A comparative study for the quantitative determination of soluble solids content,pH and firmness of pears by Vis/NIR spectroscopy

Visible and near infrared (Vis/NIR) spectroscopy was investigated to determine the soluble solids content (SSC), pH and firmness of different varieties of pears. Two-hundred forty samples (80 for each variety) were selected as sample set. Two-hundred ten pear samples (70 for each variety) were selected randomly for the calibration set, and the remaining 30 samples (10 for each variety) for the validation set. Partial least squares (PLS) and least squares-support vector machine (LS-SVM) with different spectral preprocessing techniques were implemented for calibration models. Different wavelength regions including Vis, NIR and Vis/NIR were compared. It indicated that Vis/NIR (400–1800 nm) was optimal for PLS and LS-SVM models. Then, LS-SVM models were developed with a grid search technique and RBF kernel function. All LS-SVM models outperformed PLS models. Next, effective wavelengths (EWs) were selected according to regression coefficients. The EW-LS-SVM models were developed and a good prediction precision and stability was achieved compared with PLS and LV-LS-SVM models. The correlation coefficient of prediction (r_p), root mean square error of prediction (RMSEP) and bias for the best prediction by EW-LS-SVM were 0.9164, 0.2506 and −0.0476 for SSC, 0.8809, 0.0579 and −0.0025 for pH, whereas 0.8912, 0.6247 and −0.2713 for firmness, respectively. The overall results indicated that the regression coefficient was an effective way for the selection of effective wavelengths. LS-SVM was superior to the conventional linear PLS method in predicting SSC, pH and firmness in pears. Therefore, non-linear models may be a better alternative to monitor internal quality of fruits. And the EW-LS-SVM could be very helpful for development of portable instrument or real-time monitoring of the quality of pears.     

基于正交信号校正和偏最小二乘(OSC/PLS)的苹果糖度近红外检测

采用正交信号校正法(OSC)对苹果的近红外光谱(1300nm～2100nm)进行预处理，并结合偏最小二乘法(PLS)建立了苹果光谱对糖度的预测模型。应用结果表明，经OSC法预处理后，光谱形状总体上与原始光谱没有差别，但光谱曲线变得更为光滑，排列更为整齐、紧密。这说明正交信号校正法(OSC)滤除了原始光谱中的部分噪声，但又保留了原光谱中的主要信息。苹果光谱对糖度的PLS校正模型采纳的最佳因予数会随着OSC因子的被逐个滤除而逐渐减少，甚至可减少至1(当然模型精度也有变化)。本研究中，校正模型的最佳性能产生于原始光谱被滤除10个OSC因了时，此时其采纳的最佳因了数为2，校正时的相关系数r2和标准偏差SEC分别为0．92644和0．40250，预测时的标准偏差SEP为0．50229。与OSC法处理前的PLS模型相比，其精度虽没有大幅提高，但由于采纳的因子数少，模型变得十分简洁。     

Comparison of Bayesian and partial least squares regression methods for mid-infrared prediction of cheese-making properties in Montbéliarde cows

