Least-squares support vector machines and near infrared spectroscopy for quantification of common adulterants in powdered milk

This paper proposes the use of the least-squares support vector machine (LS-SVM) as an alternative multivariate calibration method for the simultaneous quantification of some common adulterants (starch, whey or sucrose) found in powdered milk samples, using near-infrared spectroscopy with direct measurements by diffuse reflectance. Due to the spectral differences of the three adulterants a nonlinear behavior is present when all groups of adulterants are in the same data set, making the use of linear methods such as partial least squares regression (PLSR) difficult. Excellent models were built using LS-SVM, with low prediction errors and superior performance in relation to PLSR. These results show it possible to built robust models to quantify some common adulterants in powdered milk using near-infrared spectroscopy and LS-SVM as a nonlinear multivariate calibration procedure.     

Non-Destructive Analysis of Chlorpheniramine Maleate Tablets and Granules by Chemometrics-Assisted Attenuated Total Reflectance Infrared Spectroscopy

Non-destructive analysis of chlorpheniramine maleate (CPM), pharmaceutical tablets, and granules was conducted by chemometrics-assisted attenuated total reflectance infrared spectroscopy (ATR-IR). For tablets, an optimum PLSR model with eight latent factors was obtained from area-normalized and standard normal variate (SNV) pretreated ATR-IR spectral data with correlation coefficients (R²) of calibration and cross-validation of 0.9716 and 0.9602, respectively. The model capability for the 42 test set samples was proven with R² between the reference and model prediction values of 0.9632, and a root-mean-square error of prediction (RMSEP) of 1.7786. The successive PLSR model for granules was constructed from SNV and first derivative pretreated ATR-IR spectral data with two latent factors and correlation coefficients (R²) of calibration and cross-validation of 0.9577 and 0.9450, respectively.     

Quantitative analysis of routine chemical constituents in tobacco by near-infrared spectroscopy and support vector machine

It is important to monitor quality of tobacco during the production of cigarette. Therefore, in order to scientifically control the tobacco raw material and guarantee the cigarette quality, fast and accurate determination routine chemical of constituents of tobacco, including the total sugar, reducing sugar, Nicotine, the total nitrogen and so on, is needed. In this study, 50 samples of tobacco from different cultivation areas were surveyed by near-infrared (NIR) spectroscopy, and the spectral differences provided enough quantitative analysis information for the tobacco. Partial least squares regression (PLSR), artificial neural network (ANN), and support vector machine (SVM), were applied. The quantitative analysis models of 50 tobacco samples were studied comparatively in this experiment using PLSR, ANN, radial basis function (RBF) SVM regression, and the parameters of the models were also discussed. The spectrum variables of 50 samples had been compressed through the wavelet transformation technology before the models were established. The best experimental results were obtained using the (RBF) SVM regression with gamma=1.5, 1.3, 0.9, and 0.1, separately corresponds to total sugar, reducing sugar, Nicotine, and total nitrogen, respectively. Finally, compared with the back propagation (BP-ANN) and PLSR approach, SVM algorithm showed its excellent generalization for quantitative analysis results, while the number of samples for establishing the model is smaller. The overall results show that NIR spectroscopy combined with SVM can be efficiently utilized for rapid and accurate analysis of routine chemical compositions in tobacco. Simultaneously, the research can serve as the technical support and the foundation of quantitative analysis of other NIR applications.     

Solvent sorption measurements in polymeric membranes with ATR-IR spectroscopy

Long-term stability and performance of polymeric membranes in solvent and mixed solvent media can be reduced due to sorption and swelling of the membrane matrix. For this reason quantification of sorption and swelling is of major importance for the development of future applications of membrane processes in solvent and mixed solvent media. In this work a method is discussed, based on attenuated total reflectance infrared spectroscopy (ATR-IR), to establish sorption and sorption selectivity of a cellulose acetate (CA) membrane in water/methanol and water/ethanol mixtures. By analysis of specific peaks from the ATR-IR spectra of the solvents, the preferential sorption of water in CA membranes can be quantified. In the presence of methanol, the selectivity for water ranges from 2.5 to 3.5 between 52 and 90% of methanol. For ethanol, the selectivity for water ranges from about 1 (30% ethanol) to 2 (90% ethanol). From the work it follows that ATR-IR provides an easy and non-destructive method to study the sorption behavior of the polymeric membrane separation layer.     

