基于最小二乘支持向量机的橄榄油掺杂拉曼快速鉴别方法

提出了一种基于最小二乘支持向量机(LS-SVM)的橄榄油掺杂拉曼快速鉴别方法。首先,收集若干己知类别的橄榄油样作为训练样本,获取其拉曼谱图,并对其谱图进行预处理和波段选择,进而构建LSSVM分类器;对于未知类别的油样,获取其拉曼谱图,并进行相应的预处理和波段选择,由LSSVM分类器获得鉴别结果。实验以7种已知的特级初榨橄榄油为基础,分别掺入4种其它植物油(大豆油、菜籽油、玉米油、葵花籽油),获得112个掺杂油样。将全部样本随机分成训练集和测试集,对测试集样本的预测实验结果表明,本文方法能有效鉴别橄榄油掺杂,且掺杂量最低检测限为5%。与其它分类方法相比,LSSVM分类法具有最佳的分类性能。该方法快速、简便,为橄榄油掺杂鉴别提供了一种全新的方法。     

基于激光近红外的稻米油掺伪定性-定量分析

该文主要研究激光近红外光谱分析技术结合化学计量学方法对稻米油掺伪进行定性-定量分析。分别将大豆油、玉米油、菜籽油、餐饮废弃油掺入稻米油中,按照不同质量比配置189个掺伪油样,利用激光近红外光谱仪采集光谱;对采集的稻米油掺伪图谱数据进行多元散射校正(MSC)、正交信号校正 (OSC)、标准正态变量变换和去趋势技术联用算法(SNV_DT)三种不同预处理并与原始数据进行比较。采用连续投影算法(SPA)对经过预处理的光谱数据进行特征波长提取,应用支持向量机分类(SVC)方法建立稻米油掺伪样品的定性分类校正模型,选择网格搜索算法对模型参数组合(C,g)进行寻优,确定最优参数组合。另采用后向间隔偏最小二乘法(BiPLS)和SPA对预处理后的光谱数据进行特征波长提取,分别应用偏最小二乘法(PLS)和支持向量机回归(SVR)建立掺伪油含量的定量校正模型,并选用网格搜索算法对SVR模型参数组合(C,g)进行寻优,建立最优参数模型。研究表明,建立的SVC模型预测集和校正集的准确率分别达到了95%和100%;对比SVR和PLS方法建立的数学模型对稻米油中掺杂油脂的含量的预测,两种方法均能够实现含量预测,SVR模型的预测能力更好,相关系数R高于0.99,均方根误差(MSE)低于5.55×10-4,预测精度高。结果表明,采用激光近红外光谱分析技术可以实现稻米油掺伪的定性-定量分析,同时为其他油脂的掺伪分析提供了方法。     

近红外光谱和化学计量学方法用于橄榄油品质分析与掺杂量检测

基于橄榄油的近红外光谱数据,用判别分析(Discriminant analysis)方法把20个样品成功地分为特级初榨橄榄油和普通橄榄油两类,正确率为100％。同时测定了纯橄榄油中分别掺入菜籽油、玉米油、花生油、山茶油、葵花籽油、罂粟油的混合油的近红外光谱,掺杂油体积百分数范围为0～100%。选择最佳的光谱波段组合用偏最小二乘(PLS)法分别建立定量分析模型,预测相对误差范围在-5.67%～5.61%之间。研究结果表明,基于化学计量学方法和近红外光谱数据可为橄榄油的品质鉴定和掺杂量检测提供了一种简便、快捷、准确的方法。     

