Partial Least Squares Algorithm Research Articles

Effect of Green Supply Chain Management Practices on Environmental Performance: Case of Mexican Manufacturing Companies

Managers implement several Green Supply Chain Management (GSCM) practices to improve sustainability and economic performance, such as environmental management systems (EMS), eco-design (ED), source reduction (SR) and attending to external environmental management (EEM) requirements; however, the relationship among them requires a deep study. This paper reports the case of the Mexican maquiladora industry, analyzing the main relationships among GSCM practices with environmental impact (EI) and environmental cost savings (ECS). The analysis reports three structural equation models (SEM) developed as simple, second-order, and mediating models. Those relationships are tested using 160 responses to a survey applied to the Mexican maquiladora industry and with partial least squares algorithms (PLS), where conditional probabilities for different scenarios in latent variables are also reported. Findings indicate that EMS has a direct effect on EI (β = 0.442) and ECS (β = 0.227), indicating that EMS reduces EI and cost associated with the production process; however, ED has no direct effect on EI (β = 0.019) and ECS ((β = 0.006), and it can be due to the maquiladora nature as foreign companies focused on manufacturing and not to product design.

Distributed Measurement-Based Optimal DER Dispatch With Estimated Sensitivity Models

This paper presents a distributed measurement-based method to determine distributed energy resource (DER) active-and reactive-power setpoints that minimize bus voltage deviations from prescribed references, bus active-and reactive-power deviations from desired values, as well as cost of DER outputs. The proposed method partitions the system into multiple areas and performs per-area computations in parallel, thus mitigating scalability concerns of centralized implementations. A linear sensitivity model for each area is first estimated from measurements via the recursive weighted partial least-squares algorithm. The estimated sensitivity models are then embedded in an optimization problem, the structure of which is amenable to decomposition into per-area subproblems. The subproblems are solved in parallel using consensus-based alternating direction method of multipliers to obtain optimal DER setpoints. Both the estimation and optimization tasks require only the exchange of information at boundary buses among adjacent areas. Numerical simulations involving the IEEE 33-bus distribution test system illustrate the ability of the proposed method to determine optimal DER setpoints that adapt to operating-point changes in a distributed fashion. Additional numerical simulations involving the IEEE 123-bus system demonstrate computational scalability and the application to multi-phase systems in a practical scenario.

Monitoring of Nitrogen Indices in Wheat Leaves Based on the Integration of Spectral and Canopy Structure Information

Canopy spectral reflectance can indicate both crop nutrient and canopy structural information. Differences in canopy structure can affect spectral reflectance. However, a non-imaging spectrometer cannot distinguish such differences while monitoring crop nutrients, because the results are likely to be influenced by the canopy structure. In addition, nitrogen application rate is one of the main factors influencing the canopy structure of crops. Strong correlations exist between indices of canopy structure and leaf nitrogen, and thus, these can be used to compensate for the spectral monitoring of nitrogen content in wheat leaves. In this study, canopy structural indices (CSI) such as wheat coverage, height, and textural features were obtained based on the RGB and height images obtained by the RGB-D camera. Moreover, canopy spectral reflectance was obtained by an ASD hyperspectral spectrometer, based on which two vegetation indices—ratio vegetation index (RVI) and angular insensitivity vegetation index (AIVI)—were constructed. With the vegetation indices and CSIs as input parameters, a model was established to predict the leaf nitrogen content (LNC) and leaf nitrogen accumulation (LNA) of wheat based on partial least squares (PLS) and random forest (RF) regression algorithms. The results showed that the RF model with RVI and CSI as inputs had the highest prediction accuracy for LNA, the coefficient of determination (R2) reached 0.79, and the root mean square error (RMSE) was 1.54 g/m2. The vegetation indices and coverage were relatively important features in the model. In addition, the PLS model with AIVI and CSI as input parameters had the highest prediction accuracy for LNC, with an R2 of 0.78 and an RMSE of 0.35%, among the vegetation indices. In addition, parts of both the textural and height features were important. The results suggested that PLS and RF regression algorithms can effectively integrate spectral and canopy structural information, and canopy structural information effectively supplement spectral information by improving the prediction accuracy of vegetation indices for LNA and LNC.

