烟叶总还原糖近红外光谱稳健模型的建立及其在多台仪器的长期应用

该文使用基于光谱图像特征抽提的尺度不变特征变换（SIFT）的多步波长筛选方法建立了烟叶总还原糖（TRS）的近红外光谱（NIRS）稳健模型，实现了其在多台仪器的直接共享和长期应用。首先采用SIFT方法根据代表性主机样品光谱挑选特征光谱点集合Uc，然后从Uc中剔除样本光谱标准方差（SDSS）过低的点，挑选重要特征光谱点集合Uic，此两步波长筛选法简称为SIFT-SDSS。随后进一步从Uic中挑选对水分不敏感（Moisture-unsensitive,MUS）的波长点，得到重要且稳定的光谱点集合Uisc，此3步波长筛选法简称为SIFT-SDSSMUS。从2011～2013年采集的292个主机烟叶样品中按TRS浓度区间选择80%样品作为建模集，建立不同波长集合下烟叶TRS的偏最小二乘回归（PLSR）校正模型。结果表明，基于SIFT-SDSS两步波长筛选的光谱点建立的TRS模型传递到6台从机预测另外77个2011～2013年样品的TRS时，所有从机样品的平均相对误差绝对值（MARE）均小于6%，满足企业内控要求。该模型对5台近红外仪上2014～2020年各年度样品、1台近红外仪上2014～201...     

偏最小二乘近红外光谱模型中潜变量个数对模型传递性能的影响

以玉米中水分、蛋白质、脂肪和淀粉4种主要成分含量以及烟叶总植物碱的偏最小二乘近红外光谱(PLS-NIRs)模型传递为例,考察了模型中潜变量个数(nLVs)对模型传递误差的影响。研究发现,根据累积贡献率大于99.9%确定的玉米、烟叶样品PLS-NIRs模型的nLVs分别为1和13,nLVs=1时建立的玉米模型对两台从机样品4个成分的预测值和主机预测值的重现性指标均满足国标要求;nLVs=13时建立的烟叶总植物碱模型经分段直接校正(PDS)后,可使4台从机样品的平均相对预测误差(MRE)小于6%。采用留一交叉验证或四折交叉验证确定的玉米、烟叶PLS-NIRs模型的nLVs分别为5～10,16与19,在这些nLVs下建立的玉米PLS-NIRs模型对从机样品的预测误差显著增大,超过许可的误差范围,且模型即使经PDS校正后,从机样品预测值与主机样品预测值的重现性指标大多不满足国标要求;nLVs13时所建烟叶总植物碱PLS-NIRs模型的转移误差随nLVs增大而增大,且PDS校正后不能保证模型对所有从机样品的MRE小于6%。根据累积贡献率大于99.9%或接近99.9%为准则选取nLVs,可有效避免过拟合,提高NIRs模型的传递性能。     

基于MC-UVE-VIP两步波长筛选实现近红外光谱模型的无标样传递

该文将蒙特卡洛-无变量信息消除(MC-UVE)算法和变量重要性投影(VIP)算法结合,挑选出重要、有信息的波长变量,建立了MC-UVE-VIP两步波长筛选方法。该法首先采用MC-UVE筛选出稳定性参数大于某一阈值(M_threshold)的有信息波长集合U_UVE,然后采用VIP算法从U_UVE中筛选出VIP参数大于U_UVE中所有波长VIP均值的波长,作为重要、有信息的波长集合U_UVE-VIP。基于U_UVE-VIP建立玉米中蛋白质含量的偏最小二乘回归(PLSR)近红外光谱预测模型,模型的潜变量个数根据累计贡献率大于99.9%确定。该模型变量少、稳健、可解释性强、运算速度快,其预测两台从机样品蛋白质的平均相对误差(MARE)分别为1.64%与1.88%,均小于MC-UVE模型的从机MARE(5.40%与5.19%)和VIP模型的从机MARE(6.23%与7.16%)。因此,基于MC-UVE-VIP两步波长筛选法所建立的玉米蛋白质含量近红外光谱模型可直接传递到从机,...     