茶叶浸出液中农药残留表面拉曼光谱检测与初步定量分析

选取甲基对硫磷和水胺硫磷为研究对象,改良了传统的QuEChERS前处理工艺,以自制纳米金溶胶为增强基底,利用表面增强拉曼光谱(SERS)技术,对茶叶浸出液中的农药残留进行检测。通过比对两种有机磷农药的拉曼特征峰进行定性分析。同时,选取570,1034,1107和1202 cm^-1等拉曼位移附近的特征峰光谱数据,利用微分等数学手段,结合偏最小二乘法(PLSR)建立回归方程,预测样品中农药残留含量。所得预测数值与气相色谱-质谱联用(GC-MS)法检测值对比,验证本方法的可行性与可信度。结果表明:基于SERS技术对上述两种有机磷农药的检出限可达0.05 mg/L;通过数学模型分析建立回归方程,其线性相关系数范围为0.9077~0.9824,预测均方根误差(RMSEP)范围为0.77%~2.68%;利用回归方程得到的预测值与GC-MS检测结果基本接近,相对误差范围-5.16%~9.03%,回收率为81.4%~115.1%,说明可以用SERS技术对茶叶浸出液中的有机磷农药残留进行定性和初步定量分析。     

High and low frequency unfolded partial least squares regression based on empirical mode decomposition for quantitative analysis of fuel oil samples

Accurate prediction of the model is fundamental to the successful analysis of complex samples. To utilize abundant information embedded over frequency and time domains, a novel regression model is presented for quantitative analysis of hydrocarbon contents in the fuel oil samples. The proposed method named as high and low frequency unfolded PLSR (HLUPLSR), which integrates empirical mode decomposition (EMD) and unfolded strategy with partial least squares regression (PLSR). In the proposed method, the original signals are firstly decomposed into a finite number of intrinsic mode functions (IMFs) and a residue by EMD. Secondly, the former high frequency IMFs are summed as a high frequency matrix and the latter IMFs and residue are summed as a low frequency matrix. Finally, the two matrices are unfolded to an extended matrix in variable dimension, and then the PLSR model is built between the extended matrix and the target values. Coupled with Ultraviolet (UV) spectroscopy, HLUPLSR has been applied to determine hydrocarbon contents of light gas oil and diesel fuels samples. Comparing with single PLSR and other signal processing techniques, the proposed method shows superiority in prediction ability and better model interpretation. Therefore, HLUPLSR method provides a promising tool for quantitative analysis of complex samples.     

Combined Experimental and Multivariate Model Approaches for Glycoalkaloid Quantification in Tomatoes

The intake of tomato glycoalkaloids can exert beneficial effects on human health. For this reason, methods for a rapid quantification of these compounds are required. Most of the methods for α-tomatine and dehydrotomatine quantification are based on chromatographic techniques. However, these techniques require complex and time-consuming sample pre-treatments. In this work, HPLC-ESI-QqQ-MS/MS was used as reference method. Subsequently, multiple linear regression (MLR) and partial least squares regression (PLSR) were employed to create two calibration models for the prediction of the tomatine content from thermogravimetric (TGA) and attenuated total reflectance (ATR) infrared spectroscopy (IR) analyses. These two fast techniques were proven to be suitable and effective in alkaloid quantification (R² = 0.998 and 0.840, respectively), achieving low errors (0.11 and 0.27%, respectively) with the reference technique.     

Analytical determination of antioxidants in tomato: typical components of the Mediterranean diet

Diets in the countries of the Mediterranean basin are characterised by abundant plant foods (fruits, vegetables, breads, nuts, seeds, wine, and olive oil) and include fish and low-fat dairy products. Among the vegetables, tomatoes are a main component of the traditional Mediterranean diet, which has been associated with health protection and longevity. Eating tomatoes has been associated with reduced risks of some types of cancer and other diseases. These beneficial properties appear to be related to the antioxidant content of the fruit, particularly carotenoids (lycopene and beta-carotene), ascorbic acid, and phenols, which may play a role in inhibiting reactions mediated by reactive oxygen species. Due to the importance of antioxidant compounds in tomatoes and tomato products, we present here an overview of current analytical methods (from 2000 until the present date) for determining the different antioxidants. The analytical procedures used to determine individual compounds involve extraction from the sample, analytical separation, and quantification. The choice of analytical method depends on the particular focus of the analysis and the kind of product analysed. High-performance liquid chromatography is the technique of choice for the analysis of tomato antioxidants.     