Assessing the cheese-making properties (CMP) of milks with a rapid and cost-effective method is of particular interest for the Protected Designation of Origin cheese sector. The aims of this study were to evaluate the potential of mid-infrared (MIR) spectra to estimate coagulation and acidification properties, as well as curd yield (CY) traits of Montbéliarde cow milk. Samples from 250 cows were collected in 216 commercial herds in Franche-Comté with the objectives to maximize the genetic diversity as well as the variation in milk composition. All coagulation and CY traits showed high variability (10 to 43%). Reference analyses performed for soft (SC) and pressed cooked (PCC) cheese technology were matched with MIR spectra. Prediction models were built on 446 informative wavelengths not tainted by the water absorbance, using different approaches such as partial least squares (PLS), uninformative variable elimination PLS, random forest PLS, Bayes A, Bayes B, Bayes C, and Bayes RR. We assessed equation performances for a set of 20 CMP traits (coagulation: 5 for SC and 4 for PCC; acidification: 5 for SC and 3 for PCC; laboratory CY: 3) by comparing prediction accuracies based on cross-validation. Overall, variable selection before PLS did not significantly improve the performances of the PLS regression, the prediction differences between Bayesian methods were negligible, and PLS models always outperformed Bayesian models. This was likely a result of the prior use of informative wavelengths of the MIR spectra. The best accuracies were obtained for curd yields expressed in dry matter (CY_DM) or fresh (CY_FRESH) and for coagulation traits (curd firmness for PCC and SC) using the PLS regression. Prediction models of other CMP traits were moderately to poorly accurate. Whatever the prediction methodology, the best results were always obtained for CY traits, probably because these traits are closely related to milk composition. The CY_DM predictions showed coefficient of determination (R²) values up to 0.92 and 0.87, and RS_y,x values of 3 and 4% for PLS and Bayes regressions, respectively. Finally, we divided the data set into calibration (2/3) and validation (1/3) sets and developed prediction models in external validation using PLS regression only. In conclusion, we confirmed, in the validation set, an excellent prediction for CY_DM [R² = 0.91, ratio of performance to deviation (RPD) = 3.39] and a very good prediction for CY_FRESH (R² = 0.84, RPD = 2.49), adequate for analytical purposes. We also obtained good results for both PCC and SC curd firmness traits (R² ≥ 0.70, RPD ≥1.8), which enable quantitative prediction.     

Shortwave-near infrared spectroscopy for determination of reducing sugar content during grape ripening,winemaking, and aging of white and red wines

The feasibility of near infrared (NIR) spectroscopy for predicting reducing sugar content during grape ripening, winemaking, and aging was assessed. NIR calibration models were developed using a set of 146 samples scanned in a quartz flow cell with a 50 mm path length in the NIR region (800–1050 nm), in a fiber spectrometer system working in transmission mode. Principal component analysis (PCA), partial least squares (PLS), and multiple linear (MLR) regressions were used to interpret spectra and to develop calibrations for reducing sugar content in grape, must, and wine. The PLS model based on the full spectral range (800–1050 nm), yielded a determination coefficient (r²) of 0.98, a standard error of cross validation (SECV) of 13.62 g/l and a root mean square error of cross validation (RMSECV) of 13.58 g/l. The mathematical model was tested with independent validation samples (n = 48); the resulting values for r², the standard error of prediction (SEP) and the root mean square error of prediction (RMSEP) for the same parameter were 0.98, 10.84, and 12.20 g/l, respectively. The loading weights of latent variables from the PLS model were used to identify sensitive wavelengths. To assess their suitability, MLR models were built using these wavelengths. Wavelength significance was analyzed by ANOVA, and four wavelengths (909, 951, 961, and 975 nm) were selected, setting statistical significance at the 99% confidence level. The MLR model yielded acceptable results for r² (0.92), SEP (19.97 g/l) and RMSEP (20.51 g/l). The results suggest that NIR spectroscopy is a promising technique for predicting reducing sugar content during grape ripening, as well as during the fermentation and aging of white and red wines. Individual fingerprint wavelengths strongly associated with reducing sugar content could be used to enhance the efficacy of this simple, efficient and low-cost instrument.     

Multivariate determination of free fatty acids and moisture in fish oils by partial least-squares regression and near-infrared spectroscopy

The oxidative and hydrolytic degradation of lipids in fish oil was monitored using partial least-squares (PLS) regression and near-infrared reflectance (NIR) spectroscopy. One hundred and sixty (n=160) fish oil samples from a fishmeal factory were scanned in transflectance by an NIR monochromator instrument (1100–2500 nm). Calibration models were performed for free fatty acids (FFA), moisture (M), peroxide value (PV) and anisidine value (AV). Coefficients of determination in calibration (R²) and standard errors of cross validation (SECV) were 0.96 (SECV: 0.59) and 0.94 (SECV: 0.03) for FFA and M in g/kg, respectively. The accuracy of the NIR calibration models were tested using a validation set, yielding coefficients of correlation (r) and standard errors of prediction (SEP) of 0.98 (SEP: 0.50) and 0.80 (SEP: 0.05) for FFA and M in g/kg, respectively. Poor accuracy (R²<0.80) was obtained for the NIR calibration models developed for PV and AV. The paper demonstrates that fish oil hydrolytic degradation of lipids, which seriously affect oil use and storage under industrial conditions, can be successfully monitored using PLS regression and NIR spectroscopy by the fishmeal industry.     

