Piecewise Direct Standardization Research Articles

NIR model transfer of alkali-soluble polysaccharides in Poria cocos with piecewise direct standardization

Objective To investigate the feasibility for establishing near-infrared spectra model transfer with traditional Chinese medicine. Method Poria cocos, a kind of fungi (called “ Fuling” in Chinese), was used as an investigative object. NIR quantification model transfer of alkali-soluble polysaccharides in Poria cocos was studied. Spectra were obtained from Thermo Antaris II (master device) and Buchi NIRFlex N-500 (slave device), respectively. Procedures and factors that may have effects on the performance of spectral standardization have been investigated. Spline interpolation was applied to align spectra from two different instruments, and piecewise direct standardization was employed to standardize spectra from slave instrument. Full cross-validation was used to evaluate the result of model transfer. Results Spectral pre-processing including multiplicative signal correction and wavelength selection played an important role in operating the model transfer. Spectra within the region of 9000–6500 cm−1 provided relatively good transfer result. In addition, increasing window size had positive effect on improving the spectral transfer. In this study, a window size of 13 provided the best spectra standardization result. Test validation with five samples produced the best full cross-validation result with the values of correlation coefficient of calibration ([Formula: see text]), correlation coefficient of prediction ([Formula: see text]) and root mean square error of prediction as 0.86, 0.73 and 2.3, respectively. Conclusion In this study, many factors influenced the quality of the transferred slave spectra. And it is hard to provide a pretty good quantitative model transfer result about alkali-soluble polysaccharide in Poria cocos. The following factors have great effects on the quality of model transfer: (i) multiplicative signal correction which is necessary for model building; (ii) increasing the window size which has a positive effect on slave spectra standardization; (iii) a proper wavelength region benefits for model building; (iv) a proper scale of standardization group including proper samples is necessary.

Strategies for noise reduction and standardization of milk mid-infrared spectra from dairy cattle

The use of Fourier-transform mid-infrared (FTIR) spectroscopy is of interest to the dairy industry worldwide for predicting milk composition and other novel traits that are difficult or expensive to measure directly. Although there are many valuable applications for FTIR spectra, noise from differences in spectral responses between instruments is problematic because it reduces prediction accuracy if ignored. The purpose of this study was to develop strategies to reduce the impact of noise and to compare methods for standardizing FTIR spectra in order to reduce between-instrument variability in multiple-instrument networks. Noise levels in bands of the infrared spectrum caused by the water content of milk were characterized, and a method for identifying and removing outliers was developed. Two standardization methods were assessed and compared: piecewise direct standardization (PDS), which related spectra on a primary instrument to spectra on 5 other (secondary) instruments using identical milk-based reference samples (n = 918) analyzed across the 6 instruments; and retroactive percentile standardization (RPS), whereby percentiles of observed spectra from routine milk test samples (n = 2,044,094) were used to map and exploit primary- and secondary-instrument relationships. Different applications of each method were studied to determine the optimal way to implement each method across time. Industry-standard predictions of milk components from 2,044,094 spectra records were regressed against predictions from spectra before and after standardization using PDS or RPS. The PDS approach resulted in an overall decrease in root mean square error between industry-standard predictions and predictions from spectra from 0.190 to 0.071 g/100 mL for fat, from 0.129 to 0.055 g/100 mL for protein, and from 0.143 to 0.088 g/100 mL for lactose. Reductions in prediction error for RPS were similar but less consistent than those for PDS across time, but similar reductions were achieved when PDS coefficients were updated monthly and separate primary instruments were assigned for the North and South Islands of New Zealand. We demonstrated that the PDS approach is the most consistent method to reduce prediction errors across time. We also showed that the RPS approach is sensitive to shifts in milk composition but can be used to reduce prediction errors, provided that secondary-instrument spectra are standardized to a primary instrument with samples of broadly equivalent milk composition. Appropriate implementation of either of these approaches will improve the quality of predictions based on FTIR spectra for various downstream applications.

