Prediction of Starch Amylose Content Versus Total Grain Amylose Content in Corn by Near-Infrared Transmittance Spectroscopy

A study was conducted to investigate methods of improving a near-infrared transmittance spectroscopy (NITS) amylose calibration that could serve as a rapid, nondestructive alternative to traditional methods for determining amylose content in corn. Calibrations were developed using a set of genotypes possessing endosperm mutations in single- and double-mutant combinations ranging in starch-amylose content (SAC) from -8.5 to 76%, relative to a standard curve. The influence of three factors were examined including comparing calibrations made against SAC versus grain amylose content (GAC), developing calibrations using partial least squares (PLS) analysis versus artificial neural networking (ANN), and using all samples in the calibrations set versus using progressively narrower ranges of SAC or GAC in the calibration set. Grain samples were divided into calibration and validation sets for PLS analysis while samples used in ANN were assigned to a training set, test set, and validation set. Performance statistics of the validation sets that were considered were the coefficient of determination (R), the standard error of prediction (SEP), and the ratio of the standard deviation of amylose values to the SEP (RPD), which were used to compare all NITS models. The study revealed an NITS prediction model for SAC (R = 0.96, SEP = 5.1%, RDP = 3.8) of similar precision to the best GAC model (R = 0.96, SEP = 2.7%, RPD = 3.5). Narrowing the amylose range of the calibration set generally did not improve performance statistics except for PLS models for SAC in which a decrease in SEP values was observed. In one model, the SEP improved while R and RPD remained constant (R = 0.94, SEP = 4.2%, RPD = 2.8) when samples with SAC values <20% were removed from the calibration set. Although the NITS amylose calibrations in this study are of limited precision, they may be useful when a rough screening method is needed for SAC. For example, NITS may be useful to detect severe contamination during transport and storage of specialty grains or to aid breeders when selecting for amylose content from large numbers of grain samples.     

近红外光谱法快速测定土壤碱解氮、速效磷和速效钾含量

运用偏最小二乘法(PLS)和人工神经网络(ANN)方法分别建立了0.9 mm筛分风干黑土土壤碱解氮、速效磷和速效钾含量预测的近红外光谱(NIRS)分析模型。使用偏最小二乘算法建立的碱解氮、速效磷和速效钾校正模型的决定系数R²分别为0.9520、0.8714和0.7300，平均相对误差分别为3.42%、13.40%和7.40%。人工神经网络方法建立的碱解氮、速效磷和速效钾校正模型的决定系数分别为0.9563、0.9493和0.9522，相对误差分别为2.67%、6.48%和2.27%，测试集仿真的相对误差分别为5.44%、16.65%和7.87%。结果表明，人工神经网络方法所建立的校正模型均优于偏最小二乘法所建模型；用近红外光谱分析法预测土壤碱解氮含量是可行的，而速效磷、速效钾模型的测试集样品仿真的相对误差较大，其预测可行性还需做进一步研究。     

Estimation of wood density and chemical composition by means of diffuse reflectance mid-infrared Fourier transform (DRIFT-MIR) spectroscopy

Sitka spruce (Picea sitchensis) samples (491) from 50 different clones as well as 24 different tropical hardwoods and 20 Scots pine (Pinus sylvestris) samples were used to construct diffuse reflectance mid-infrared Fourier transform (DRIFT-MIR) based partial least squares (PLS) calibrations on lignin, cellulose, and wood resin contents and densities. Calibrations for density, lignin, and cellulose were established for all wood species combined into one data set as well as for the separate Sitka spruce data set. Relationships between wood resin and MIR data were constructed for the Sitka spruce data set as well as the combined Scots pine and Sitka spruce data sets. Calibrations containing only five wavenumbers instead of spectral ranges 4000-2800 and 1800-700 cm(-1) were also established. In addition, chemical factors contributing to wood density were studied. Chemical composition and density assessed from DRIFT-MIR calibrations had R2 and Q2 values in the ranges of 0.6-0.9 and 0.6-0.8, respectively. The PLS models gave residual mean squares error of prediction (RMSEP) values of 1.6-1.9, 2.8-3.7, and 0.4 for lignin, cellulose, and wood resin contents, respectively. Density test sets had RMSEP values ranging from 50 to 56. Reduced amount of wavenumbers can be utilized to predict the chemical composition and density of a wood, which should allow measurements of these properties using a hand-held device. MIR spectral data indicated that low-density samples had somewhat higher lignin contents than high-density samples. Correspondingly, high-density samples contained slightly more polysaccharides than low-density samples. This observation was consistent with the wet chemical data.     