基于光谱比值分析的无标样近红外模型传递方法

测量环境及光谱仪台间差异导致近红外光谱(NIRS)模型传递到从机后,常产生较大误差。该文使用标准正态变量变换(SNV)+微分处理光谱消除光谱散射和基线漂移的影响,提出通过仪器间光谱信号比值分析筛选波长的方法(Screening wavelengths based on spectrum ratio analysis,SWSRA),选出仪器间一致性较好且样本间差异大的光谱特征波长,采用筛选出的波长信号建立待测性质的偏最小二乘近红外光谱定标模型。以80个玉米样品中水分、油、蛋白质含量及72个黄芩样品中黄芩苷含量的NIRS预测对该方法进行了检验。结果表明,SWSRA主机模型预测从机样品的各成分含量的平均相对误差均小于4.3%,明显优于全波长模型直接传递的结果,且其预测均方根残差RMSEP与文献报道的其他模型传递方法的结果相当或更优。SWSRA方法具有模型参数少、稳健、简便易行等优点,可以在同类型近红外光谱仪器之间实现模型的无标样传递。     

基于稳定一致波长筛选的无标样近红外光谱模型传递方法

测量环境及仪器间光谱信号的差异导致近红外光谱模型从主机传递到从机后,经常会产生过大误差。本研究提出了一种基于稳定一致波长筛选的无标样近红外模型传递方法(Screening stable and consistent wavelengths,SSCW),剔除主从仪器间差谱的标准偏差大于样品精密度测试光谱标准偏差的波长,以及精密度测试偏差过大的波长,筛选出仪器间光谱信号一致性好且稳定的波长建立近红外光谱定标模型。分别以玉米和黄芩样本集对本算法的有效性进行了检验。结果表明,SSCW模型传递后对从机样品的预测均方根残差RMSEP较全波长PLS模型直接传递结果小一个量级,大部分情况下优于分段直接校正算法(Piecewise direct standardization,PDS)的结果和文献报道的无标样模型传递结果。本方法具有传递性能好、模型参数少、稳健等优点,在不同仪器间可实现近红外光谱模型的无标样传递。     

波长筛选结合直接校正法用于近红外光谱模型传递研究

该文提出了一种新的传递方法模型--波长筛选结合直接校正法(WSDS).首先利用样品的性质信息筛选出最有代表性的波长点信息,然后用直接校正法消除这些信息中包含的仪器间差异,以预测标准偏差(SEP)考察模型传递的效果.利用此算法对航空煤油的近红外光谱分析模型在不同仪器之间进行传递研究.经WSDS校正后,对航空煤油密度预测的...     

基于稳定一致波长优选的综纤维素近红外分析模型传递

以实现纸浆材综纤维素含量的近红外分析模型在3台不同型号光谱仪上共享为目标,提出SWCSS-UVE及SWCSS-CARS联用算法。即分别利用竞争性自适应重加权采样算法（CARS）和无信息变量剔除（UVE）算法,减少SWCSS方法中入选的无信息或信息少波长的不利影响,以提高模型转移精度,并与单独的SWCSS和分段直接标准化算法（PDS）以及斜率截距（S/B）算法校正后的传递结果进行比较。结果表明,通过SWCSS-UVE方法最终可从稳定一致光谱信号中进一步优选出91个波长建立模型,该模型能同时应用于2台从机所测量光谱的分析,预测标准偏差（RMSEP）分别从模型转移前的2.0114和9.4518下降到了1.5919与1.6818,优于SWCSS, SWCSS-CARS和PDS以及S/B算法的结果。这表明SWCSS-UVE算法可以有效剔除SWCSS方法中包含的无效波长,简化模型传递过程,提高模型传递效率和稳健性。     

近红外光谱混合模型定量分析不同物理状态样品的研究

近红外光谱(NIRS)以漫反射模式对非均质样本进行测量时,由于其光谱散射和吸收系数差异较大,建立的校正模型准确性和稳健性较低,因此,本研究提出了一种基于均质样本和模型转移方法建立混合模型的策略,解决非均质样本近红外光谱检测的问题.以烟叶样本为研究对象,分别建立了基于Shenk专利算法(Shenk′s)、分段直接标准化(PDS)和基于典型相关分析的模型转移算法(CTCCA)的烟粉+烟丝、烟粉+烟片混合模型,用于烟丝和烟片样本中烟碱含量的预测.结果表明,混合模型对烟丝和烟片样本的预测均方误差(RMSEP)较直接建模分别降低了1.39%和2.73%,预测结果有一定的改善,稳健性提高,3种方法中CTCCA表现最优.因此,采用近红外光谱均质模型和模型转移方法建立的混合模型对非均质样本的测定具有可行性,有利于在线近红外光谱分析技术的发展,可为近红外光谱模型的共享提供参考.     