Improved calibration transfer between near-Infrared (NIR) spectrometers using canonical correlation analysis

The application of mobile near-infrared (NIR) spectrometers in field measurements is growing. Calibration transfer techniques offer simple solutions for enabling models constructed on benchtop instruments for use on mobile spectrometers. Since different types of spectrometers with different components, scanning ranges and resolutions cause great differences in the spectral response, calibration transfer is difficult to apply. In this paper, we focus on calibration transfer among benchtop, portable and handheld spectrometers by a method of calibration transfer based on canonical correlation analysis (CTCCA). Its capability was illustrated by the example of a group of NIR spectra dataset for predicting reducing sugars, total sugar, and nicotine contents in tobacco leaves. The experimental results showed that the transferability of CTCCA was superior to other conventional calibration transfer methods, including piecewise direct standardization, spectral space transformation, calibration transfer based on independent component analysis, and calibration transfer based on the weight matrix. Moreover, the best transfer results were obtained in the three cases by canonical correlation analysis method executing transfer while the spectra were not interpolated, which shows that this approach has the advantage of easy implementation for calibration transfer. Therefore, CTCCA without interpolation calculation offers a new and simple solution for transferring the spectra acquired by mobile spectrometers to the optimized spectral models built on benchtop devices to improve the accuracy of the results. Additionally, the results show that the benchtop spectrometer is more suitable as the master instrument for calibration transfer with more accurate prediction than using a portable device as the master.

Standardization of complex biologically derived spectrochemical datasets.

Spectroscopic techniques such as Fourier-transform infrared (FTIR) spectroscopy are used to study interactions of light with biological materials. This interaction forms the basis of many analytical assays used in disease screening/diagnosis, microbiological studies, and forensic/environmental investigations. Advantages of spectrochemical analysis are its low cost, minimal sample preparation, non-destructive nature and substantially accurate results. However, an urgent need exists for repetition and validation of these methods in large-scale studies and across different research groups, which would bring the method closer to clinical and/or industrial implementation. For this to succeed, it is important to understand and reduce the effect of random spectral alterations caused by inter-individual, inter-instrument and/or inter-laboratory variations, such as variations in air humidity and CO2 levels, and aging of instrument parts. Thus, it is evident that spectral standardization is critical to the widespread adoption of these spectrochemical technologies. By using calibration transfer procedures, in which the spectral response of a secondary instrument is standardized to resemble the spectral response of a primary instrument, different sources of variation can be normalized into a single model using computational-based methods, such as direct standardization (DS) and piecewise direct standardization (PDS); therefore, measurements performed under different conditions can generate the same result, eliminating the need for a full recalibration. Here, we have constructed a protocol for model standardization using different transfer technologies described for FTIR spectrochemical applications. This is a critical step toward the construction of a practical spectrochemical analysis model for daily routine analysis, where uncertain and random variations are present.

PLS Subspace-Based Calibration Transfer for Near-Infrared Spectroscopy Quantitative Analysis.

In order to enable the calibration model to be effectively transferred among multiple instruments and correct the differences between the spectra measured by different instruments, a new feature transfer model based on partial least squares regression (PLS) subspace (PLSCT) is proposed in this paper. Firstly, the PLS model of the master instrument is built, meanwhile a PLS subspace is constructed by the feature vectors. Then the master spectra and the slave spectra are projected into the PLS subspace, and the features of the spectra are also extracted at the same time. In the subspace, the pseudo predicted feature of the slave spectra is transferred by the ordinary least squares method so that it matches the predicted feature of the master spectra. Finally, a feature transfer relationship model is constructed through the feature transfer of the PLS subspace. This PLS-based subspace transfer provides an efficient method for performing calibration transfer with only a small number of standard samples. The performance of the PLSCT was compared and assessed with slope and bias correction (SBC), piecewise direct standardization (PDS), calibration transfer method based on canonical correlation analysis (CCACT), generalized least squares (GLSW), multiplicative signal correction (MSC) methods in three real datasets, statistically tested by the Wilcoxon signed rank test. The obtained experimental results indicate that PLSCT method based on the PLS subspace is more stable and can acquire more accurate prediction results.

High-performance organized media-enhanced spectrofluorimetric determination of pirimiphos-methyl in maize.

A novel method for the determination of pirimiphos-methyl (PMM) in maize grains by fluorescence spectroscopy and three-way calibration was developed. The formation of supramolecular complexes and their effect on the luminescence properties of PMM were studied. A solvent extraction step followed by solid phase extraction for sample clean-up was optimized. A chemometric approach consisting in PARAFAC as second-order data processing tool and piecewise direct standardization (PDS) for reducing the complexity of the calibration process was developed to overcome the matrix effect. This strategy allowed dealing with the matrix effect while reducing the number of samples to be processed and, consequently, the solvent consumption and the total analysis time. Finally, three-way calibration was applied to predict the PMM concentration in unknown samples. The mean recovery was 115% and the limits of detection and quantitation were in the order of the parts per trillion, i.e. 6 and 20 ng g-1, respectively.

