郎枣轻微损伤可见/近红外光谱分波段动态判别研究

为了实现轻微损伤郎枣的快速无损检测,以完好和轻微损伤郎枣为研究对象,动态采集其可见/近红外光谱数据。依据光谱波段定义将采集的光谱数据分为可见光(Vis)、短波近红外(SW-NIR)、长波近红外(LW-NIR)、可见/短波近红外(Vis/SW-NIR)、近红外(NIR)和可见/近红外(Vis/NIR)等6个波段,分别选取各波段最佳预处理方法。采用连续投影法(SPA)和主成分分析法(PCA)分别对各波段光谱数据降维,以全波长、SPA提取的特征波长和PCA提取的主成分作为输入,分别建立偏最小二乘回归法(PLSR)和最小二乘支持向量机(LS-SVM)模型,通过比较预测集的判别准确率,确定最佳建模方法。结果表明,PLSR模型优于LS-SVM模型,SW-NIR波段较其余5个波段有更好的判别能力,所建SW-NIR-SNV-SPA-PLSR模型判别准确率为93.3%,为最佳模型。本实验为轻微损伤郎枣的快速无损检测和相关仪器的开发提供了理论基础。     

近红外光谱法快速鉴别转基因大豆模型优化

目的应用近红外光谱(NIR)结合偏最小二乘判别分析(PLS-DA)建立转基因大豆的快速鉴别模型,并选择最优模型。方法主成分分析(PCA)用于从光谱数据中提取相关特征并剔除异常样品。在试验中,94份样品用于构建模型,41份样品用作验证评估模型的效果。分别讨论样品形态(整粒和粉末)、波长范围和光谱预处理方法对所建模型判别正确率的影响。结果粉末状大豆样品建模的效果好于整粒大豆样品。其中判定效果最好的模型,整粒大豆在9 403～5 438 cm~(-1)范围内,采用二阶导数(2nd)处理光谱,模型的校正集和验证集的判定正确率均为100.00%;粉末状大豆在7 505～4 597 cm~(-1)范围内,采用矢量归一化+一阶导数(SNV+1st)处理光谱,模型的校正集和验证集的判定正确率也均为100.00%。结论通过选择样品形态、波长范围和光谱预处理方法可以优化鉴别模型,提高近红外判别模型的鉴别正确率。     

苹果品种及损伤苹果的FT-NIR鉴别研究

用傅里叶近红外光谱技术(FT-NIR)对不同品种的苹果以及损伤嘎啦和完好嘎啦进行快速、无损检测,比较不同判别方法对所建立的区分苹果品种及苹果损伤模型的影响。结果表明:损伤嘎啦和完好嘎啦的近红外图谱经小波分析预处理后,用12000～4000cm-1波数范围的前5个主成分分别结合多层感知神经网络、径向基神经网络、Fisher判别3种方法所建立的判别模型对未知样本的正确判别率分别为97.8%、87.2%和84.8%,基于权重法用多元线性回归(MLR)所选择的特征波长所建立的Fisher判别模型对未知样本的正确判别率为89.1%;用偏最小二乘判别(PLS-DA)所建立的判别模型对未知样本的正确判别率为100%,由于PLS-DA模型对训练集和验证集的正确判别率均为100%,因此PLS-DA模型优于其他模型。不同品种苹果的光谱经平滑预处理后,用全波数范围12000～4000cm-1的前6个主成分所建立的判别模型优于经验波数范围8000～4500cm-1所建立的判别模型,其较优模型对建模集和验证集的正确判别率分别为90.9%和92.1%。近红外光谱技术结合化学计量学可以快速、无损鉴别苹果是否有损伤以及不同品种的苹果。     

近红外光谱在食醋品牌和贮藏年份鉴别中的应用研究

近红外光谱用于食醋品牌和食醋贮藏年份的鉴别。144个食醋样品用于食醋品牌的鉴别,其中114个为"恒顺"牌食醋,其余30个为山西"水塔"和天津"独流"品牌食醋;114个"恒顺"牌食醋用于食醋贮藏年份的鉴别;采用kennard-stone(KS)方法将样品划分为校正集和验证集,主成分分析(principal component analysis,PCA)和偏最小二乘判别分析(partial least squares-discriminant analysis,PLS-DA)用于食醋品牌和年份的鉴别;competitive adaptive reweighted sampling(CARS)方法用于食醋特征变量的筛选。结果表明,样品经PLS-DA方法后,食醋品牌的校正识别率为98.96%,验证识别率为95.83%;食醋年份的校正识别率为97.37%,验证识别率为100%;食醋光谱经CARS方法优选波长后结合PLS-DA方法进行判别,所有的识别率都为100%;近红外光谱结合CARS-PLS-DA方法可以用于食醋品牌和贮藏年份的鉴别.为食醋原产地保护和年份鉴别提供一种快速的参考方法。     

