磨盘柿可溶性固形物的可见/近红外漫反射光谱无损检测

研究可见/近红外漫反射光谱技术快速检测磨盘柿可溶性固形物的方法。在可见/近红外光谱区域(570～1848nm),对比分析不同数学建模算法、不同导数处理方法和不同散射及标准化处理的果实可溶性固形物定标模型。结果表明：应用改进偏最小二乘回归算法、一阶导处理和去散射处理所建果实可溶性固形物定标模型的预测性能较优,其定标交互验证相关系数(Rcv)和预测相关系数(Rp2)分别为0.8076和0.8085,定标交互验证均方根误差(RMSECV)和预测均方根误差(RMSEP)分别为0.4546°Brix和0.4482°Brix。这表明,可见/近红外漫反射技术对磨盘柿可溶性固形物的快速无损检测具有可行性。     

可见/近红外漫反射光谱无损检测磨盘柿果实硬度的研究

建立可见/近红外光谱与磨盘柿果实硬度之间的数学模型,评价可见/近红外光谱技术无损检测磨盘柿硬度的应用价值。在可见/近红外光谱区域(570～1848nm),实验对比分析了不同数学建模算法、不同导数处理方法和不同散射及标准化处理的磨盘柿果实硬度定标模型。结果表明,应用偏最小二乘回归算法、一阶导处理和标准正常化和散射处理所建柿果实硬度定标模型的预测性能较优,模型的相关系数(Rc2)为0.7992,均方根误差(RMSEC)为2.0642;用该模型对40个预测样本进行预测,其相关系数(Rp2)为0.8267,预测均方根误差(RMSEP)为2.0223。研究表明,可见/近红外漫反射技术对磨盘柿果实硬度的快速无损检测具有可行性。     

磨盘柿褐变指标的可见/近红外漫反射无损预测研究

为了建立可见/近红外漫反射光谱与磨盘柿果皮和果肉褐变之间的关系,作者在全光谱区域(570～1 848 nm)对比分析了不同处理方法对磨盘柿果皮颜色b*和果肉浊度定标模型的影响。结果表明,应用MPLS、原始光谱和无散射处理建立果皮颜色b*的定标模型预测性能较好,Rp2为0.968,RMSEP为1.417 7,RPD为7.92。应用PLS、一阶导处理和无散射处理建立磨盘柿果肉浊度的定标模型预测性能较好,Rp2为0.757,RMSEP为0.107 9,RPD为2.22。因此,可见/近红外漫反射技术对磨盘柿果皮颜色b*和果肉浊度的快速无损检测具有可行性。     

冷鲜羊肉品质的高光谱成像无损检测

利用400~1000 nm可见近红外高光谱成像系统对冷鲜羊肉蛋白质含量、嫩度、p H进行无损检测研究。采集冷鲜羊肉表面的高光谱散射图像,提取样本感兴趣区域的反射光谱曲线获得原始数据。先对原始光谱预处理并建立偏最小二乘回归(PLSR)模型,优选最佳预处理方法,后采用正自适应加权算法(CARS)和连续投影算法(SPA)提取特征波长,建立不同特征波长下各品质参数的PLSR预测模型。结果表明:利用原始光谱建立的冷鲜羊肉蛋白质、嫩度和p H的PLSR模型均优于经过光谱预处理所建PLSR模型;在不同波长下建立预测模型,OS-PLSR光谱模型对冷鲜羊肉蛋白质含量预测效果最佳,Rp=0.869,RMSEP=0.097;建立的SPA-PLSR光谱预测模型对p H预测效果理想,Rp=0.958,RMSEP=0.067;CARS-PLSR光谱预测模型对嫩度的预测能力较高,Rp=0.862,RMSEP=0.706。研究表明:利用可见近红外高光谱技术对冷鲜羊肉品质进行快速无损检测是可行的。     