Spatial mapping Zataria multiflora using different machine-learning algorithms

Understanding the relationships between environmental factors that influence the distribution of medicinal plants is crucial to identifying suitable habitats for them. Studies have shown that the responses of such species to environmental influences is unclear. A region known as one of the most important areas for Zataria multiflora is Fars Province in southwestern Iran. This study determines the importance of 13 environmental factors (elevation, distance from rivers, distance from roads, pH, electrical conductivity, mean annual temperature, mean annual rainfall, slope angle, slope aspect, plan curvature, and soil properties) to the distribution of Zataria multiflora. The suitable habitats for Zataria multiflora are distinguished by the species-variable relationships and the application of five machine-learning techniques (MLTs): generalized linear model (GLM), generalized boosting model (GBM), boosted regression tree (BRT), functional discrimination analysis (FDA), and mixture discriminant analysis (MDA). The partial least-squares algorithm was used to determine the rank of importance of each variable. The results reveal that the most important factors influencing Zataria multiflora distribution are slope, elevation, EC, and mean annual temperature. The MLTs were applied, and the predictions were classified into four classes (very high, high, moderate, and low). Results indicate that the region of low habitat suitability is in the central portion of the study area and the percentages of the study area classified as having low potential are: 62.01% for GLM, 74.51% for MDA, 63.56% for FDA, 70.14% for GBM, and 23.19% for BRT. The models accuracies as indicated by AUC are MDA (93.6%), GBM (90.3%), GLM (89.1%), FDM (88.1%), and (83.4%). Modeling of habitat suitability can improve farmers’ and managers’ decisions regarding the protection of medicinal plants.

Rapid determination of tea polyphenols content in Qingzhuan tea based on near infrared spectroscopy in conjunction with three different PLS algorithms

Tea polyphenols are one of the most important ingredients in Qingzhuan tea. Usually, a chemical method is used to determine tea polyphenols content, but it was time-consuming and laborious. This paper attempted to use near infrared spectroscopy (NIRS) technology combined with three partial least squares methods to predict tea polyphenols content quickly and nondestructively. The partial least squares (PLS), synergy interval PLS (siPLS) and genetic algorithm based PLS (gaPLS) were used to establish prediction models, the performance of the final model was showed by root mean square error of prediction (RMSEP) and determination coefficient (Rp2) in prediction set. The best spectral preprocessing method was multivariate scattering correction (MSC); the RMSEP and Rp2 of PLS model were 0.145% and 0.8974, respectively; the siPLS model was established with four spectral regions (4377.6 cm-1-4751.7 cm-1, 4755.6 cm-1-5129.7 cm-1, 6262.7 cm-1-6633.9 cm-1 and 7386 cm-1-7756.3 cm-1), whose RMSEP and Rp2 were 0.0652% and 0.9235, respectively; the gaPLS model was established with 36 spectra dada points and showed the best performance (RMSEP=0.0624%, Rp2=0.9769) compared with the PLS and si-PLS models. Therefore, the application of near infrared technology combined with the gaPLS method could predict tea polyphenols content in Qingzhuan tea more accurately and rapidly.

UV-VIS spectrophotometric-assisted chemometric calibration models for simultaneous determination of thiamine and pyridoxine vitamins in powdered infant formula

Thiamine and pyridoxine, which are hydrophilic B vitamins, are compounds that play an important role in many biochemical events for the health of infants and adults. Recently, because of the complexity of food and pharmaceutical composition, chemometric models are preferred to obtain relevant information from multivariate measured data. The aim of this study was to determine the simultaneous quantitative analysis of thiamine and pyridoxine in powdered infant formula and pharmaceutical formulations by the UV-visible spectrophotometric method coupled with chemometric calibration models (partial least squares (PLS) and principal component regression (PCR)). These vitamins were extracted by addition of trichloroacetic acid (precipitation of proteins) after samples of powdered infant formula was dissolved in Milli-Q water. Factorial design was used to prepare the calibration (25 samples) and validation (8 samples) sets containing mixture of thiamine and pyridoxine within their linear range (2.5-25 μg/mL). Spectra of obtained mixtures and samples were recorded between wavelengths of 200-360 nm with the intervals Δλ=1 nm. In regression models created by using PLS and PCR algorithm, the results had acceptable recovery 98.14% for both compounds. These chemometric models predict the quantification of both, thiamine and pyridoxine in powdered infant formula samples via interpreting the UV-Vis spectrum. The average thiamine and pyridoxine contents of powdered infant formula samples were found to be 5.02±0.065 μg/g and 4.32±0.086 μg/g for PLS model and 4.98±0.078 μg/g and 4.03±0.091 μg/g for PCR model, respectively.

