A consensus successive projections algorithm – multiple linear regression method for analyzing near infrared spectra

A Sensitive SERS Sensor Combined with Intelligent Variable Selection Models for Detecting Chlorpyrifos Residue in Tea

Chlorpyrifos is one of the most widely used broad-spectrum insecticides in agriculture. Given its potential toxicity and residue in food (e.g., tea), establishing a rapid and reliable method for the determination of chlorpyrifos residue is crucial. In this study, a strategy combining surface-enhanced Raman spectroscopy (SERS) and intelligent variable selection models for detecting chlorpyrifos residue in tea was established. First, gold nanostars were fabricated as a SERS sensor for measuring the SERS spectra. Second, the raw SERS spectra were preprocessed to facilitate the quantitative analysis. Third, a partial least squares model and four outstanding intelligent variable selection models, Monte Carlo-based uninformative variable elimination, competitive adaptive reweighted sampling, iteratively retaining informative variables, and variable iterative space shrinkage approach, were developed for detecting chlorpyrifos residue in a comparative study. The repeatability and reproducibility tests demonstrated the excellent stability of the proposed strategy. Furthermore, the sensitivity of the proposed strategy was assessed by estimating limit of detection values of the various models. Finally, two-tailed paired t-tests confirmed that the accuracy of the proposed strategy was equivalent to that of gas chromatography-mass spectrometry. Hence, the proposed method provides a promising strategy for detecting chlorpyrifos residue in tea.

Optimization of Online Soluble Solids Content Detection Models for Apple Whole Fruit with Different Mode Spectra Combined with Spectral Correction and Model Fusion

Soluble solids content (SSC) is one of the main quality indicators of apples, and it is important to improve the precision of online SSC detection of whole apple fruit. Therefore, the spectral pre-processing method of spectral-to-spectral ratio (S/S), as well as multiple characteristic wavelength member model fusion (MCMF) and characteristic wavelength and non-characteristic wavelength member model fusion (CNCMF) methods, were proposed for improving the detection performance of apple whole fruit SSC by diffuse reflection (DR), diffuse transmission (DT) and full transmission (FT) spectra. The modeling analysis showed that the S/S- partial least squares regression models for all three mode spectra had high prediction performance. After competitive adaptive reweighted sampling characteristic wavelength screening, the prediction performance of all three model spectra was improved. The particle swarm optimization-extreme learning machine models of MCMF and CNCMF had the most significant enhancement effect and could make all three mode spectra have high prediction performance. DR, DT, and FT spectra all had some prediction ability for apple whole fruit SSC, with FT spectra having the strongest prediction ability, followed by DT spectra. This study is of great significance and value for improving the accuracy of the online detection model of apple whole fruit SSC.

A Novel Variable Selection Method Based on Ordered Predictors Selection and Successive Projections Algorithm for Predicting Gastrodin Content in Fresh Gastrodia elata Using Fourier Transform Near-Infrared Spectroscopy and Chemometrics

Gastrodin is one of the most important biologically active components of Gastrodia elata, which has many health benefits as a dietary and health food supplement. However, gastrodin measurement traditionally relies on laboratory and sophisticated instruments. This research was aimed at developing a rapid and non-destructive method based on Fourier transform near infrared (FT-NIR) to predict gastrodin content in fresh Gastrodia elata. Auto-ordered predictors selection (autoOPS) and successive projections algorithm (SPA) were applied to select the most informative variables related to gastrodin content. Based on that, partial least squares regression (PLSR) and multiple linear regression (MLR) models were compared. The autoOPS-SPA-MLR model showed the best prediction performances, with the determination coefficient of prediction (Rp2), ratio performance deviation (RPD) and range error ratio (RER) values of 0.9712, 5.83 and 27.65, respectively. Consequently, these results indicated that FT-NIRS technique combined with chemometrics could be an efficient tool to rapidly quantify gastrodin in Gastrodia elata and thus facilitate quality control of Gastrodia elata.

Characteristic wavelength optimization for partial least squares regression using improved flower pollination algorithm

Wavelength selection is crucial to the success of near-infrared (NIR) spectroscopy analysis as it considerably improves the generalization of the multivariate model and reduces model complexity. This study proposes a new wavelength selection method, interval flower pollination algorithm (iFPA), for spectral variable selection in the partial least squares regression (PLSR) model. The proposed iFPA consists of three phases. First, the flower pollination algorithm is applied to search for informative spectral variables, followed by variable elimination. Subsequently, the iFPA performs a local search to determine the best continuous interval spectral variables. The interpretability of the selected variables is assessed on three public NIR datasets (corn, diesel and soil datasets). Performance comparison with other competing wavelength selection methods shows that the iFPA used in conjunction with the PLSR model gives better prediction performance, with the root mean square error of prediction values of 0.0096-0.0727, 0.0015-3.9717 and 1.3388-29.1144 are obtained for various responses in corn, diesel and soil datasets, respectively.