近红外结合线性回归算法快速预测小麦籽粒干物质和重量

为了实现小麦品质(干物质、重量)的快速无损检测,对35个小麦品种样品进行了近红外系统扫描,获取光谱信息,并进行高斯滤波平滑(GFS)、归一化(N)和基线校正(BC)预处理.采用偏最小二乘(PLS)算法分别建立光谱信息与干物质和重量参考值之间的定量关系.采用回归系数法(RC)和连续投影算法(SPA)两种方法在900～17...     

Prediction of moisture,color and pH in cooked,pre-sliced turkey hams by NIR hyperspectral imaging system

The investigation was conducted to develop a hyperspectral imaging system in the near infrared (NIR) region (900–1700 nm) to predict the moisture content, pH and color in cooked, pre-sliced turkey hams. Hyperspectral images were acquired by scanning the ham slices (900–1700 nm) originated from different quality grade of turkey hams. Spectral data were then extracted and analyzed using partial least-squares (PLSs) regression, as a multivariate calibration method, to reduce the high dimensionality of the data and to correlate the NIR reflectance spectra with quality attributes of the samples considered. Instead of using a wide range of spectra, the number of wavebands was reduced for more stable, comprehensive and faster model in the subsequent multispectral imaging system. From this point of view, important wavelengths were selected to improve the predictive power of the calibration models as well as to simplify the model by avoiding repetition of information or redundancies. With the help of PLS regression analysis, nine wavelengths (927, 944, 1004, 1058, 1108, 1212, 1259, 1362 and 1406 nm) were selected as the optimum wavelengths for moisture prediction, eight wavelengths (927, 947, 1004, 1071, 1121, 1255, 1312 and 1641 nm) for pH prediction and nine wavelengths (914, 931, 991, 1115, 1164, 1218, 1282, 1362 and 1638 nm) were identified for color (a^*) prediction. With the identified reduced number wavelengths, good coefficients of determination (R²) of 0.88, 0.81 and 0.74 with RMSECV of 2.51, 0.02 and 0.35 for moisture, pH and color, respectively, were achieved, reflecting reasonable accuracy and robustness of the models.     

Quantification of glucose,fructose and sucrose in bayberry juice by NIR and PLS

Bayberry plays an important role in the nutrition and is a very important fruit-product. It has a high economic and officinal value. In this study, glucose, fructose and sucrose in bayberry juice were detected and quantified using near-infrared (NIR) spectroscopy. The HPLC method was assumed to provide the reference value of the analyte for calibration. Partial least-squares regression (PLSR) was used to construct calibration models with different pre-processing methods. The number of PLS factors was optimised. The results show PLS models are good for predicting glucose, fructose and sucrose concentrations in bayberry juice, and their prediction accuracy can be improved by using derivative process with the exception of the glucose. The best models were mostly given by the second derivative processed spectra, especially for sucrose with the determination coefficient, R² of 0.9931. This demonstrates the potential of NIR spectroscopy to quickly detect these components simultaneously in bayberry juice with the reference method of HPLC.     