基于双脉冲LIBS结合偏最小二乘回归的稀土元素定量分析

激光诱导击穿光谱(LIBS)是一种以激光为激发源的等离子体发射光谱分析技术,已有将其用于稀土元素的定量分析研究,但由于稀土矿基体差异大、元素含量低,定量分析灵敏度和准确度仍有待提高。通过使用单激光分束构造双脉冲LIBS系统,并结合偏最小二乘回归(PLSR)算法实现对稀土矿石样品中的稀土元素La、Dy、Yb和Y的定量分析。结果表明,双脉冲LIBS结合PLSR可建立更加稳定的定标模型,与常规基本定标法相比,La、Dy、Yb和Y元素的相对均方根预测误差(RMSEP)从0.0061 %、0.0037%、0.0045%、0.0280 %降低至0.0044%、0.0016%、0.0029%、0.0134%,平均相对预测误差(AREP)从10.88%、15.27%、6.42%、17.20%降低至6.67%、3.62%、4.10%、7.98%。因此,双脉冲LIBS结合PLSR方法可以有效地提高LIBS对稀土矿石中稀土元素的定量分析能力。     

Quantitative analysis of two adulterants in Cynanchum stauntonii by near-infrared spectroscopy combined with multi-variate calibrations

Authentication of traditional Chinese medicines (TCMs) has become important because they can be adulterated with relatively cheap herbal medicines similar in appearance. Detection of such adulterated samples is needed because their presence is likely to reduce the pharmacological potency of the original TCM and, in the worst cases, the samples may be harmful. The aim of this study was to develop a rapid near-infrared spectroscopy (NIRS) analytical method which was supported by multi-variate calibration, e.g. partial least squares regression (PLSR) and radial basis function artificial neural networks (RBF-ANN), in order to quantify the TCM and the adulterants. In this work, Cynanchum stauntonii (CS), a commonly used TCM, in mixtures with one or two adulterants ?? two morphological types of TCM, Cynanchum atrati (CA) and Cynanchum paniculati (CP), were determined using NIR reflectance spectroscopy. The three sample sets, CS adulterated with CA or CP, and CS with both CA and CP, were measured in the range of 800?C2500 nm. Both PLSR and RBF-ANN calibration models provided satisfactory results, even at an adulteration level of 5 mass %, but the RBF-ANN models with better root mean square error of prediction (RMSEP) values for CS, CA, and CP arguably performed better. Consequently, this work demonstrates that the NIR method of sampling complex mixtures of similar substances such as CS adulterated by CA and/or CP is capable of producing data suitable for the quantitative analysis of mixtures consisting of the original TCM adulterated by one or two similar substances, provided the spectral data are interrogated by multi-variate methods of data analysis such as PLS or RBF-ANN.     

The ability of spectrum autocorrelation models to predict the lycopene concentration in foods through visible spectroscopic data

We developed a novel computerized approach based on lag-k autocorrelation coefficients (LCCs) and linear models (LMs) to estimate the concentration of lycopene in foods by the spectroscopy. The LCCs were calculated using the data obtained using whole visible scans from 400 to 600 nm (vide supra) of lycopene standards and food samples (ketchup, tomato juice and tomato sauce). The chaotic parameter (CP) was then transferred into a LM to estimate the concentration of lycopene compound. The integrated LCC/visible spectroscopy method developed can be considered as a satisfactory analytical technique able to estimate lycopene concentration in food samples in a fast accurate way, with a mean prediction error lower than 5.7% and a mean correlation coefficient higher than 0.957.     

Application of multivariate curve resolution alternating least squares (MCR-ALS) to the quantitative analysis of pharmaceutical and agricultural samples

Application of multivariate curve resolution alternating least squares (MCR-ALS), for the resolution and quantification of different analytes in different type of pharmaceutical and agricultural samples is shown. In particular, MCR-ALS is applied first to the UV spectrophotometric quantitative analysis of mixtures of commercial steroid drugs, and second to the near-infrared (NIR) spectrophotometric quantitative analysis of humidity and protein contents in forage cereal samples. Quantitative results obtained by MCR-ALS are compared to those obtained using the well established partial least squares regression (PLSR) multivariate calibration method.     

中药材三七提取液近红外光谱的支持向量机回归校正方法

提出近红外光谱的支持向量机回归校正建模方法.以中药材三七渗漉提取液为实际分析对象,对其近红外光谱数据进行预处理和主成分分析后,用支持向量机回归算法建立人参皂苷R_g1,R_b1和R_d以及三七总皂苷的近红外光谱校正模型.以R_g1,R_b1和R_d的HPLC测定值及三七总皂苷的比色法测定值为参照,将本文方法与偏最小二乘回归和径向基神经网络建模方法相比较,结果表明,本文所建模型的预测准确性优于后两者,可推广应用于中药提取过程的近红外光谱分析.     