Prediction of Cooked Rice Texture Using an Extrusion Test in Combination with Partial Least Squares Regression and Artificial Neural Networks

Spectral stress strain analysis was used in combination with partial least squares (PLS) regression and artificial neural networks (ANN) to predict nine sensory texture attributes of cooked rice. The models calculated with ANN were significantly more accurate in predicting most of the sensory texture characteristics evaluated than the PLS models. Furthermore, ANN models were more robust and discriminative than PLS models.     

Triticale Moisture and Protein Content Prediction by Near-Infrared Spectroscopy (NIRS)

The use of near-infrared spectroscopy (NIRS) for the prediction of whole-grain triticale moisture and protein content was evaluated. Because triticale is genetically close to wheat, commercially available wheat prediction models for Foss Infratec analyzers were applied in a year-by-year basis to triticale samples harvested in Iowa between 2002 and 2006. Wheat models were not applicable to moisture prediction (SEP_avg = 0.37% pt; expected SEP on wheat samples 0.15% pt), but usable for screening for protein (SEP_avg = 0.38% pt; expected SEP on wheat samples 0.25% pt). Dedicated triticale calibrations were developed from 2002 to 2005 data. Prediction results for 2006 samples only were compared. Triticale calibrations performed better than wheat calibrations for 2006 samples (moisture SEP_triticale = 0.29% pt, SEP_wheat = 0.50% pt; protein SEP_triticale = 0.30% pt, SEP_wheat = 0.68% pt).     

Major components of honey analysis by near-infrared transflectance spectroscopy

NIR transflectance spectroscopy was used to analyze fructose, glucose, and moisture in honey. A total of 161 honey samples were collected during 1992 (46), 1995 (58), and 1996 (57). Samples were analyzed by instrumental, enzymatic (fructose and glucose), and refractometric (moisture) methods. Initially, different calibrations were performed for each of the 3 years of sampling. Good predictions were obtained for all three components with equations of the particular year. But good predictions were not always obtained when the equations calculated one year were applied to samples from another year. To perform a lasting calibration, unique calibration (121 samples) and validation (40 samples) sets were built; honeys of the 3 years were included in both sets. Good statistics (bias, standard error of validation (SEV), and R(2)) were obtained for all three components of the validation set. No statistically significant differences (p = 0.05) were found between instrumental and reference methods.     

Estimating hydrogen cyanide in forage sorghum ( Sorghum bicolor ) by near-infrared spectroscopy

Hydrogen cyanide (HCN) is a toxic chemical that can potentially cause mild to severe reactions in animals when grazing forage sorghum. Developing technologies to monitor the level of HCN in the growing crop would benefit graziers, so that they can move cattle into paddocks with acceptable levels of HCN. In this study, we developed near-infrared spectroscopy (NIRS) calibrations to estimate HCN in forage sorghum and hay. The full spectral NIRS range (400-2498 nm) was used as well as specific spectral ranges within the full spectral range, i.e., visible (400-750 nm), shortwave (800-1100 nm) and near-infrared (NIR) (1100-2498 nm). Using the full spectrum approach and partial least-squares (PLS), the calibration produced a coefficient of determination (R(2)) = 0.838 and standard error of cross-validation (SECV) = 0.040%, while the validation set had a R(2) = 0.824 with a low standard error of prediction (SEP = 0.047%). When using a multiple linear regression (MLR) approach, the best model (NIR spectra) produced a R(2) = 0.847 and standard error of calibration (SEC) = 0.050% and a R(2) = 0.829 and SEP = 0.057% for the validation set. The MLR models built from these spectral regions all used nine wavelengths. Two specific wavelengths 2034 and 2458 nm were of interest, with the former associated with C═O carbonyl stretch and the latter associated with C-N-C stretching. The most accurate PLS and MLR models produced a ratio of standard error of prediction to standard deviation of 3.4 and 3.0, respectively, suggesting that the calibrations could be used for screening breeding material. The results indicated that it should be feasible to develop calibrations using PLS or MLR models for a number of users, including breeding programs to screen for genotypes with low HCN, as well as graziers to monitor crop status to help with grazing efficiency.     

