仪器噪声在近红外光谱偏最小二乘模型内的传播效应

在实际多元校正应用中有很多因素会影响偏最小二乘(PLS)模型的预测效果,作为光谱数据本源的仪器噪声是其中的重要影响因素。以往的研究工作多使用各种滤波器或平滑方法来降低仪器噪声的影响,然而对于仪器噪声如何影响偏最小二乘的建模过程和模型预测能力鲜有报道。该文阐述并论证了仪器噪声怎样通过第一个隐变量的计算被引入模型中,经过对偏最小二乘计算过程的理论推导,论述了噪声的引入对偏最小二乘权重向量、载荷向量计算具有累积效应,并随着后续隐变量的计算不断在模型中传递,从而对偏最小二乘模型产生影响。同时对偏最小二乘模型的预测误差进行理论分解,将其划分为无噪理想模型本身的误差和由噪声传播导致的误差。结果表明,仪器噪声不仅会降低偏最小二乘模型的预测性能,还会影响偏最小二乘模型的最优复杂度选择。     

应用多模型共识偏最小二乘法和FTIR/ATR光谱技术建立苯丙酮尿症的筛查模型

利用多模型共识偏最小二乘法(cPLS)建立新生儿苯丙酮尿症(PKU)的红外光谱筛查模型,比较PLS和cPLS模型的性能。对原始光谱进行一阶微分预处理,分别用PLS和cPLS建立干血片中苯丙氨酸浓度的定量校正模型,各运行40次,以预测均方根误差(RMSEP)、平均相对误差(MRE)和预测准确率(Acc)为指标,考察两种模型对独立测试集的预测效果。PLS模型的RMSEP、MRE、Acc的平均值和标准差分别为103.3、0.32、97.1和30.0、0.07、4.4;而cPLS模型的RMSEP、MRE、Acc的平均值和标准差分别为88.4、0.26、99.3和19.8、0.04、2.4。cPLS较PLS模型预测更准确,稳定性更好,更适于建立PKU的红外光谱筛查模型。     

近红外光谱法对头孢氨苄粉末药品的非破坏定量分析

采用近红外漫反射光谱法对头孢氨苄粉末药品中主要成分头孢氨苄进行快速、无损定量分析.采用偏最小二乘法建立近红外光谱信息与待测组分含量间的最佳数学校正模型.对3种光谱(SNV光谱、一阶导数、二阶导光谱)的预测结果进行了比较,讨论了光谱的预处理方法和主成分数对偏最小二乘法定量预测能力的影响,并对预测集样品进行预测.     

多模型共识偏最小二乘法用于近红外光谱定量分析

将多模型共识偏最小二乘法用于近红外光谱定量分析。利用随机抽取的训练子集建立一系列偏最小二乘模型,选取其中性能较好的部分模型作为成员模型,用这些成员模型来预测未知样品。将该方法用于一组生物样本的近红外光谱与样品中人血清白蛋白、γ-球蛋白以及葡萄糖含量之间的建模研究,并与单模型偏最小二乘法了进行比较。结果 PLS对独立测试集中三种组分进行50次重复预测的平均RMSEP分别为0.1066,0.0853和0.1338,RMSEP的标准偏差分别为0.0174,0.0144和0.0416;而本方法重复预测的平均RMSEP分别为0.0715,0.0750和0.0781,RMSEP的标准偏差分别为0.0033,0.2729×10-4和0.0025。     

复杂样品近红外光谱定量分析模型的构建方法

针对复杂样品近红外光谱分析中校正集的设计问题, 探讨了标准样品参与复杂样品建模的可行性. 通过标准样品和复杂基质样品共同构建的偏最小二乘(PLS)模型, 考察了波段筛选和建模参数对预测结果的影响. 结果表明, 采用PLS方法建立定量模型时, 校正集样品性质应该尽量与预测集样品相似, 当样品的性质相差较大时, 适当增加校正集样品的差异性可使模型具有更强的预测能力. 同时, 波段优选对提高预测结果的准确性具有重要的意义.     

土壤总氮近红外光谱分析的波段优选

利用移动窗口偏最小二乘( MWPLS)和Savitzky-Golay(SG)平滑方法优选土壤总氮的近红外(NIR)光谱分析模型.从全部97个土壤样品中随机选出35个样品作为检验集;基于偏最小二乘交叉检验预测偏差(PLSPB),将余下62个样品划分为具有相似性的建模定标集(37个样品)、建模预测集(25个样品).最优波段为1692～2138 nm,SG平滑的导数阶数(OD)、多项式次数(DP)、平滑点数(NSP)分别为0,6,69,PLS因子数为11,建模预测均方根偏差(M-RMSEP)、建模预测相关系数(M-Rp)分别为0.015％,0.931,检验预测均方根偏差(V-RM-SEP)、检验预测相关系数(V-RP)分别为0.018％,0.882.其结果可为设计专用NIR仪器提供有价值的参考.     