Quantification of Corn Adulteration in Wet and Dry-Processed Peaberry Ground Roasted Coffees by UV–Vis Spectroscopy and Chemometrics

In this present research, a spectroscopic method based on UV–Vis spectroscopy is utilized to quantify the level of corn adulteration in peaberry ground roasted coffee by chemometrics. Peaberry coffee with two types of bean processing of wet and dry-processed methods was used and intentionally adulterated by corn with a 10–50% level of adulteration. UV–Vis spectral data are obtained for aqueous samples in the range between 250 and 400 nm with a 1 nm interval. Three multivariate regression methods, including partial least squares regression (PLSR), multiple linear regression (MLR), and principal component regression (PCR), are used to predict the level of corn adulteration. The result shows that all individual regression models using individual wet and dry samples are better than that of global regression models using combined wet and dry samples. The best calibration model for individual wet and dry and combined samples is obtained for the PLSR model with a coefficient of determination in the range of 0.83–0.93 and RMSE below 6% (w/w) for calibration and validation. However, the error prediction in terms of RMSEP and bias were highly increased when the individual regression model was used to predict the level of corn adulteration with differences in the bean processing method. The obtained results demonstrate that the use of the global PLSR model is better in predicting the level of corn adulteration. The error prediction for this global model is acceptable with low RMSEP and bias for both individual and combined prediction samples. The obtained RPD_p and RER_p in prediction for the global PLSR model are more than two and five for individual and combined samples, respectively. The proposed method using UV–Vis spectroscopy with a global PLSR model can be applied to quantify the level of corn adulteration in peaberry ground roasted coffee with different bean processing methods.     

The potential of Raman spectroscopy for characterisation of the fatty acid unsaturation of salmon

Raman spectroscopy has been evaluated for characterisation of the degree of fatty acid unsaturation (iodine value) of salmon (Salmo salar). The Norwegian Quality Cuts from 50 salmon samples were obtained, and the samples provided an iodine value range of 147.8-170.0 g I₂/100 g fat, reflecting a normal variation of farmed salmon. Raman measurements were performed both on different spots of the intact salmon muscle, on ground salmon samples as well as on oil extracts, and partial least squares regression (PLSR) was utilised for calibration. The oil spectra provided better iodine value predictions than the other data sets, and a correlation coefficient of 0.87 with a root mean square error of cross-validation of 2.5 g I₂/100 g fat was achieved using only one PLSR component. The ground samples provided comparable results, but at least two PLSR components were needed. Higher prediction errors were obtained from Raman spectra of intact salmon muscle, and this may partly be explained by sampling uncertainties in the relation between Raman measurements and reference analysis. All PLSR models obtained were based on chemically sound regression coefficients, and thus information regarding fatty acid unsaturation is readily available from Raman spectra even in systems with high contents of protein and water. The accuracy, the robustness and the low complexity of the PLSR models obtained suggest Raman spectroscopy as a promising method for rapid in-process control of the degree of unsaturation in salmon samples.     

Quantitative Detection of Chromium Pollution in Biochar Based on Matrix Effect Classification Regression Model

Returning biochar to farmland has become one of the nationally promoted technologies for soil remediation and improvement in China. Rapid detection of heavy metals in biochar derived from varied materials can provide a guarantee for contaminated soil, avoiding secondary pollution. This work aims first to apply laser-induced breakdown spectroscopy (LIBS) for the quantitative detection of Cr in biochar. Learning from the principles of traditional matrix effect correction methods, calibration samples were divided into 1–3 classifications by an unsupervised hierarchical clustering method based on the main elemental LIBS data in biochar. The prediction samples were then divided into diverse classifications of calibration samples by a supervised K-nearest neighbor (KNN) algorithm. By comparing the effects of multiple partial least squares regression (PLSR) models, the results show that larger numbered classifications have a lower averaged relative standard deviations of cross-validation (ARSDCV) value, signifying a better calibration performance. Therefore, the 3 classification regression model was employed in this study, which had a better prediction performance with a lower averaged relative standard deviations of prediction (ARSDP) value of 8.13%, in comparison with our previous research and related literature results. The LIBS technology combined with matrix effect classification regression model can weaken the influence of the complex matrix effect of biochar and achieve accurate quantification of contaminated metal Cr in biochar.     