IPLSL and IPLSQ: Two types of imputation PLS algorithms for hierarchical latent variable model

In many applications of hierarchical latent variable model, manifest variables could be missing due to various reasons. Improper missing data techniques or data imputation algorithms may lead to incredible data sets and inaccurate estimates. In our paper, we propose two types of imputation partial least square (PLS) algorithms to deal with missing data problems in hierarchical latent variable model. One is the imputation PLS algorithms based on linear regression (IPLSL), the other is the imputation PLS algorithms based on quantile regression (IPLSQ). In IPLSL, we apply the idea of complete case analysis (CC), inverse probability weighting (IPW) and fractional imputation (FI) to one kind of PLS algorithm which is different from the existing repeated indicators approach, two-step approach and hybrid approach. In IPLSQ, we also apply CC, IPW and FI to a modified PLS algorithm based on quantile regression. Compared with IPLSL, IPLSQ has the advantages in capturing overall view of structural relationships at different quantiles and highlighting the changing relations according to the explored quantile of interest. Together with mean and median imputation, we investigate the performances of our IPLSL and IPLSQ algorithms through simulation studies and then apply them to national science and technology innovation capability study based on part of World Bank database and Global Innovation Index report.

In-line monitoring of the application weight of an adhesion promoter and the residual moisture content in textile finishing by hyperspectral imaging using a NIR camera

Hyperspectral imaging was used for monitoring of both the application weight of an adhesion promoter for rubber applied to a polyester fabric by impregnation and the residual moisture in the fabric after drying at the end of the finishing process. A NIR camera with a spectral range from 1320 to 1900 nm was used for imaging. Quantitative data were derived from the spectra by chemometric methods using partial least squares (PLS) regression. Reference data for calibration and validation were determined by gravimetry. The root mean square errors of prediction (RMSEP) for the application weight and the moisture content were found to be 1.2 g/m² (for a probed range up to 25 g/m²) and 0.34 wt% (for water contents up to 10 wt%), respectively. Moreover, nonuniformities in both application weight and drying could be clearly uncovered. Mean values for application weight and moisture content obtained by averaging of the individual predictions from all pixels of each spectral image were found to show excellent correlation with the corresponding reference values from gravimetry. The results reveal that hyperspectral imaging with a NIR camera in combination with the PLS algorithm and adequate calibration is able to provide data with sufficient precision for in-line monitoring of both technical parameters and confirm the efficiency of this analytical approach for process control in technical textile converting.

Partial Least Square (PLS) Analysis

Partial least square (PLS) analysis is the most favourite tool in chemometrics to develop calibration models. PLS technique allows us to decipher even the complex systems by analysing all the variables instead of looking at them one at a time. PLS technique not only capture the maximum variation associated with predictor (i.e. spectra) and predicted (i.e. concentration) variables but also maximises the correlation between them. The present article describes the working scheme of the PLS algorithm. It also describes important technical details that need to be considered for developing a parsimonious and robust calibration model.

Quick assessment of chicken spoilage based on hyperspectral NIR spectra combined with partial least squares regression