小麦粉质特性的可见/近红外光谱快速测定研究

采用可见/近红外光谱对小麦粉质特性参数进行了快速测定研究。在小麦粉厂收集强、中和弱筋小麦粉样品共180份,采用标准方法测定了其粉质特性参数值,然后在波长570~1 080 nm下采集了样品的光谱。对原始光谱进行多元散射校正及一阶导数处理后,首先在全谱范围内建立了形成时间、稳定时间、吸水率、弱化度4个参数的PLS定量预测模型,以吸水率结果最优,其Rp=0.99,RMSEP=1.02;其次是形成时间和弱化度,其Rp值分别为0.97和0.93,RMSEP值分别为0.48和10.01;稳定时间结果稍差,其Rp=0.80,RMSEP=2.40。然后采用SPA方法分别提取了各粉质特性参数的光谱特征变量,对应建立了MLR模型,所建模型和PLS方法结果接近。表明可见/近红外光谱在小麦粉粉质特性评价中具有可行性,同时也为专用便携仪器的研制及小麦粉品质在线设备的开发提供了初步的理论依据。     

近红外结合Si-ELM检测食醋品质指标

为了提高近红外光谱技术检测食醋中可溶性无盐固形物含量(SSFSC)的精度和稳定性,提出采用联合区间偏最小二乘(Si-PLS)筛选光谱特征区间,再利用极限学习机(ELM)算法建立非线性回归模型,并对该方法的优越性进行系统比较;试验通过交互验证优化模型相关参数,以预测时的相关系数(Rp)和预测均方根误差(RMSEP)作为模型的评价指标。结果表明,Si-PLS结合ELM算法(Si-ELM)所建模型最佳,预测结果:Rp=0.973 9,RMSEP=1.232g/100mL。说明利用近红外光谱技术可以快速准确检测食醋中的SSF-SC,Si-ELM的应用可以适当提高该预测模型的精度。     

二维相关光谱的鲜核桃青皮含水率检测

青皮含水率是衡量鲜食核桃新鲜度的重要指标,研究基于可见/近红外光谱技术进行鲜核桃的二维相关光谱分析,以实现青皮含水率的检测。利用4种预处理方法进行光谱数据预处理,经MSC预处理后所建模型的预测结果最好,预测集的决定系数(Rp2)和均方根误差(RMSEP)分别为0.9244和1.23%。在此基础上,进行不同时间下鲜核桃的二维相关光谱分析,优选出7个自相关峰对应的波长(732、560、680、1471、1958、2315、1068 nm)为特征波长。然后,利用最小二乘支持向量机(LS-SVM)建立鲜核桃青皮含水率的预测模型,结果表明所建LS-SVM模型得到了较优的预测结果(Rp2=0.9146,RMSEP=1.32%)。二维相关的可见/近红外光谱分析可实现鲜核桃青皮含水率预测,为鲜核桃品质无损检测方法的研究提供了基础。     

生鲜紫薯花青素等多品质参数的可见-近红外快速无损检测

基于实验室自行搭建的可见-近红外光谱系统,以市售生鲜紫薯为研究对象,探讨其花青素、可溶性固形物（soluble solid contents,SSC）以及总糖（total sugars,TS）的同时快速无损检测方法。对紫薯原始光谱进行SG（Savitzky-Golay）平滑、标准正态变量变换以及一阶求导预处理,然后用偏最小二乘回归法进行建模分析。对于花青素和TS,经SG平滑结合一阶求导预处理的模型预测效果最佳;对于SSC,经SNV预处理的模型预测效果最好。针对紫薯各参数最佳预处理光谱采用竞争性自适应加权算法进行波长筛选,再次建立模型。花青素模型预测集的相关系数为0.942 1,预测均方根误差（root mean square error of prediction,RMSEP）为0.225?9?mg/g;SSC模型预测集相关系数为0.943?1,RMSEP为0.878?7?°Brix;TS模型预测集的相关系数为0.925?3,RMSEP为0.244?3%。结果显示,利用可见-近红外光谱可以实现对生鲜紫薯的花青素、SSC以及TS的同时快速无损检测,对生鲜紫薯品质的快速无损检测分选有着重要的实用意义。     