灵武长枣蔗糖含量的高光谱无损检测

利用高效液相色谱法检测蔗糖含量,同时运用高光谱成像技术结合化学计量方法建立蔗糖预测模型;通过竞争性自适应加权（competitive adaptive reweighted sampling,CARS）算法、连续投影算法（successive projection algorithm,SPA）和无信息消除变量（uninformative variable elimination,UVE）降维处理,建立特征波段和全波段的主成分回归（principal component regression,PCR）、偏最小二乘回归（partial least squares regression,PLSR）和多元线性回归（multivariable linear regression,MLR）模型。结果表明,采用蒙特卡洛方法剔除异常样本后,相关系数由0.611增大到0.846;正交信号校正法预处理效果最佳,RC和RP分别为0.853和0.794;利用SPA、UVE、CARS、CARS＋SPA和CARS＋UVE五种方法提取了5、21、17、10、18 个特征变量,其中CARS-PCR模型最好,校正集、预测集的相关系数为0.861、0.843,校正集、预测集的均方根误差为0.013 mg/g和0.014 mg/g。综上,高光谱成像技术可以实现长枣蔗糖含量的预测,为更深一步探讨枣的内部品质提供参考。     

可见/近红外光谱技术无损检测新鲜鸡蛋蛋白质含量的研究

鸡蛋是一种重要的食品,蛋白质是鸡蛋的主要营养成分。本研究利用可见近红外反射光谱技术无损检测新鲜鸡蛋的蛋白质含量。使用光谱仪获取新鲜鸡蛋在400~1100 nm波段范围内的漫反射光谱;分别使用多元散射校正(MSC)法和一阶导数法(1-D)对反射光谱进行预处理;对反射光谱、MSC处理光谱和1-D光谱,使用逐步回归法判别法选择最优波长组合,建立多元线性回归模型,使用全交叉验证法验证模型。结果表明,可见/近红外反射光谱经过多元散射校正后,确定的10个最优波长(400、403.16、407.9、714.6、715、715.58、970.4、970.75、973和974.45 nm)组合建立模型的校正和验证结果最好:选定模型的校正结果为R=0.92,SEC=0.42%;验证结果为Rcv=0.89,SECV=0.47%。研究表明可见/近红外反射光谱技术可以较好的预测新鲜鸡蛋的蛋白质含量,本研究可为可见近红外光谱技术在鸡蛋营养成分的快速检测提供一定的理论基础。     

Shedding light on human tissue (in vivo) to predict satiation,satiety, and food intake using near infrared reflectance spectroscopy: A preliminary study

The aim of this study was to evaluate the ability of a portable near infrared (NIR) instrument to collect the spectra in vivo of different tissues in healthy individuals and to relate their spectral information with food and energy intake, satiation, and satiety data. In this study, a hand-held NIR instrument was used to collect the spectra of different human tissues (e.g. arm, ear, face, jaw and wrist) with partial least squares (PLS) regression used to relate the NIR data with food and energy intake, satiation, and satiety measured in healthy individuals. The coefficient of determination in cross-validation (R²_CV) and the standard error in cross validation (SECV) for the prediction of satiety ranged between 0.58 and 0.62 and 223.3–235.0 total area under the curve (AUC), respectively, depending on the tissue analysed. The PLS cross-validation models based on the NIR spectra collected in both the arm and face tissues gave the best prediction of food intake (R² _CV 0.47–0.51, SECV 110.8-115 g). No workable calibrations were developed for the prediction of satiation, which might be associated with the inherent complexity of this parameter as well as the experimental conditions used to collect the data (e.g. type of tissue analysed). These results demonstrated the potential ability of in vivo NIR spectroscopy to identify tissue differences associated with satiety and food intake in individuals. However, a wider variety of food types, diets, and human subjects (samples) are needed to develop robust relationships between the NIR spectra of a tissue with both satiety and food intake.     

Near-infrared spectroscopy coupled chemometric algorithms for prediction of antioxidant activity of black goji berries (<Emphasis Type="Italic">Lycium ruthenicum</Emphasis> Murr.)