Pseudomonas spp. and Enterobacteriaceae are dominant spoilage bacteria in chicken during cold storage (0°C-4°C). In this study, high resolution spectra in the range of 900-1700 nm were acquired and preprocessed using Savitzky-Golay convolution smoothing (SGCS), standard normal variate (SNV) and multiplicative scatter correction (MSC), respectively, and then mined using partial least squares (PLS) algorithm to relate to the total counts of Pseudomonas spp. and Enterobacteriaceae (PEC) of fresh chicken breasts to predict PEC rapidly. The results showed that with full 900-1700 nm range wavelength, MSC-PLS model built with MSC spectra performed better than PLS models with other spectra (RAW-PLS, SGCS-PLS, SNV-PLS), with correlation coefficient (RP) of 0.954, root mean square error of prediction (RMSEP) of 0.396 log10 CFU/g and residual predictive deviation (RPD) of 3.33 in prediction set. Based on the 12 optimal wavelengths (902.2 nm, 905.5 nm, 923.6 nm, 938.4 nm, 946.7 nm, 1025.7 nm, 1124.4 nm, 1211.6 nm, 1269.2 nm, 1653.7 nm, 1691.8 nm and 1693.4 nm) selected from MSC spectra by successive projections algorithm (SPA), SPA-MSC-PLS model had RP of 0.954, RMSEP of 0.397 log10 CFU/g and RPD of 3.32, similar to MSC-PLS model. The overall study indicated that NIR spectra combined with PLS algorithm could be used to detect the PEC of chicken flesh in a rapid and non-destructive way. Keywords: hyperspectral NIR spectra, chicken, dominant spoilage, partial least squares regression, quick assessment DOI: 10.25165/j.ijabe.20211401.5726 Citation: Jiang S Q, He H J, Ma H J, Chen F S, Xu B C, Liu H, et al. Quick assessment of chicken spoilage based on hyperspectral NIR spectra combined with partial least squares regression. Int J Agric & Biol Eng, 2021; 14(1): 243–250.

Metabolomics-based profiling with chemometric approach to identify bioactive compounds in Salacca zalacca fruits extracts and in silico molecular docking

Salak (Salacca zalacca) is well-known as snake fruit and it is immensely studied for its antioxidative and antidiabetic active metabolites throughout the southeast Asian countries. However, there are many remaining unidentified metabolites due to very low abundance and natural variation, which need to be further explored. Nowadays mass spectrometry (MS/MS) facilitates the tentative identification of unknown compounds in the crude herbal extracts. This study described the metabolite profiling of hydroalcoholic extracts of S. zalaccaanalysed by LC-QTOF-MS/MS. The 60% ethanolic extract exhibited the highest α-glucosidase inhibition and ferric reducing antioxidant power activities with IC50 of 15.94 µg/mL and 78.13 μg AAE/g, respectively. Multivariate data analysis (MVDA) by an orthogonal partial least-squares (OPLS) algorithm was conducted to correlate the α-glucosidase inhibition activity with the LC- QTOF-MS data. A total of 4 compounds were reported for first time in this fruit and identified based on the molecular mass and fragment ions. LC-QTOF-MS analysis indicated the presence of carexane I, 5-phenoxytetrazol-1-yl)-2,3,5,6-hexahydrofurofuran-3-ethylurea, 3-acetylphenoxy)-N-[(2)-1-amino-4-methyl-1-oxopentan-2-yl]-4,5-dihydroxycyclohexene-1-carboxamide and Ethyl 4-[5-methyl-2-oxo-1′,2′,5′,6′,7′,7′a-hexahydro-1H-spiro[indole-3,3′-pyrrolizine]-2′-ylamido] benzoate. Molecular docking of those compounds with the α–glucosidase enzyme was performed to confirm their antidiabetic potential. These bioactive compounds could be suggested as α-glucosidase inhibitors and functional food additives.

Fast assay of ethyl acetate content of double-base oblate spherical propellant after balling process by near-infrared spectroscope

Ethyl acetate (EAC) is commonly used as a solvent in the balling process of double-base oblate spherical propellant (DOSP) because of its excellent performance in swelling. However, the residual content of EAC in the DOSP has an adverse effect on combustion performance of DOSP. Therefore, it is necessary to fast assay the EAC content of DOSP in the production process for avoiding economic loss caused by unqualified products. This work is to investigate the feasibility of using a Fourier transform near-infrared (NIR) spectroscope coupled with partial least squares (PLS) algorithm to construct a quantitative model, which can rapidly monitor the EAC content of DOSP after balling process. In the NIR spectra, two characteristic peaks were observed in the range of 6096–5464 cm−1 and 4824–4524 cm−1, which were employed as modeling intervals for analyzing the content of EAC in DOSP intermediate samples. According to the minimum value of the root mean square error of cross-validation (RMSECV), first derivative and standard normal variate (SNV) were chosen as original spectral preprocessing method, and the optimum number of PLS factors for EAC calibration model was 6. The quantitative EAC model was developed based on PLS algorithm. The determination coefficients of the calibration (RC2) and prediction (RP2) for the developed model were equal to 0.9786 and 0.9883, respectively. The root means square error of calibration and prediction (RMSEC and RMSEP) were 0.0536 and 0.0412, respectively. The residual predictive deviation (RPD) values of calibration and prediction were 6.83 and 10.7, respectively. Using independent samples as prediction set to test robustness of the developed model, and the average deviation between traditional measured values and NIR predicted values was 0.017%. Therefore, the experimental results indicated that the NIR spectroscope can give a fast and accurate analysis the EAC content of DOSP after the balling process.