Modeling of maximum dry density and optimum moisture content of stabilized soil using artificial neural networks

This study considers the use of artificial neural networks (ANNs) to predict the maximum dry density (MDD) and optimum moisture content (OMC) of soil‐stabilizer mix. Multilayer perceptron (MLP), one of the most widely used ANN architectures in the literature, is utilized to construct comprehensive and accurate models relating the MDD and OMC of stabilized soil to the properties of natural soil such as particle‐size distribution, plasticity, linear shrinkage, and the type and quantity of stabilizing additives. Five ANN models are constructed using different combinations of the input parameters. Two separate sets of ANN prediction models, one for MDD and the other for OMC, and also a combined ANN model for multiple outputs are developed using the potentially influential input parameters. Relative‐importance values of various inputs of the models are calculated to determine the significance of each of the predictor variables to MDD and OMC. Inferring the most relevant input parameters based on Garson's algorithm, modified ANN models are separately developed for MDD and OMC. The modified ANN models are utilized to introduce explicit formulations of MDD and OMC. A parametric study is also conducted to evaluate the sensitivity of MDD and OMC due to the variation of the most influencing input parameters. A comprehensive set of data including a wide range of soil types obtained from the previously published stabilization test results is used for training and testing the prediction models. The performance of ANN‐based models is subsequently analyzed and compared in detail. The results demonstrate that the accuracy of the proposed models is satisfactory as compared to the experimental results.     

Soil Particulate Organic Matter (POM) Prediction in a Mountainous Watershed using Artificial Neural Networks

Soil organic matter is a very important component of soil that supports the sustainability and quality in all ecosystems, especially in arid and semi-arid regions. A comparison study was carried out to verify when the artificial neural network (ANN) and multiple linear regression (MLR) models are appropriate for the prediction of soil organic matter (SOM) and particulate organic matter (POM). Discussions of advantages and disadvantages are given for both methods. Three different sets of easily available properties (soil properties alone, topographic and vegetation index, a combination of soil and topographic data) were used as inputs and the one affecting the model the most was determined. The smallest prediction errors were obtained by the ANN method; however, the prediction accuracies of the constructed MLR models using different data sets were closed to the ANN models in many cases.     

基于近红外光谱的灌浆期玉米籽粒水分小样本定量分析

玉米灌浆期含水率测定是考种育种的重要指标。为了节约样本且快速准确测定灌浆期玉米水分,该文应用近红外光谱技术,提出了基于小样本条件下的自举算法(Bootstrap)与基于x-y距离结合的样本划分方法(SPXY,sample set partitioning based on joint x-y distances)相结合的样本优化方法的偏最小二乘(PLS,partial least square)水分定量分析模型Bootstrap-SPXY-PLS模型。试验结果表明,当Bootstrap重抽样本次数等于500,样本数量大于等于10时,模型的性能稳定,并且随着样本数量增加,重抽样本次数相对减少;样本数量为10和50时,全谱Bootstrap-SPXY-PLS模型的预测均方根误差(RMSEP,root-mean-square error of prediction)均值分别为0.38%和0.40%,预测相关系数(correlation coefficients of prediction)分别为0.975 1和0.968 5,决定系数R~2分别为0.999 9和0.993 6;基于竞争性自适应重加权采样算法(CARS,competitive adaptive reweighed sampling)波长变量筛选后的CARS-Bootstrap-SPXY-PLS模型的预测均方根误差RMSEP均值分别为0.36%和0.35%,预测相关系数分别为0.973 6和0.975 0,模型决定系数R~2分别为0.924 5和0.918 0。因此,全谱Bootstrap-SPXY-PLS模型和CARS-Bootstrap-SPXY-PLS模型均具有稳定的预测能力,为玉米育种时灌浆期种子水分测定提供了一种稳定、高效的方法。     

Near-infrared analysis of fat, protein, and casein in cow's milk.

