结合数据融合技术与近红外光谱的休闲苹果脆片综合品质评价

以加工过程中的苹果脆片为对象,对其水分、可溶性固形物、总糖、可滴定酸和硬度5个品质指标进行综合分析,得到各指标的权重和脆片品质的综合得分,根据综合得分情况,将脆片分为A(高品质)、B(中品质)、C(低品质)三类。利用近红外光谱技术获取苹果脆片光谱信息,运用偏最小二乘判别分析(partial least-squares discriminant analysis,PLSDA)方法建立基于光谱特征的苹果脆片综合品质得分的判别模型,对3类脆片进行分类的实际值和预测值的相关系数R分别为0.84,0.63,0.89,均方根误差RMSEC分别为0.26,0.34,0.22,预测集样本的判别准确率分别为83.33%,80.0%,93.33%,说明了结合数据融合技术与近红外光谱评价加工过程中苹果脆片综合品质具有较好的可行性。     

近红外光谱定量技术在方便面油份快速测定中的应用

探讨了用近红外漫反射光谱快速无损检测方便面含油率的数据处理方法，采用浸反射光谱、一阶导数光谱和二阶导数光谱，使用了四元线性向前逐步回归和BP人工神经网络的数学方法，对40个校正样本建立了的线性和非线性两种校正模型，用28个预测样要检验了校正模型的预测精度，其中线性校正模型中，采用二阶导数光谱的预测精度最好，预测平均误差为5．741％，预测误差的标准差为1．842；非线性校正模型中，采用一阶导数光谱，隐层单元数为2时，校正模型的预测精度最好，预测平均相对误差为5．149％，预测误差的标准差为1．675结果表明近红外漫反射光谱分析检测方便面的含油率能满足实际生产的要求。     

基于NIRS的食用醋品牌溯源模型的建立与优化

本文主要探讨了近红外光谱(NIRS)结合模式识别技术应用于食用醋品牌溯源研究。采集了四个品牌(四川保宁香醋、山西东湖老陈醋、镇江恒顺香醋、镇江香醋)共160组食醋样品的近红外漫反射光谱,通过主成分分析(PCA)进行光谱变量压缩及剔除8个异常样本数据后,随机选取其中的114组样品组成训练集用于建立溯源模型,剩余38组样品用作测试集进行模型验证。比较了MSC、SD、SNV等几种不同光谱预处理方法以及它们的不同组合对溯源模型的影响,同时考察了PLS-DA与SIMCA两种建模方法对模型的影响。结果表明:选择MSC与SD相结合的方法对光谱数据进行预处理,并采用SIMCA建模方法所建立的醋品牌溯源模型对四大品牌醋的正确识别率分别可达100%、100%、91.7%、90%。由此说明采用近红外光谱技术结合模式识别技术可有效实现食用醋品牌溯源的目的。     

近红外光谱技术快速检测小龙虾新鲜度

应用近红外光谱技术实现对小龙虾新鲜度的快速检测。利用化学计量学方法,通过对近红外品质分析仪采集的虾肉绞碎前后光谱（850～1 050 nm）调整不同预处理方法、偏最小二乘法和组合算法,建立一种基于总挥发性盐基氮（total volatile basic nitrogen,TVB-N）含量的小龙虾新鲜度定量预测模型。结果表明：采用标准正态变量变换与一阶导数结合的预处理方法模型预测效果最好,且绞碎后的虾肉光谱比绞碎前建模效果更好;为满足实际应用需要,对绞碎前的虾肉TVB-N含量预测模型进行分析,其交叉验证误差为3.123,交叉验证相关系数为0.947,用此模型对预测集24 个样品进行预测,预测值与实测值的交叉验证相关系数为0.951 4,在TVB-N含量超过20 mg/100 g（不新鲜）的检测准确率为100%。近红外光谱技术可应用于快速检测小龙虾新鲜度,所建模型具有较好的预测能力。     

Authentication of Green Asparagus Varieties by Near-Infrared Reflectance Spectroscopy

ABSTRACT: Near-infrared reflectance spectroscopy (NIRS) was used for the authentication of 2 green asparagus varieties (Taxara and UC-157), grown in Huetor-Tajar (Granada, Spain) protected by the Quality Specific Appellation "Espárragos de Huétor-Tájar". To develop the prediction model, the method chosen was modified partial least square (MPLS) regression. Two sample sets (N = 219 and N2 = 145 samples, respectively) were used to obtain the calibration equations. The standard error of cross-validation (SECV) and the r2 value were 0.082 and 0.97, respectively, for the 1st calibration set and 0.077 and 0.97 for the 2nd calibration set. The 2nd chemometric model obtained was tested with independent validation sample set (N3 = 74 samples), and the resulting values for standard error of prediction (SEP) and for r2 were 0.07 and 0.96, respectively. These results prove that NIRS is an accurate technology for identification and authentication of asparagus varieties and easily implemented in industry.     