Calibration Transfer of Soil Total Carbon and Total Nitrogen between Two Different Types of Soils Based on Visible-Near-Infrared Reflectance Spectroscopy

Although visible-near-infrared spectroscopy can rapidly and accurately determine soil nutrients without sample destruction, some problems remain unresolved, such as the mismatch of the established spectral model with different types of samples, limiting the wide application of this technology. Here, we took riverside and mountain soils as examples to explore the calibration transfer between two different types of soils by the WMPDS-S/B algorithm (wavelet multiscale piecewise direct standardization combined with Slope/Bias correction method) and by adding new samples. The predicted TN and TC concentrations improved significantly after being transformed. Compared with adding new samples, the WMPDS-S/B algorithm obtained more accurate results. The average relative errors dropped from 440.2% (without transformation) to approximately 6% for TN and from 342.0% to approximately 7% for TC. The maximum relative errors were reduced from 538.1% to less than 20% for TN and from 403.7% to less than 20% for TC. The RMSEP decreased from 2.42 to approximately 0.04 for TN and from 15.74 to approximately 0.4 for TC. The WMPDS-S/B algorithm had advantages in selecting fewer known samples and obtaining better prediction results. In contrast to past studies, which resolved the calibration transfer between different spectrometers and the measurement environment for the same samples, our study resolved the calibration transfer between different types of samples under the same spectrometer and the measurement environment. The former could only be used for correction among instruments, while the latter fundamentally solved the problem of model sharing across different samples.

Screening wavelengths with consistent and stable signals to realize calibration model transfer of near infrared spectra.

Measurement environmental changes and spectral signal differences among multi-spectrometers may lead to big error in the process of transferring the model of near infrared (NIR) spectra to secondary instruments. Basing on the common sense, NIR calibration models could be shared directily among multi-instruments, if they were built on the wavelengths at which the spectral signals of secondary instruments are stable and well consistent with the primary's. Present work advanced a method named as screening wavelengths with consistent and stable signals (SWCSS) to transfer NIR calibration models. It eliminates the wavelengths at which the standard deviation of difference spectra between the primary and secondary instruments (SDDSI) is much higher than the standard deviation of precision detection spectra (SDPDS) of a sample tested on the primary and the wavelengths with higher SDPDS values. So that the spectral signals of different instruments at these selected wavelengths are consistent well and stable. The NIR calibration model is built by partial least square regression (PLS) based on the screened wavelengths. Two datasets of corn and radix scutellariae samples measured with different NIR instruments are used to test the performance of the method. The results show that the overall prediction performance of the SWCSS-PLS models for samples measured on secondaries is much better than that of the full-wavelength PLS models. The root mean square of error prediction (RMSEP) of the SWCSS-PLS models for samples tested on secondaries is equivalent or superior to that of the piecewise direct standardization (PDS) correction. The SWCSS-PLS model is of fewer parameters, robust and can give good prediction results for samples of secondary instruments. Because standard samples are no longer needed during transferring the calibration models to secondary instruments, SWCSS-PLS models could be directly shared by multi-spectroscopy instruments.

Direct calibration transfer to principal components via canonical correlation analysis

In order to solve the calibration transfer problem in near-infrared (NIR) spectroscopy, a fast and efficient method named principal components canonical correlation analysis (PC-CCA) has been proposed. PC-CCA can extract principal components of spectra from slave instrument with principal component analysis (PCA), and then transfer the slave principal components toward latent variables of partial least squares (PLS) model with canonical correlation analysis directly. Two NIR datasets of corn and tobacco samples measured with three and two spectrometers, respectively, were used to test the reliability of this method. The piecewise direct standardization (PDS), spectral space transformation (SST) and calibration transfer method based on canonical correlation analysis (CTCCA) methods were performed for comparative study of the proposed model transfer technique. The results of both datasets reveal that PC-CCA can drastically reduce time of transfer and lead to dozens-fold speedup. It can also reduce prediction errors and achieve the smallest root mean square errors of prediction (RMSEPs). For example, the spectra transfer from M5 to MP5, the comparative experiment results show that RMSEP with the proposed method PC-CCA is reduced from 2.5641 (without transfer) to 0.0934, and much smaller than that with PDS (0.1999), CTCCA (0.1377) and SST (0.1296) at N = 50. These advantages make PC-CCA a promising calibration transfer method in NIR application.