Fat, crude protein, true protein, and casein were determined in cow milks by near-infrared transmission spectroscopy (NIR). Partial and overall PLS calibrations were performed on two sets of samples: partial calibration included 76 unhomogenized samples, whereas overall calibration used 96 homogenized and unhomogenized samples. Standard errors of calibration were 0.12% for fat, 0.06% for crude protein, 0.04% for true protein, and 0.05% for casein in the overall calibration. Validation of the overall calibration with an independent set of samples gave standard errors of prediction of 0. 07% for fat, 0.06% for crude protein and casein, and 0.05% for true protein. Except for fat, all of the statistical parameters were better with overall than with partial calibrations, which indicates that homogenization has an effect on NIR fat determination. Despite the relatively small number of samples included in the calibration model, NIR transmission was found to be a reliable method for the determination of fat and nitrogenous constituents in milk.     

Performance comparison of UV and FT-Raman spectroscopy in the determination of conjugated linoleic acids in cow milk fat

The determination of conjugated linoleic acids (CLA) in cow milk fat was studied by using UV (210-250 nm) and Fourier transform (FT)-Raman (900-3400 cm (-1)) spectroscopy in order to determine the best spectrophotometric technique for routine analysis of milk fat. A collection of 57 milk fat samples was randomly divided into two sets, a calibration set and a validation set, representing two-thirds and one-third of the samples, respectively. All calculations were performed on the calibration set and then applied to the validation set. The CLA content ranged from 0.56 to 4.70%. A comparison of various spectral pretreatments and different multivariate calibration techniques, such as partial least-squares (PLS) and multiple linear regression (MLR), was done. This paper shows that UV spectroscopy is as reliable as FT-Raman spectroscopy to monitor CLA in cow milk fat. The best calibration for FT-Raman was given by a PLS model of seven factors with a standard error of prediction (SEP) of 0.246. For UV spectroscopy, PLS models were also better than MLR models. The most robust PLS model was constructed with only one factor and with SEP=0.288.     

Rapid Determination of Carbon,Nitrogen, Silicon,Phosphorus, and Potassium in Sugar Mill By-products,Mill Mud,and Ash using Near Infrared Spectroscopy

This article describes a proof-of-concept exercise to examine the ability of near infrared spectroscopy (NIRS)–based methods to predict the major nutrient properties of sugar mill by-products, particularly mill mud, ash, and mixtures of mud and ash. Sixty mill mud, mixed mud/ash, and ash samples were subsampled three times and analyzed using traditional analytical techniques for carbon (C), nitrogen (N), silicon (Si), phosphorus (P), and potassium (K), and the NIR spectra were recorded. Two different partial least squares (PLS) regression models were constructed, one using all samples and the other without the ash samples included in the model development. Three mud, one mixed mud/ash, and two ash samples were retained for predictive purposes and were not included in the model development process. R² values in the range of 0.77 to 0.98 were obtained for all constituents across both sets of PLS models. The standard errors of prediction (SEP) were similar for both models for N (0.10 and 0.08), P (0.17 and 0.16), and K (0.05 and 0.05). However, the SEP obtained for Si (3.53 and 1.04) and C (1.92 and 1.00) varied between the two models. These preliminary results are very encouraging. Future research will extend to robust NIRS calibrations for these nutrients and develop applications for their use within laboratory or field situations to permit nutrient monitoring in various sugar mill by-products.     

Initial study of honey adulteration by sugar solutions using midinfrared (MIR) spectroscopy and chemometrics

Fourier transform infrared (FTIR) spectroscopy and attenuated total reflection (ATR) sampling have been used to detect adulteration of honey samples. The sample set comprised 320 spectra of authentic (n = 99) and adulterated (n = 221) honeys. Adulterants used were solutions containing both d-fructose and d-glucose prepared in the following respective weight ratios: 0.7:1.0, 1.2:1.0 (typical of honey composition), and 2.3:1.0. Each adulterant solution was added to individual honeys at levels of 7, 14, and 21% w/w. Spectral data were compressed and analyzed using k-nearest neighbors (kNN) and partial least squares (PLS) regression techniques. A number of data pretreatments were explored. Best classification models were achieved with PLS regression on first derivative spectra giving an overall correct classification rate of 93%, with 99% of samples adulterated at levels of 14% w/w or greater correctly identified. This method shows promise as a rapid screening technique for detection of this type of honey adulteration.     