基于近红外技术和偏最小二乘判别法对无花果成熟度的快速判别

以无花果为试验对象,对其进行近红外光谱采集,并对其糖度、单果重、纵径、横径、硬度5个指标进行K-均值聚类;根据光谱数据、主成分分析确定最优聚类效果的成分和各类别的指标分布构建偏最小二乘判别分析(PLS-DA)模型进行聚类判别,以实现对果实成熟度(幼果期、成长期、成熟期)分类的准确、快速、无损伤鉴别。结果表明,3种成熟阶段的无花果样品的糖度、单果重和硬度均具有显著性差异,成熟果和成长果与幼果的纵径和横径间具有显著性差异。根据PLS-DA判别模型累计训练集的分类正确率为99.59%,测试集的分类正确率为99.15%。说明主成分分析与光谱数据所建立的PLS-DA模型性能较好,对无花果成熟度的快速鉴别是有效且可行的。     

基于中红外光谱技术的甘氨酸铁螯合物判别研究

目的研究基于中红外光谱(mid infrared spectroscopy,MIRS)技术定性判别有机微量元素添加剂掺假的可行性。方法以甘氨酸铁螯合物和硫酸亚铁为研究对象,分析样品的中红外光谱,解析不同样品光谱的特异性;建立偏最小二乘判别(partial least squares discriminant analysis,PLS-DA)校正模型对掺假样品进行判别,并比较不同预处理方法、全光谱与特征波段对校正模型判别效果的影响。结果甘氨酸铁螯合物与硫酸亚铁光谱差异显著,主要分布在(3500～3000) cm~(-1)、(1600～1300) cm~(-1)、(1300～1000) cm~(-1)、(660～550) cm~(-1),通过采用平滑(smoothing,SM)、归一化(normalization,Norm)与一阶导数(first derivative,FD)相结合的方法对光谱进行预处理,结合1300 cm~(-1)～1000 cm~(-1)波段建立的PLS-DA校正模型判别效果最优,校正集的判别正确率为97.5%,验证集的判别正确率为100.0%,对外部样品的判别正确率达到92.7%。结论中红外光谱技术结合化学计量学方法能够对甘氨酸铁螯合物的掺假进行准确判别。     

基于近红外漫反射光谱的云芝提取物品级分类研究

为探索快速无损分析云芝提取物品级的方法,采集不同产地云芝提取物的近红外漫反射光谱,通过主成分分析(PCA)对样本原始光谱数据进行降维、压缩,并分别结合偏最小二乘判别法(PLS-DA)和反向传输人工神经网络(BP-ANN)建立识别模型。结果表明:采用主成分分析结合偏最小二乘判别法,建模集和验证集的识别正确率分别为100%和84%;采用主成分分析结合反向传输人工神经网络模型,其建模集和验证集的识别正确率均为100%。由此可见,主成分分析结合反向传输人工神经网络模型可以更好地实现对不同品级的云芝提取物进行分类识别。     

基于近红外高光谱成像技术的宁夏羊肉产地鉴别

使用900~1700 nm高光谱成像系统采集宁夏银川、固原、盐池三个不同产地的绵羊后腿样本的近红外高光谱数据,对光谱采用面积归一化方法预处理,利用SPA、CARS、UVE算法对预处理后的光谱数据提取特征波长分别为17、40、121个;结合PLS-DA及KNN建立特征波段下的判别模型。结果表明KNN判别模型效果较差,3种特征波长中利用CARS提取的特征波长建模效果最佳,代替全光谱建立PLS-DA判别模型是可行的;综合对比模型效果,CARS-PLS-DA为最优模型,校正集正确率90.48%,预测集正确率84.21%。证明利用近红外高光谱成像技术对羊肉产地鉴别是可行的。     