基于FTIR的芝麻油真伪鉴别和掺伪定量分析模型

把低价油掺入到高价油是食用油脂中的常见掺伪现象,芝麻油由于品质好价格高,市场上时有假冒伪劣产品,因此应用FTIR并结合化学计量学,建立了芝麻油的真伪和掺伪的快速分析方法。首先分析了芝麻油与大豆油、葵花籽油在4 000～650 cm-1范围的FTIR谱图,由于食用植物油都是不同脂肪酸甘油三酯的混合物,其谱图极为相似,很难发现芝麻油与其他油脂的明显差异。但是不同食用油的脂肪酸组成不同,其1 800～650 cm-1红外指纹特征区也有所不同,因此可以选择该区域,对红外光谱数据用化学计量学方法进行分类识别。通过建立主成分分析(PCA)和簇类独立软模式识别(SIMCA)模型,进行了芝麻油的真伪鉴别,该模型聚类效果较为理想,识别正确率达到了100％;采用标准正态化校正(SNV)和偏最小二乘法(PLS),经过PCA分析计算,芝麻油中掺入大豆油、葵花籽油的掺伪检测限均为10%;利用FTIR和PLS,建立了芝麻油掺的定量分析模型,该模型预测值与实际值有着良好的对应关系,预测相对误差为-6.87％～8.07％之间,说明定量模型可行。本方法能够实现芝麻油的快速真伪鉴别和掺伪定量分析,其优点是模型一旦建立,分析简便、快速,可以满足大量样品的日常监测。     

近红外光谱结合改进鲸鱼算法优化模型BAS-WOA-SVR检测藤椒油掺伪

鉴于藤椒油市场良莠不齐,以近红外光谱技术为基础,藤椒油为研究对象,展开对藤椒油掺伪检测研究。首先将纯藤椒油作为基底油,按比例配置掺入大豆油、玉米油、葵花籽油得到油样,采集藤椒油掺伪样品的近红外光谱数据;光谱数据经归一化处理后采用标准正态变换(SNV)、多元散射矫正(MSC)进行预处理,然后采用竞争性自适应重加权算法(CARS)、连续投影算法(SPA)进行特征数据提取,组合不同预处理算法与特征数据提取算法,通过支持向量机回归(SVR)建立藤椒油掺伪预测模型。结果表明：MSC-CARS-SVR模型校正集和预测集的决定系数(R²)最高,校正集R²达到了0.756 1,预测集R²达到0.705 2;均方根误差(RMSE)最小,校正集RMSE达到0.743,预测集RMSE达到0.794。为了提高模型的准确性,采用鲸鱼算法(WOA)和改进鲸鱼算法(BAS-WOA)优化SVR模型,改进的鲸鱼算法以每一次鲸鱼群的最优鲸鱼作为当前天牛须的出发位置,分别探索左右须前进,计算前进后的目标函数,如果目标函数优于当前最优鲸鱼的值,则用前进后的天牛...     

对比分析多种化学计量学方法在激光诱导击穿光谱土壤元素定量分析中的应用

为提高激光诱导击穿光谱技术对土壤元素检测的精度,建立了相关向量机土壤元素定量分析模型,并将该模型与已有的支持向量机模型和最小二乘支持向量机模型进行对比分析。以土壤元素Ni的4条特征谱线作为分析线,对其进行全谱归一化处理后,利用训练样品集建立相关向量机、支持向量机和最小二乘支持向量机模型。测试样品集的测试结果表明:在模型预测精度方面,支持向量机模型比另两种模型方法差;在稳定性方面,最小二乘支持向量机模型比另两种模型差。在实际应用中,相关向量机模型在稳定性及预测精度上的优势使其比另两个模型更适合用于激光诱导击穿光谱技术的定量分析中。     

可见/近红外光谱的油茶籽油三元体系掺假检测模型优化

采用可见/近红外光谱技术结合化学计量学方法对油茶籽油三元体系掺假进行定量检测研究。将菜籽油和花生油按不同比例掺入纯油茶籽油中,获得掺假样本。采集纯油茶籽油及掺假样本在350~1 800 nm范围内的可见/近红外光谱数据,随机分为校正集和预测集,并从不同建模波段、预处理方法及建模方法角度对掺假预测模型进行优化。研究结果表明,菜籽油、花生油和总掺伪量的最优建模波段及预处理方法分别为750~1 770,900~1 770 ,870~1 770 nm和多元散射校正(MSC)、标准归一化处理(SNV)和二阶微分,而最优的建模方法均为最小二乘支持向量机(LSSVM)。对于最优掺假模型,菜籽油、花生油和总掺伪量的预测集相关系数(R_p)和预测均方根误差(RMSEP)分别为0.963,0.982,0.993和2.1%,1.5%,1.8%。由此可见,可见/近红外光谱技术结合化学计量学方法可以用于油茶籽油的三元体系掺假定量检测。     