A Lightweight convolutional neural network for nicotine prediction in tobacco by near-infrared spectroscopy

The content of nicotine, a critical component of tobacco, significantly influences the quality of tobacco leaves. Near-infrared (NIR) spectroscopy is a widely used technique for rapid, non-destructive, and environmentally friendly analysis of nicotine levels in tobacco. In this paper, we propose a novel regression model, Lightweight one-dimensional convolutional neural network (1D-CNN), for predicting nicotine content in tobacco leaves using one-dimensional (1D) NIR spectral data and a deep learning approach with convolutional neural network (CNN). This study employed Savitzky-Golay (SG) smoothing to preprocess NIR spectra and randomly generate representative training and test datasets. Batch normalization was used in network regularization to reduce overfitting and improve the generalization performance of the Lightweight 1D-CNN model under a limited training dataset. The network structure of this CNN model consists of four convolutional layers to extract high-level features from the input data. The output of these layers is then fed into a fully connected layer, which uses a linear activation function to output the predicted numerical value of nicotine. After the comparison of the performance of multiple regression models, including support vector regression (SVR), partial least squares regression (PLSR), 1D-CNN, and Lightweight 1D-CNN, under the preprocessing method of SG smoothing, we found that the Lightweight 1D-CNN regression model with batch normalization achieved root mean square error (RMSE) of 0.14, coefficient of determination (R 2) of 0.95, and residual prediction deviation (RPD) of 5.09. These results demonstrate that the Lightweight 1D-CNN model is objective and robust and outperforms existing methods in terms of accuracy, which has the potential to significantly improve quality control processes in the tobacco industry by accurately and rapidly analyzing the nicotine content.

Early warning and diagnostic visualization of Sclerotinia infected tomato based on hyperspectral imaging

This research explored the feasibility of early warning and diagnostic visualization of Sclerotinia infected tomato by using hyperspectral imaging technology. Healthy tomato plants and tomato plants with Sclerotinia sclerotiorum were cultivated, and hyperspectral images at 400-1000 nm were collected from healthy and infected tomato leaves at 1, 3, 5, and 7 days of incubation. After preprocessing the spectra with first derivative (FD), second derivative (SD), standard normal variant (SNV), and multiplicative scatter correction (MSC) partial least squares discriminant analysis (PLS-DA) and support vector machine (SVM) were used to construct tomato sclerotinia identification model and select the best preprocessing method. On this basis, two band screening methods, competitive adaptive reweighted sampling (CARS) and successive projections algorithm (SPA), were introduced to reduce data redundancy and improve the model's prediction accuracy. The results showed that the accuracy of the validation sets and operation speed of the CARS-PLS and CARS-SVM models were 87.88% and 1.8 s, and 87.95% and 1.78 s, respectively. The experiment was based on the SNV-CARS-SVM prediction model combined with image processing, spectral extraction, and visualization analysis methods to create diagnostic visualization software, which opens a new avenue to the implementation of online monitoring and early warning system for sclerotinia infected tomato.

Salinization as a driver of eutrophication symptoms in an urban lake (Lake Wilcox, Ontario, Canada)

Lake Wilcox (LW), a shallow kettle lake located in southern Ontario, has experienced multiple phases of land use change associated with human settlement and residential development in its watershed since the early 1900s. Urban growth has coincided with water quality deterioration, including the occurrence of algal blooms and depletion of dissolved oxygen (DO) in the water column. We analyzed 22 years of water chemistry, land use, and climate data (1996-2018) using principal component analysis (PCA) and multiple linear regression (MLR) to identify the contributions of climate, urbanization, and nutrient loading to the changes in water chemistry. Variations in water column stratification, phosphorus (P) speciation, and chl-a (as a proxy for algal abundance) explain 76 % of the observed temporal trends of the four main PCA components derived from water chemistry data. MLR results further imply that the intensity of stratification, quantified by the Brunt-Väisälä frequency, is a major predictor of the changes in water quality. Other important factors explaining the variations in nitrogen (N) and P speciation, and the DO concentrations, are watershed imperviousness and lake chloride concentrations that, in turn, are closely correlated. We conclude that the observed in-lake water quality trends over the past two decades are linked to urbanization via increased salinization associated with expanding impervious land cover, rather than increasing external P loading. The rising salinity promotes water column stratification, which reduces the oxygenation of the hypolimnion and enhances internal P loading to the water column. Thus, stricter controls on the application and runoff of de-icing salt should be considered as part of managing eutrophication symptoms in lakes of cold climate regions.