樱桃番茄可溶性固形物含量的可见/近红外透射光谱无损检测

基于可见/近红外透射原理,针对樱桃番茄内部品质不均,果径不同等特点,建立樱桃番茄透射检测系统,结合相关性分析和归一化处理对樱桃番茄的果径进行校正,在此基础上对樱桃番茄可溶性固形物(SSC)含量做快速无损检测。将80个样品按3∶1的比例随机分为校正集与预测集,选取波长范围600～960 nm内的光谱曲线先SG卷积平滑后进行一阶导数、二阶导数预处理,再对二者于波长903 nm和826 nm处进行归一化处理,采用偏最小二乘回归法对樱桃番茄可溶性固形物含量建立预测模型。结果显示,一阶微分和二阶微分预处理后,其预测模型的校正集和预测集相关系数与原始光谱相比均有明显提高。二阶微分光谱的预测模型校正集和预测集相关系数分别为0.8938和0.8337,均方根误差分别为0.3625°Brix和0.5793°Brix。果径归一化处理后,其预测模型的校正集和预测集相关系数进一步提高。果径归一化处理后的二阶微分光谱预测模型,其校正集和预测集相关系数分别达到0.9383和0.9360,均方根误差分别为0.2796°Brix和0.3955°Brix。结果表明,可见/近红外透射光谱结合果径归一化处理能有效预测樱桃番茄的内部品质,消除果径不同带来的误差,该检测方法的精度和稳定性较为理想,可预测樱桃番茄内部品质。     

NIR高光谱成像技术检测冷鲜羊肉嫩度

利用900~1700 nm近红外高光谱成像系统对冷鲜羊肉嫩度进行快速无损检测研究。采集冷鲜羊肉(1~8 d)表面的高光谱散射图像,提取样本感兴趣区域反射光谱曲线并用剪切力值表征冷鲜羊肉的标准嫩度。以原始光谱、特征区域光谱和Savitzky-Golay卷积平滑预处理光谱建立冷鲜羊肉嫩度的偏最小二乘回归(PLSR)模型,预处理的特征区域光谱建立的模型效果更优。结果表明:特征区域光谱可有效替代全波段光谱,经过S-G卷积平滑预处理后,模型预测效果最佳,预测相关系数(Rp)和均方根误差(RMSEP)分别为0.773和1.060。研究表明:利用近红外高光谱成像技术结合偏最小二乘回归法对冷鲜羊肉嫩度的快速无损检测是可行的。     

Nondestructive determination of soluble solids content and pH in tomato juice using NIR transmittance spectroscopy

The potential of near-infrared (NIR) transmittance spectroscopy to nondestructively detect soluble solids content (SSC) and pH in tomato juices was investigated. A total of 200 tomato juice samples were used for NIR spectroscopy analysis at 800–2400 nm using an FT-NIR spectrometer. Multiplicative signal correction (MSC), and the first and second derivative were applied for pre-processing spectral data. The relationship between SSC, pH, and FT-NIR spectra of tomato juice were analyzed via partial least-squares (PLS) regression. PLS regression models were able to predict SSC and pH in tomato juices. The r _c, RMSEC, RMSEP, and RMSECV for SSC were 0.92, 0.0703°Brix, 0.150°Brix, and 0.138°Brix, respectively, whereas those values for pH were 0.90, 0.0333, 0.0316, and 0.0489, respectively. It is concluded that the combination of NIR transmittance spectroscopy and PLS methods can be used to provide a technique of convenient, versatile, and rapid analysis for SSC and pH in tomato juices.     

基于高光谱技术的柑橘不同部位糖度预测模型研究

利用高光谱技术研究柑橘不同部位的糖度预测模型,将花萼、果梗和赤道部位的高光谱信息分别建立与其对应部位糖度的预测模型,建立基于偏最小二乘(Least squares regression,PLSR)、主成分回归(Principal component regression,PCR)和多元线性回归(Stepwise multivariate linear regression,SMLR)预测模型,3种预测模型中PLSR模型检测效果最好,通过Norris derivative预处理方法对花萼光谱数据进行处理后,预测集相关系数r_(pre)=0.950,预测集均方根误差RMSEP=0.636°Brix。结果表明,采用柑橘不同部位的高光谱信息与对应糖度预测模型是可行的,花萼部位所建立模型的效果优于果梗、赤道部位,因此花萼部位可作为优先选择的光谱检测部位,这对于指导实际检测分级生产中柑橘的摆放位置具有重要意义;采用PLSR方法建立柑橘花萼、果梗和赤道部位的高光谱信息与平均糖度的预测模型时,花萼部位模型效果最好,预测集相关系数r_(pre)=0.913,预测集均方根误差RMSEP=0.621°Brix,建模效果相较于对应部位光谱与糖度模型差,因此,采用柑橘全部果肉的平均糖度与采集部位光谱建立糖度预测模型具有一定的局限性。     