黄酒糖度预测的可见-近红外光谱方法研究

提出了用可见近红外光谱结合不同化学计量学方法预测黄酒糖度的新方法。用240个黄酒样本建模,60个样本进行预测。通过对光谱数据进行平滑、变量标准化及一阶导数等预处理,建立并比较了偏最小二乘法,小波变换与偏最小二乘法相结合,主成分分析与人工神经网络相结合以及主成分分析与最小二乘支持向量机相结合四种不同建模方法的预测精度,以相关系数r、预测标准差、偏差等为评判标准,得到黄酒糖度预测的最优模型为最小二乘支持向量机模型。该模型对黄酒糖度预测的相关系数为0.962、预测标准差为0.021、偏差为-0.001,获得了理想的预测精度。结果表明应用可见近红外光谱对黄酒糖度进行预测是可行的,且最小二乘支持向量机模型能得到最优的预测结果。     

近红外光谱-BP神经网络-PLS法用于橄榄油掺杂分析

橄榄油兼有食用和保健的作用,价值与价格远远高于其他食用油,所以橄榄油中以劣充好的现象十分普遍。可采用近红外光谱法测定初榨橄榄油中掺杂芝麻油、大豆油和葵花籽油的光谱数据,运用改进的BP算法——Levenberg-Marquardt方法,建立PCA-BP人工神经网络方法对其进行定性判别。同时采用偏最小二乘法(PLS)建立了初榨橄榄油中芝麻油、大豆油、葵花籽油含量的近红外光谱定标模型,用交互验证法进行验证。结果表明,BP人工神经网络有很好的定性鉴别能力,PLS建立的芝麻油、大豆油、葵花籽油定标模型的相关系数分别为98.77,99.37,99.44,交叉验证的均方根误差分别为1.3,1.1,1.04。该方法无损、快速、简便,为橄榄油掺杂的检测提供了一种新的途径。     

拉曼光谱结合PSO-LSSVM算法检测三组分食用调和油含量

提出了一种将拉曼光谱和基于粒子群的最小二乘支持向量机(PSO-LSSVM)算法相结合快速定量检测三组分食用调和油含量的方法。以三组分的食用调和油为研究对象,对拉曼光谱分四步进行了预处理,进而准确提取拉曼光谱的特征峰强度。以训练集样本的特征峰强度和调和油样品的百分比含量作为回归预测模型的输入值和输出值,建立LSSVM和PSO-LSSVM数学模型,通过测试集样本的相关系数和均方误差对模型的预测能力进行分析。非线性建模的最小二乘支持向量机(LSSVM)算法的核函数参数σ和正则化参数γ对模型的学习和泛化能力影响很大,导致模型的预测精度和泛化能力过度依赖于参数--在优化步长过小时耗时较长,过大时又无法得到全局最优值。提出的PSO-LSSVM算法,利用粒子群全局优化能力和收敛速度快的特点对LSSVM的模型参数σ和γ进行优化,从而克服LSSVM算法中耗时与盲目性的问题。分析结果表明,PSO-LSSVM算法对三组分食用调和油中大豆油、花生油和葵花仁油定量预测模型的测试集相关系数分别为0.967 7,0.997 2,0.995 3;均方误差分别为0.054 9,0.009 2,0.047 1。与LSSVM算法相比,PSO-LSSVM模型的预测精度更高。因此,该方法可以快速、准确地检测三组分食用调和油的含量。     

Quantitative detection of adulterated olive oil by Raman spectroscopy and chemometrics