Use of visible and near infrared spectroscopy and least squares-support vector machine to determine soluble solids content and pH of cola beverage

Visible and near infrared (VIS/NIR) transmission spectroscopy and chemometric methods were utilized for the fast determination of soluble solids content (SSC) and pH of cola beverage. A total of 180 samples were used for the calibration set, whereas 60 samples were used for the validation set. Some preprocessing methods were applied before developing the calibration models. Several PLS factors, extracted by partial least squares (PLS) analysis, were used as the inputs of least squares-support vector machine (LS-SVM) model according to their accumulative reliabilities. The correlation coefficient (r), root mean square error of prediction (rmsEP), bias, and RPD were 0.959, 1.136, -0.185, and 3.5 for SSC, whereas 0.973, 0.053, 0.017, and 4.1 for pH, respectively. An excellent prediction precision was achieved by LS-SVM compared with PLS. The results indicated that VIS/NIR spectroscopy combined with LS-SVM could be applied as a rapid and alternative way for the fast determination of SSC and pH of cola beverage.     

Transferability of continuous‐ and class‐pedotransfer functions to predict water retention properties of semiarid Syrian soils

Hydraulic properties of soils, particularly water retention, are key for appropriate management of semiarid soils. Very few pedotransfer functions (PTF s) have been developed to predict these properties for soils of Mediterranean regions, where data are particularly scarce. We investigated the transferability of PTF s to semiarid soils. The quality of the prediction was compared to that for soils originating from temperate regions for which most PTF s were developed. We used two soil data sets: one from the Paris basin (French data set, n  = 30) and a Syrian data set (n  = 30). Soil samples were collected in winter when the water content was near field capacity. Composition and water content of the samples were determined at seven water potentials. Continuous‐ and class‐PTF s developed using different predictors were tested using the two data sets and their performance compared to those developed using artificial neural networks (ANN ). The best performance and transferability of the PTF s for both data sets used soil water content at field capacity as predictor after stratification by texture. The quality of prediction was similar to that for ANN ‐PTF s. Continuous‐ and class‐PTF s may be transferable to other countries with performances that vary according to their ability to account for variation in soil composition and structure. Taking into account predictors of composition (particle size distribution, texture, organic carbon content) and structure (bulk density, porosity, field capacity) did not lead to a better performance or the best transferability potential.     

Comparison of spectroscopic techniques for the determination of Kjeldahl and ammoniacal nitrogen content of farmyard manure

The feasibility of determining the nitrogen content of farmyard manure using infrared spectroscopy was investigated. Fifteen samples each of cattle, pig, and turkey manure were analyzed by three infrared techniques: Fourier transform mid-infrared (MIR), using attenuated total reflection (ATR); near-infrared reflectance (NIR-R); and near-infrared optothermal photoacoustic (NIR-OT). The near-infrared measurements were made at wavelengths determined respectively by four (NIR-OT) and five (NIR-R) band-pass filters. The total nitrogen (using the Kjeldahl method) and volatile (ammoniacal) nitrogen contents of all samples were measured by wet chemistry. Internally cross-validated (ICV) partial least-squares (PLS) regression was then used to obtain calibrations for the nitrogen content. The data sets obtained by each technique were treated separately. Within these sets, data from each manure type were treated both separately and combined: the best predictive ability was obtained by combining data from all three manure types. From the combined data set, the residual standard deviations and correlation coefficients for the ICV-predicted versus actual Kjeldahl nitrogen content were, respectively, 6772 mg/kg dry wt, 0.862 (MIR); 9434 mg/kg dry wt, 0.771 (NIR-OT); and 8943 mg/kg dry wt, 0.865 (NIR-R). For the ammoniacal nitrogen content, the residual standard deviations and correlation coefficients were 3869 mg/kg dry wt, 0.899 (MIR); 6079 mg/kg dry wt, 0.820 (NIR-OT); and 3498 mg/kg dry wt, 0.961 (NIR-R).     