近红外光谱协同BP神经网络的泰国茉莉香米掺伪含量快速鉴定

利用近红外光谱协同BP神经网络算法,对泰国茉莉香米及其掺伪样品的近红外光谱进行多元散射校正预处理,挑选出48 个特征波长;以特征波长的吸光度为BP神经网络输入层神经元,以样品中泰国茉莉香米的含量为输出层神经元,获得BP神经网络算法的最优结构模型,即为单层隐含层、隐含层神经元数7、隐含层传递函数logsig、输出层传递函数tansig、训练函数trainlm、网络学习函数learngdm和学习速率0.35。所建立模型的均方根误差、校正集相关系数、验证集相关系数、测试集相关系数分别为0.000 830、0.992 9、0.976 1和0.975 5,呈现出优良的预测效果,实现了泰国茉莉香米掺伪含量的快速鉴定。     

Rapid measurement of total acid content (TAC) in vinegar using near infrared spectroscopy based on efficient variables selection algorithm and nonlinear regression tools

Total acid content (TAC) is an important index in assessing vinegar quality. This work attempted to determine TAC in vinegar using near infrared spectroscopy. We systematically studied variable selection and nonlinear regression in calibrating regression models. First, the efficient spectra intervals were selected by synergy interval PLS (Si-PLS); then, two nonlinear regression tools, which were extreme learning machine (ELM) and back propagation artificial neural network (BP-ANN), were attempted. Experiments showed that the model based on ELM and Si-PLS (Si-ELM) was superior to others, and the optimum results were achieved as follows: the root mean square error of prediction (RMSEP) was 0.2486 g/100mL, and the correlation coefficient (R(p)) was 0.9712 in the prediction set. This work demonstrated that the TAC in vinegar could be rapidly measured by NIR spectroscopy and Si-ELM algorithm showed its superiority in model calibration.     

拉曼光谱技术快速检测专用煎炸油极性组分

为能够快速、无损检测专用煎炸油的极性组分含量,采集不同煎炸时间下煎炸油样本的拉曼光谱图。为建立稳定性高、误差小、精度高的模型,研究不同预处理方法对模型效果的影响,建立相应的偏最小二乘回归模型以选择最优的光谱预处理方法。结果表明：标准正态变换处理后的偏最小二乘模型最优,预测均方根误差（root mean square error of prediction,RMSEP）为1.18,决定系数R2为0.940?4。其次,将标准正态变换处理后的光谱数据分别建立误差反向传播（error back propagation,BP）算法和径向基函数算法神经网络模型,通过比较稳定性以及误差大小,得出采集到的拉曼光谱经过标准正态变换处理后采用BP神经网络建立的模型效果最好,RMSEP为0.032?6,R2为0.972。该方法可以用作专用煎炸油极性组分的快速分析。     

Parameter optimization in soluble solid content prediction of entire bunches of grape based on near infrared spectroscopic technique

The object of this research was to evaluate grape’s soluble solid content (SSC) nondestructively based on near infrared spectroscopic technique using a detection probe designed in house and focus on optimization of three detection parameters that were light power (P), outer diameter of the probe (D), distance between the light source to the probe (L). Statistical models between diffuse transmittance spectra with grape’s SSC were developed using partial least square (PLS) regression. Orthogonal experiment was applied to choose optimal parameters. Comprehensive performance of different models under each combination of factor levels was assessed in terms of correlation coefficient of calibration (r _c ), root mean square error of prediction (RMSEP) and differential values of RMSEP and root mean square error of calibration (Δ). The PLS model obtained the best results with the r _c of 0.83, the RMSEP of 0.76 °Brix and the Δ of 0.84 °Brix on condition that P, D and L were 70 W, 70 and 85 mm, respectively. The results in the study show that SSC prediction of grape using the testing probe is feasible and parameter L has more impact on the performance of models than others. Better models can be obtained through reasonable parameters combination. This research can provide reference for the nondestructive detection of the entire bunches of grapes.     