油茶果自然霉变程度的可见/近红外与中短波近红外光谱检测

分析利用可见/近红外光谱（400～1 000 nm）与中短波近红外光谱（900～1 700 nm）对不同自然霉变程度油茶果检测判别的可行性,实验同时采集不同霉变程度油茶果赤道阴面、阳面和接合面三点的两波段光谱,样品平均光谱的主成分分析（principal component analysis,PCA）发现不同霉变程度样品同组内具有一定聚类效果且PC1和PC2对于判别不同组间样品有效,全光谱偏最小二乘判别分析模型结果显示原始光谱已具有足够信息,建立的模型性能比预处理后全光谱更优。进一步进行特征波长选取,发现相比于PC载荷,连续投影法在两光谱范围选取波长建立的简化模型均为最优,预测集判别准确率与Kappa系数均为84.4%与0.766 7。结合预测集混淆矩阵发现,两光谱范围最优简化模型预测不同霉变组样品特异度相当,均在0.84以上,但900～1 700 nm中短波近红外光谱对于中等霉变程度的判别灵敏度（0.72）略高。本研究表明近红外光谱技术可用于油茶果的自然霉变程度检测,可见/近红外与中短波近红外光谱能力相当,考虑到仪器成本问题,可见/近红外光谱具有更好的实时检测应用前景。     

近红外光谱结合PLS-DA划分烟叶等级

为了对烟叶等级进行快速分类,采用云南曲靖地区150个烟草样品近红外光谱,结合偏最小二乘判别分析(PLS-DA),建立了烟叶等级分类模型,并对60个预测集样品进行了等级分类预测.结果表明:①训练集和预测集的预测正确率分别为100.0％(150/150)和96.7％(58/60).②PLS-DA对烟叶等级具有良好的分类效果.该模型为烟叶等级分类提供了一种新的快速鉴别分析的方法.     

An overview of the use of infrared spectroscopy and chemometrics in authenticity and traceability of cereals

Although both near infrared (NIR) spectroscopy and mid infrared (MIR) spectroscopy combined with multivariate data analysis (MVA) have been extensively used to measure chemical composition (e.g. protein, moisture, oil) in a wide number of grains few reports can be found on the use of this methods for varietal discrimination and traceability of cereals. In this overview applications of NIR spectroscopy and MIR spectroscopy combined with multivariate data methods such as principal component analysis (PCA), partial least squares discriminant analysis (PLS-DA), linear discriminant analysis (LDA) to aid on the authentication and traceability of cereals are discussed.     

Comparison of Infrared Spectroscopy and Nuclear Magnetic Resonance Techniques in Tandem with Multivariable Selection for Rapid Determination of ω-3 Polyunsaturated Fatty Acids in Fish Oil

This study investigated the potential of using four spectroscopic techniques including visible–short-wave near infrared, long-wave near infrared (LNIR), mid-infrared, and nuclear magnetic resonance (NMR) spectroscopy in tandem with multivariable selection and calibration for rapid determination of three important ω-3 polyunsaturated fatty acids (PUFA), namely eicosapentaenoic acid (EPA), docosahexaenoic acid (DHA), and docosapentaenoic acid (DPA) in fish oil. Quantitative models were established between the spectral data and reference PUFA contents of samples based on partial least squares regression (PLSR) algorithm. Successive projections algorithm (SPA) and uninformative variable elimination (UVE) were used to select the most important variables for prediction. The average decrements of 23.20 % for root mean square error of cross-validation (RMSECV) and 64.90 % for the absolute value between root mean square error of calibration and RMSECV (AV_RMSE) in all 12 cases achieved after over 90 % variables were eliminated. UVE was also found to be helpful to improve the efficiency of SPA’s variable selection in 8/12 cases. The best predictions for EPA, DHA, and DPA were all achieved by NMR spectroscopy (determination coefficients of cross-validation (r _CV ² ) of 0.970, 0.982, and 0.983 and the RMSECV of 11.48, 4.73, and 0.77 mg/g for the EPA, DHA, and DPA predictions, respectively). LNIR spectra also did good predictions similar to NMR. The results demonstrated that the laborious and time-consuming gas chromatography method could be replaced by spectroscopic techniques in tandem with PLSR modeling and variable selection in order to provide a rapid and reliable inspection of PUFA in fish oil.     

A Non-invasive Method for Screening Sodium Hydroxymethanesulfonate in Wheat Flour by Near-Infrared Spectroscopy

A rapid and non-invasive method, based on near infrared diffuse reflectance spectroscopy, was established for screening sodium hydroxymethanesulfonate in wheat flour. Successive projection algorithm was used for spectral variable selection. The selected variables were applied as inputs to partial least square discriminant analysis (PLS-DA) and advanced K-means dynamic clustering. The first two principal components extracted by PLS-DA had been applied as inputs to least squares support vector machine (LS-SVM). Three algorithms, including PLS-DA, advanced K-means dynamic clustering, and LS-SVM, were used to establish the calibration model. The results of LS-SVM outperformed that of the other two methods, with the classification accuracy of 92.0% for the validation and 94.7% for the prediction. The results of the study showed the potential of near-infrared spectroscopy as a non-invasive and environmentally acceptable method for the screening of sodium hydroxymethanesulfonate in wheat flour.     