基于最小二乘支持向量机的油页岩含油率近红外光谱分析

为了提高油页岩含油率近红外光谱分析建模的预测精度和稳定性,开展了基于最小二乘支持向量机(LS-SVM)建模方法的对比研究.采用主成分-马氏距离(PCA-MD)和基于蒙特卡洛采样(MCS)2种方法进行了奇异样本的检测,采用径向基核函数的LS-SVM、偏最小二乘(PLS)和反向传播神经网络(BPANN)3种方法进行建模方法对比.结果表明,对于64个油页岩岩芯样本,与PCA-MD方法相比,采用MCS方法剔除奇异样本后所建PLS模型的预测精度提高了28%.对于MCS方法剔除奇异样本后的58个样品,采用KennardStone法划分了44个样品的校正集和14个样品的预测集,采用2阶导数和标准化预处理方法,建立了100个LS-SVM的校正模型,模型的预测决定系数R2平均值达到0.90以上,高于PLS和BPANN模型的对应值;且R2的变化量(0.02)小于BPANN模型的对应值(0.32).因此,MCS奇异样本检测结合LS-SVM方法可提高油页岩含油率样本建模的精度和稳定性.     

拉曼光谱结合后向间隔偏最小二乘法用于调和汽油辛烷值定量分析

采用后向间隔偏最小二乘(Backward interval partial least squares,BiPLS)提取汽油拉曼光谱特征谱段,并用于研究法辛烷值(Research octane number,RON)的定量分析。实验中首先使用SPXY(Sample set partitioning based on joint x-y distances)方法划分训练集、交叉验证集和测试集,并采用稳健回归方法剔除异常的样本数据,再结合BiPLS方法筛选特征谱段,利用特征谱段建立偏最小二乘模型。与全谱段偏最小二乘模型的预测性能对比结果表明,后向间隔偏最小二乘方法可使输入模型的特征数据维数降低50.00%,交叉验证均方根误差(Root mean square error of cross validation,RMSECV)降低18.92%,预测均方根误差(Root mean square error of prediction,RMSEP)降低13.86%。后向间隔偏最小二乘方法可有效提取汽油拉曼光谱的特征谱段,降低模型复杂度,同时提高模型预测精度,在调和汽油研究法辛烷值定量分析方面有较好的应用前景。     

CARSiPLS用于烟煤中水分与挥发分的近红外光谱测定北大核心CSCD

将竞争自适应重加权采样(CARS)与区间偏最小二乘回归(iPLS)相结合的变量筛选建模方法 CARSiPLS,用于烟煤中水分与挥发分的近红外光谱测定。以CARS逐步筛选出每个区间与待测量相关的变量,建立烟煤中水分与挥发分近红外光谱测定的偏最小二乘回归模型。结果表明:与PLS、iPLS相比,CARSiPLS可以显著减少变量数,同时提高模型预测性能;挥发分建模变量从1557个减少至15个,水分建模变量从1557个减少至317个;挥发分、水分的预测平均绝对百分误差分别从0.031 5降至0.018 4、从0.188 4降至0.094 6;挥发分、水分的预测均方差分别从0.010 8降至0.006 7、从0.005 0降至0.002 8。     

红外光声光谱技术结合区间、组合区间偏最小二乘测定油菜籽含氮量和含油量

应用红外光声光谱技术结合区间、组合区间偏最小二乘,建立了油菜籽含氮量和含油量的校正模型。结果表明,红外光声光谱技术可以应用于油菜籽品质的快速测定。相对于全谱偏最小二乘建模,区间、组合区间偏最小二乘的采用筛选出了含氮量和含油量的相关波段,使模型简化,并提高了模型预测精度。     

A Partial Least Squares‐Based Consensus Regression Method for the Analysis of Near‐Infrared Complex Spectral Data of Plant Samples

Abstract

A consensus regression approach based on partial least square (PLS) regression, named as cPLS, for calibrating the NIR data was investigated. In this approach, multiple independent PLS models were developed and integrated into a single consensus model. The utility and merits of the cPLS method were demonstrated by comparing its results with those from a regular PLS method in predicting moisture, oil, protein, and starch contents of corn samples using the NIR spectral data. It was found that cPLS was superior to regular PLS with respect to prediction accuracy and robustness.     

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.     

A practical approach for near infrared spectral quantitative analysis of complex samples using partial least squares modeling

The number of latent variables (LVs) or the factor number is a key parameter in PLS modeling to obtain a correct prediction. Although lots of work have been done on this issue, it is still a difficult task to determine a suitable LV number in practical uses. A method named independent factor diagnostics (IFD) is proposed for investigation of the contribution of each LV to the predicted results on the basis of discussion about the determination of LV number in PLS modeling for near infrared (NIR) spectra of complex samples. The NIR spectra of three data sets of complex samples, including a public data set and two tobacco lamina ones, are investigated. It is shown that several high order LVs constitute main contributions to the predicted results, albeit the contribution of the low order LVs should not be neglected in the PLS models. Therefore, in practical uses of PLS for analysis of complex samples, it may be better to use a slightly large LV number for NIR spectral analysis of complex samples. Supported by the National Natural Science Foundation of China (Grant Nos. 20775036 & 20835002)     

A strategy for enhancing the reliability of near-infrared spectral analysis

Near-infrared (NIR) spectroscopy will present a more promising tool for quantitative measurement if the reliability of the calibration model is further improved. To achieve this purpose, a new partial least squares (PLSs) technique based on Monte Carlo (MC) resampling is proposed, which is named as MCPLS. In this method, the outliers are firstly removed based on probability statistics. Then, the models without outliers are averaged and combined into a single prediction model as done in a consensus modeling, which can greatly enhance the reliability of PLS calibration. To validate the effectiveness and universality of the proposed method, it was applied to two different sets of NIR spectra. It was found that MCPLS could effectively avoid the swamping and masking effects caused by multiple outliers. The results show that the method is of value to enhance the reliability of PLS model involving complex NIR matrices with a small number of outliers.     