Commercially available extra virgin olive oils are often adulterated with some other cheaper edible oils with similar chemical compositions. A set of extra virgin olive oil samples adulterated with soybean oil, corn oil and sunflower seed oil were characterized by Raman spectra in the region 1000–1800 cm⁻¹. Based on the intensity of the Raman spectra with vibrational bands normalized by the band at 1441 cm⁻¹ (CH₂), external standard method (ESM) was employed for the quantitative analysis, which was compared with the results achieved by support vector machine (SVM) methods. By plotting the adulterant content of extra virgin olive oil versus its corresponding band intensity in the Raman spectrum at 1265 cm⁻¹, the calibration curve was obtained. Coefficient of determination (R²) of each curve was 0.9956, 0.9915 and 0.9905 for extra virgin olive oil samples adulterated with soybean oil, corn oil and sunflower seed oil, respectively. The mean absolute relative errors were calculated as 7.41, 7.78 and 9.45%, respectively, with ESM, while they were 5.10, 6.96 and 4.55, in the SVM model, respectively. The prediction accuracy shows that the ESM based on Raman spectroscopy is a promising technique for the authentication of extra virgin olive oil. The method also has the advantages of simplicity, time savings and non‐requirement of sample preprocessing; especially, a portable Raman system is suitable for on‐site testing and quality control in field applications. Copyright © 2011 John Wiley & Sons, Ltd.     

Visible Raman spectroscopy for the discrimination of olive oils from different vegetable oils and the detection of adulteration

We have investigated the potential of Raman spectroscopy with excitation in the visible spectral range (VIS Raman) as a tool for the classification of different vegetable oils and the quantification of adulteration of virgin olive oil as an example. For the classification, principal component analysis (PCA) was applied, where 96% of the spectral variation was characterized by the first two components. A significant similarity between sunflower oil and extra‐virgin olive oil was found using this approach. Therefore, sunflower oil is a potential candidate for adulteration in most commercially available olive oils. Beside the classification of the different vegetable oils, we have successfully applied Raman spectroscopy in combination with partial least‐squares (PLS) regression analysis for very fast monitoring of adulteration of extra‐virgin olive oil with sunflower oil. Different mixtures of extra‐virgin olive oil with three different sunflower oil types were prepared between 5 and 100% (v/v) in 5% increments of sunflower oil. While in the present context the adulteration usually refers to the addition of reasonable amounts of the adulterant (given the similarity with the basic product), we show that the technique proposed can also be used for trace analysis of the adulterant. Without using techniques like surface‐enhanced Raman scattering (SERS), a quantitative detection limit down to 500 ppm (0.05%) could be achieved, a limit irrelevant for adulteration in commercial terms but significant for trace analysis. The qualitative detection limit even was at considerably lower concentration values. Based on PCA, a clear discrimination between pure extra‐virgin olive oil and olive oil adulterated with sunflower oil was achieved. The adulterant content was successfully determined using PLS regression with a high correlation coefficient and small root mean‐square error for both prediction and validation. Copyright © 2009 John Wiley & Sons, Ltd.     

Partial Least Squares Processing of Near‐Infrared Spectra for Discrimination and Quantification of Adulterated Olive Oils

Abstract

A new processing based on partial least squares (PLS) algorithm for the discrimination and determination of adulterants in pure olive oil using near‐infrared (NIR) spectroscopy has been introduced. The 280 adulterations of olive oil with corn oil (n=70), hazelnut oil (n=70), soya oil (n=70), and sunflower oil (n=70) were prepared, and their NIR spectra in the region 12,000–4550 cm^?1 were collected. The 70 spectra of each adulteration of olive oil were divided into two sets, 50 spectra for a calibration set and 20 spectra for a prediction set. The spectra of a total calibration set (n=200) were separated into individual adulterant calibration sets (n_i=50, i=corn, hazelnut, soya, sunflower) by using discriminant PLS (DPLS) analysis, and PLS calibration models for the quantification of adulterants with corn oil, hazelnut oil, soya oil, or sunflower oil were developed separately. A variety of wavelength ranges and data pretreatments were examined for obtaining optimal results for the discrimination and quantification objects. Four PLS models for differentiating the adulterant types were evaluated by classifying the NIR spectra of a total prediction set (n=80) into known adulterant types. Then, these known adulterant spectra were analyzed by the PLS calibration models developed for each type to determine the content of an adulterant in pure olive oil. The results of evaluation revealed that the processing reported in this article works excellently for the discrimination and quantification of the adulterations of olive oil.     