Multivariate Modeling for Quantifying Adulteration of Sunflower Oil with Low Level of Safflower Oil Using ATR-FTIR, UV-Visible, and Fluorescence Spectroscopies: A Comparative Approach

For the first time, a quick and simple analytical method was developed for the discrimination and the quantification of low level (< 10%) of safflower oil (SAF) in sunflower oil (SUN). Different spectroscopic techniques, such as attenuated total reflectance-Fourier transform infrared (ATR-FTIR), ultraviolet-visible (UV-Vis), and fluorescence (FL), have been used and their abilities to quantify SAF content in SUN were compared using statistical quality parameters of the developed calibration models. To quantify SAF content in SUN samples, partial least squares (PLS) regression (model 1) was used. To correlate SAF in the calibration set with their spectra, 30 multivariate calibration models were built by PLS algorithm. The performance and accuracy of PLS models were evaluated by the value of R-square, root mean square error of calibration (RMSEC), root mean square error of cross-validation (RMSECV), and root mean square error of prediction (RMSEP). To detect SAF adulterations, several principal component analysis (PCA) models (model 2) were utilized. The performance of PCA models developed was evaluated by principal components (PC) percentages, the factor numbers reached, F-Residuals limits, and Hotelling’s T2 limits. Both for the quantify and the discrimination, the best predictions were achieved using normal spectra in FL spectroscopy with the lowest RMSEC of 0.2553, RMSEV of 0.5398, RMSEP of 0.2674, and F-Residuals limit of 0.7040 and with the highest R-square of 0.9937, PC percentages of 69%, the factor numbers of 7, and Hotelling’s T2 limit of 13.3208 in all spectral region.

Rapid quantification of constituents in tobacco by NIR fiber‐optic probe

AbstractThis study aims to develop, evaluate, and optimize the application of near‐infrared spectroscopy (NIR) autosampler device equipped with a fiber‐optic probe associated with chemometric methods for the fast quantification of routine chemical constituents such as total alkaloids, reducing sugars, nitrate, and ammonia in tobacco. For this purpose, an NIR autosampler device with capacity for 40 samples was used. The spectra were collected in the range of 950 to 2,500 nm, with three spins on the sample, a 3.0‐cm2 sample scanning area, and 2.0 ± 0.2 mm distance between the fiber‐optic probe and the sample. Four partial least‐squares (PLS) models were developed, and different preprocessing methods were investigated. The predicted results were compared with those obtained from the reference method (continuous‐flow analysis), and root mean square error of prediction values of 0.31%, 1.27%, 0.47%, and 0.026% were obtained for total alkaloids, reducing sugars, nitrate, and ammonia, respectively. The proposed method performed well for the analysis of total alkaloids and reducing sugars with an appropriate goodness‐of‐fit and fair precision. In conclusion, considering the performance of the regression models and the associated environmental and economic advantages, the application of NIR spectrometer autosampler device equipped with a fiber‐optic probe associated with a PLS and synergy interval PLS algorithms cannot replace the reference method, but it is a promising tool for tobacco monitoring.