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。     

复烤片烟常规化学成分的傅里叶变换近红外光谱法的模型转移

为实现复烤片烟常规化学成分的模型在不同品牌傅里叶变换近红外仪器上的使用与共享,以贵州产区复烤片烟样品为研究对象,利用Kennard-Stone算法选择标准样品,将偏移量校正(BC)、截距斜率校正(SBC)和光谱空间转换(SST)等3种模型转移算法应用于不同品牌傅里叶变换近红外仪器的模型转移,并对3种模型转移算法的转移结果进行分析。结果表明:将复烤片烟常规化学成分的主机模型直接应用于从机预测时,主机和从机的预测值之间存在显著性差异;采用BC、SBC和SST可以实现不同品牌傅里叶变换近红外仪器的模型转移,其中SST转移结果最优。     

Applications of maximum likelihood principal component analysis: incomplete data sets and calibration transfer

The application of a new method to the multivariate analysis of incomplete data sets is described. The new method, called maximum likelihood principal component analysis (MLPCA), is analogous to conventional principal component analysis (PCA), but incorporates measurement error variance information in the decomposition of multivariate data. Missing measurements can be handled in a reliable and simple manner by assigning large measurement uncertainties to them. The problem of missing data is pervasive in chemistry, and MLPCA is applied to three sets of experimental data to illustrate its utility. For exploratory data analysis, a data set from the analysis of archeological artifacts is used to show that the principal components extracted by MLPCA retain much of the original information even when a significant number of measurements are missing. Maximum likelihood projections of censored data can often preserve original clusters among the samples and can, through the propagation of error, indicate which samples are likely to be projected erroneously. To demonstrate its utility in modeling applications, MLPCA is also applied in the development of a model for chromatographic retention based on a data set which is only 80% complete. MLPCA can predict missing values and assign error estimates to these points. Finally, the problem of calibration transfer between instruments can be regarded as a missing data problem in which entire spectra are missing on the ‘slave’ instrument. Using NIR spectra obtained from two instruments, it is shown that spectra on the slave instrument can be predicted from a small subset of calibration transfer samples even if a different wavelength range is employed. Concentration prediction errors obtained by this approach were comparable to cross-validation errors obtained for the slave instrument when all spectra were available.     

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.     

基于正交信号校正的秸秆青贮饲料粗蛋白近红外分析模型传递方法

探讨了基于不同数据预处理方法的正交信号校正在秸杆饲料近红外光谱模型传递中的应用.以141个秸杆青贮饲料样品为研究对象,以其粗蛋白含量为目标参数,研究了基于无处理、局部中心化、全局中心化和Z-score标准化预处理方法的正交信号校正,在源仪器(SPECTRUM ONE NTS)和目标仪器1(ANTA-RIS)与目标仪器2(FOSS 6500)之间的模型传递效果.实验表明:对于两台傅里叶变换型近红外光谱仪,采用局部中心化、全局中心化和Z-score标准化预处理方法的正交信号校正均可成功实现模型传递,其中局部中心化和全局中心化法的作用效果基本一致,且优于Z-score标准化法.对于傅立叶变换和光栅型近红外光谱仪,全局中心化的作用效果明显优于其它3组处理效果,且只有全局中心化预处理的正交信号校正传递后的模型可用于实际预测.     