激光诱导击穿光谱结合CARS变量选择方法定量检测倍硫磷含量

利用双脉冲激光诱导击穿光谱(LIBS)技术对溶液中的倍硫磷含量进行定量检测。采用二通道高精度光谱仪采集不同浓度倍硫磷样品在206.28~481.77 nm波段的LIBS光谱,并对光谱进行多元散射校正(MSC)、标准正态变量变换(SNV)及3点平滑预处理,根据偏最小二乘(PLS)建模确定最优的预处理方法。在此基础上,利用竞争性自适应重加权算法(CARS)筛选与倍硫磷相关的重要变量,然后应用PLS回归建立溶液中倍硫磷含量的定量分析模型,并与单变量定量分析模型及未变量选择的PLS定量分析模型进行比较。结果表明,相比单变量定量分析模型及原始光谱PLS定量分析模型,CARS-PLS定量分析模型的性能更优,其模型的校正集和预测集的决定系数及平均相对误差分别为0.969 4、15.537%和0.995 9、5.016%。此外,与原始光谱PLS模型相比,CARS-PLS模型仅使用其中1.9%的波长变量,但预测集平均误差却由9.829%下降为5.016%。由此可见,LIBS技术检测溶液中的倍硫磷含量具有一定的可行性,且CARS方法能简化定量分析模型,提高模型的预测精度。     

Quantitative Determination of the Components in Corn and Tobacco Samples by Using Near-Infrared Spectroscopy and Multiblock Partial Least Squares

Multiblock partial least squares (MB-PLS) are applied for determination of corn and tobacco samples by using near-infrared diffuse reflection spectroscopy. In the model, the spectra are separated into several sub-blocks along the wavenumber, and different latent variable number was used for each sub-block. Compared with ordinary PLS, the importance and the contribution of each sub-block can be balanced by super-weights and the usage of different latent variable numbers. Therefore, the prediction obtained by the MB-PLS model is superior to that of the ordinary PLS, especially for the large data sets of tobacco samples with a large number of variables.     

Rapid determination of total trihalomethanes index in drinking water

A method for the rapid determination of total trihalomethanes (THMs) index in drinking water has been developed by using a headspace-mass spectrometry (HS-MS) system and partial least squares (PLS) multivariate regression approach. Due to the presence of residual amounts of chlorine and organic matter in the drinking water, the use of a quenching reagent in order to avoid THM generation during the sample manipulation is necessary. The optimization experiments revealed that ascorbic acid was the best quenching reagent compared with sodium thiosulfate and ammonium sulfate. The use of a classification chemometric technique as soft independent modeling of class analogy before the PLS regression improved the results obtained in the prediction of the total THMs index, lowering the relative standard error of prediction (RSEP) from 11.4% to lower than 6.0%. The results obtained by the proposed HS-MS method were compared with those provided by a conventional chromatographic method after analyzing 20 real drinking water samples. A good agreement in the results was observed and no systematic differences were found, which corroborates the good performance of the proposed method.     

LapRLSR for NIR spectral modeling and its application to online monitoring of the column separation of Salvianolate

A novel near infrared (NIR) modeling method—Laplacian regularized least squares regression (LapRLSR) was presented, which can take the advantage of many unlabeled spectra to promote the prediction performance of the model even if there are only few calibration samples. Using LapRLSR modeling, NIR spectral analysis was applied to the online monitoring of the concentration of salvia acid B in the column separation of Salvianolate. The results demonstrated that LapRLSR outperformed partial least squares (PLS) significantly, and NIR online analysis was applicable.     

应用遗传算法和PLS的近红外光谱预测玉米中淀粉含量的研究

以普通玉米籽粒为试验材料,在应用遗传算法结合偏最小二乘回归法对近红外光谱数据进行特征波长选择的基础上,应用偏最小二乘回归法建立了特征波长测定玉米籽粒中淀粉含量的校正模型．试验结果表明,基于11个特征波长所建立的校正模型,其校正误差（RMSEC）、交叉检验误差（RMSECV）和预测误差（RMSEP）分别为0.30％、0.35％和0.27％,校正数据集和独立的检验数据集的预测值与实际测定值之间的相关系数分别达到0.9279和0.9390,与全光谱数据所建立的预测模型相比,在预测精度上均有所改善,表明应用遗传算法和PLS进行光谱特征选择,能获得更简单和更好的模型,为玉米籽粒中淀粉含量的近红外测定和红外光谱数据的处理提供了新的方法与途径．