Piecewise Direct Standardization Research Articles

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.

Calibration transfer between NIR spectrometers: New proposals and a comparative study

Calibration transfer between near‐infrared (NIR) spectrometers is a subtle issue in chemometrics and process industry. In fact, as even very similar instruments may generate strongly different spectral responses, regression models developed on a first NIR system can rarely be used with spectra collected by a second apparatus. In this work, two novel methods to perform calibration transfer between NIR spectrometers are proposed. Both of them permit to exploit the specific relationships between instruments for imputing new unmeasured spectra, which will be then resorted to for building an improved predictive model, suitable for the analysis of future incoming data. Specifically, the two approaches are based on trimmed scores regression and joint‐Y partial least squares regression, respectively. The performance of these novel strategies will be assessed and compared to that of well‐established techniques such as maximum likelihood principal component analysis and piecewise direct standardisation in two real case studies.

Calibration transfer across near infrared spectrometers for measuring hematocrit in the blood of grazing cattle

For fast diagnosis of anemia for cattle farmed on pastures, portable short wavelength near infrared spectrometer instrument was built, and the feasibility of estimating hematocrit by partial least squares regression modeling was validated in our previous work. As a follow-up, the present study reports calibration transfer from one master instrument to two slave instruments. Different approaches, i.e. making robust models, skew and bias correction, and piecewise direct standardization, were compared. Our results show that making more use of simple models based on appropriate preprocessing, number of latent variables, and wavelength selection, can sometimes be as effective as applying standardization algorithm (e.g. piecewise direct standardization) when tackling the spectral differences between instruments. The importance of a robust model during the process of calibration transfer is shown. Application of standardization such as piecewise direct standardization could be risky when the model to be transferred is not robust enough.

Temperature Compensation by Calibration Transfer for an AC Voltammetric Analyzer of Electroplating Baths

AbstractThe application of methods for mitigating the effects of temperature fluctuations on the analytical performance of an in‐situ DC‐ and AC‐voltammetric sensor employed for electroplating process control in semiconductor manufacturing is presented. This sensor is a part of an automated analytical system capable of predicting concentration values of deliberately‐added bath constituents based on the component‐specific multivariate voltammetric responses. However, these responses include physicochemical phenomena, some of which are strongly dependent on temperature; therefore temperature fluctuations can produce an additional source of variance in the voltammetric responses adversely affecting the accuracy of analyte concentration predictions. Several calibration‐transfer‐based techniques, both discrete and continuous, using Piecewise Direct Standardization and Direct Standardization combined with PCR and PLS analytical models are comparatively validated for temperature compensation using AC voltammetric data for the example of accelerator additive. An extension of implementation of continuous methods for Direct Standardization is proposed along with an introduction of a new hybrid method of Standardization Models.

NIR models for predicting total sugar in tobacco for samples with different physical states

Due to the spectra variation of the inhomogeneous tobacco flakes results the inaccuracy and instability of the near infrared model. This paper presented the strategies of calibration transfer and hybrid modeling for determining total sugar content in tobacco based on the homogeneous powder model. The necessity judgments and acceptance criteria of the calibration transfer were also proposed. Calibration transfer methods include Slope/Bias Correction (S/B), Piecewise Direct Standardization (PDS), double window piecewise direct standardization (DWPDS), and Shenk’s were adopted, a transfer set of 15 samples were chosen for each methods, and the results showed that Shenk’s is the adequate transfer method as only one indicator did not fulfill the acceptance criteria of the transfer. Other methods were all dissatisfied with the acceptance criteria and cannot be applied to the calibration transfer between the tobacco flake and powder. While the hybrid model of adding some flake samples to the powder model achieved preferred prediction ability. The study showed that adding around 10% variation samples caused the average prediction error of total sugar content (range 12.1–37.2%) in flake samples from 7.25% (predicted by a flake model) significantly dropping to 4.98%, even close to the prediction of the same powder samples (4.21%) by the powder model. It will valuable for the promotion of the NIR network and online analysis.

Spectra Transfer Between a Fourier Transform Near-Infrared Laboratory and a Miniaturized Handheld Near-Infrared Spectrometer.