基于CUVE-PLS-DA的鸡蛋新鲜度在线检测分级

针对目前鸡蛋新鲜度检测技术方法存在劳动强度大、检测精度低、分级效率不足等缺陷,本研究在4 800 枚/h的禽蛋传输机上搭建了可见-近红外透射光谱（501～1 000 nm）在线检测装置,动态采集鸡蛋透射光谱数据,并建立光谱信息与鸡蛋哈夫值等级的偏最小二乘判别模型。采用3∶1原则对鸡蛋样本进行随机划分,其中校正集169 个,验证集57 个,通过比较多种光谱预处理方法以及两种特征波长选择方法,得出标准正态变换预处理方法和多模式共识方法能够有效地提高模型的正确率、运算效率和预测能力,优化模型后的校正集和验证集准确率分别为92.31%、91.23%。结果表明本实验建立的可见-近红外光谱透射光谱检测方法能够对鸡蛋的新鲜度进行无损、智能、在线检测分级。     

基于可见/近红外光谱技术的橘小实蝇侵染柑橘检测研究

目的 使用可见/近红外光谱技术实施橘小实蝇侵染柑橘不同时期的无损检测。方法 研究选取人工制备的不同侵染时期的柑橘样本作为研究对象,利用搭建的可见/近红外光谱系统测量的光谱信息结合人工标定的侵染时期,对原始光谱进行了5种预处理,采用竞争性自适应重加权算法(competitive adaptive reweighted sampling, CARS)、连续投影算法(successive projections algorithm, SPA)两类方法提取反映侵染柑橘时期变化的光谱特征波长,应用偏最小二乘判别分析(partial least squares discriminant analysis,PLS-DA)建立基于特征波长光谱的柑橘侵染时期分类模型,对比分析不同光谱预处理方法的模型分类效果。结果 原始光谱经多元散射校正(multiplicative scatter correction, MSC)预处理的模型分类效果最佳,分别经CARS方法和SPA方法优选出了34和16个光谱特征波长。采用MSC-CARS-PLS-DA方法构建的模型分类效果最好,总准确率、假阳率分别为96.8%和0.0...     

Metabolic profiling of early-lactation dairy cows using milk mid-infrared spectra

Metabolic disorders in early lactation have negative effects on dairy cow health and farm profitability. One method for monitoring the metabolic status of cows is metabolic profiling, which uses associations between the concentrations of several metabolites in serum and the presence of metabolic disorders. In this cross-sectional study, we investigated the use of mid-infrared (MIR) spectroscopy of milk for predicting the concentrations of these metabolites in serum. Between July and October 2017, serum samples were taken from 773 early-lactation Holstein Friesian cows located on 4 farms in the Gippsland region of southeastern Victoria, Australia, on the same day as milk recording. The concentrations in sera of β-hydroxybutyrate (BHB), fatty acids, urea, Ca, Mg, albumin, and globulins were measured by a commercial diagnostic laboratory. Optimal concentration ranges for each of the 7 metabolites were obtained from the literature. Animals were classified as being either affected or unaffected with metabolic disturbances based on these ranges. Milk samples were analyzed by MIR spectroscopy. The relationships between serum metabolite concentrations and MIR spectra were investigated using partial least squares regression. Partial least squares discriminant analyses (PLS-DA) were used to classify animals as being affected or not affected with metabolic disorders. Calibration equations were constructed using data from a randomly selected subset of cows (n = 579). Data from the remaining cows (n = 194) were used for validation. The coefficient of determination (R²) of serum BHB, fatty acids, and urea predictions were 0.48, 0.61, and 0.90, respectively. Predictions of Ca, Mg, albumin, and globulin concentrations were poor (0.06 ≤ R² ≤ 0.17). The PLS-DA models could predict elevated fatty acid and urea concentrations with an accuracy of approximately 77 and 94%, respectively. A second independent validation data set was assembled in March 2018, comprising blood and milk samples taken from 105 autumn-calving cows of various breeds. The accuracies of BHB and fatty acid predictions were similar to those obtained using the first validation data set. The PLS-DA results were difficult to interpret due to the low prevalence of metabolic disorders in the data set. Our results demonstrate that MIR spectroscopy of milk shows promise for predicting the concentration of BHB, fatty acids, and urea in serum; however, more data are needed to improve prediction accuracies.     