Simultaneous detection for adulterations of maltodextrin,sodium carbonate,and whey in raw milk using Raman spectroscopy and chemometrics

To achieve rapid on-site identification of raw milk adulteration and simultaneously quantify the levels of various adulterants, we combined Raman spectroscopy with chemometrics to detect 3 of the most common adulterants. Raw milk was artificially adulterated with maltodextrin (0.5–15.0%; wt/wt), sodium carbonate (10–100 mg/kg), or whey (1.0–20.0%; wt/wt). Partial least square discriminant analysis (PLS-DA) classification and a partial least square (PLS) regression model were established using Raman spectra of 144 samples, among which 108 samples were used for training and 36 were used for validation. A model with excellent performance was obtained by spectral preprocessing with first derivative, and variable selection optimization with variable importance in the projection. The classification accuracy of the PLS-DA model was 95.83% for maltodextrin, 100% for sodium carbonate, 95.84% for whey, and 92.25% for pure raw milk. The PLS model had a detection limit of 1.46% for maltodextrin, 4.38 mg/kg for sodium carbonate, and 2.64% for whey. These results suggested that Raman spectroscopy combined with PLS-DA and PLS model can rapidly and efficiently detect adulterants of maltodextrin, sodium carbonate, and whey in raw milk.     

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。     

基于光谱融合的茶油真伪快速鉴别研究

目的 为实现高值茶油的快速鉴别。 方法 优化设备条件,同时采集茶油的近红外光谱(NIRS)和拉曼光谱(RS),分别使用六种方法进行预处理,再优选了四种方法来提取光谱特征波段,并应用了数据层、特征层两种策略融合多光谱信息,比较验证不同模型的准确率（Accuracy）和预测均方根误差（RMSEP）来评估效果。结果 单独使用NIRS经标准正态变换（SNV）处理后的偏最小二乘判别分析（PLS-LDA）结果最优,Accuracy为0.8361,RMSEP为0.1060;单独使用RS经二阶导数（Sg2nd）处理后的结果最优,Accuracy为0.8443,RMSEP为0.1332;经NIRS和RS融合后数据结果高于任意单一光谱结果,其中数据层光谱融合模型Accuracy为0.8525,RMSEP为0.1270,特征层融合后的模型效果较好,最佳结果为基于核主成分分析（KPCA）下的支持向量机（SVM）模型,Accuracy达到95.082%。结论 表明光谱融合提升茶油掺伪定性鉴别具有较好的应用前景。     

Evaluation of green coffee beans quality using near infrared spectroscopy: A quantitative approach

Characterisation of coffee quality based on bean quality assessment is associated with the relative amount of defective beans among non-defective beans. It is therefore important to develop a methodology capable of identifying the presence of defective beans that enables a fast assessment of coffee grade and that can become an analytical tool to standardise coffee quality. In this work, a methodology for quality assessment of green coffee based on near infrared spectroscopy (NIRS) is proposed. NIRS is a green chemistry, low cost, fast response technique without the need of sample processing. The applicability of NIRS was evaluated for Arabica and Robusta varieties from different geographical locations. Partial least squares regression was used to relate the NIR spectrum to the mass fraction of defective and non-defective beans. Relative errors around 5% show that NIRS can be a valuable analytical tool to be used by coffee roasters, enabling a simple and quantitative evaluation of green coffee quality in a fast way.     