Quantitative detection of zearalenone in wheat grains based on near-infrared spectroscopy

Zearalenone (ZEN) can easily contaminate wheat, seriously affecting the quality and safety of wheat grains. In this study, a near-infrared (NIR) spectroscopy detection method for rapid detection of ZEN in wheat grains was proposed. First, the collected original near-infrared spectra were denoised, smoothed and scatter corrected by Savitzky-Golay smoothing (SG-smoothing) and multiple scattering correction (MSC), and then normalized. Three wavelength variable selection algorithms were used to select variables from the preprocessed NIR spectra, which were random frog (RF), successive projections algorithm (SPA), least absolute shrinkage and selection operator (LASSO). Finally, based on the feature variables extracted by the above algorithms, support vector machine (SVM) models were established respectively to realize the quantitative detection of the ZEN in wheat grains. Eventually, the prediction effect of the LASSO-SVM model was the best, the prediction correlation coefficient (R_P) was 0.99, the root mean square error of prediction (RMSEP) was 2.1 μg·kg^-1, and the residual prediction deviation (RPD) was 6.0. This research shows that the NIR spectroscopy can be used for high-precision quantitative detection of the ZEN in grains, and the research gives a new technical solution for the in-situ detection of mycotoxins in stored grains.

Detection of Water pH Using Visible Near-Infrared Spectroscopy and One-Dimensional Convolutional Neural Network

pH is an important parameter for water quality detection. This study proposed a novel calibration regression strategy based on a one-dimensional convolutional neural network (1D-CNN) for water pH detection using visible near-infrared (Vis-NIR) spectroscopy. Two groups of Vis-NIR spectral analysis experiments of water pH detection were employed to evaluate the performance of 1D-CNN. Two conventional multivariate regression calibration methods, including partial least squares (PLS) and least squares support vector machine (LS-SVM), were introduced for comparative analysis with 1D-CNN. The successive projections algorithm (SPA) was adopted to select the feature variables. In addition, the learning mechanism of 1D-CNN was interpreted through visual feature maps by convolutional layers. The results showed that the 1D-CNN models obtained the highest prediction accuracy based on full spectra for the two experiments. For the spectrophotometer experiment, the root mean square error of prediction (RMSEP) was 0.7925, and the determination coefficient of prediction (Rp2) was 0.8515. For the grating spectrograph experiment, the RMSEP was 0.5128 and the Rp2 was 0.9273. The convolutional layers could automatically preprocess the spectra and effectively extract the spectra features. Compared with the traditional regression methods, 1D-CNN does not need complex spectra pretreatment and variable selection. Therefore, 1D-CNN is a promising regression approach, with higher prediction accuracy and better modeling convenience for rapid water pH detection using Vis-NIR spectroscopy.

Detection of Aflatoxin B1 in Single Peanut Kernels by Combining Hyperspectral and Microscopic Imaging Technologies

To study the dynamic changes of nutrient consumption and aflatoxin B₁ (AFB₁) accumulation in peanut kernels with fungal colonization, macro hyperspectral imaging technology combined with microscopic imaging was investigated. First, regression models to predict AFB₁ contents from hyperspectral data ranging from 1000 to 2500 nm were developed and the results were compared before and after data normalization with Box-Cox transformation. The results indicated that the second-order derivative with a support vector regression (SVR) model using competitive adaptive reweighted sampling (CARS) achieved the best performance, with R_C² = 0.95 and R_V² = 0.93. Second, time-lapse microscopic images and spectroscopic data were captured and analyzed with scanning electron microscopy (SEM), transmission electron microscopy (TEM), and synchrotron radiation-Fourier transform infrared (SR-FTIR) microspectroscopy. The time-lapse data revealed the temporal patterns of nutrient loss and aflatoxin accumulation in peanut kernels. The combination of macro and micro imaging technologies proved to be an effective way to detect the interaction mechanism of toxigenic fungus infecting peanuts and to predict the accumulation of AFB₁ quantitatively.

Consensual Regression of Soluble Solids Content in Peach by Near Infrared Spectrocopy

In order to reduce the uncertainty of the genetic algorithm (GA) in optimizing the near-infrared spectral calibration model and avoid the loss of spectral information of the unselected variables, a strategy of fusing consensus models is proposed to measure the soluble solids content (SSC) in peaches. A total of 266 peach samples were collected at four arrivals, and their interactance spectra were scanned by an integrated analyzer prototype, and then an internal index of SSC was destructively measured by the standard refractometry method. The near-infrared spectra were pre-processed with mean centering and were selected successively with a genetic algorithm (GA) to construct the consensus model, which was integrated with two member models with optimized weightings. One was the conventional partial least square (PLS) optimized with GA selected variables (PLS_GA), and the other one was the derived PLS developed with residual variables after GA selections (PLS_RV). The performance of PLS_RV models showed some useful spectral information related to peaches’ SSC and someone performed close to the full-spectral-based PLS model. Among these 10 runs, consensus models obtained a lower root mean squared errors of prediction (RMSEP), with an average of 1.106% and standard deviation (SD) of 0.0068, and performed better than that of the optimized PLS_GA models, which achieved a RMSEP of average 1.116% with SD of 0.0097. It can be concluded that the application of fusion strategy can reduce the fluctuation uncertainty of a model optimized by genetic algorithm, fulfill the utilization of the spectral information amount, and realize the rapid detection of the internal quality of the peach.

