苹果产地差异对可溶性固形物近红外光谱检测模型影响的研究

为更好地利用近红外光谱预测苹果可溶性固形物含量,减少产地差异对近红外光谱检测模型的影响,以4种不同产地的富士苹果为研究对象,采用基于x-y共生距离的样本划分方法分别对不同产地的苹果选取代表性样本作为校正集,利用偏最小二乘算法,建立和比较单一产地和混合产地下的苹果可溶性固形物近红外光谱检测模型,并结合竞争性自适应重加权算法(CARS)和连续投影算法(SPA)对苹果可溶性固形物的建模变量进行筛选。相比单一产地和其它混合产地模型,混合所有4种苹果产地的校正集样本建立的模型取得了最好的预测结果,另外,结合CARS-SPA筛选的16个特征波长,模型得到了进一步简化,其预测相关系数和预测均方根误差分别为0.978和0.441°Brix。结果表明,利用多个产地的苹果样本建立的混合模型,结合有效特征波长,可提高对苹果可溶性固形物含量的预测精度,减小产地差异对可溶性固形物近红外光谱检测的影响。     

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。     

基于近红外光谱和OPLS-DA的不同牌号卷烟分类识别方法研究

为了对卷烟牌号进行准确分类鉴别,提出了一种基于近红外光谱(NIRS)分析技术结合有监督的模式识别快速鉴别卷烟牌号的新方法。利用标准正态变量变换(SNV)、多元散射校正(MSC)、一阶导数(FD)、二阶导数(SD)和Savitzky-Golay平滑(SG)及其相结合的光谱预处理方法对烟丝光谱进行预处理,通过近红外光谱结合主成分分析(PCA)、偏最小二乘判别分析(PLS-DA)和正交偏最小二乘判别分析(OPLS-DA) 3种模式识别方法对不同牌号烟丝进行分类识别研究,并采用分类识别正确率作为评价指标。实验结果表明：(1)烟丝近红外光谱主成分得分图交叉重叠,区分不明显,PCA无法识别出5种牌号的成品烟丝;(2)烟丝光谱经MSC+FD预处理后的PLS-DA模型可得到较好的识别效果,校正集和测试集的分类识别正确率分别为100%和98.3%;(3)烟丝光谱经MSC+SD预处理后的OPLS-DA模型的模式识别效果最好,模型对自变量拟合指数(R2X）,因变量的拟合指数(R2Y)和模型预测指数(Q2)分别为0.485、0.907 和0.748,近红外光谱校正集和测试集的分类识别正确率均为100%。说明近红外光谱技术结合有监督模式识别方法OPLS-DA建立的烟丝牌号分类模型具有高效快速、准确无损的优点,为卷烟烟丝分类提供了一种新的快速鉴别方法。     

近红外光谱结合模式识别方法所建模型分析卷烟烟丝配方比例北大核心CSCD

为卷烟配方替代和产品质量稳定性评价奠定基础,利用近红外光谱结合模式识别方法,建立了卷烟烟丝配方比例的识别模型。在某牌号卷烟成品烟丝中添加5种不同比例的A模块烟丝,采集其近红外光谱信息,采用求导法(一阶求导、二阶求导)和平滑法(Savitzky-Golay平滑、Norris平滑)对样品近红外光谱进行预处理,结合主成分分析-马氏距离(PCA-MD)、偏最小二乘法-判别分析(PLS-DA)和正交偏最小二乘法-判别分析(OPLS-DA)建立上述5种成品烟丝的识别模型。结果显示,最佳光谱预处理方式为一阶求导+Savitzky-Golay平滑,最佳模式识别方法为OPLS-DA。当主成分数为4时,最佳识别模型的光谱变量累计解释能力为0.995,分类变量累计解释能力为0.953,特征值为0.196,累计交叉有效性为0.912,模型外部验证的整体识别率为99%。置换验证结果表明该模型稳定可靠,未出现过拟合现象。对5种成品烟丝进行感官评吸,该模型对不同卷烟烟丝配方比例的识别效果更好。     

PDS算法进行近红外定量模型更新的效果评估

以不同厂家阿莫西林胶囊及其内容物近红外(Near infrared,NIR)光谱为例,寻找评价分段直接标准化算法(Piecewise direct standardization,PDS)进行光谱校正是否成功的量化指标。本研究共涉及76批阿莫西林胶囊样品,其中54批用于建立胶囊剂的定量模型。通过聚类分析,所有胶囊的NIR光谱分成5类,每类视为一个均质样本;分别计算每个均质样本的平均光谱,从该样本中选择10~15张光谱作为PDS校正的目标光谱,对76批阿莫西林胶囊内容物粉末光谱进行校正,利用阿莫西林胶囊定量模型对校正后的光谱进行含量预测;计算校正后的光谱与PDS校正中目标光谱所属均质样本的平均光谱的相似系数,分析其与预测误差的关系。结果表明,校正结果与所选择的目标光谱关系密切。PDS校正光谱与模型中不同均质样本平均光谱的相似系数(r)越大,通常校正效果越好;当r<99%时,一般可判断PDS校正失败(预测误差>5%)。因此,可以用PDS校正后光谱与校正时使用的目标光谱所属的均质样本的平均光谱的相似系数作为判断PDS校正是否成功的标志。     