可见-近红外光谱分析技术对鱼油掺假定量快速无损检测方法研究

对掺入不同含量大豆油和菜籽油的鱼油进行鱼油掺假含量的可见-近红外光谱(Vis-NIR)研究。向3个不同品牌鱼油中分别掺入不同比例的大豆油,另外3个不同品牌中分别掺入不同比例的菜籽油,共获得300个样本。对所采集样本的光谱数据分别采用原始光谱,以及平滑,变量标准化(SNV),多元散射校正(MSC),一阶求导和二阶求导等预处理算法进行处理后,建立偏最小二乘回归(PLSR)模型。基于全波段光谱的鱼油中大豆油和菜籽油掺假含量预测的最优模型分别为全波段PLSR模型和MSC-PLSR模型,其预测相关系数(R_p)分别达到0.938 6和0.959 3。进一步采用连续投影算法(SPA)分析鱼油中大豆油和菜籽油掺假样品的光谱,并分别获得了11个和15个光谱特征波长变量。基于特征变量的PLSR模型的R_p分别为0.941 2和0.932 6。试验研究表明, 可以采用Vis-NIR技术实现对鱼油掺假物含量的检测。     

傅里叶变换近红外光谱结合RVM与新聚类算法鉴别灵芝孢子油多样掺假类别

食品掺假种类众多,手段隐蔽,成为食品安全检测一个重要难题。为摆脱传统模型识别食品中是否存在新掺假类别的局限性,实验以纯净的灵芝孢子油和掺杂不同比例花生油、玉米油、薏仁油、地沟油的五种类别为研究对象,采用傅里叶变换近红外光谱(Fourier transform near infrared spectroscopy, FT-NIR)收集12 400～4 000 cm-1范围内的近红外光谱。假设掺杂地沟油为新掺假类别,利用前四种类别的校正集样本构建相关向量机(RVM)多分类器,分别对建模的预测集样本和掺杂地沟油样本进行判别,并借助新聚类算法对判别为纯净的灵芝孢子油的样本做进一步分析验证。研究表明,RVM分类器对于建模的预测集样本判别准确率高达93.75%,说明模型有较强的判别能力,但由于模型局限性,掺杂地沟油样品被误判为纯净的灵芝孢子油;在新聚类算法的决策图上,纯净灵芝孢子油校正集和预测集混合样本的聚类中心数为1,而纯净灵芝孢子油校正集和掺杂了地沟油混合样本聚类中心数为2,直观验证判别结果的准确性。结果表明利用FT-NIR技术结合RVM分类器与新聚类算法对于灵芝孢子油掺假能够有效识别,并且能够定性识别新型掺假类型,为解决食品掺假多样化问题提供一种新思路。     

激光拉曼光谱检测灵芝孢子油

采用激光拉曼光谱分析比较了灵芝孢子油、橄榄油、葵花籽油及鱼肝油的光谱特征,结果显示激光拉曼光谱法可以用于快速检测灵芝孢子油：灵芝孢子油具有位于1 563 cm-1处峰强较弱线宽较宽的特征拉曼峰,而且位于1 445和1 660 cm-1两处拉曼峰的相对强度比与其他油不同。同时运用激光拉曼光谱法分析了变质的灵芝孢子油和廉价的灵芝孢子油,发现暴露在空气中一段时间后的灵芝孢子油的活性成分基本被氧化了,市场上廉价的灵芝孢子油可能是由变质的灵芝孢子油、葵花籽油、或其他廉价植物油混合掺杂而成的。