On-line monitoring of all-acrylic emulsion polymerization reactors by Raman spectroscopy

Fourier Transform Raman spectroscopy was used as an on-line sensor in order to monitor high solids content (50 wt%) n-BA/MMA emulsion copolymerization reactions. Due to the similarity of the chemical structure of the monomers, no separate bands could be detected for each monomer, and therefore a multivariate calibration technique was required (Partial Least Squares Regression, PLSR). Using experimental data from several semi-batch reactions independent PLSR models were built for the solids content, cumulative copolymer composition and unreacted amounts of n-BA and MMA. Those models were experimentally validated by monitoring reactions not used for calibration. It is demonstrated that FT-Raman spectroscopy can be successfully applied to on-line monitor emulsion polymerization reactors. This technique also shows a high potential for process control purposes because independent information about several molecular properties can be obtained from a single apparatus.     

Light at the interface: the potential of attenuated total reflection infrared spectroscopy for understanding heterogeneous catalysis in water

IR spectroscopy has been an important tool for studying detailed interactions of reactants and reaction-intermediates with catalyst surfaces. Studying reactions in water is, however, far from trivial, due to the excessive absorption of infrared light by water. One way to deal with this is the use of Attenuated Total Reflection spectroscopy (ATR-IR) minimizing the path length of infrared light through the water. Moreover, ATR-IR allows for a direct comparison of reactions in gas and water on the same sample, which bridges the gap between separate catalyst investigations in gas and liquid phase. This tutorial review describes recent progress in using ATR-IR for studying heterogeneous catalysts in water. An overview is given of the important aspects to be taken into account when using ATR-IR to study heterogeneous catalysts in liquid phase, like the procedure to prepare stable catalyst layers on the internal reflection element. As a case study, CO adsorption and oxidation on noble metal catalysts is investigated with ATR-IR in gas and water. The results show a large effect of water and pH on the adsorption and oxidation of CO on Pt/Al(2)O(3) and Pd/Al(2)O(3). From the results it is concluded that water affects the metal particle potential as well as the adsorbed CO molecule directly, resulting in higher oxidation rates in water compared to gas phase. Moreover, also pH influences the metal particle potential with a clear effect on the observed oxidation rates. Finally, the future outlook illustrates that ATR-IR spectroscopy holds great promise in the field of liquid phase heterogeneous catalysis.     

基于粒子群算法的最小二乘支持向量机在红花提取液近红外定量分析中的应用

提出一种基于粒子群算法的最小二乘支持向量机(PSO-LS-SVM)方法,用于建立红花提取过程关键质控指标的定量分析模型.近红外光谱数据经波段选择、预处理和主成分分析(降维)后,利用粒子群优化(PSO)算法对最小二乘支持向量机算法中的参数进行优化,然后使用最优参数建立固含量和羟基红花黄色素A(HSYA)浓度的定量校正模型.将校正结果与偏最小二乘法回归(PLSR)和BP神经网络(BP-ANN)比较,并将所建的3个模型用于红花提取过程未知样本的预测.结果表明,BP-ANN校正结果优于PSO-LS-SVM和PLSR,但是对验证集和未知样品集的预测能力较差,而PSO-LS-SVM和PLSR模型的校正、验证结果相近,相关系数均大于0.987,RMSEC和RMSEP值相近且小于0.074,RPD值均大于6.26,RSEP均小于5.70％.对于未知样品集,pSO-LS-SVM模型的RPD值大于8.06,RMSEP和RSEP值分别小于0.07％和5.84％,较BP-ANN和PLSR模型更低.本研究所建立的PSO-LS-SVM模型表现出较好的模型稳定性和预测精度,具有一定的实践意义和应用价值,可推广用于红花提取过程的近红外光谱定量分析.     

Application of FT-Raman Spectroscopy and Chemometric Analysis for Determination of Adulteration in Milk Powder

In this work, FT-Raman spectroscopy is explored as a rapid technique for the assessment of the milk powder quality. Based on information provided by Raman spectra of samples adulterated with starch and whey, a quantitative method is developed to identify the fraud, using Partial Least Squares regression (PLS). In regression models using PLS the results are satisfactory, and such models can be used to identify and quantify samples presenting whey and starch in milk powder at concentrations of 2.32% and 1.64% (w/w), respectively. In the whey determination, the obtained values in the PLS model of the new samples are compared with those obtained by the spectrophotometric method of acid ninhydrin. This result shows that there is no significant difference with the 95% level of confidence between the values provided by the PLS regression method and the acid ninhydrin. The present work shows Raman spectroscopy as an analytical tool which can be used in quality control of milk powder, even in fraud processes, and the calculated figures of merit such as sensitivity, accuracy, limit of detection and limit of quantification clearly demonstrate this potential use. Although the multivariate models developed are not strictly quantitative, especially for low concentrations, they can be used as screening methods for routine analysis, as showed by this work.