The aim of this contribution is to demonstrate the transfer of spectra that have been measured on two different laboratory Fourier transform near-infrared (FT-NIR) spectrometers to the format of a handheld instrument by measuring only a few samples with both spectrometer types. Thus, despite the extreme differences in spectral range and resolution, spectral data sets that have been collected and quantitative as well as qualitative calibrations that have been developed thereof, respectively, over a long period on a laboratory instrument can be conveniently transferred to the handheld system. Thus, the necessity to prepare completely new calibration samples and the effort required to develop calibration models when changing hardware platforms is minimized. The enabling procedure is based on piecewise direct standardization (PDS) and will be described for the data sets of a quantitative and a qualitative application case study. For this purpose the spectra measured on the FT-NIR laboratory spectrometers were used as "master" data and transferred to the "target" format of the handheld instrument. The quantitative test study refers to transmission spectra of three-component liquid solvent mixtures whereas the qualitative application example encompasses diffuse reflection spectra of six different current polymers. To prove the performance of the transfer procedure for quantitative applications, partial least squares (PLS-1) calibrations were developed for the individual components of the solvent mixtures with spectra transferred from the master to the target instrument and the cross-validation parameters were compared with the corresponding parameters obtained for spectra measured on the master and target instruments, respectively. To test the retention of the discrimination ability of the transferred polymer spectra sets principal component analyses (PCAs) were applied exemplarily for three of the six investigated polymers and their identification was demonstrated by Mahalanobis distance plots for all polymers.

Transfer of multivariate regression models between high-resolution NMR instruments: application to authenticity control of sunflower lecithin.

In recent years the number of spectroscopic studies utilizing multivariate techniques and involving different laboratories has been dramatically increased. In this paper the protocol for calibration transfer of partial least square regression model between high-resolution nuclear magnetic resonance (NMR) spectrometers of different frequencies and equipped with different probes was established. As the test system previously published quantitative model to predict the concentration of blended soy species in sunflower lecithin was used. For multivariate modelling piecewise direct standardization (PDS), direct standardization, and hybrid calibration were employed. PDS showed the best performance for estimating lecithin falsification regarding its vegetable origin resulting in a significant decrease in root mean square error of prediction from 5.0 to 7.3% without standardization to 2.9-3.2% for PDS. Acceptable calibration transfer model was obtained by direct standardization, but this standardization approach introduces unfavourable noise to the spectral data. Hybrid calibration is least recommended for high-resolution NMR data. The sensitivity of instrument transfer methods with respect to the type of spectrometer, the number of samples and the subset selection was also discussed. The study showed the necessity of applying a proper standardization procedure in cases when multivariate model has to be applied to the spectra recorded on a secondary NMR spectrometer even with the same magnetic field strength. Copyright © 2016 John Wiley & Sons, Ltd.

Calibration transfer in temperature modulated gas sensor arrays

Shifts in working temperature are an important issue that prevents the successful transfer of calibration models from one chemical instrument to another. This effect is of special relevance when working with gas sensor arrays modulated in temperature. In this paper, we study the use of multivariate techniques to transfer the calibration model from a temperature modulated gas sensor array to another when a global change of temperature occurs. To do so, we built 12 identical master sensor arrays composed of three different types of commercial Figaro sensors and acquired a dataset of sensor responses to three pure substances (ethanol, acetone and butanone) dosed at 7 concentrations. The master arrays are then shifted in temperature (from −50 to 50°C, ΔT=10°C) and considered as slave arrays. Data correction is performed for an increasing number of transfer samples with 4 different calibration transfer techniques: Direct Standardization, Piece-wise Direct Standardization, Orthogonal Signal Correction and Generalized Least Squares Weighting. In order to evaluate the performance of the calibration transfer, we compare the Root Mean Square Error of Prediction (RMSEP) of master and slave arrays, for each instrument correction. Best results are obtained from Piece-wise Direct standardization, which exhibits the lower RMSEP values after correction for the smaller number of transfer samples.