A quick method based on SIMPLISMA-KPLS for simultaneously selecting outlier samples and informative samples for model standardization in near infrared spectroscopy

A novel method based on SIMPLe-to-use Interactive Self-modeling Mixture Analysis (SIMPLISMA) and Kernel Partial Least Square (KPLS), named as SIMPLISMA-KPLS, is proposed in this paper for selection of outlier samples and informative samples simultaneously. It is a quick algorithm used to model standardization (or named as model transfer) in near infrared (NIR) spectroscopy. The NIR experiment data of the corn for analysis of the protein content is introduced to evaluate the proposed method. Piecewise direct standardization (PDS) is employed in model transfer. And the comparison of SIMPLISMA-PDS-KPLS and KS-PDS-KPLS is given in this research by discussion of the prediction accuracy of protein content and calculation speed of each algorithm. The conclusions include that SIMPLISMA-KPLS can be utilized as an alternative sample selection method for model transfer. Although it has similar accuracy to Kennard–Stone (KS), it is different from KS as it employs concentration information in selection program. This means that it ensures analyte information is involved in analysis, and the spectra (X) of the selected samples is interrelated with concentration (y). And it can be used for outlier sample elimination simultaneously by validation of calibration. According to the statistical data results of running time, it is clear that the sample selection process is more rapid when using KPLS. The quick algorithm of SIMPLISMA-KPLS is beneficial to improve the speed of online measurement using NIR spectroscopy.

Sampling Error Profile Analysis for calibration transfer in multivariate calibration

A new strategy named Sampling Error Profile Analysis (SEPA) is proposed in the optimization for some parameters in piecewise direct standardization (PDS), such as the number of principal components and window size, and the evaluation for the calibration transfer. Partial least squares (PLS) with mean-centering is used in PDS for calibration transfer. Random re-sampling is carried out in SEPA to obtain a series of subsets and build same number sub-models that produce corresponding number root mean square errors (RMSE), of which the mean value and standard deviation are calculated. To take both accuracy and stability into account, the sum of the mean value and standard deviation are used for parameter optimization and model evaluation. The performance of the proposed strategy has been tested on two data sets: a ternary mixture dataset and a corn dataset. Compared with PDS, SEPA-PDS obtained lower prediction errors, indicating that the transfer model would be more robust and effective when using the parameters optimized by SEPA. Compared with other two commonly used calibration transfer methods of slope and bias correction (SBC) and spectral space transformation (SST), SEPA-PDS acquired more satisfactory results.

Calibration Transfer from Micro NIR Spectrometer to Hyperspectral Imaging: a Case Study on Predicting Soluble Solids Content of Bananito Fruit (Musa acuminata)

Calibration transfer from a handheld micro NIR spectrometer (NIR-point, 939–1602 nm, 6.2 nm) to a desktop hyperspectral imaging (NIR-HSI) for predicting soluble solids content (SSC) of bananito flesh was investigated in the study. Different spectral pre-processing and standardization methods were employed for correcting spectra so as to minimise spectral differences between NIR-point and NIR-HSI. Results show that application of standard normal variate (SNV) reduced spectral differences from 31.49 to 8.96%. The best standardization method was developed based on piecewise direct standardization (PDS) algorithm using ten transfer samples. The developed PLS model yielded a high prediction performance (R 2 p = 0.922 and RMSEP = 1.451%) for predicting SSC of validation samples using the NIR-point spectra. After SNV and standardization, the model was successfully transferred to NIR-HSI data, giving a comparable prediction accuracy of R 2 p = 0.925 and RMSEP = 1.592%. The results illustrated the potential of transferring calibration models from a simple and easy-available micro NIR spectrometer to a more expensive and sophisticated hyperspectral imaging system, when the spatial distribution of quality information is required.