Application of a Partial Least Squares Regression Algorithm for Posterior Chamber Phakic Intraocular Lens Sizing and Postoperative Vault Prediction

To develop and validate a new algorithm for predicting the postoperative vault of the myopic EVO Visian Implantable Collamer Lens (ICL) V4c (STAAR Surgical AG). This study included 81 eyes of 43 patients who had undergone ICL implantation. Preoperative data obtained by swept-source optical coherence tomography, Scheimpflug camera, and anterior segment optical coherence tomography were applied to develop a new partial least squares (PLS) regression algorithm. ICL sizing was performed using the standard white-to-white method with the online calculation and ordering system. The postoperative vault was assessed based on anterior segment optical coherence tomography. The PLS approach was applied to create the calibration model for predicting the postoperative vault. The new PLS model was cross-validated using the leave-one-out method and compared to a recently published linear regression model. Agreement between the actual and predicted vault values for the two methods was assessed by the Bland-Altman method. There was a statistically significant correlation (P < .001, r = 0.73) between the postoperative vault values and those predicted by the PLS algorithm. Validation of the PLS model yielded lower mean differences and limits of agreement (0 and 410 µm, respectively) than the linear regression method (400 and 750 µm, respectively). The PLS algorithm increases the precision of ICL vault prediction. However, it shows a tendency to overestimate small vault values and underestimate high vaults. [J Refract Surg. 2020;36(9):606-612.].

Analysis of Chlorophyll Concentration in Potato Crop by Coupling Continuous Wavelet Transform and Spectral Variable Optimization

The analysis of chlorophyll concentration based on spectroscopy has great importance for monitoring the growth state and guiding the precision nitrogen management of potato crops in the field. A suitable data processing and modeling method could improve the stability and accuracy of chlorophyll analysis. To develop such a method, we collected the modelling data by conducting field experiments at the tillering, tuber-formation, tuber-bulking, and tuber-maturity stages in 2018. A chlorophyll analysis model was established using the partial least-square (PLS) algorithm based on original reflectance, standard normal variate reflectance, and wavelet features (WFs) under different decomposition scales (21–210, Scales 1–10), which were optimized by the competitive adaptive reweighted sampling (CARS) algorithm. The performances of various models were compared. The WFs under Scale 3 had the strongest correlation with chlorophyll concentration with a correlation coefficient of −0.82. In the model calibration process, the optimal model was the Scale3-CARS-PLS, which was established based on the sensitive WFs under Scale 3 selected by CARS, with the largest coefficient of determination of calibration set (Rc2) of 0.93 and the smallest Rc2−Rcv2 value of 0.14. In the model validation process, the Scale3-CARS-PLS model had the largest coefficient of determination of validation set (Rv2) of 0.85 and the smallest root–mean–square error of cross-validation (RMSEV) value of 2.77 mg/L, demonstrating good prediction capability of chlorophyll concentration. Finally, the analysis performance of the Scale3-CARS-PLS model was measured using the testing data collected in 2020; the R2 and RMSE values were 0.69 and 3.36 mg/L, showing excellent applicability. Therefore, the Scale3-CARS-PLS model could be used to analyze chlorophyll concentration. This study indicated the best decomposition scale of continuous wavelet transform and provided an important support method for chlorophyll analysis in the potato crops.

Competitive adaptive reweighted sampling assisted partial least square analysis of excitation-emission matrix fluorescence spectroscopic data sets of certain polycyclic aromatic hydrocarbons.

Excitation-emission matrix fluorescence (EEMF) spectroscopy is a simple and sensitive analytical technique. EEMF spectrum is essentially a collection of emission and excitation spectra acquired as increasing functions of excitation and emission wavelengths, respectively. EEMF spectral data sets produced per sample are highly correlated and larger in amount that need the assistance of chemometric techniques such partial least square (PLS) analysis if one desire to build robust calibration model. The objective of the PLS algorithm is to explain maximum variation of the spectral and concentration data matrices and to maximise the correlation between them. The application of a suitable variable selection technique can significantly improve the performance of PLS calibration model. Towards this, the present work proposes application of competitive adaptive reweighted sampling (CARS) as a variable selection approach prior to PLS analysis of EEMF spectral data sets. The utility of proposed approach was successfully demonstrated by analysing the significantly overlapped EEMF spectral data set of aqueous mixtures of Anthracene, Chrysene, Fluoranthene and Pyrene that are highly carcinogenic and mutagenic in nature. The developed procedure was also successfully used for the analysis of Chrysene and Pyrene mixtures in gasoline spiked ground water samples. The CARS assisted PLS model was also compared with full spectrum PLS, genetic algorithm assisted PLS, ant colony optimisation assisted PLS and N-way PLS models. The obtained results of the present work clearly indicated that application of PLS algorithm on CARS optimised EEMF spectral variables significantly improved the performance of the calibration models.