偏最小二乘回归用于近红外光谱分析的稳健策略

偏最小二乘法（PLS）在近红外光谱（NIR）定量分析中占有重要地位,但预测结果往往容易受到样本分组和奇异样本等因素的影响,稳健性不强。多模型PLS (EPLS）方法在模型稳健性上得到提高,然而它无法识别样本中存在的奇异样本。为了同时提高模型的预测准确性和稳健性,本文提出了一种根据取样概率重新取样的多模型PLS方法,称为稳健共识PLS（RE-PLS）方法。该方法通过迭代赋权偏最小二乘法(IRPLS)计算样本回归残差得到每个校正集样本的取样概率,然后根据样本的取样概率来选择训练子集建立多个PLS模型,最后将所有PLS模型的预测结果平均作为最终预测结果。该方法用于两种不同植物样品的近红外光谱建模,并与传统的PLS及EPLS方法进行比较。结果表明该方法可以有效的避免校正集中奇异样本对模型的影响,同时可以提高预测精确度和稳健性。对于含有较多奇异样本的,复杂近红外光谱烟草实际样本,利用简单PLS或者EPLS方法建模预测效果不是很理想,而RE-PLS凭借其独特优势则有望在这种复杂光谱定量分析中得到广泛的应用。     

粒子群算法结合支持向量机回归法用于近红外光谱建模

研究了最小二乘法支持向量机(LSSVM)应用于烟丝样品和小麦样品的近红外光谱建模,采用粒子群优化算法(PSO)优化LSSVM的参数。通过对烟草样品和小麦样品的近红外光谱建模和预测,并与常规的偏最小二乘法(PLS)比较发现,PSO-LSSVM法具有更好的预测效果和稳健性。     

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。     

基于平行因子分析法提高近红外无创血糖校正模型稳健性的研究

采用近红外光谱进行无创血糖检测时, 样品背景变动造成的预测集样本与校正集样本量测体系不一致的问题是导致预测精度低的原因之一. 提出一种将母体背景作为变量引入回归建模中, 结合各个母体背景下的样本光谱信息构建三维光谱矩阵以提高校正模型稳健性的分析方法. 将平行因子分析(PARAFAC)与多元线性回归(MLR)相结合, 对人体三层皮肤模型的蒙特卡罗模拟实验和葡萄糖水溶液及其混合物的离体实验进行了验证. 实验结果表明, 与传统的单一母体背景所建立的偏最小二乘模型相比, 将母体背景作为建模元素采用PARAFAC-MLR法所建立的校正模型具有更好的预测能力和稳健性.     

小波变换结合多维偏最小二乘方法用于近红外光谱定量分析

将小波变换和多维偏最小二乘法相结合用于近红外光谱定量校正模型的建立.首先将原始光谱进行小波变换分解,得到系列小波细节系数,通过选取一组受外界因素少、信息强的小波系数组成三维光谱阵,然后再采用多维偏最小二乘法建立校正模型.实验结果表明,该方法所建近红外校正模型的预测能力更强,并更具稳健性.     

基于尺度不变特征变换筛选稳定特征波长的近红外光谱模型传递方法

该研究利用一维尺度不变特征变换(SIFT)算法寻找烟叶近红外光谱(Near infrared spectroscopy,NIRS)的稳定特征波长,根据样品精密度测试光谱筛选的波长计算重现率和重现度,采用L_9(3~3)正交表优化SIFT算法中的相关参数,使重现率和重现度尽可能高。基于优化的参数和主机上10个代表性样品的光谱,筛选出10个稳定特征波长集合,以这些波长集合并集的光谱响应为自变量,采用偏最小二乘(PLS)方法构建烟叶总植物碱NIRS模型(简称SIFT-PLS)。该模型直接传递到3台从机后,对3台从机样品总植物碱的平均相对预测误差(MRE)均满足小于6%的企业内控要求,而全光谱模型(WW-PLS)直接转移后仅1台从机的MRE满足要求,经分段直接校正(PDS)方法校正从机光谱后,WW-PLS模型也仅对1台从机的MRE小于6%。采用SIFT算法筛选稳定特征波长建立的NIRS模型可在3台从机直接共享,无需转移集,不需对从机光谱或光谱模型进行校正,实现了真正意义的无标样NIRS模型的直接转移。     

Improved calibration transfer between near-Infrared (NIR) spectrometers using canonical correlation analysis