Rapid determination of hemoglobin concentration by a novel ensemble extreme learning machine method combined with near-infrared spectroscopy

A novel ensemble extreme learning machine (ELM) approach that combines Monte Carlo (MC) sampling and least absolute shrinkage and selection operator (LASSO), named as MC-LASSO-ELM, is proposed to determine hemoglobin concentration of blood. It employs MC sampling to randomly select samples from the training set and LASSO further to choose variables from selected samples to establish plenty of ELM sub-models. The final prediction is obtained by combining the predictions of these sub-models. Combined with near-infrared spectroscopy, MC-LASSO-ELM is used to determine the hemoglobin concentration of blood. Compared with ELM, MC-ELM and LASSO-ELM, MC-LASSO-ELM can obtain the best stability and highest accuracy.

Image of the distribution profile of targets in skin by Raman spectroscopy-based multivariate analysis

Raman spectroscopic imaging is a label-free spectral technology to investigate the distribution of transdermal targets in skin. However, it is difficult to analyze low content of analytes in skin by direct imaging analysis. Combining Raman mapping technology with multiple linear regression algorithms, concentration contribution factor of targets in ex vivo human skin tissue at every point has been calculated. The distribution profiles are visualized as heat maps demonstrating the targets levels in different skin layers. This method has been successfully employed to investigate the vibrational imaging of distribution of hyaluronic acid and lidocaine in skin. Moreover, three dimensional (3D) images of the penetration profiles of hyaluronic acid with different molecular weight have been obtained. The results from 3D images were in good agreement with these from two-dimensional images, indicating that this method was a reliable way for monitoring the distribution of targets in skin.

Determination of Fatty Acid Content of Rice during Storage Based on Feature Fusion of Olfactory Visualization Sensor Data and Near-Infrared Spectra

This study innovatively proposes a feature fusion technique to determine fatty acid content during rice storage. Firstly, a self-developed olfactory visualization sensor was used to capture the odor information of rice samples at different storage periods and a portable spectroscopy system was employed to collect the near-infrared (NIR) spectra during rice storage. Then, principal component analysis (PCA) was performed on the pre-processed olfactory visualization sensor data and the NIR spectra, and the number of the best principal components (PCs) based on the single technique model was optimized during the backpropagation neural network (BPNN) modeling. Finally, the optimal PCs were fused at the feature level, and a BPNN detection model based on the fusion feature was established to achieve rapid measurement of fatty acid content during rice storage. The experimental results showed that the best BPNN model based on the fusion feature had a good predictive performance where the correlation coefficient (R_P) was 0.9265, and the root mean square error (RMSEP) was 1.1005 mg/100 g. The overall results demonstrate that the detection accuracy and generalization performance of the feature fusion model are an improvement on the single-technique data model; and the results of this study can provide a new technical method for high-precision monitoring of grain storage quality.

M3GPSpectra: A novel approach integrating variable selection/construction and MLR modeling for quantitative spectral analysis

Quantitative analysis of the physical or chemical properties of various materials by using spectral analysis technology combined with chemometrics has become an important method in the field of analytical chemistry. This method aims to build a model relationship (called prediction model) between feature variables acquired by spectral sensors and components to be measured. Feature selection or transformation should be conducted to reduce the interference of irrelevant information on the prediction model because original spectral feature variables contain redundant information and massive noise. Most existing feature selection and transformation methods are single linear or nonlinear operations, which easily lead to the loss of feature information and affect the accuracy of subsequent prediction models. This research proposes a novel spectroscopic technology-oriented, quantitative analysis model construction strategy named M3GPSpectra. This tool uses genetic programming algorithm to select and reconstruct the original feature variables, evaluates the performance of selected and reconstructed variables by using multivariate regression model (MLR), and obtains the best feature combination and the final parameters of MLR through iterative learning. M3GPSpectra integrates feature selection, linear/nonlinear feature transformation, and subsequent model construction into a unified framework and thus easily realizes end-to-end parameter learning to significantly improve the accuracy of the prediction model. When applied to six types of datasets, M3GPSpectra obtains 19 prediction models, which are compared with those obtained by seven linear or non-linear popular methods. Experimental results show that M3GPSpectra obtains the best performance among the eight methods tested. Further investigation verifies that the proposed method is not sensitive to the size of the training samples. Hence, M3GPSpectra is a promising spectral quantitative analytical tool.