In this study, near-infrared (NIR) spectroscopy coupled with partial least-squares (PLS) regression and various efficient variable selection algorithms, synergy interval-PLS (Si-PLS), backward interval PLS (Bi-PLS) and genetic algorithm-PLS (GA-PLS) were applied comparatively for the prediction of antioxidant activity in black wolfberry (BW). The eight assays were used for quantification of antioxidant content. The developed models were assessed using correlation coefficients (R²) of the calibration (Cal.) and prediction (Pre.); root mean square error of prediction, RMSEP; standard Error of Cross-Validation, RMSECV and residual predictive deviation, RPD. The performance of the built model greatly improved by the application of Si-PLS, Bi-PLS and GA-PLS compared with full spectrum PLS. The R² values determined for calibration and prediction set ranged from 0.8479 to 0.9696 and 0.8401 to 0.9638, respectively. These findings revealed that NIR spectroscopy combined with chemometric algorithms can be used for quantification of antioxidant activity in BW samples.     

Application of Curve Fitting and Wavelength Selection Methods for Determination of Chlorogenic Acid Concentration in Coffee Aqueous Solution by Vis/NIR Spectroscopy

Coffee is considered as a functional food due to its being rich in bioactive compounds, mainly chlorogenic acid (CGA). CGA concentration in coffee aqueous solution was investigated based on visible/near-infrared (Vis/NIR) spectroscopy in this research. To enhance the spectral difference among different samples and increase the signal to noise ratio, Lorentz function curve fitting was applied to fit raw Vis/NIR spectra of samples. Then, the fitting parameters were used to correct raw full spectra. Partial least squares (PLS) regression method was used to develop calibration models of CGA concentration. Full-spectrum models were built with raw and fitting parameter-corrected spectra, respectively. Further, wavelength selection methods, such as genetic algorithms (GAs) and success projection algorithms (SPAs), were applied to eliminate redundancy information and identify relevant information from full spectra. Calibration models based on the effective wavelengths selected by GA and SPA methods were developed. The overall results showed that LFPs a/b-corrected spectra had a better performance compared with other processing methods. Performance of the selected wavelength model was better than that of the full-spectrum model. Final results indicated that the SPAs-PLS method provided a more precise prediction model of CGA concentration with R _c of 0.913 and R _cv of 0.795.     

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.     

On-line prediction of fresh pork quality using visible/near-infrared reflectance spectroscopy

Visible/near-infrared (Vis/NIR) spectroscopy was tested to predict the quality attributes of fresh pork (content of intramuscular fat, protein and water, pH and shear force value) on-line. Vis/NIR spectra (350–1100 nm) were obtained from 211 samples using a prototype. Partial least-squares regression (PLSR) models were developed by external validation with wavelet de-noising and several pre-processing methods. The 6th order Daubechies wavelet with 6 decomposition levels (db6–6) showed high de-noising ability with good information preservation. The first derivative of db6–6 de-noised spectra combined with multiplicative scatter correction yielded the prediction models with the highest coefficient of determination (R²) for all traits in both calibration and validation periods, which were all above 0.757 except for the prediction of shear force value. The results indicate that Vis/NIR spectroscopy is a promising technique to roughly predict the quality attributes of intact fresh pork on-line.     

Detection of Organic Acids and pH of Fruit Vinegars Using Near-Infrared Spectroscopy and Multivariate Calibration

Near-infrared (NIR) spectroscopy was investigated to determine the acetic, tartaric, formic acids and pH of fruit vinegars. Optimal partial least squares (PLS) models were developed with different preprocessing. Simultaneously, the performance of least squares-support vector machine (LS-SVM) models was compared with three kinds of inputs, including wavelet transform (WT), latent variables, and effective wavelengths (EWs). The results indicated that all LS-SVM models outperformed PLS models. The optimal correlation coefficient (r), root mean square error of prediction and bias for validation set were 0.9997, 0.3534, and −0.0110 for acetic acid by WT-LS-SVM; 0.9985, 0.1906, and 0.0025 for tartaric acid by WT-LS-SVM; 0.9987, 0.1734, and 0.0012 for formic acid by EW-LS-SVM; and 0.9996, 0.0842, and 0.0012 for pH by WT-LS-SVM, respectively. The results indicated that NIR spectroscopy (7,800–4,000 cm⁻¹) combined with LS-SVM could be utilized as a precision method for the determination of organic acids and pH of fruit vinegars.     