The application of mobile near-infrared (NIR) spectrometers in field measurements is growing. Calibration transfer techniques offer simple solutions for enabling models constructed on benchtop instruments for use on mobile spectrometers. Since different types of spectrometers with different components, scanning ranges and resolutions cause great differences in the spectral response, calibration transfer is difficult to apply. In this paper, we focus on calibration transfer among benchtop, portable and handheld spectrometers by a method of calibration transfer based on canonical correlation analysis (CTCCA). Its capability was illustrated by the example of a group of NIR spectra dataset for predicting reducing sugars, total sugar, and nicotine contents in tobacco leaves. The experimental results showed that the transferability of CTCCA was superior to other conventional calibration transfer methods, including piecewise direct standardization, spectral space transformation, calibration transfer based on independent component analysis, and calibration transfer based on the weight matrix. Moreover, the best transfer results were obtained in the three cases by canonical correlation analysis method executing transfer while the spectra were not interpolated, which shows that this approach has the advantage of easy implementation for calibration transfer. Therefore, CTCCA without interpolation calculation offers a new and simple solution for transferring the spectra acquired by mobile spectrometers to the optimized spectral models built on benchtop devices to improve the accuracy of the results. Additionally, the results show that the benchtop spectrometer is more suitable as the master instrument for calibration transfer with more accurate prediction than using a portable device as the master.     

近红外光谱分析模型传递简易方法研究

本文在不同时间安装的多台同型号近红外光谱仪上建立推进剂校正模型时,由于推进剂样品数量少且难于保存,新到仪器在建模时常遇到代表性样品数量严重不足.为此,提出将2台波长一致性好的近红外光谱仪器上采集的光谱组成一个混合校正样品光谱集,使用偏最小二乘法(PLS)建立模型的方法.结果表明,在用户缺少专业模型传递软件情况下,该方法...     

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.     

Subspace Regression Ensemble Method Based on Variable Clustering for Near-Infrared Spectroscopic Calibration

Abstract

An ensemble approach, based on the combination of multiple linear regressions in subspace and variable clustering and therefore named VCS-MLR, was proposed for near-infrared spectroscopy (NIRS) calibration. By an experiment involving the determination of five components in tobacco samples, it was shown that VCS-MLR improved the performance by 61.4, 23.3, 10.2, 20.5, and 18, respectively, with respect to partial least squares regression (PLSR). The results confirmed that VCS-MLR can result in a more accurate calibration model but without the increase of computational burden. Moreover, the superiority of VCS-MLR was highlighted for small sample problems.     

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.     

Characterization of Tobacco Leaves by Near-Infrared Reflectance Spectroscopy and Electronic Nose with Support Vector Machine

The determination of different regions of tobacco leaves is vital in the tobacco industry. Different parts of tobacco leaves produce varying flavors due to the different chemical compositions. Here, near infrared spectroscopy and electronic nose were combined with support vector machine to predict the parts of tobacco leaves. Comparing to the single data model as near infrared spectroscopy with support vector machine or electronic nose with support vector machine, near infrared spectroscopy and electronic nose with support vector machine model show higher accuracy. The accuracy of near infrared spectroscopy and electronic nose with support vector machine model is 95.31%, while the accuracy of leave-one-out cross-validation is 79.69%. The optimal model was then applied to 60 unknown tobacco samples from different parts of tobacco leaves to test its accuracy, which is 81.67%.     

Qualitative Analysis of Maize Haploid Kernels Based on Calibration Transfer by Near-Infrared Spectroscopy

Haploid breeding is one of the most important modern crop selection technologies. Near-infrared spectroscopy (NIRS) has been used to identify haploids rapidly and to non-destructively accelerate the selection process. However, the change of the external environment weakens the performance of the model, as the training and the test spectra may be collected separately from different environments. Thus, a novel calibration transfer method is proposed to calibrate the model in order to reduce the impact of the environment. The near-infrared spectra of 400 maize kernels of two varieties were collected from 9000 to 4000?cm^?1. Principal component analysis was performed to construct a feature space and extract features. In the constructed feature space, the calibration transfer method was used to calibrate test sets. Finally, support vector machine was employed to establish a haploid identification model. The results show that when the spectra of the test set and the training set were collected in the same environment, the corrected acceptance of the model was above 90%. While the spectra of the test set and the training set were collected from different environments, the corrected acceptance was 77.87%. However, when the model used the calibration transfer method, the corrected acceptance increased by 12.46%. Moreover, compared with direct standardization, this calibration transfer method achieved better results without detailed sample chemical information and many standards. The results demonstrate that the calibration transfer method based on NIRS was effective for identifying maize haploid kernels in variable environments.     

Comparison and joint use of near infrared spectroscopy and Fourier transform mid infrared spectroscopy for the determination of wine parameters

A study of the statistic characteristics of the multidetermination of several enological parameters - namely, alcoholic degree, volumic mass, total acidity, glycerol, total polyphenol index, lactic acid and total sulphur dioxide - depending on the spectroscopic zone employed, was carried out. The two techniques used were near infrared spectroscopy (NIRS) and Fourier transform mid infrared spectroscopy (FT-MIRS). The combination of these two regions (sum of their spectra) was also studied. NIRS yielded better results, but the use of both zones improved the determination of glycerol and total sulphur dioxide. The training and validation sets used for developing general equations were built with samples from different apellation d’origine, different wine types, etc. Partial least squares regression was used for multivariate calibration, using systematic cross validation in the calibration stage and external validation in the testing stage. Sample preparation was not required.