基于便携式近红外光谱仪的食品接触性塑料鉴别

采用便携式近红外光谱仪对聚对苯二甲酸乙二酯(PET)、高密度聚乙烯(HDPE)、低密度聚乙烯(LDPE)、聚氯乙烯(PVC)、聚苯乙烯(PS)和聚碳酸酯(PC)6类食品接触性塑料材质进行鉴别研究。用5点平滑、多元散射校正(MSC)、一阶导数和标准正态变量变换(SNV)4种方法对塑料样品光谱进行预处理;主成分分析(PCA)和偏最小二乘判别分析(PLS-DA)分别用于塑料样品光谱空间分布分析和定性判别模型的建立。结果表明:光谱经SNV和MSC预处理后,6类塑料样品在前3个主成分空间得到了较好的分离;PLS-DA结合SNV预处理方法可得到精简的塑料材质定性判别模型,模型校正集和预测集的正确识别率(CRR)均为100%。该方法可为食品接触性塑料材质的快速鉴别提供参考。     

红外光谱结合多元统计分析快速鉴别不同种类牛肝菌

采用傅里叶变换红外光谱结合多元统计分析方法快速鉴别不同种类食用牛肝菌。采集10 个不同种类93 个牛肝菌子实体的红外光谱,分析食用牛肝菌的红外光谱特征;用多元散射校正（multiplicative signal correction,MSC）、标准正态变量（standard normal variate,SNV）、二阶导数（second derivative,SD）、Norris平滑（ND）、正交信号校正（orthogonal signal correction,OSC）、小波压缩等方法对光谱进行优化处理;经优化处理的光谱数据分别建立马氏距离分类模型及偏最小二乘判别分析（partial least squares discriminant analysis,PLSDA）。结果显示,牛肝菌在3 325、2 934、2 927、1 637、1 547、1 402、1 375、1 259、1 453、1 081、1 029 cm－1等附近有多个吸收峰,主要归属为蛋白质、多糖、氨基酸等的特征吸收峰。MSC＋SD＋ND（15∶5）和SNV＋SD＋ND（15∶5）两种预处理方式前10 个主成分累积贡献率分别为95.58%、95.54%,基于两种预处理方法建立马氏距离分类模型,验证集预测准确率分别为90%和95%。PLS-DA结果显示经MSC＋SD＋ND（15∶5）和SNV＋SD＋ND（15∶5）预处理不易于区分牛肝菌种类;原始光谱经正交信号校正及小波压缩（orthogonal signal correction waveletcompression,OSCW）、优化处理并进行PLS-DA分析,能够很好地区分不同种类牛肝菌。马氏距离分类模型不仅能反映样品的分类情况,同时计算出与测试样品相似度最大的物种,可为食用菌种类鉴别和未知物种鉴定提供可靠依据;OSCW预处理后进行PLS-DA分析能有效鉴别不同种类牛肝菌,为野生食用菌的鉴别分类提供一种辅助方法。     

植物油中掺煎炸动物油的近红外快速无损检测

利用近红外技术结合偏最小二乘法建立掺煎炸动物油植物油的定量模型。对100个植物油样本,通过近红外光谱仪扫描获得从10 000～4 000cm~(-1)的光谱信息。运用TQ-Analyst软件进行计算,选择全谱区,结合偏最小二乘法(PLS)算法,得到光谱最佳预处理方法为一阶导加Norris平滑。进行内部交叉验证,相关系数r为0.992 0,预测误差为3.11,且预测结果与真实值可通过t检验,说明模型是可行的。     

Comparison of near-infrared and dielectric spectra for quantitative identification of bovine colostrum adulterated with mature milk

The nonhomogeneity of bovine colostrum leads to strong scattering effects for electromagnetic waves, which affects the application of electromagnetic spectroscopy in detecting colostrum. This work aimed to compare the performance of near-infrared spectroscopy (NIRS) and dielectric spectroscopy (DS) in quantitatively predicting the content of mature milk as an adulterant in colostrum. The near-infrared spectra in the range of 833 to 2,500 nm and the dielectric spectra in the range of 20 to 4,500 MHz of 150 adulterated colostrum samples containing 0 to 50% mature milk were analyzed. The different proportions of mature milk in colostrum significantly changed near-infrared and dielectric spectra. The principal component analysis score plot showed that both NIRS and DS could identify the proportion of mature milk in colostrum, but the 2 methods had different characteristics. Linear partial least squares regression and nonlinear least squares support vector machine (LSSVM) models based on near-infrared and dielectric spectra were established to identify doping proportions. The results showed that DS had better identification performance with a root-mean-square error of prediction of 4.9% and a residual prediction deviation of 3.441 by successive projection algorithm LSSVM, whereas NIRS was relatively weak with a root-mean-square error of prediction of 7.3% and a residual prediction deviation of 2.301 by full-spectra LSSVM. This work provides important insights for the quantitative prediction of nonhomogeneous liquid food by DS.     