Standardization of milk mid-infrared spectrometers for the transfer and use of multiple models

An increasing number of models are being developed to provide information from milk Fourier transform mid-infrared (FT-MIR) spectra on fine milk composition, technological properties of milk, or even cows' physiological status. In this context, and to take advantage of these existing models, the purpose of this work was to evaluate whether a spectral standardization method can enable the use of multiple equations within a network of different FT-MIR spectrometers. The piecewise direct standardization method was used, matching "slave" instruments to a common reference, the "master." The effect of standardization on network reproducibility was assessed on 66 instruments from 3 different brands by comparing the spectral variability of the slaves and the master with and without standardization. With standardization, the global Mahalanobis distance from the slave spectra to the master spectra was reduced on average from 2,655.9 to 14.3, representing a significant reduction of noninformative spectral variability. The transfer of models from instrument to instrument was tested using 3 FT-MIR models predicting (1) the quantity of daily methane emitted by dairy cows, (2) the concentration of polyunsaturated fatty acids in milk, and (3) the fresh cheese yield. The differences, in terms of root mean squared error, between master predictions and slave predictions were reduced after standardization on average from 103 to 17 g/d, from 0.0315 to 0.0045 g/100 mL of milk, and from 2.55 to 0.49 g of curd/100 g of milk, respectively. For all the models, standard deviations of predictions among all the instruments were also reduced by 5.11 times for methane, 5.01 times for polyunsaturated fatty acids, and 7.05 times for fresh cheese yield, showing an improvement of prediction reproducibility within the network. Regarding the results obtained, spectral standardization allows the transfer and use of multiple models on all instruments as well as the improvement of spectral and prediction reproducibility within the network. The method makes the models universal, thereby offering opportunities for data exchange and the creation and use of common robust models at an international level to provide more information to the dairy sector from direct analysis of milk.

Calibration transfer of a Raman spectroscopic quantification method for the assessment of liquid detergent compositions between two at-line instruments installed at two liquid detergent production plants

Calibration transfer of partial least squares (PLS) quantification models is established between two Raman spectrometers located at two liquid detergent production plants. As full recalibration of existing calibration models is time-consuming, labour-intensive and costly, it is investigated whether the use of mathematical correction methods requiring only a handful of standardization samples can overcome the dissimilarities in spectral response observed between both measurement systems. Univariate and multivariate standardization approaches are investigated, ranging from simple slope/bias correction (SBC), local centring (LC) and single wavelength standardization (SWS) to more complex direct standardization (DS) and piecewise direct standardization (PDS). The results of these five calibration transfer methods are compared reciprocally, as well as with regard to a full recalibration. Four PLS quantification models, each predicting the concentration of one of the four main ingredients in the studied liquid detergent composition, are aimed at transferring. Accuracy profiles are established from the original and transferred quantification models for validation purposes. A reliable representation of the calibration models performance before and after transfer is thus established, based on β-expectation tolerance intervals. For each transferred model, it is investigated whether every future measurement that will be performed in routine will be close enough to the unknown true value of the sample. From this validation, it is concluded that instrument standardization is successful for three out of four investigated calibration models using multivariate (DS and PDS) transfer approaches. The fourth transferred PLS model could not be validated over the investigated concentration range, due to a lack of precision of the slave instrument. Comparing these transfer results to a full recalibration on the slave instrument allows comparison of the predictive power of both Raman systems and leads to the formulation of guidelines for further standardization projects. It is concluded that it is essential to evaluate the performance of the slave instrument prior to transfer, even when it is theoretically identical to the master apparatus.

Selection of robust variables for transfer of classification models employing the successive projections algorithm

Multivariate models have been widely used in analytical problems involving quantitative and qualitative analyzes. However, there are cases in which a model is not applicable to spectra of samples obtained under new experimental conditions or in an instrument not involved in the modeling step. A solution to this problem is the transfer of multivariate models, usually performed using standardization of the spectral responses or enhancement of the robustness of the model. This present paper proposes two new criteria for selection of robust variables for classification transfer employing the successive projections algorithm (SPA). These variables are then used to build models based on linear discriminant analysis (LDA) with low sensitivity with respect to the differences between the responses of the instruments involved. For this purpose, transfer samples are included in the calculation of the cost for each subset of variables under consideration. The proposed methods are evaluated for two case studies involving identification of adulteration of extra virgin olive oil (EVOO) and hydrated ethyl alcohol fuel (HEAF) using UV–Vis and NIR spectroscopy, respectively. In both cases, similar or better classification transfer results (obtained for a test set measured on the secondary instrument) employing the two criteria were obtained in comparison with direct standardization (DS) and piecewise direct standardization (PDS). For the UV–Vis data, both proposed criteria achieved the correct classification rate (CCR) of 85%, while the best CCR obtained for the standardization methods was 81% for DS. For the NIR data, 92.5% of CCR was obtained by both criteria as well as DS. The results demonstrated the possibility of using either of the criteria proposed for building robust models as an alternative to the standardization of spectral responses for transfer of classification.