Nondestructive measurement of soluble solid content of navel orange fruit by visible-NIR spectrometric technique with PLSR and PCA-BPNN

A relationship was established between the soluble solid content (SSC) of navel orange fruit determined by destructive measurement and visible-near infrared diffuse reflectance spectra in the wavelength range of 350-1800 nm. Multiplicative scatter correction (MSC) and standard normal variate correction (SNV) were applied to the spectra, partial least squares regression (PLSR) and back propagation neural network (BPNN) based on principal component analysis (PCA) were used to develop the models for predicting the SSC of intact navel orange fruit. Thirty-eight unknown samples were used to evaluate the performance of these models. The principal component analysis-back propagation (PCA-BPNN) method with MSC spectral pretreatment obtain the best predictive results, resulting in correlation coefficient, root mean square error of prediction (RMSEP), average difference between predicted and measured values (Bias) of 0.90, 0.68 °Brix and 0.16 °Brix, respectively. Experimental results indicate that PCA-BPNN is a suitable tool to model the non-linear complex system, with additional advantages over PLSR, and the vis/NIR spectrometric technique can be used for measuring the SSC of intact navel orange fruit, nondestructively.     

基于近红外高光谱成像技术的涩柿SSC含量无损检测

对150个涩柿采集900~1 700nm波段的近红外高光谱图像信息,利用蒙特卡罗—无信息变量消除(MC-UVE)和连续投影算法(SPA)对感兴趣区域光谱进行波长优选。通过MC-UVE-SPA优选出924.69,928.05,1 112.72,1 270.91,1 365.3,1 402.42,1 453.06,1 547.69nm 8个特征波长,对应的光谱反射率作为柿子可溶性固性物含量(SSC)检测的偏最小二乘回归(PLSR)检测模型输入,其预测集相关系数rpre=0.942,预测集均方根误差RMSEP=1.009°Brix。结果表明,MC-UVE-SPA可以有效提取与柿子SSC含量相关的特征信息,从而保留较少的波长建立较好的预测模型。     

Measurement of Soluble Solid Contents and pH of White Vinegars Using VIS/NIR Spectroscopy and Least Squares Support Vector Machine

Visible and near-infrared (VIS/NIR) spectroscopy combined with least squares support vector machine (LS-SVM) was employed to determine soluble solid contents (SSC) and pH of white vinegars. Three hundred twenty vinegar samples were distributed into a calibration set (240 samples) and a validation set (80 samples). Partial least squares (PLS) analysis was implemented for the regression model and extraction of latent variables (LVs). The selected LVs were used as LS-SVM input variables. Finally, LS-SVM models with radial basis function kernel were achieved with the comparison of PLS models. The results indicated that LS-SVM outperformed PLS models. The correlation coefficient (r), root mean square error of prediction, bias, and residual prediction deviation for the validation set were 0.988, 0.207°Brix, 0.183, and 6.4 for SSC whereas these were 0.988, 0.041, ?0.002, and 6.5 for pH, respectively. The overall results indicated that VIS/NIR spectroscopy and LS-SVM could be used as a rapid alternative method for the prediction of SSC and pH of white vinegars, and the results could be helpful for the fermentation process and quality control monitoring of white vinegar production.     

傅立叶近红外光谱法测定桃果中果胶含量

目的 基于傅里叶近红外光谱(Fourier transform near infrared)检测桃果中果胶含量的研究。方法 近红外光谱采集样品利用两个品种的桃,探究光谱预处理对建模的影响,建模采用偏最小二乘法(PLS)以及主成分回归(PCR)方法,模型的评价标准采用建模相关系数(R_C)、建模均方偏差(RMSE_C)、预测相关系数(R_P)、预测均方偏差(RMSE_P)。结果 两个品种的近红外光谱图和果胶含量无明显差异(P＞0.05),采用标准正态变量变换(SNV)和多元散射校正(MSC)对原始光谱的光程进行选择,所得建模结果影响基本一致,合适光谱数据格式以及平滑处理,能提高PLS和PCR模型的预测精度和稳定性。综合得出模型最佳是利用PLS方法建模并采用MSC/SNV结合一阶导数和 Savitzky-Golay (S-G)平滑对近红外光谱图进行预处理,评价参数分别为R_C=0.7795、R_P=0.7545、RMSE_C=0.0933、RMSE_P=0.0534和R_C=0.7800、R_P=0.7530、RMSE_C=0.0932、RMSE_P=0.0534。结论 该方法为利用近红外建模快速检测桃果中果胶含量提供重要依据。