Verification of fresh grass feeding,pasture grazing and organic farming by FTIR spectroscopy analysis of bovine milk

In the present study, a total of 116 tank milk samples were collected from 30 farms located in The Netherlands and analysed by Fourier-transform infrared (FTIR) spectroscopy. Samples were collected in April, May and June 2011 and in February 2012. The samples differed in the time spent by the cows on pasture, presence/absence of fresh grass in the daily ration and the farming system (organic/biodynamic or conventional). Classification models based on partial least square discriminant analysis (PLS-DA) of FTIR spectra were developed for the prediction of fresh grass feeding, pasture grazing and organic farming. The PLS-DA model discriminated between milk from cows that had fresh grass in the daily ration and milk from cows that had not fresh grass with sensitivity and specificity values of 88% and 83% in external validation and all the samples from cows that had no fresh grass collected in spring were correctly classified. The PLS-DA model developed for the authentication of pasture grazing showed comparable accuracy when the whole sample set is considered but was less accurate on the spring samples (75% of samples from cows indoors in spring correctly classified). Discrimination of organic and conventional milk was also accomplished with acceptable accuracy with % correct classification of 80% and 94% respectively in external validation. The results suggest that milk FTIR spectra contain valuable information on cows' diet that can be used for authentication purposes.     

Can near‐infrared reflectance of green coffee be used to detect introgression in Coffea arabica cultivars?

Most new coffee cultivars disseminated over the last 15 years are derived from the Timor Hybrid (Coffea arabica × C canephora). Introgression of genes from the C canephora genome has been estimated at between 9 and 29% of the genome. It has been shown that introgression can have a negative impact on the cup quality of cultivars derived from the Timor Hybrid. Consequently, coffee buyers or roasters may wish to assess whether the coffee they are purchasing comes from introgressed varieties. The possibility of distinguishing between non‐introgressed Arabicas and genotypes carrying chromosome fragments introgressed from C canephora was investigated (i) using some classical chemical compounds (caffeine, chlorogenic acids, trigonelline, fat and sucrose) and (ii) using a new approach based on spectra acquired by near‐infrared reflectance of green coffee. Near‐infrared spectra were obtained for 129 samples from two collections (Nicaragua and Costa Rica) of introgressed and non‐introgressed coffee trees. The spectral collections were treated by principal component and factorial discrimination. When the introgressed coffee trees were compared with the non‐introgressed trees using the chemical compounds, small but significant differences were found in caffeine, trigonelline and chlorogenic acid contents. However, the small variations in those compounds are not enough to detect introgression. The spectral collections treated by principal component and factorial discrimination made it possible to class from 92.30 to 94.87% of the analysed samples correctly, while the percentages of correctly classified samples in the verification file varied from 88.23 to 94.11%. The NIRS method appears to be an efficient method for determining whether a green coffee comes from an introgressed variety. Copyright © 2005 Society of Chemical Industry     

基于近红外光谱法快速测定许氏平鲉脂肪和 水分含量的方法研究

目的建立近红外光谱法结合偏最小二乘法测定许氏平鲉鱼肉中的脂肪和水分含量,以期简便、快速地对许氏平鲉进行品质分析与评价。方法采用常规分析手段测定70个样品的脂肪和水分含量,同时采集其近红外光谱数据,结合偏最小二乘法(partial least square,PLS)建立许氏平鲉鱼肉中脂肪和水分的定量预测模型,并对比不同光谱预处理方法、光谱范围和因子数对定量预测模型的影响。结果光谱经Savitzky-Golay(S-G)和标准正态变量变换(standardized normal variate,SNV)预处理后,在5341.85~4007.36 cm~(-1)、6556.79~5345.71cm~(-1)和8651.10~7162.33 cm~(-1)光谱范围内,选取主因子数10,建立脂肪的校正模型性能最优;光谱经过SNV预处理后,在8886.38~4061.35cm~(-1)光谱范围内,分别选取主因子数为9时,建立的水分的校正模型性能最优。脂肪和水分含量相对最优PLS模型的校正集相关系数分别为0.9918和0.9912,校正标准偏差分别为0.2680和0.3300,交叉验证相关系数分别为0.9820和0.9810,交叉验证均方差分别为0.3980和0.4850,验证集相关系数分别为0.9804和0.9798,验证集均方差分别为0.3260和0.3070。结论本方法可较为准确地预测许氏平鲉鱼肉中的脂肪和水分含量,能够满足快速分析评价许氏平鲉品质的要求。     

