便携式X射线荧光光谱法结合支持向量回归算法定量分析土壤中的砷含量

研究了基于统计学习理论的支持向量机（SVM）回归法在X射线荧光光谱定量分析中的应用。以39个农田土壤样品作为实验材料,以其中32个土壤样品作为校正集,选用SVM模型中Linear、Poly和RBF 3种核函数对As元素含量与荧光光谱数据进行回归建模。用3种不同模型对预测集中7个土壤样品的As元素含量进行预测分析,结果显示模型预测As元素含量与电感耦合等离子体发射光谱法测定的As元素含量之间的相关系数R2均大于0.99,相对分析误差RPD均大于3,表明所建立的SVM模型具有较好的使用价值。为了进一步考察SVM回归模型的预测效果,同应用较成熟的PLS回归模型的预测结果进行对比,结果显示SVM法的预测结果更好,表明SVM回归模型亦可用于便携式X射线荧光光谱法的定量预测分析。     

植物纤维材料中化学成分含量模型的建立和含量测定方法

一种植物纤维材料中化学成分含量模型的建立方法，该方法包括采集植物纤维材料样品的近红外光谱，并采用化学计量学方法根据该近红外光谱建立植物纤维材料样品中化学成分含量的定量分析模型，其中，所述植物纤维材料样品至少部分为混合植物纤维材料样品，该混合植物纤维材料样品为所述至少一种化学成分含量已知的植物纤维材料样品的混合物。采用本发明提供的模型建立方法，只需要采集少量的化学成分含量分布不同的几个植物纤维粉末样品，即可获得建模所需的较多的化学含量不同的其它样品，从而大大减少样品的实地采集量，提高建模速度。通过控制化学含量的均匀分布还能够有效地提高模型的准确度。     

近红外反射光谱法分析玉米秸秆纤维素含量的研究

利用近红外反射光谱分析技术和偏最小二乘回归法（PLS）,通过比较不同光谱范围和光谱预处理方法,采用二阶导数光谱预处理,在7540．3-5361．1cm^-1和4882.9—4504．9cm^-1谱区内建立了近红外光谱测定玉米秸秆纤维素含量的校正模型。利用15个玉米秸秆样品对所建模型的实际预测效果进行了验证,预测值与化学值的相关系数（r）可达0．9953,最大相对误差仅为5．20。结果表明,近红外光谱技术可以快速、准确地测定玉米秸秆纤维素,该结果对玉米秸秆材料的快速鉴定和筛选利用具有重要的意义。     

藏药五脉绿绒蒿提取过程的在线近红外光谱质量控制研究北大核心CSCD

利用近红外光谱技术和自建的在线检测系统,实现了藏药五脉绿绒蒿提取过程中总黄酮含量的在线近红外光谱监测和提取终点的判定。以403个样品为建模集,分别获得了主成分回归(PCR)、偏最小二乘(PLS)、决策树(DT)、随机森林(RF)算法下的最佳光谱预处理方法和建模区间,以残差预测偏差(RPD)值为指标选择最佳建模方法。以62个样品为外部验证集,考察模型应用于总黄酮含量实时监测的可行性。此外,还探讨了利用模型预测值进行相对浓度变化率(RCCR)分析直接判定提取终点的可行性,并比较了标准偏差绝对距离法(ADSD)和移动窗口标准偏差法(MBSD)对提取终点判定的适用性。结果表明,在预处理方法为Constant+一阶导数+SG平滑、建模区间5300~9000 cm^(-1)条件下所建的总黄酮含量的PLS模型效果最好,其校正集和验证集的误差均方根均小于0.14、相关系数均大于0.97,RPD值为4.68。所建PLS模型对未知样品的平均预测率为79%,实际值与预测值的相关系数大于0.98,表明模型有较好的预测效果。外部验证集中RCCR法判定的预测提取终点和ADSD法判定的提取终点均与实际提取终点一致。所建模型性能较好,通过对未知样品进行准确快速的定量分析,实现了五脉绿绒蒿提取过程中总黄酮含量的实时监测,同时,以RCCR和ADSD作为提取终点的判定方法较为准确,可为藏药材提取过程在线近红外光谱分析技术的研究提供有益借鉴。     

PDS用于不同温度下的近红外光谱模型传递研究

采用合适的计算方法可降低测定环境对近红外光谱校正模型稳健性的影响。该文以喷气燃料为研究对象,考察了分段直接校正算法对所建模型预测结果的影响,通过选择转移样品数及窗口宽度,建立了最佳的校正模型和光谱转移参数。结果表明,在20℃下建立近红外光谱校正模型,直接预测30℃下喷气燃料的密度,预测集样品均方根误差（RMSEP）为0.2031,而30℃近红外光谱采用分段直接校正算法模型转移后,预测集样品均方根误差（RMSEP）降低为0.1354,预测结果得到明显改善,有效地解决了样品温度对近红外光谱分析结果的影响。     