A new multivariate calibration model transfer method of near-infrared spectral analysis

Near-infrared (NIR) has been successfully applied for rapid and nondestructive analyses in diverse fields, but the issue of calibration model transfer has not been clarified thus far. Typically, the calibration model developed for one instrument cannot be applied directly to other instruments in many cases. To achieve calibration model transfer between the master and slave instruments, an improved piecewise direct standardization designated Rank–Kennard–Stone-PDS (Rank-KS-PDS) is proposed in this paper. An optimal sample selection method (Rank-KS) is proposed to select the transfer samples. The process of sample selection is based simultaneously on the distribution of spectral space and of property space. Thus, the samples selected by Rank-KS have greater representativeness and wider coverage. The Rank-KS-PDS method has been used to predict the alkaloid and glycoside content in tobacco. Comparative studies of calibration model transfer with the proposed method, random selection (RS), and KS have also been performed. For the prediction model of alkaloids, the comparative experiment results have verified the reduction in the number of transfer samples required from 12 to 8 and in the root-mean-square error of prediction (RMSEP) from 0.1440 to 0.1250 with the proposed method. For the prediction model of glycosides, the accuracy of model transfer was found to improve significantly, accompanied by a reduction in RMSEP from 1.6945 to 1.5850 without any increase in the number of transfer samples. With the proposed Rank-KS-PDS method, the selected transfer samples based on one property can be directly applied to the calibration model transfer of other properties with satisfactory results.

Improving Calibration Transfer between Shortwave near Infrared Silicon Photodiode Array Instruments

The use of a model developed on spectra of one (master) instrument with spectra collected using another (slave) instrument requires differences in spectra of master and slave units to be orthogonal to the calibration model. The more spectral similarity is achieved in hardware, i.e. by matching the optical characteristics of the devices, the less chemometric correction is required. The transfer of partial least squares models for total soluble solids (TSS) of intact apple fruit between instrumentation based on silicon photodiode arrays was improved by use of more accurate wavelength assignments over the wavelength range used in the model. Several transfer methodologies were trialled, including piecewise direct standardisation (PDS), transfer by orthogonal projection, model updating (MU) and difference spectrum adjustment. The difference spectrum method combined with new wavelength assignments and MU gave results comparable to the performance of the master instrument and to models directly developed on the slave instruments ( r2 = 0.95, SEP-b = 0.47 and bias = −0.03% TSS, for a population of mean = 14.45 and SD = 1.64% w/v). The use of average difference spectrum adjustment combined with MU was preferred over PDS because of ease of implementation.

Spectrophotometer Ageing and Prediction of Fruit Attributes

Deterioration of lamp output quality over time and degradation of detector signal-to-noise ratio are issues associated with ageing of a spectrophotometer. To document the effect of instrument ageing on short wavelength near infrared spectroscopy-based assessment of internal attributes of fruit quality prediction (total soluble solids, TSS, of juice), an assessment was conducted of several handheld photodiode array-based spectrophotometers over several years, with repeated spectra of a reference Teflon (PTFE) tile and spectra of 20 apple fruit acquired at yearly intervals. The repeatability of each instrument was assessed as the standard deviation of absorbance of repeated measures of a reference, typically around 0.2 mAbs. Instrument changes were identified in performance and in principal components analysis plots, but performance (apple TSS model) was not related to instrument repeatability. A piecewise direct standardisation method is recommended to maintain a multivariate calibration model across spectrometers.

Calibration transfer from powder mixtures to intact tablets: A new use in pharmaceutical analysis for a known tool