基于siPLS的猕猴桃糖度近红外光谱检测

为了探寻一种快速无损检测猕猴桃糖度的方法,利用小波滤噪法对猕猴桃1000～2500nm 近红外光谱进行了预处理,并用偏最小二乘法(PLS)、区间偏最小二乘法(iPLS)和联合区间偏最小二乘法(siPLS)分别建立预测模型。结果表明,采用联合区间偏最小二乘法将光谱划分为16 个子区间,利用其中的第9、11、13 号3 个子区间联合建立的糖度模型效果最佳,其校正集相关系数和均方根误差分别为0.9414 和0.3788。预测集相关系数和均方根误差分别为0.9295 和0.3904,主因子数为7 个。研究表明,用小波滤噪和联合区间偏最小二乘法所建立的猕猴桃糖度模型不但减少建模运算时间,剔除噪声过大的谱区,而且预测能力和精度均有所提高。     

Improvement of Near-Infrared Spectral Calibration Models for Brix Prediction in ‘Gannan’ Navel Oranges by a Portable Near-Infrared Device

A portable near-infrared (NIR) device was developed to nondestructively predict Brix value in intact ‘Gannan’ navel oranges. This research focused on developing calibration models which were less disturbed by the challenges of portable applications. The spectra of 150 samples were collected in the wavelength range of 820–950 nm. Wavelet transformed (WT) was applied to compress the raw data for improving the optimization efficiency. Classical linear partial least squares regression and nonlinear least squares support vector regression (LSSVR) were applied to building calibration models. By comparison, both prediction precision and optimization efficiency of the compressed regression models were improved. The LSSVR models outperformed the PLS models with higher accuracy and lower error. LSSVR combined with WT compression (WT–LSSVR) produced the best correlation coefficient value (r) and the root mean squared error of prediction of 0.918 and 0.321 ^oBrix. Based on these results, WT–LSSVR is to be a promising method to improve precision and optimization efficiency of NIR spectral calibration models for Brix prediction in ‘Gannan’ navel oranges by the portable near-infrared device.     

Monitoring water uptake in whole barley (Hordeum vulgare L.) grain during steeping using near infrared reflectance spectroscopy

The aim of this study was to evaluate the use of near infrared reflectance (NIR) spectroscopy to monitor water uptake and steeping time in whole barley samples as a rapid and easy to use technique. Whole barley grain samples were steeped in water, and subsamples were analyzed for water uptake (gravimetric method) and using NIR spectroscopy. The spectra and the analytical data were used to develop partial least squares (PLS) calibrations to predict water uptake and steeping time. Cross validation models for water uptake and steeping time gave a coefficient of determination in cross validation (R²) and the standard error of prediction (SEP) of 0.90 (SEP = 5.36 g/100 g fw) and 0.92 (SEP = 3.93 h), respectively. This study showed that NIR spectroscopy combined with PLS regression showed promise as a rapid, non-destructive method to monitor and measure water uptake and steeping time in whole barley during soaking.     

Quantification of soluble solids in reconstituted açaí (Euterpe oleracea Mart.) pulp using near‐infrared spectroscopy

Açaí consumption is increasing worldwide because of the growing recognition of its nutritional and therapeutic properties. This product is classified based on its soluble solids content (SS), but the determination of SS in pulp is time consuming, tedious and not suitable for modern food processing plants. As near‐infrared (NIR) systems have been implemented to measure various quality attributes of food products, the objective of this study was to evaluate the feasibility of NIR diffuse reflectance spectroscopy to quantify the SS content of açaí pulp. Partial least squares (PLS) regression models were constructed to predict the SS. An optimum PLS model required one latent variable [principal component (PC)1 = 97%] with a root‐mean‐square error of calibration (RMSEC) of 1.06% for the calibration data set and the root‐mean‐square error of prediction (RMSEP) of 1.03% for internal cross‐validation. External validation using an independent data set showed good performance (RMSEP = 1.33% and Rp² = 0.82). NIR spectroscopy is a reliable method with which to determine SS in açaí pulp and thereby to classify açaí pulp according to established minimum quality standards.