Prediction of Triticale Grain Quality Properties,Based on Both Chemical and Indirectly Measured Reference Methods,Using Near‐Infrared Spectroscopy

The increasing demand for triticale as food, feed, and fuel has resulted in the availability of cultivars with different grain quality characteristics. Analyses of triticale composition can ensure that the most appropriate cultivars are obtained and used for the most suitable applications. Near‐infrared (NIR) spectroscopy is often used for rapid measurements during quality control and has consequently been investigated as a method for the measurement of protein, moisture, and ash contents, as well as kernel hardness (particle size index [PSI]) and sodium dodecyl sulfate (SDS) sedimentation from both whole grain and ground triticale samples. NIR spectroscopy prediction models calculated using ground samples were generally superior to whole grain models. Protein content was the most effectively modeled quality property; the best ground grain calibration had a ratio of the standard error of test set validation to the standard deviation of the reference data of the test set (RPD_test) of 4.81, standard error of prediction (SEP) of 0.52% (w/w), and r² of 0.95. Whole grain protein calibrations were less accurate, with optimum RPD_test of 3.54, SEP of 0.67% (w/w), and r² of 0.92. NIR spectroscopy calibrations based on direct chemical reference measurements (protein and moisture contents) were better than those based on indirect measurements (PSI, ash content, and SDS sedimentation). Calibrations based on indirect measurements would, however, still be useful to identify extreme samples.     

Predicting Cationic Exchange Capacity in Calcareous Soils of East-Azerbaijan Province,Northwest Iran

The aim of this research is to study the efficiency of pedotransfer functions (PTFs) and artificial neural networks (ANNs) for cationic exchange capacity (CEC) prediction using readily available soil properties. Here, 417 soil samples were collected from the calcareous soils located in East-Azerbaijan province, northwest Iran and readily available soil properties, such as particle size distribution (PSD), organic matter (OM) and calcium carbonate equivalent (CCE), were measured. The entire 417 soil samples were divided into two groups, a training data set (83 soil samples) and test data set (334 soil samples). The performances of several published and derived PTFs and developed neural network algorithms using multilayer perceptron were compared, using a test data set. Results showed that, based on statistics of RMSE and R², PTFs and ANNs had a similar performance, and there was no significant difference in the accuracy of the model results. The result of the sensitivity analysis showed that the ANN models were very sensitive to the clay variable (due to the high variability of the clay). Finally, the models tested in this study could account for 85% of the variations in cationic exchange capacity (CEC) of soils in the studied area.

Abbreviations: ANN: arti?cial neural networks; MLP: multilayer perceptron; MLR: multiple linear regression; PTFs: Pedotransfer Functions; RBF: Radial Basis Function; MAE: mean absolute error; MSE: mean square error; CEC: cationic exchange capacity     

Development of a Near‐Infrared Imaging System for Determination of Rice Moisture

The objective of this study was to develop a near‐infrared (NIR) imaging system to determine rice moisture content. The NIR imaging system fitted with 15 band‐pass filters (wavelengths of 870–1,014 nm) was used to capture the spectral image. In this work, calibration methods including multiple linear regression (MLR), partial least squares regression (PLSR), and artificial neural network (ANN) were used in both near‐infrared spectrometry (NIRS) and the NIR imaging system to determine the moisture content of rice. Comprehensive performance comparison among MLR, PLSR, and ANN approaches has been conducted. To reduce repetition and redundancy in the input data and obtain a more accurate network, six significant wavelengths selected by the MLR model, which had high correlation with the moisture content of rice, were used as the input data of the ANN. The performance of the developed system was evaluated through experimental tests for rice moisture content. This study adopted the coefficient of determination (r_val²), the standard error of prediction (SEP), and the relative performance determinant (RPD) as the performance indices of the NIR imaging system with respect to the tests of rice moisture content. Utilizing these three models, the analysis results of r_val², SEP, and RPD for the validation set were within 0.942–0.952, 0.435–0.479%, and 4.2–4.6, respectively. From experimental results, the performance of NIR imaging system was almost the same as that of NIRS. Using the developed NIR imaging system, all of the three different calibration methods (MLR, PLSR, and ANN) provided a high prediction capacity for the determination of moisture in rice samples. These results indicated that the NIR imaging system developed in this study can be used as a device for the measurement of rice moisture content.