Near-infrared calibration transfer for undried whole maize plant between laboratory and on-site spectrometers

The analysis of the maize plant immediately after harvest is essential in order to check the composition and maturity of the plant to optimise the quality of silage. NIRS calibrations were carried out on chopped maize using three spectrophotometers: a laboratory instrument (FOSS NIRSystems 5000 scanning monochromator, FOSS, Silver Spring, MD) and two versions of new-generation portable instruments (poliSPECNIR, PL1 and PL2). The aim was to verify the quality of the transfer of the calibration curves between FOSS, PL1 and PL2 and between PL1 and PL2, obtained by three methods of spectra processing: pre-processing, piecewise direct standardisation (PDS) and direct standardisation (DS). Seventy-six samples of chopped whole maize plant were scanned with the three instruments and were analysed by wet chemistry for dry matter (DM), ash, crude protein (CP), neutral detergent fibre (NDF), acid detergent fibre (ADF), starch and total sugars, to develop calibration equations. Two more datasets of 15 samples each were used for the standardisation of equations and validation. The calibration transfer obtained, according to the values of R2, standard error of prediction and bias, can be considered satisfactory (0.72 > R2 <0.97) for DM, ash and NDF for both poliSPECNIR, while CP and ADF have shown a good accuracy of prediction (0.78 > R2 <0.82) with PL2. Using FOSS as a master instrument, the choice of method of standardisation varies depending on the slave instrument even though the best results are obtained using PDS with PL2. The most accurate predictions are reached using PDS even when PL1 is the master.

Evaluation of calibration transfer methods using the ATR-FTIR technique to predict density of crude oil

Multivariate calibration combined with infrared technique is an alternative to traditional methods of determination of physicochemical parameters in crude oil. However, a multivariate model can only be applied for the instrument in which the spectra were measured. In case of equipment upkeep or change of instrument, transferring the calibration model is necessary for the new instrumental condition or new instrument. In this study, Fourier transform infrared spectra (FTIR) were measured in the mid-infrared region (MIR) in two different instruments for 96 crude oil samples with API gravity ranging from 11.2 to 54.0. Multivariate calibration models by PLS (Partial Least Squares) and OPLS (Orthogonal Projections to Latent Structures) were developed and forefront techniques in the calibration transfer area were tested, namely SBC (Slope and Bias Correction), DS (Direct Standardization) and PDS (Piecewise Direct Standardization). The OPLS method stands out for not requiring transfer samples, although it compromises the accuracy of prediction. Applying spectra transferred by PDS to the OPLS model resulted in accuracy statistically equal to that of the PLS original model.

Calibration transfer of a Raman spectroscopic quantification method from at-line to in-line assessment of liquid detergent compositions

The industrial production of liquid detergent compositions entails delicate balance of ingredients and process steps. In order to assure high quality and productivity in the manufacturing line, process analytical technology tools such as Raman spectroscopy are to be implemented. Marked chemical specificity, negligible water interference and high robustness are ascribed to this process analytical technique. Previously, at-line calibration models have been developed for determining the concentration levels of the being studied liquid detergents main ingredients from Raman spectra. A strategy is now proposed to transfer such at-line developed regression models to an in-line set-up, allowing real-time dosing control of the liquid detergent composition under production. To mimic in-line manufacturing conditions, liquid detergent compositions are created in a five-liter vessel with an overhead mixer. Raman spectra are continuously acquired by pumping the detergent under production via plastic tubing towards a Raman superhead probe, which is incorporated into a metal frame with a sapphire window facing the detergent fluid. Two at-line developed partial least squares (PLS) models are aimed at transferring, predicting the concentration of surfactant 1 and polymer 2 in the examined liquid detergent composition. A univariate slope/bias correction (SBC) is investigated, next to three well-acknowledged multivariate transformation methods: direct, piecewise and double-window piecewise direct standardization. Transfer is considered successful when the magnitude of the validation sets root mean square error of prediction (RMSEP) is similar to or smaller than the corresponding at-line prediction error. The transferred model offering the most promising outcome is further subjected to an exhaustive statistical evaluation, in order to appraise the applicability of the suggested calibration transfer method. Interval hypothesis tests are thereby performed for method comparison. It is illustrated that the investigated transfer approach yields satisfactory results, provided that the original at-line calibration model is thoroughly validated. Both SBC transfer models return lower RMSEP values than their corresponding original models. The surfactant 1 assay met all relevant evaluation criteria, demonstrating successful transfer to the in-line set-up. The in-line quantification of polymer 2 levels in the liquid detergent composition could not be statistically validated, due to the poorer performance of the at-line model.