A Scalable Algorithm for Large-Scale Unsupervised Multi-View Partial Least Squares

We present an unsupervised multi-view partial least squares (PLS) by learning a common latent space from given multi-view data. Although PLS is a frequently used technique for analyzing relationships between two datasets, its extension to more than two views in unsupervised setting is seldom studied. In this article, we fill up the gap, and our model bears similarity to the extension of canonical correlation analysis (CCA) to more than two sets of variables and is built on the findings from analyzing PLS, CCA, and its variants. The resulting problem involves a set of orthogonality constraints on view-specific projection matrices, and is numerically challenging to existing methods that may have numerical instabilities and offer no orthogonality guarantee on view-specific projection matrices. To solve this problem, we propose a stable deflation algorithm that relies on proven numerical linear algebra techniques, can guarantee the orthogonality constraints, and simultaneously maximizes the covariance in the common space. We further adapt our algorithm to efficiently handle large-scale high-dimensional data. Extensive experiments have been conducted to evaluate the algorithm through performing two learning tasks, cross-modal retrieval, and multi-view feature extraction. The results demonstrate that the proposed algorithm outperforms the baselines and is scalable for large-scale high-dimensional datasets.

Near-infrared spectroscopy to determine cold-flow improver concentrations in diesel fuel

The properties of diesel fuels must be controlled during industrial production. Significant diesel additives are cold-flow improvers that affect fuel properties at low temperature properties of diesel fuels. Improvers are added to fuels during processing in order to lower their cold filter plugging point (CFPP). In order to meet the European standard (EN 590), large quantities of cold-flow improvers may be required, increasing the cost of processing.In this study, near-infrared (NIR) spectroscopy was used for the rapid determination of cold-flow improver concentration. Our predictive models included 150 calibration standards and predictions were verified using 15 validation standards. The concentration of cold-flow improvers ranged from 41 to 325 mg/kg in the partial least squares (PLS) and from 60 to 325 mg/kg in the principal component regression (PCR) algorithm. The RSD of repeatability was 5.89% for the PLS algorithm and the RSD of 3.51% for the PCR algorithm of the model. Thus, NIR spectroscopy provides a fast and accurate tool for the determination of cold-flow improver concentrations in diesel fuel.

FT-NIRS Coupled with PLS Regression as a Complement to HPLC Routine Analysis of Caffeine in Tea Samples.

Daily consumption of caffeine in coffee, tea, chocolate, cocoa, and soft drinks has gained wide and plentiful public and scientific attention over the past few decades. The concentration of caffeine in vivo is a crucial indicator of some disorders—for example, kidney malfunction, heart disease, increase of blood pressure and alertness—and can cause some severe diseases including type 2 diabetes mellitus (DM), stroke risk, liver disease, and some cancers. In the present study, near-infrared spectroscopy (NIRS) coupled with partial least-squares regression (PLSR) was proposed as an alternative method for the quantification of caffeine in 25 commercially available tea samples consumed in Oman. This method is a fast, complementary technique to wet chemistry procedures as well as to high-performance liquid chromatography (HPLC) methods for the quantitative analysis of caffeine in tea samples because it is reagent-less and needs little or no pre-treatment of samples. In the current study, the partial least-squares (PLS) algorithm was built by using the near-infrared NIR spectra of caffeine standards prepared in tea samples scanned by a Frontier NIR spectrophotometer (L1280034) by PerkinElmer. Spectra were collected in the absorption mode in the wavenumber range of 10,000–4000 cm−1, using a 0.2 mm path length and CaF2 sealed cells with a resolution of 2 cm−1. The NIR results for the contents of caffeine in tea samples were also compared with results obtained by HPLC analysis. Both techniques provided good results for predicting the caffeine contents in commercially available tea samples. The results of the proposed study show that the suggested FT-NIRS coupled with PLS regression algorithun has a high potential to be routinely used for the quick and reproducible analysis of caffeine contents in tea samples. For the NIR method, the limit of quantification (LOQ) was estimated as 10 times the error of calibration (root mean square error of calibration (RMSECV)) of the model; thus, RMSEC was calculated as 0.03 ppm and the LOQ as 0.3 ppm.