Calibration transfer is commonly used for spectra obtained in different spectrometers or other conditions. This paper proposed the use of calibration transfer between spectra recorded for the same samples in different physical forms. A new method was developed for the direct determination of nevirapine in solid pharmaceutical formulations based on diffuse reflectance near infrared spectroscopy (NIRS) and partial least squares (PLS). This method was developed with 50 powder mixtures and then, successfully extended to the quantification in intact tablets by using calibration transfer with double window piecewise direct standardization (DWPDS). This chemometric strategy provided good results with a small number of tablet transfer samples, only seven, prepared out of the narrow range of active principle ingredients (API) content around the nominal value of the formulation (100%). The method was fully validated in the working range of 83.0–113.9% of nevirapine and the use of DWPDS allowed to significantly decreasing the root mean square error of prediction (RMSEP) from 4.8% (tablets predicted by a model built with only powder samples) to 2.6%. The range of relative errors decreased from −5.1/8.7% to −4.6/3.3%. Considering that the amount of raw materials demanded for preparing tablets is up to ten times higher than for powder mixtures, this type of application is of particular interest in pharmaceutical analysis. In the context of process analytical technology (PAT), the use of the same multivariate model in different steps of the production is very advantageous, saving time and labor.

Standardization of near infrared spectra based on multi-task learning

ABSTRACTIn order to model the near infrared spectral difference between two instruments, this paper presents an approach based on multi-task learning for multivariate instrument standardization. A multi-task learning approach using trace norm regularization is employed to estimate the transformation matrix in direct standardization, and then is extended to the construction of the nonlinear transformation. The proposed approach is compared with the piecewise direct standardization (PDS) on two real data sets. Experimental results show that the proposed approach sometimes outperforms the conventional PDS method, and the multi-task learning method can be a promising way to overcome the over-fitting problem existing in direct standardization.

Solving signal instability to maintain the second-order advantage in the resolution and determination of multi-analytes in complex systems by modeling liquid chromatography–mass spectrometry data using alternating trilinear decomposition method assisted with piecewise direct standardization

The application of calibration transfer methods has been successful in combination with near-infrared spectroscopy or other tools for prediction of chemical composition. One of the developed methods that can provide accurate performances is the piecewise direct standardization (PDS) method, which in this paper is firstly applied to transfer from one day to another the second-order calibration model based on alternating trilinear decomposition (ATLD) method built for the interference-free resolution and determination of multi-analytes in complex systems by liquid chromatography–mass spectrometry (LC–MS) in full scan mode. This is an example of LC–MS analysis in which interferences have been found, making necessary the use of second-order calibration because of its capacity for modeling this phenomenon, which implies analytes of interest can be resolved and quantified even in the presence of overlapped peaks and unknown interferences. Once the second-order calibration model based on ATLD method was built, the calibration transfer was conducted to compensate for the signal instability of LC–MS instrument over time. This allows one to reduce the volume of the heavy works for complete recalibration which is necessary for later accurate determinations. The root-mean-square error of prediction (RMSEP) and average recovery were used to evaluate the performances of the proposed strategy. Results showed that the number of calibration samples used on the real LC–MS data was reduced by using the PDS method from 11 to 3 while producing comparable RMSEP values and recovery values that were statistically the same (F-test, 95% confidence level) to those obtained with 11 calibration samples. This methodology is in accordance with the highly recommended green analytical chemistry principles, since it can reduce the experimental efforts and cost with regard to the use of a new calibration model built in modified conditions.

Improving the transfer ability of prediction models for electronic noses

Calibration transfer is attracting more and more attention in the field of electronic noses (e-noses). It aims at making the prediction model trained on one device transferable to other devices, which is important for the large-scale deployment of e-noses, especially when the cost of sample collection is high. In this paper, the transfer ability of prediction models is improved in two steps. First, windowed piecewise direct standardization (WPDS) is used to standardize the slave device, i.e. to transform the variables from the slave device to match the master one. Then, data from the master device are used to develop prediction models with a novel strategy named standardization error based model improvement (SEMI). Finally, the standardized slave data can be predicted by the models with a better accuracy. The proposed WPDS is a generalization of the widely used PDS algorithm. The main idea of SEMI is to make the trained models rely more on variables with small standardization errors, thus less sensitive to the inconsistency of the devices. It links the standardization step and the prediction step. To evaluate the algorithms, three e-noses specialized for breath analysis are adopted to collect a dataset, which contains pure chemicals and breath samples. Experiments show that WPDS outperforms previous methods in the sense of standardization error and prediction accuracy; SEMI consistently enhances the accuracy of the master model applied to standardized slave data. This study provides effective and extensible methods for model transfer of e-noses.