Measurement of Soluble Solids Content and pH of Yogurt Using Visible/Near Infrared Spectroscopy and Chemometrics

Visible/near infrared spectroscopy (Vis/NIRs) technique was applied to non-destructive quantification of sugar and pH value in yogurt. Partial least squares (PLS) analysis and least squares support vector machine (LS-SVM) were implemented for calibration models. In this paper, three brands (Mengniu, Junyao, and Guangming) were set as the calibration, and the remaining two brands (Yili and Shuangfeng) were used as prediction set. In the LS-SVM model, the correlation coefficient (r), root mean square error of prediction, and bias in prediction set were 0.9427, 0.2621°Brix, 1.804e−09 for soluble solids content, and 0.9208, 0.0327, and 1.094e−09 for pH, respectively. The correlation spectra corresponding to the soluble solids content and pH value of yogurt were also analyzed through PLS method. LS-SVM model was better than PLS models for the measurements of soluble solids content and pH value. The results showed that the Vis/NIRs combined with LS-SVM models could predict the soluble solids content and pH value of yogurt.     

气相色谱结合化学计量在核桃油、菜籽油掺伪混合物含量判别分析中的应用

目的：识别核桃油中同时掺入多种其他植物油的多元掺伪。方法：采用气相色谱技术分析核桃油、菜籽油掺伪混合物中脂肪酸含量,结合化学计量方法对气相色谱数据进行建模,并对不同比例核桃油、菜籽油混合物进行判别分析。结果：主成分分析法（PCA）能快速鉴别出纯核桃油和掺伪核桃油,并在一定程度上反映样本的掺伪比例;Bayes判别分析将83.33%的样品归入正确的分类;偏最小二乘判别分析法（PLS-DA）的判别准确率达87.50%;基于BP神经网络模型的判别分析,其训练集的正确率为84.21%,测试集的正确率为80.00%;基于遗传算法优化支持向量机（SVM-ga）的判别分析,其训练集和测试集的正确率均为100%。结论：多种分析模型均能不同程度地识别核桃油、菜籽油掺伪比例,其中SVM-ga模型的预测精度最佳。     

Detecting bunch withering disorder in date fruit by near infrared spectroscopy

This study introduces the application of near infrared spectroscopy (NIRs) to detect bunch withering disorder in date fruit (cv. Mazafati). The samples included intact as well as infected date fruits at different stages of ripening. Chemometric evaluation of the data was performed by soft independent modeling of class analogy (SIMCA), partial least squares discriminant analysis (PLS-DA), and principal components analysis combined with artificial neural networks (PCA–ANN). The PLS-DA algorithm was able to provide models with the best classification performance, followed by SIMCA and then PCA–ANN. The maturity stage of samples influenced the performance of the classification methods. The classification accuracy for the late harvested samples was better than those harvested at normal time and the combined data set in all classification analyses. The total accuracies of 82%, 93% and 86%, respectively for normal, late and combined data sets demonstrate that NIRs with PLS-DA has a strong potential to detect the bunch withering disorder in date fruit.     

Feasibility of Discriminating Dried Dairy Ingredients and Preheat Treatments Using Mid-Infrared and Raman Spectroscopy

This study investigated the feasibility of mid-infrared (MIR) and Raman spectroscopy for (i) discrimination of three dried dairy ingredients, namely skim milk powder (SMP), whey protein concentrate (WPC) and demineralised whey protein (DWP) powder, and (ii) discrimination of preheat treatments of dried dairy ingredients using partial least squares discriminant analysis (PLS-DA). PLS1-DA models developed using MIR ranges of 800–1800 and 1200–1800 cm^?1 yielded the best discrimination (correct identification of 97.2% for SMP discrimination and 100% for WPC and DWP discrimination). The best PLS2-DA model using MIR spectroscopy was developed over the spectral range of 800–1800 cm^?1 and produced correct identification of 100% for dairy ingredient discrimination. Models developed using Raman 800–1800 and 1200–1800 cm^?1 spectral ranges correctly discriminated (100% correctly identified) each dairy ingredient. Although all PLS1-DA and PLS2-DA models developed using both spectral technologies for preheat treatment discrimination had good discrimination accuracy (86–100%), they employed a high number of factors (8–9 for the best model). The use of the Martens uncertainty test successfully reduced the number of factors employed (3–4 for the best models) and improved the performance of PLS1-DA models for preheat treatment discrimination (all 100% correctly identified). This feasibility study demonstrates the potential of both MIR and Raman spectroscopy for rapid characterisation of dried dairy ingredients.