烟草组分的近红外光谱和支持向量机分析

测定了120个产自福建、安徽和云南烟草样品的近红外光谱. 在利用支持向量机(SVM)技术建立其定量、定性分析模型之前, 用小波变换技术对光谱变量进行了有效的压缩, 然后采用径向基核函数建立了75个烟草样品的分类模型, 同时建立了总糖、还原糖、烟碱和总氮4个组分的定量分析模型, 并利用45个烟草样品对模型进行了检验. 仿真实验表明, 建立的SVM分类模型分类准确率达到100%, 而4个组分的定量分析模型的预测决定系数(R2)、预测均方差(RMSEP)和平均相对误差(RME)3个指标值显示其模型泛化能力非常强, 预测效果良好, 可见这是一种有效的近红外光谱的建模分析方法.     

组合偏最小二乘回归方法在近红外光谱定量分析中的应用

针对近红外光谱数据局部效应显著,变量个数多,彼此间常存在严重的复共线性,并多与样品组分含量呈非线性关系,构建一种组合非线性偏最小二乘回归(E-S-QPLSR)方法。它采用无重复采样技术(subag-ging),从训练样本中生成若干子样,然后每个子样通过二次多项式偏最小二乘回归(QPLSR),建立其子模型,并实现对训练样本因变量的定量预测,再将它们交由线性PLS算法用于计算各子模型的组合权系数。将该法应用于80个玉米样品的水组分含量与其近红外光谱的定量关系建模,效果良好,显示出很强的学习能力,所建模型的预报性能也优于其它方法。     

近红外光谱法测定30%TBP/正十二烷中硝酸含量

核燃料后处理工艺控制分析中,有机相中硝酸含量是一项重要的控制参数。通过研究TBP/正十二烷介质中硝酸的近红外光谱,将有机相样品的傅立叶变换近红外光谱与偏最小二乘回归法相结合,建立了含铀后处理有机相样品中硝酸浓度的测量方法。建立的定量校正模型的最佳校正标准偏差(RMSEC)、预测标准偏差(RMSEP)以及相关系数(r)分别为0.011,0.014,0.999。方法检出限为0.05 mol/L,测量结果的相对标准偏差不大于4%(n=6)。采用近红外分析法与滴定法对模拟样品进行测量,对测量结果进行t检验,结果表明两种方法的测定结果无显著性差异。所建方法无需样品预处理,可直接测量,分析速度快,结果准确,具有一定的实用性。     

近红外光谱相似性评估结合局部回归方法无损检测苹果糖度

基于Bayesian相似性评估方法结合偏最小二乘局部回归,对苹果近红外数据库进行数据挖掘。通过相似性计算方法搜索出与预测样品相近的近红外光谱,形成校正子集后采用局部回归方法获得待测样品的相关信息。该方法所建立局部模型的平均检验标准偏差(SEV)约为0.57,分析30个预测样品的预测标准偏差(SEP)约为0.61;基于马氏距离的传统方法建立的偏最小二乘局部模型的平均SEV为0.59,分析30个待测样品的预测SEP为0.64;而采用整个数据库建立的全局偏最小二乘模型的SEV约为0.65,分析30个预测样品SEP约为0.70。基于Bayesian相似性评估的局部回归方法在苹果糖度的近红外无损定量分析中获得较好的应用结果,在实际应用中该方法比全局回归方法具有更强的适用性,为近红外光谱分析提供了新的分析工具。     

近红外光谱结合LSTSVM算法判别不同等级烟叶

本文用近红外光谱结合最小二乘双胞胎支持向量机(LSTSVM)算法建立了烟叶等级分类模型。从三个等级共210个烟叶样品中,取出120个样品作为建模集,剩余90个样品作为预测集。为了建立最优模型,对光谱预处理方法和模型参数进行筛选优化,最优模型对预测集样品的平均识别率为95.56%,结果表明该方法可以作为烟叶等级分类的一种有效方法。此外,将该算法与SIMCA、PLS-DA、SVM等三种常见的模式识别算法进行了比较,结果表明基于样品的原始光谱,同等条件下,LSTSVM算法的预测效果优于其他三种算法。     

Qualitative and quantitative analysis of oxytetracycline by near-infrared spectroscopy