A new ensemble modeling method for multivariate calibration of near infrared spectra

Ensemble modeling has gained increasing attention for improving the performance of quantitative models in near infrared (NIR) spectral analysis. Based on Monte Carlo (MC) resampling, least absolute shrinkage and selection operator (LASSO) and partial least squares (PLS), a new ensemble strategy named MC-LASSO-PLS is proposed for NIR spectral multivariate calibration. In this method, the training subsets for building the sub-models are generated by sampling from both samples and variables to ensure the diversity of the models. In detail, a certain number of samples as sample subsets are randomly selected from training set. Then, LASSO is used to shrink the variables of the sample subset to form the training subset, which is used to build the PLS sub-model. This process is repeated N times and N sub-models are obtained. Finally, the predictions of these sub-models are used to produce the final prediction by simple average. The prediction ability of the proposed method was compared with those of LASSO-PLS, MC-PLS and PLS models on the NIR spectra of corn, blend oil and orange juice samples. The superiority of MC-LASSO-PLS in prediction ability is demonstrated.

Intelligent evaluation of taste constituents and polyphenols-to-amino acids ratio in matcha tea powder using near infrared spectroscopy

Matcha tea is rich in taste and bioactive constituents, quality evaluation of matcha tea is important to ensure flavor and efficacy. Near-infrared spectroscopy (NIR) in combination with variable selection algorithms was proposed as a fast and non-destructive method for the quality evaluation of matcha tea. Total polyphenols (TP), free amino acids (FAA), and polyphenols-to-amino acids ratio (TP/FAA) were assessed as the taste quality indicators. Successive projections algorithm (SPA), genetic algorithm (GA), and simulated annealing (SA) were subsequently developed from the synergy interval partial least squares (SiPLS). The overall results revealed that SiPLS-SPA and SiPLS-SA models combined with NIR exhibited higher predictive capabilities for the effective determination of TP, FAA and TP/FAA with correlation coefficient in the prediction set (R_p) of R_p > 0.97, R_p > 0.98 and R_p > 0.98 respectively. Therefore, this simple and efficient technique could be practically exploited for tea quality control assessment.

Rapid on-site identification of pesticide residues in tea by one-dimensional convolutional neural network coupled with surface-enhanced Raman scattering

In this study, a novel analytical approach is proposed for the identification of pesticide residues in tea by combining surface-enhanced Raman scattering (SERS) with a deep learning method one-dimensional convolutional neural network (1D CNN). First, a handheld Raman spectrometer was used for rapid on-site collection of SERS spectra. Second, the collected SERS spectra were augmented by a data augmentation strategy. Third, based on the augmented SERS spectra, the 1D CNN models were established on the cloud server, and then the trained 1D CNN models were used for subsequent pesticide residue identification analysis. In addition, to investigate the identification performance of the 1D CNN method, four conventional identification methods, including partial least square-discriminant analysis (PLS-DA), k-nearest neighbour (k-NN), support vector machine (SVM) and random forest (RF), were also developed on the basis of the augmented SERS spectra and applied for pesticide residue identification analysis. The comparative studies show that the 1D CNN method possesses better identification accuracy, stability and sensitivity than the other four conventional identification methods. In conclusion, the proposed novel analytical approach that exploits the advantages of SERS and a deep learning method (1D CNN) is a promising method for rapid on-site identification of pesticide residues in tea.

Rapid Assessment of Exercise State through Athlete's Urine Using Temperature-Dependent NIRS Technology

Athletes usually take nutritional supplements and perform the specialized training to improve the performance of sport. A quick assessment of their athletic status will help to understand the current physical function of athletes' status and the effect of nutritional supplementation. Human urine, as one of the most important body indicators, is composed of many metabolites, which can provide effective monitoring information for physical conditions. In this study, temperature-dependent near-infrared spectroscopy (NIRS) technology was used to collect the spectra of athlete's urine for evaluating the feasibility of rapidly detecting the exercise state of the basketball player. To obtain the detection results accurately, several chemometrics methods including principal component analysis (PCA), variables selection method of variable importance in projection (VIP), continuous 1D wavelet transform (CWT), and partial least square-discriminant analysis (PLS-DA) were employed to develop a classifier to distinguish the physical status of athletes. The optimal classifying results were obtained by wavelet-PLS-DA classifier, whose average precision, sensitivity, and specificity are all above 0.95, and the overall accuracy of all samples is 0.97. These results demonstrate that temperature-dependent NIRS can be used to rapidly assess the physical function of athlete's status and the effect of nutritional supplementation is feasible. It can be believed that temperature-dependent NIR spectroscopy will obtain applications more widely in the future.