Clay content mapping from airborne hyperspectral Vis-NIR data by transferring a laboratory regression model

Visible Near-Infrared (Vis-NIR, 400–2500nm) hyperspectral imaging has proven to be a valuable tool for mapping soil properties over bare soils. To date, most predictive models presented in literature, have been built from calibration databases made up of both Vis-NIR imaging spectra (predictor variables) and soil properties (response variables). Nevertheless, the constitution of such calibration databases is costly both in terms of time and money, as this implies soil sampling over hundreds of pixels of bare soils and physico-chemical soil analysis of these samples. We propose to test the transfer of predictive models built from laboratory database, to Vis-NIR hyperspectral image. Four transfer methods were tested (model updating, Repfile, Transfer by Orthogonal Projection TOP and Piecewise Direct Standardization PDS). Their respective performances were evaluated and compared to those obtained using two other predictive models. The first predictive model was obtained by directly applying a partial least square regression (PLSR) calibrated in laboratory, onto the hyperspectral image. The second model was obtained by applying a PLSR built from Vis-NIR spectra extracted from the hyperspectral image, onto the hyperspectral image. The transferred models are based on the use of standards. Standards were selected in order to (i) take into account or (ii) ignore field soil stratification knowledge. Moreover, the impact of the number of standards used in the transferred models was studied. This approach was tested for clay content prediction over the La Peyne Valley area in Southern France (24km2, in a Mediterranean context) covered by HyMap Vis-NIR airborne data. The results show that 1) applying PLSR model from laboratory spectra to hyperspectral image without calibration transfer, provides poor prediction performances (R2val=0.41, RMSEP=103g/kg), 2) transferring this model from laboratory spectra to hyperspectral image offered good prediction performances (R2test median above 0.5 and RMSEP median below 70g/kg), whatever the transfer method used and from only 15 used standards, and 3) taking into account field soil stratification knowledge in the standards selection improves prediction performances (R2test median above 0.6 and RMSEP median below 60g/kg) whatever the transfer method and from only 10 used standards. Finally, transferring models from the laboratory to a hyperspectral image gave better mapping performances than those obtained using PLSR models built from airborne spectra.

Transfer of multivariate classification models applied to digital images and fluorescence spectroscopy data

This work evaluates the use of transfer of classification models for identifying adulteration of extra virgin olive oil (EVOO) samples involving, separately, two analytical techniques: fluorescence spectroscopy and digital imaging. The chemometric procedures, including development of classification models and application of classification transfer methods, were performed individually for each analytical technique. Methods of direct standardization (DS) and piecewise direct standardization (PDS) were applied to transfer samples sets in order to estimate an adjustment function and apply it to a samples set measured by the secondary instrument. For purposes of comparison, classification models were built based on linear discriminant analysis (LDA) with previous selection of variables by the successive projections algorithm (SPA), and partial least squares discriminant analysis (PLS-DA). The performance of the classification models was evaluated according to the number of errors and correct classification rate (CCR) for the prediction set measured by the secondary instrument. Before standardization, SPA-LDA and PLS-DA models achieved the same CCR using two analytical techniques: 54% for fluorescence emission spectra and 47% for histograms of digital images. After the standardization, a substantial increase of the CCR was observed. For the SPA-LDA models, a CCR of 88% was obtained for the fluorescence emission spectra and 82% for the histograms of the digital images. The PLS-DA classification models reached 85% and 76% of CCR for the fluorescence and imaging data, respectively, after standardization. These results demonstrate the efficiency of standardization procedures applied to multivariate classification models developed from fluorescence spectroscopy and digital images.