Near-infrared (NIR) spectroscopy, in combination with chemometrics, enable the analysis of raw materials without time-consuming sample preparation methods. The aim of our work was to estimate critical parameters in the analytical specification of oxytetracycline, and consequently the development of a method for quantification and qualification of these parameters by NIR spectroscopy. A Karl Fischer (K.F.) titration to determine the water content, a colorimetric assay method, and Fourier transform-infrared (FT-IR) spectroscopy to identify the oxytetracycline base, were used as reference methods, respectively. Multivariate calibration was performed on NIR spectral data using principal component analysis (PCA), partial least-squares (PLS 1) and principal component regression (PCR) chemometric methods. Multivariate calibration models for NIR spectroscopy have been developed. Using PCA and the Soft Independent Modelling of Class Analogy (SIMCA) approach, we established the cluster model for the determination of sample identity. PLS 1 and PCR regression methods were applied to develop the calibration models for the determination of water content and the assay of the oxytetracycline base. Comparing the PLS and PCR regression methods we found out that the PLS is better established by NIR, especially as the spectroscopic data (NIR spectra) are highly collinear and there are many wavelengths due to non-selective wavelengths. The calibration models for NIR spectroscopy are convenient alternatives to the colorimetric method and to the K.F. method, as well as to FT-IR spectroscopy, in the routine control of incoming material.     

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.     

Chemometric Techniques Applied for Classification and Quantification of Binary Biodiesel/Diesel Blends

In this paper, three different types of biodiesel, which were synthesized from peanut, corn, and canola oils, were characterized by positive-ion electrospray ionization (ESI) and Fourier transform ion cyclotron resonance mass spectrometry (FT-ICR MS). Different biodiesel/diesel blends containing 2–90% (V/V) of each biodiesel type were prepared and analyzed by near infrared spectroscopy (NIR). In the next step, the chemometric methods of hierarchical clusters analysis (HCA), principal component analysis (PCA), and support vector machines (SVM) were used for exploratory analysis of the different biodiesel samples, and the SVM was able to give the best classification results (correct classification of 50 peanut and 50 corn samples, and only one misclassification out of 49 canola samples). Then, partial least squares (PLS) and multivariate adaptive regression splines (MARS) models were evaluated for biodiesel quantification. Both methods were considered equivalent for quantification purposes based on the values smaller than 5% for the root mean square error of calibration (RMSEC) and root mean square of validation (RMSEP), as well as Pearson correlation coefficients of at least 0.969. The combination of NIR to the chemometric techniques of SVM and PLS/MARS was proven to be appropriate to classify and quantify biodiesel from different origins.     

A consensus least squares support vector regression (LS-SVR) for analysis of near-infrared spectra of plant samples

Consensus modeling of combining the results of multiple independent models to produce a single prediction avoids the instability of single model. Based on the principle of consensus modeling, a consensus least squares support vector regression (LS-SVR) method for calibrating the near-infrared (NIR) spectra was proposed. In the proposed approach, NIR spectra of plant samples were firstly preprocessed using discrete wavelet transform (DWT) for filtering the spectral background and noise, then, consensus LS-SVR technique was used for building the calibration model. With an optimization of the parameters involved in the modeling, a satisfied model was achieved for predicting the content of reducing sugar in plant samples. The predicted results show that consensus LS-SVR model is more robust and reliable than the conventional partial least squares (PLS) and LS-SVR methods.     

Construction of global and robust near-infrared calibration models based on hybrid calibration sets using Partial Least Squares (PLS) regression

Near-infrared spectroscopy (NIR) models built on a particular instrument are often invalid on other instruments due to spectral inconsistencies between the instruments. In the present work, global and robust NIR calibration models were constructed by partial least square (PLS) regression based on hybrid calibration sets, which are composed of both primary and secondary spectra. Three datasets were used as case studies. The first consisted of 72 radix scutellaria samples measured on two NIR spectrometers with known baicalin content. The second was composed of 80 corn samples measured on two instruments with known moisture, oil, and protein concentrations. The third dataset included 279 primary samples of tobacco with known nicotine content and 78 secondary samples of tobacco with known nicotine concentrations. The effect of the number of secondary spectra in the hybrid calibration sets and the methods for selecting secondary spectra on the PLS model performance were investigated by comparing the results obtained from different calibration sets. This study shows that the global and robust calibration models accurately predicted both primary and secondary samples as long as the ratios of the number of primary spectra to the number of secondary spectra were less than 22. The models performance was not influenced by the selection method of the secondary spectra. The hybrid calibration sets included the primary spectral information and also the secondary spectra; information, rendering the constructed global and robust models applicable to both primary and secondary instruments.     