Building a stable and accurate model for heavy metal detection in mulberry leaves based on a proposed analysis framework and laser-induced breakdown spectroscopy

Laser-induced breakdown spectroscopy (LIBS) was used to rapidly detect heavy metals in mulberry leaves. For the purpose of increasing detection stability and accuracy, a novel analysis framework consisting of a Kohonen self-organizing map (SOM), a variable selection method using the successive projection algorithm (SPA) and uninformative variable elimination (UVE), and a consensus modeling strategy was proposed for processing LIBS data to determine copper (Cu) and chromium (Cr) content. Results showed that the best regression model for Cu and Cr content achieved the residual predictive deviation (RPD) values of 10.0494 and 8.3874, respectively, and root mean square error of prediction (RMSEP) values of 110.4550 and 41.4561, respectively. The proposed strategy provides a high-accuracy and rapid alternative to the traditional method for monitoring heavy metals in mulberry leaves, which could guarantee the quality of mulberry leaves and potentially be used in food-related industries.

Investigation of nonlinear relationship of surface enhanced Raman scattering signal for robust prediction of thiabendazole in apple

Thiabendazole (TBZ) is extensively used in agriculture to control molds; residue of TBZ may pose a threat to humans. Herein, surface-enhanced Raman spectroscopy (SERS) coupled variable selected regression methods have been proposed as simple and rapid TBZ quantification technique. The nonlinear correlation between the TBZ and SERS data was first diagnosed by augmented partial residual plots method and calculated by runs test. Au@Ag NPs with strong enhancement factor (EF = 4.07 × 10⁶) of Raman signal was used as SERS active material to collect spectra from TBZ. Subsequently, three nonlinear regression models were comparatively investigated and the competitive adaptive reweighted sampling-extreme learning machine (CARS-ELM) achieved a higher correlation coefficient (Rp² = 0.9406) and the lower root-mean-square-error of prediction (RMSEP = 0.5233 mg/L). Finally, recoveries of TBZ in apple samples were 83.02-93.54% with relative standard deviation (RSD) value < 10%. Therefore, SERS coupled CARS-ELM could be employed as a rapid and sensitive approach for TBZ detection in Fuji apples.

Quantification of deltamethrin residues in wheat by Ag@ZnO NFs-based surface-enhanced Raman spectroscopy coupling chemometric models

Deltamethrin, one of the most toxic pyrethroids, is commonly used to inhibit pests in wheat. However, the trace levels of deltamethrin in wheat is alarming to human health. In this study, surface-enhanced Raman spectroscopy (SERS)-active silver nanoparticles-plated-zinc oxide nanoflowers (Ag@ZnO NFs) nano-sensor were employed for rapid and sensitive quantification of deltamethrin in wheat. To sufficiently utilize the chemical-related information in SERS spectra, various spectral pretreatment and chemometric models were studied. The mean centering (MC) coupling successive projection algorithm-partial least squares regression (SPA-PLS) provided optimal predictive performance (correlation coefficient of prediction (Rp) = 0.9736 and residual predictive deviation (RPD) = 4.75). The proposed method achieved the limit of detection (LOD) = 0.16 μg·kg^-1, the recovery of predicted results was in the range of 96.33-109.17% and the relative standard deviation (RSD) was < 5%. The overall results suggested that SERS based Ag@ZnO NFs combined with MC-SPA-PLS could be an easy and efficient method to quantify deltamethrin residue levels in wheat.

Rapid and Non-Destructive Detection of Compression Damage of Yellow Peach Using an Electronic Nose and Chemometrics

The rapid and non-destructive detection of mechanical damage to fruit during postharvest supply chains is important for monitoring fruit deterioration in time and optimizing freshness preservation and packaging strategies. As fruit is usually packed during supply chain operations, it is difficult to detect whether it has suffered mechanical damage by visual observation and spectral imaging technologies. In this study, based on the volatile substances (VOCs) in yellow peaches, the electronic nose (e-nose) technology was applied to non-destructively predict the levels of compression damage in yellow peaches, discriminate the damaged fruit and predict the time after the damage. A comparison of the models, established based on the samples at different times after damage, was also carried out. The results show that, at 24 h after damage, the correct answer rate for identifying the damaged fruit was 93.33%, and the residual predictive deviation in predicting the levels of compression damage and the time after the damage, was 2.139 and 2.114, respectively. The results of e-nose and gas chromatography-mass spectrophotometry (GC–MS) showed that the VOCs changed after being compressed—this was the basis of the e-nose detection. Therefore, the e-nose is a promising candidate for the detection of compression damage in yellow peach.