基于近红外光谱与组合间隔偏最小二乘法的稻米镉含量快速检测

采用近红外光谱(near infrared spectroscopy,NIRS)结合组合间隔偏最小二乘法(synergy interval partial least squares,siPLS)建立稻米镉含量快速检测的方法。收集并分析72个稻米样品的NIRS谱图。对光谱前处理方法进行优化,确定平滑、多元散射校正与均值中心化处理为最优方法。采用siPLS法筛选特征波数,建立稻米镉含量的定量模型。稻米镉siPLS模型交叉验证均方根(RMSECV)与预测均方根(RMSEP)值分别为0.247与0.261,训练集相关系数(Rc)与预测集相关系数(Rp)值分别为0.919与0.895。结果表明:运用siPLS法选择特征波长后,不但可以降低模型的复杂度,同时还能够提高预测精度。NIRS作为一种快速、无损与便捷的初筛方法,可用于检测稻米中镉含量是否超标。     

番茄总糖含量的近红外光谱无损检测方法研究

根据偏最小二乘法建立番茄总糖含量的定量分析模型,比较原始光谱和平均光谱以及10 种光谱预处理方法对近红外光谱无损检测番茄总糖含量的影响。结果表明：平均光谱所建立的偏最小二乘法校正模型明显优于原始光谱所建模型,常数偏移消除最适合番茄总糖近红外光谱的预处理,其在11998.9～7497.9cm-1 和4601.3～4256.5cm-1优化光谱区内,所建偏最小二乘法定量分析模型的预测值和实测值的相关系数(R)为0.917,校正标准差(RMSEC)为0.263%,预测标准差(RMSEP)为0.236%。平均光谱和优化的光谱预处理方法可有效提高近红外光谱无损检测番茄总糖含量的准确性。     

无效变量消除法在油菜籽芥酸近红外无损速测中的应用

探索改善油菜籽芥酸近红外预测模型准确度与精密度的方法,利用无效变量消除法（UVE）,对135个油菜籽样品近红外光谱信号进行筛选,并利用筛选后的光谱对油菜籽芥酸含量进行偏最小二乘法交叉验证。结果表明,UVE法筛选变量后建立的芥酸校正模型对未知样品预测结果的准确度和速度显著优于全波长参与建立的芥酸校正模型。散射校正加一阶导数对光谱预处理,UVE法筛选变量,偏最小二乘法交叉验证建立的校正模型效果最好,其预测值与标准值的相关系数R达到0.92,交叉验证预测均方差为2.2。因此,用UVE进行波长选择后建立的近红外模型,能准确快速地对油菜籽芥酸含量进行定量分析。     

Applications of FT-NIRS combined with PLS multivariate methods for the detection & quantification of saccharin adulteration in commercial fruit juices

Detection of adulteration in carbohydrate-rich foods like fruit juices is particularly difficult because of the variety of the commercial sweeteners available that match the concentration profiles of the major carbohydrates in the foods. In present study, a new sensitive and robust assay using Fourier Transform Near-Infrared Spectroscopy (FT-NIRS) combined with partial least square (PLS) multivariate methods has been developed for detection and quantification of saccharin adulteration in different commercial fruit juice samples. For this investigation, six different commercially available fruit juice samples were intentionally adulterated with saccharin at the following percentage levels: 0%, 0.10%, 0.30%, 0.50%, 0.70%, 0.90%, 1.10%, 1.30%, 1.50%, 1.70% and 2.00% (weight/volume). Altogether, 198 samples were used including 18 pure juice samples (unadulterated) and 180 juice samples adulterated with saccharin. PLS multivariate methods including partial least-squares discriminant analysis (PLS-DA) and partial least-squares regressions (PLSR) were applied to the obtained spectral data to build models. The PLS-DA model was employed to differentiate between pure fruit juice samples and those adulterated with saccharin. The R² value obtained for the PLS-DA model was 97.90% with an RMSE error of 0.67%. Similarly, a PLS regression model was also developed to quantify the amount of saccharin adulterant in juice samples. The R² value obtained for the PLSR model was 97.04% with RMSECV error of 0.88%. The employed model was then cross-validated by using a test set which included 30% of the total adulterated juice samples. The excellent performance of the model was proved by the low root mean squared error of prediction value of 0.92% and the high correlation factor of 0.97. This newly developed method is robust, nondestructive, highly sensitive and economical.