Comparison of Multivariate Calibration Techniques Applied to Experimental NIR Data Sets

Recebido em 25/7/06; aceito em 9/11/06; publicado na web em 2/7/07 CALIBRATION TRANSFER IN MULTIVARIATE METHODS. Calibration transfer has received considerable attention in the recent literature. Several standardization methods have been proposed for transferring calibration models between equipments. The goal of this paper is to present a general revision of calibration transfer techniques. Basic concepts will be reviewed, as well as the main advantages and drawbacks of each technique. A case study based on a set of 80 NIR spectra of maize samples recorded on two different instruments is used to illustrate the main calibration transfer techniques (direct standardization, piecewise direct standardization, orthogonal signal correction and robust variable selection).Keywords: calibration transfer; NIR; standardization INTRODUÇÃOA construção e implementação de modelos de calibração multivariada 1 passa por várias etapas, cada uma das quais é determinante para as subseqüentes. A aplicação de um modelo desenvolvido em um determinado equipamento -que vamos chamar de primário -a espectros medidos em um outro equipamento (o secundário) 1 , ou a sua utilização sob novas condições ambientais ou instrumentais, por exemplo, exige muito cuidado. É provável que haja diferenças entre as respostas instrumentais de diferentes equipamentos e, mesmo que o equipamento seja um só, sua resposta pode variar ao longo do tempo. Tudo isto pode levar o modelo original a fornecer previsões errôneas.Um modelo pode tornar-se inválido caso variações não incluídas na etapa de calibração sejam introduzidas nos novos espectros. Existem basicamente três causas para isto 2 : mudanças na constituição química e/ou física das amostras (viscosidade, tamanho de partícu-las, textura da superfície etc.); mudanças no ambiente do equipamento (variações de temperatura e umidade, por exemplo, podem provocar deslocamentos das bandas de absorção e mudanças não lineares nas suas intensidades 3 ); mudanças na função de resposta do equipamento (que farão com que o espectro de uma dada amostra apresente o mesmo perfil, mas intensidades diferentes). Mudanças podem ser causadas por substituição de partes do equipamento, envelhecimento da fonte, instabilidade do detector ou, é claro, pela aquisição dos espectros em um outro equipamento.Se as fontes de variação forem identificadas, podem ser incorporadas ao modelo, acrescentando-se novas amostras durante a calibração. Pode-se também recorrer a técnicas de planejamento experimental como Convergência de Instrumentos ("Instrument Matching") 4 e Atualização de Modelos 5. Para que essas soluções funcionem, porém, é necessário que o analista tenha condições de prever futuras fontes de variação e controlar os parâmetros experimentais.Quando não se consegue identificar as fontes de variação ou quando se deseja evitar a despesa adicional de um processo de recalibração, é preciso usar alguma outra estratégia de transferên-cia. As duas mais empregadas têm sido a adaptação do modelo de calibração ou das respostas espectrais (padr...

show abstract

“…Tais efeitos podem ser minimizados com modelos PLS ou PCR, ou por técnicas de modelagem não-linear 25 .…”

Section: Modelos Globaisunclassified

Transferência de calibração em métodos multivariados

Honorato¹,

Neto²,

Martins³

et al. 2007

Quím. Nova

View full text Add to dashboard Cite

show abstract

“…Another regression method, locally weighted regression (LWR), is considered in this study because of its suitability for heterogeneous data, success dealing with non linearities (Center et al, 2000), and support to several data distributions (Atkeson, 1996).…”

Section: Calibration and Predictionmentioning

confidence: 99%

Permeation Studies of PVC Pipes with near Infrared Spectroscopy

Agelet

Hurburgh

Mao

et al. 2007

Journal of Near Infrared Spectroscopy

View full text Add to dashboard Cite

Polyvinyl chloride (PVC) pipes are commonly used to transport drinking water. Although PVC is resistant to natural environmental conditions, organic solvents may attack the pipe wall causing swelling, softening, water lines failure and drinking water pollution. Leaks from underground storage tanks and random accidental spills of organic solvents or fuels place the pipes in contact with organic solvents. Near infrared (NIR) spectroscopy was used to track the permeation of PVC pipes by three major organic solvents (toluene, benzene and gasoline) at different concentrations. Partial least squares (PLS) calibrations with NIR spectra and reference data gave accurate models with R2 > 0.9, relative performance determinant ( RPD) > 3 and low standard errors of prediction ( SEP). These models could predict the permeation status measured by mm of solvent moving front, weight gain, or days under permeation. A second study correlated pipe permeation susceptibility to pure toluene in mm h−1/2 to the pipe spectra. Spectra differences from several pipe brands and sizes were modelled with locally weighted regression (LWR), resulting in models with accuracy ( RPD) of around 5. NIR was a suitable tool to evaluate the permeation of PVC pipes and to predict the susceptibility of PVC pipes to permeation.

show abstract

“…The aim of this paper is to extend the criteria for determination of optimum ranges of voltammograms by a novel application of techniques such as Uninformative Variable Elimination-(UVE-) PLS [21,22], UVE-PCR [23], and PLS-Variable Importance in the Projection (VIP) [24,25] along with Interval PLS (IPLS) [26], Interval PCR (IPCR), and Moving Window PLS (MWPLS) [27] in electroanalysis. These variable selection techniques have been used in spectroscopy (predominantly near infrared and infrared [22,26,27]), chromatography, and mass spectrometry, but with the exception of IPLS [28] they have not been applied to electroanalysis.…”

Section: Introductionmentioning

confidence: 99%

Online Monitoring of Copper Damascene Electroplating Bath by Voltammetry: Selection of Variables for Multiblock and Hierarchical Chemometric Analysis of Voltammetric Data

Jaworski¹,

Wikiel²,

Wikiel³

2017

International Journal of Electrochemistry

View full text Add to dashboard Cite

The Real Time Analyzer (RTA) utilizing DC- and AC-voltammetric techniques is an in situ, online monitoring system that provides a complete chemical analysis of different electrochemical deposition solutions. The RTA employs multivariate calibration when predicting concentration parameters from a multivariate data set. Although the hierarchical and multiblock Principal Component Regression- (PCR-) and Partial Least Squares- (PLS-) based methods can handle data sets even when the number of variables significantly exceeds the number of samples, it can be advantageous to reduce the number of variables to obtain improvement of the model predictions and better interpretation. This presentation focuses on the introduction of a multistep, rigorous method of data-selection-based Least Squares Regression, Simple Modeling of Class Analogy modeling power, and, as a novel application in electroanalysis, Uninformative Variable Elimination by PLS and by PCR, Variable Importance in the Projection coupled with PLS, Interval PLS, Interval PCR, and Moving Window PLS. Selection criteria of the optimum decomposition technique for the specific data are also demonstrated. The chief goal of this paper is to introduce to the community of electroanalytical chemists numerous variable selection methods which are well established in spectroscopy and can be successfully applied to voltammetric data analysis.

show abstract

Comparison of Multivariate Calibration Techniques Applied to Experimental NIR Data Sets

Cited by 80 publications

References 61 publications

Transferência de calibração em métodos multivariados

Transferência de calibração em métodos multivariados

Permeation Studies of PVC Pipes with near Infrared Spectroscopy

Online Monitoring of Copper Damascene Electroplating Bath by Voltammetry: Selection of Variables for Multiblock and Hierarchical Chemometric Analysis of Voltammetric Data

Contact Info

Product

Resources

About