Determination of acidity in metal incorporated zeolites by infrared spectrometry using artificial neural network as chemometric approach

The NH₃-TPD analysis is a costly and tedious method to determine zeolites acidity. Thus, to do so, FTIR spectroscopy was quantitatively used as a fast and cost-effectively method. Back-propagation artificial neural network (BP-ANN) was used for the analysis of multivariate base on the characteristic absorbance of 11 zeolite samples after metal substitution in the ~3612 cm^-1 region. The successive projection algorithm (SPA) was conducted for the uninformative variable elimination and feature selection strategies. The effect of pre-processing methods (e.g. MC and MSC) was examined. It is observed after using MSC for minimizing the light scattering effect and signal-to-noise correction, the minimum mean squared error (MSE) value of the testing set data reduced from 5.36 × 10^-2 to 2.19 × 10^-4 and R_tot increases from 0.91 to 0.99. Also, the results of nonparametric Wilcoxon t-test and Sign test methods also confirmed that there is no clear difference between the zeolite acidity obtained by two conventional method and the proposed method.

Rapid quantitative analysis of Hg2+ residue in dairy products using SERS coupled with ACO-BP-AdaBoost algorithm

In this study, surface-enhanced Raman spectroscopy (SERS) coupled with multivariate calibrations were employed to develop a rapid, simple and sensitive method for determination of mercury ions residues in dairy products. Initially, spherical Au@SiO₂ core shell nanoparticles with highly enhancement effect were synthesized to serve as the SERS substrate. Afterwards, an optical sensor system, namely micro-Raman spectroscopy system, was constructed for rapid acquisition of Au@SiO₂-mercury ions spectra. Then, ant colony optimization (ACO) and genetic algorithm (GA) were applied comparatively for selecting the characteristic variables from the Savitzky Golay-First derivative (SG-FD) processing data for subsequent quantitative analysis. Eventually, both linear (PLS and SW-MLR) and nonlinear (BPANN and BP-AdaBoost) methods were used for modeling. Experimental results showed that the variables selection methods significantly improved the model performance. Especially for the ACO algorithm, and the ACO-BP-AdaBoost model achieved the best results with the higher correlation coefficient of determination (R² = 0.997), and lower root-mean-square error of prediction (RMSEP = 0.092) than other quantification models. Paired sample t-test exhibited no statistically significant difference (sig > 0.05) between the reference concentrations determined by inductively coupled plasma mass spectrometry (ICP-MS) and the predicted concentrations by ACO-BP-AdaBoost model in adulterated foodstuffs.

Combining Fourier Transform Mid-Infrared Spectroscopy with Chemometric Methods to Detect Adulterations in Milk Powder

Adulteration is one of the major concerns among all the quality problems of milk powder. Soybean flour and rice flour are harmless adulterations in the milk powder. In this study, mid-infrared spectroscopy was used to detect the milk powder adulterated with rice flour or soybean flour and simultaneously determine the adulterations content. Partial least squares (PLS), support vector machine (SVM) and extreme learning machine (ELM) were used to establish classification and regression models using full spectra and optimal wavenumbers. ELM models using the optimal wavenumbers selected by principal component analysis (PCA) loadings obtained good results with all the sensitivity and specificity over 90%. Regression models using the full spectra and the optimal wavenumbers selected by successive projections algorithm (SPA) obtained good results, with coefficient of determination (R2) of calibration and prediction all over 0.9 and the predictive residual deviation (RPD) over 3. The classification results of ELM models and the determination results of adulterations content indicated that the mid-infrared spectroscopy was an effective technique to detect the rice flour and soybean flour adulteration in the milk powder. This study would help to apply mid-infrared spectroscopy to the detection of adulterations such as rice flour and soybean flour in real-world conditions.

Sample Consensus Model and Unsupervised Variable Consensus Model for Improving the Accuracy of a Calibration Model

In the quantitative analysis of spectral data, small sample size and high dimensionality of spectral variables often lead to poor accuracy of a calibration model. We proposed two methods, namely sample consensus and unsupervised variable consensus models, in order to solve the problem of poor accuracy. Three public near-infrared (NIR) or infrared (IR) spectroscopy data from corn, wine, and soil were used to build the partial least squares regression (PLSR) model. Then, Monte Carlo sampling and unsupervised variable clustering methods of a self-organizing map were coupled with the consensus modeling strategy to establish the multiple sub-models. Finally, sample consensus and unsupervised variable consensus models were obtained by assigning the weights to each PLSR sub-model. The calculated results show that both sample consensus and unsupervised variable consensus models can significantly improve the accuracy of the calibration model compared to the single PLSR model. The effectiveness of these two methods points out a new approach to achieve a further accurate result, which can take full advantage of the sample information and valid variable information.

Moving window smoothing on the ensemble of competitive adaptive reweighted sampling algorithm

A novel chemometrical method, named as MWS-ECARS, which is based on using the moving window smoothing upon an ensemble of competitive adaptive reweighted sampling, is proposed as the spectral variable selection approach for multivariate calibration in this study. In terms of elimination of uninformative variables, an ensemble of CARS is carried out first and MWS is then performed to search for effective variables around the high frequency variables. The variable subset with the lowest standard error of cross-validation (SECV) is treated as the optimal threshold and the corresponding moving window width is regarded as the optimal window width. The method was applied to mid-infrared (MIR) spectra of active ingredient in pesticide, near-infrared (NIR) spectra of soil organic matter and NIR spectra of total nitrogen in Solanaceae plants for variable selection. Overall results show that MWS-ECARS is a promising selection method with an improved prediction performance over three variable selection methods of variable importance projection (VIP), uninformative variables elimination (UVE) and genetic algorithms (GA).