近红外光谱法快速测定附子中6个生物碱的含量

应用近红外光谱(NIRS)技术结合偏最小二乘(PLS)和最小二乘支持向量机(LS-SVM)建立了附子中多指标成分的快速无损检测方法。选取38批样品建立了同时测定附子样品中6种成分含量的高效液相色谱(HPLC)方法;通过采集附子样品的NIRS图,分别采用PLS和LS-SVM建立了各个成分HPLC测定值与NIRS图的定量校正模型。所建立的苯甲酰新乌头原碱、苯甲酰乌头原碱、苯甲酰次乌头原碱、新乌头碱、次乌头碱、乌头碱、单酯型生物碱总量和双酯型生物碱总量LS-SVM模型的相对预测偏差(RPD)分别为3.3、3.2、4.1、7.7、8.8、7.6、4.0和8.6;验证集相关系数(rpre)分别为0.9486、0.9475、0.9668、0.9909、0.9946、0.9969、0.9669和0.9927,且LS-SVM模型优于PLS模型,说明NIRS模型验证集与HPLC测定值具有良好的非线性关系,模型预测效果良好。采用NIRS技术结合LS-SVM模型可以快速对附子中的上述6个生物碱含量以及单酯型生物碱总量和双酯型生物碱总量进行检测,方法操作简便,对控制附子中的生物碱含量具有一定的指导作用。     

基于近红外光谱的人工神经网络研究STR基因座分型方法

以D16S539基因座的3种(9-9、9-11、11-11)基因型为例,设计引物扩增包含该多态性位点的1段DNA片段,获得了3种基因型建模样本各50个.基于近红外光谱(NIRS)结合误差反向传播人工神经网络(BPANN)建立了测定短串联重复序列(STR)基因型的判别模型,所建立的判别模型的校正均方根残差和预测集均方根误差分别为0.082 5、0.072 5,预测准确率均为100%.该方法不需任何前处理,只需一步PCR扩增和NIRS检测即可实现STR基因型判别,具有简单、快速、低成本等优点.     

基于激光诱导击穿光谱(LIBS)的煤灰熔点快速检测

炉内结渣是影响火电机组和气化工艺可靠运行的关键因素之一，准确预测灰熔点可以提前调整炉膛出口温度以避免结渣。本论文采用激光诱导击穿光谱（LIBS）采集煤灰样中金属元素的光谱，分别建立煤灰中的金属元素的谱线强度与煤灰熔点的随机森林模型、支持向量机回归模型和线性回归模型，直接预测煤灰熔点温度。采用基于马氏距离(MD)的异常数据剔除算法和基于稀疏矩阵的基线估计与降噪算法（BEADS），对粉煤灰样的全光谱数据进行了预处理。随机森林模型对粉煤灰熔点的预测平均相对误差（MRE）为54.74%，支持向量机回归模型的预测平均相对误差为60.08%，而线性回归模型的预测平均相对误差达到了9.78%。研究结果表明，线性回归模型对煤灰熔点的预测结果更准确。     

The determination for the three genotypes of D16S539 locus based on near-infrared spectroscopy and chemical pattern recognition

The paper has established an approach of typing short tandem repeats (STRs) based on the near-infrared spectroscopy (NIRS)-chemical pattern recognition. Taking the three genotypes 9-9, 9-11 and 11-11 of D16S539 locus as example, which have a middle degree of difference, DNA fragments containing the polymorphism sites were amplified by a pair of primers to obtain three genotypes samples; these samples were tested by the NIRS directly; using their spectra as recognition variables, the chemical pattern recognition models of the three genotypes were respectively established by using the principal discriminant variate (PDV) and support vector machine (SVM). The two models have a good fitting ability and strong prediction (i.e. the predicting accuracy was 100%). They are robust for these strong collinear spectra and the small number of the calibration samples. Without any preprocessing for the analyzed samples after PCR, the three genotypes of D16S539 locus could be indirectly determined by using the NIRS-s of the samples with the help of the models. This method is simple, rapid and low cost.     

Standardization of near infrared spectra measured on multi-instrument

Calibration model transfer is essential for practical applications of near infrared (NIR) spectroscopy because the measurements of the spectra may be performed on different instruments and the difference between the instruments must be corrected. An approach for calibration transfer based on alternating trilinear decomposition (ATLD) algorithm is proposed in this work. From the three-way spectral matrix measured on different instruments, the relative intensity of concentration, spectrum and instrument is obtained using trilinear decomposition. Because the relative intensity of instrument is a reflection of the spectral difference between instruments, the spectra measured on different instruments can be standardized by a correction of the coefficients in the relative intensity. Two NIR datasets of corn and tobacco leaf samples measured with three instruments are used to test the performance of the method. The results show that, for both the datasets, the spectra measured on one instrument can be correctly predicted using the partial least squares (PLS) models built with the spectra measured on the other instruments.