersome nature of conventional laboratory Raman systems. Linear multivariate calibration models employing full spectrum analysis are often misled by spurious correlations, such as system drift and covariations among constituents. In addition, such calibration schemes are prone to overfitting, especially in the presence of external interferences that may create nonlinearities in the spectra-concentration relationship. To address both of these issues we incorporate residue error plot-based wavelength selection and nonlinear support vector regression (SVR). Wavelength selection is used to eliminate uninformative regions of the spectrum, while SVR is used to model the curved effects such as those created by tissue turbidity and temperature fluctuations. Using glucose detection in tissue phantoms as a representative example, we show that even a substantial reduction in the number of wavelengths analyzed using SVR lead to calibration models of equivalent prediction accuracy as linear full spectrum analysis. Further, with clinical datasets obtained from human subject studies, we also demonstrate the prospective applicability of the selected wavelength subsets without sacrificing prediction accuracy, which has extensive implications for calibration maintenance and transfer. Additionally, such wavelength selection could substantially reduce the collection time of serial Raman acquisition systems. Given the reduced footprint of serial Raman systems in relation to conventional dispersive Raman spectrometers, we anticipate that the incorporation of wavelength selection in such hardware designs will enhance the possibility of miniaturized clinical systems for disease diagnosis in the near future. C 2011 Society of Photo-Optical Instrumentation Engineers (SPIE).

show abstract

Section: Theoretical Background 21 Wavelength Selectionmentioning

confidence: 99%

Wavelength selection-based nonlinear calibration for transcutaneous blood glucose sensing using Raman spectroscopy

et al. 2011

View full text Add to dashboard Cite

show abstract

“…Hyperspectral images 40 are composed of hundreds of contiguous wavebands for each spatial position of an object. 41 Consequently, each pixel in a hyperspectral image contains the spectrum of that specific Rapid spectroscopic techniques show potential for replacement of slow and/or expensive 53 analytical measurements while retaining sufficient accuracy (12). Recent studies have 54 demonstrated HSI to be a useful technology for the investigation of various mushroom 55 quality related issues, such as deterioration (13), freeze damage detection (14) and blemish 56 characterization (15).…”

Section: Introductionmentioning

confidence: 99%

Prediction of Polyphenol Oxidase Activity Using Visible Near-Infrared Hyperspectral Imaging on Mushroom (Agaricus bisporus) Caps

Gaston¹,

Frías²,

Cullen³

et al. 2010

J. Agric. Food Chem.

View full text Add to dashboard Cite

1Physical stress (i.e. bruising) during harvesting, handling and transportation triggers 2 enzymatic discoloration of mushrooms, a common and detrimental phenomenon largely 3 mediated by polyphenol oxidase (PPO) enzymes. Hyperspectral imaging (HSI) is a non-4 destructive technique that combines imaging and spectroscopy to obtain information from a 5 sample. The objective of this study was to assess the ability of HSI to predict the activity of 6 PPO on mushroom caps. Hyperspectral images of mushrooms subjected to various damage 7 treatments were taken, followed by enzyme extraction and PPO activity measurement.

show abstract

“…Variable-selection techniques consist of selecting particular variables related to the response, instead of removing the interference modeled as a spectrum, the aim being to identify a subset of wavelengths that produces the smallest possible error [56]. Selecting the most correlated wavelengths may lead to better performance in PLS and PCR, but, on the other hand, selection of the most correlated wavelengths may eliminate those that correct for the influence of interfering compounds or factors [56].…”

Section: Dimensionality-reduction Methodsmentioning

confidence: 99%

Multivariate Calibration for the Development of Vibrational Spectroscopic Methods

Tomuță¹,

Porfire²,

Casian³

et al. 2018

Calibration and Validation of Analytical Methods - A Sampling of Current Approaches

View full text Add to dashboard Cite

Vibrational spectroscopy, namely near infrared (NIR) and Raman spectroscopy, is based on the interaction between the electromagnetic radiation and matter. The technique is sensitive to chemical and physical properties and delivers a wide range of information about the analyzed sample, but in order to extract the information, multivariate calibration of the spectral data is required. The main goal of this work will be to present in detail the available multivariate calibration strategy for development of NIR and Raman spectroscopic methods, which was successfully applied in pharmaceutics.

show abstract

Robustness of models developed by multivariate calibration. Part II: The influence of pre-processing methods

Cited by 137 publications

References 43 publications

Wavelength selection-based nonlinear calibration for transcutaneous blood glucose sensing using Raman spectroscopy

Wavelength selection-based nonlinear calibration for transcutaneous blood glucose sensing using Raman spectroscopy

Prediction of Polyphenol Oxidase Activity Using Visible Near-Infrared Hyperspectral Imaging on Mushroom (Agaricus bisporus) Caps

Multivariate Calibration for the Development of Vibrational Spectroscopic Methods

Contact Info

Product

Resources

About