Comparing the Potential of Near- and Mid-Infrared Spectroscopy in Determining the Freshness of Strawberry Powder from Freshly Available and Stored Strawberry

The quality of strawberry powder depends on the freshness of the fruit that produces the powder. Therefore, identifying whether the strawberry powder is made from freshly available, short-term stored, or long-term stored strawberries is important to provide consumers with quality-assured strawberry powder. Nevertheless, such identification is difficult by naked eyes, as the powder colours are very close. In this work, based on the measurement of near-infrared (NIR) spectroscopy and mid-infrared (MIR) spectra of strawberry powered, good classification results of 100.00% correct rates to distinguish whether the strawberry powder was made from freshly available or stored fruit was obtained. Furthermore, partial least squares regression and least squares support vector machines (LS-SVM) models were established based on NIR, MIR, and combination of NIR and MIR data with full variables or optimal variables of strawberry powder to predict the storage days of strawberries that produced the powder. Optimal variables were selected by successive projections algorithm (SPA), uninformation variable elimination, and competitive adaptive reweighted sampling, respectively. The best model was determined as the SPA-LS-SVM model based on MIR spectra, which had the residual prediction deviation (RPD) value of 11.198 and the absolute difference between root-mean-square error of calibration and prediction (AB_RMSE) value of 0.505. The results of this work confirmed the feasibility of using NIR and MIR spectroscopic techniques for rapid identification of strawberry powder made from freshly available and stored strawberry.

Development of a novel wavelength selection method for the trace determination of chlorpyrifos on Au@Ag NPs substrate coupled surface-enhanced Raman spectroscopy

A novel wavelength selection method named ICPA-mRMR coupled SERS was employed for the detection of CPS residues in tea samples.

Non-destructive prediction of protein content in wheat using NIRS

A steady and accurate model used for quality detection depends on precise data and appropriate analytical methods. In this study, the authors applied partial least square regression (PLSR) to construct a model based on the spectral data measured to predict the protein content in wheat, and proposed a new method, global search method, to select PLSR components. In order to select representative and universal samples for modeling, Monte Carlo cross validation (MCCV) was proposed as a tool to detect outliers, and identified 4 outlier samples. Additionally, improved simulated annealing (ISA) combined with PLSR was employed to select most effective variables from spectral data, the data's dimensionality reduced from 100 to 57, and the standard error of prediction (SEP) decreased from 0.0716 to 0.0565 for prediction set, as well as the correlation coefficients (R²) between the predicted and actual protein content of wheat increased from 0.9989 to 0.9994. In order to reduce the dimensionality of the data further, successive projections algorithm (SPA) was then used, the combination of these two methods was called ISA-SPA. The results indicated that calibration model built using ISA-SPA on 14 effective variables achieved the optimal performance for prediction of protein content in wheat comparing with other developed PLSR models (ISA or SPA) by comprehensively considering the accuracy, robustness, and complexity of models. The coefficient of determination increased to 0.9986 and the SEP decreased to 0.0528, respectively.

Determination of total organic carbon and soluble solids contents in Tanreqing injection intermediates with NIR spectroscopy and chemometrics

Near infrared spectroscopy combined with chemometrics was investigated for the fast determination of total organic carbon (TOC) and soluble solids contents (SSC) of Tanreqing injection intermediates. The NIR spectra were collected in transflective mode, and the TOC and SSC reference values were determined with Multi N/C UV HS analyzer and loss on drying method. The samples were divided into calibration sets and validation sets using the Kennard-Stone (KS) algorithm. The Dixon test, leverage and studentized residual test were studied for the sample outlier analysis. The selection of wavebands, spectra pretreated method and the number of latent variables were optimized to obtain better results. The quantitative calibration models were established with 3 different PLS regression algorithms, named linear PLS, non-linear PLS and concentration weighted PLS, and the net result was defined as the average of the predicted values of the different calibration models. The overall results indicated that the presented method is more powerful than single multivariable regression method, characterized by higher mean recovery rate (MRR) of the validation set, and can be used for the rapid determination of TOC and SSC values of Tanreqing injection intermediates, which are two important quality indicators for the process monitoring.

A novel spectral multivariate calibration approach based on a multiple fitting method

This paper introduces a novel multivariate regression approach based on a multiple fitting algorithm that combines fitting functions to accordingly configure different regression models for the quantitative analysis of spectra data.