Measurement of the percentage volume particle size distribution of powdered microcrystalline cellulose using reflectance near-infrared spectroscopy

This is the first reported method for determining the percentage volume particle size distribution of a powder (microcrystalline cellulose) by near-infrared (NIR) reflectance spectroscopy. A total of 113 samples of powdered microcrystalline cellulose were used from six different commercially available grades, with different moisture contents (range: 0.9-4.8% m/m). NIR reflectance measurements of these samples were made in narrow soda glass vials. Reference particle size data for the samples were acquired by laser diffraction. The NIR data were then calibrated to measure particle size by partial least squares regression. The effects of a range of different NIR data pre-treatments on calibration and prediction precision were investigated. Overall, simple absorbance data were found to produce regression models with the best predictive ability (root mean square error of prediction = 0.90%). The method was also found to be insensitive to moisture content.     

Prediction of wood property in Chinese Fir based on visible/near-infrared spectroscopy and least square-support vector machine

A method for the quantification of density of Chinese Fir samples based on visible/near-infrared (vis–NIR) spectrometry and least squares-support vector machine (LS-SVM) was proposed. Sample set partitioning based on joint x–y distances (SPXY) algorithm was used for dividing calibration and prediction samples, it is of value for prediction of property involving complex matrices. A stepwise procedure is employed to select samples according to their differences in both x (instrumental responses) and y (predicted parameter) spaces. For comparison, the models were also constructed by Kennard–Stone method, as well as by using the duplex and random sampling methods for subset partitioning. The results revealed that the SPXY algorithm may be an advantageous alternative to the other three strategies. To validate the reliability of LS-SVM, comparisons were made among other modeling methods such as support vector machine (SVM) and partial least squares (PLS) regression. Satisfactory models were built using LS-SVM, with lower prediction errors and superior performance in relation to SVM and PLS. These results showed possibility of building robust models to quantify the density of Chinese Fir using near-infrared spectroscopy and LS-SVM combined SPXY algorithm as a nonlinear multivariate calibration procedure.     

Non-linear calibration models for near infrared spectroscopy

Different calibration techniques are available for spectroscopic applications that show nonlinear behavior. This comprehensive comparative study presents a comparison of different nonlinear calibration techniques: kernel PLS (KPLS), support vector machines (SVM), least-squares SVM (LS-SVM), relevance vector machines (RVM), Gaussian process regression (GPR), artificial neural network (ANN), and Bayesian ANN (BANN). In this comparison, partial least squares (PLS) regression is used as a linear benchmark, while the relationship of the methods is considered in terms of traditional calibration by ridge regression (RR). The performance of the different methods is demonstrated by their practical applications using three real-life near infrared (NIR) data sets. Different aspects of the various approaches including computational time, model interpretability, potential over-fitting using the non-linear models on linear problems, robustness to small or medium sample sets, and robustness to pre-processing, are discussed. The results suggest that GPR and BANN are powerful and promising methods for handling linear as well as nonlinear systems, even when the data sets are moderately small. The LS-SVM is also attractive due to its good predictive performance for both linear and nonlinear calibrations.     

Measurement of the cumulative particle size distribution of microcrystalline cellulose using near infrared reflectance spectroscopy

The cumulative particle size distribution of microcrystalline cellulose, a widely used pharmaceutical excipient, was determined using near infrared (NIR) reflectance spectroscopy. Forward angle laser light scattering measurements were used to provide reference particle size values corresponding to different quantiles and then used to calibrate the NIR data. Two different chemometric methods, three wavelength multiple linear regression and principal components regression (three components), were compared. For each method, calibration equations were produced at each of eleven quantiles (5, 10, 20, 30, 40, 50, 60, 70, 80, 90, 95%). NIR predicted cumulative frequency particle-size distributions were calculated for each of the calibration samples (n = 34) and for an independent test set (n = 23). The NIR procedure was able to predict those obtained via forward angle laser light scattering.     

An adaptive strategy for selecting representative calibration samples in the continuous wavelet domain for near-infrared spectral analysis

Sample selection is often used to improve the cost-effectiveness of near-infrared (NIR) spectral analysis. When raw NIR spectra are used, however, it is not easy to select appropriate samples, because of background interference and noise. In this paper, a novel adaptive strategy based on selection of representative NIR spectra in the continuous wavelet transform (CWT) domain is described. After pretreatment with the CWT, an extension of the Kennard–Stone (EKS) algorithm was used to adaptively select the most representative NIR spectra, which were then submitted to expensive chemical measurement and multivariate calibration. With the samples selected, a PLS model was finally built for prediction. It is of great interest to find that selection of representative samples in the CWT domain, rather than raw spectra, not only effectively eliminates background interference and noise but also further reduces the number of samples required for a good calibration, resulting in a high-quality regression model that is similar to the model obtained by use of all the samples. The results indicate that the proposed method can effectively enhance the cost-effectiveness of NIR spectral analysis. The strategy proposed here can also be applied to different analytical data for multivariate calibration.