Determination of Corn Protein Content Using Near-Infrared Spectroscopy Combined with A-CARS-PLS

Equivalent and Complementary Variables Screening for the Optimization of Wavelengths in Spectral Multivariate Calibration

Equivalent variables (EVs) were defined on the basis of a finding that replacing a selected variable with its neighbor variable provided a similar model performance. These are a group of variables having nearly equal modeling effects and can be efficient alternative to each other. Complementary variables (CVs) were defined as different variables screened from different variable selection algorithms that can further improve multivariate calibration by combining CVs with the original selected variables. Three variable selection algorithms, stability competitive adaptive reweighted sampling (SCARS), competitive adaptive reweighted sampling (CARS), and Monte Carlo and uninformative variable elimination (MC-UVE), were used for screening EVs and CVs and verifying the replaceability of EVs and model improvability with CVs. The developed strategy of variable selection based on EVs and CVs was investigated using NIR, MIR, and UV-vis spectra datasets. Seventeen basic variables (BVs) and 54 EVs were screened from the corn NIR spectra by SCARS. The selected EVs and BVs were comparable to one another in terms of modeling, and all models built with replaced variables showed close prediction errors with a RMSEP deviation <0.003. Furthermore, 15 CVs of SCARS were screened from EVs of CARS and MC-UVE. The combination of CVs and BVs of SCARS can significantly improve model performance; RMSEC and RMSEP decreased from 0.0207 and 0.0290 to 0.0109 and 0.0136, respectively. Similar results were obtained for other datasets. Results revealed that screening CVs from EVs of other algorithms and combining BVs could effectively optimize variable selection and improve model performance.

A band selection method combining spectral color characteristics for estimating chlorophyll content of rice in different backgrounds

Spectroscopic technology is an effective method for estimating rice chlorophyll content. However, redundant spectral information and the complex background of rice in situ challenge the accuracy and robustness of the estimation. To address this problem, this study proposed a band selection method combining spectral color characteristics and established a convolutional neural network (CNN) model based on this method to estimate chlorophyll content of rice for black (background-free), clear, muddy, and green algae-covered backgrounds. We determined the optimal color characteristic bands for each background: blue, green, orange, red, and near-infrared for the black background; orange and near-infrared for the clear background; violet, cyan, yellow, red, and near-infrared for the muddy background; and blue, cyan, green and near-infrared for the green algae-covered background. Furthermore, the accuracy and robustness advantages of our proposed method were evaluated by comparing them with ten conventional wavelength or band selection techniques. The evaluation results using optimal color characteristic bands outperformed those results based on conventional methods for four backgrounds. The further validation results indicated that the conventional methods exhibited significant instability for four backgrounds, and the optimal conventional method in evaluation often lost its advantage in validation. Conversely, our proposed method demonstrated some accuracy and robustness advantages in validation. It still was the best for the black and clear backgrounds, with RMSE, R2, and RPD values of 13.565 and 17.259, 0.806 and 0.479, 2.273 and 1.386, respectively. It was superior to the UVE, MWPLS, and CARS methods for the muddy background, with RMSE, R2, and RPD values of 23.546, 0.426, and 1.320, respectively. It was slightly worse than that of the UVE method for the green algae-covered background, with RMSE, R2, and RPD values of 15.698, 0.584, and 1.551, respectively.

Quantitative Prediction of Protein Content in Corn Kernel Based on Near-Infrared Spectroscopy

Rapid and accurate detection of protein content is essential for ensuring the quality of maize. Near-infrared spectroscopy (NIR) technology faces limitations due to surface effects and sample homogeneity issues when measuring the protein content of whole maize grains. Focusing on maize grain powder can significantly improve the quality of data and the accuracy of model predictions. This study aims to explore a rapid detection method for protein content in maize grain powder based on near-infrared spectroscopy. A method for determining protein content in maize grain powder was established using near-infrared (NIR) reflectance spectra in the 940-1660 nm range. Various preprocessing techniques, including Savitzky-Golay (S-G), multiplicative scatter correction (MSC), standard normal variate (SNV), and the first derivative (1D), were employed to preprocess the raw spectral data. Near-infrared spectral data from different varieties of maize grain powder were collected, and quantitative analysis of protein content was conducted using Partial Least Squares Regression (PLSR), Support Vector Machine (SVM), and Extreme Learning Machine (ELM) models. Feature wavelengths were selected to enhance model accuracy further using the Successive Projections Algorithm (SPA) and Uninformative Variable Elimination (UVE). Experimental results indicated that the PLSR model, preprocessed with 1D + MSC, yielded the best performance, achieving a root mean square error of prediction (RMSEP) of 0.3 g/kg, a correlation coefficient (Rp) of 0.93, and a residual predictive deviation (RPD) of 3. The associated methods and theoretical foundation provide a scientific basis for the quality control and processing of maize.

Enhanced data point importance: Layered significance of variables in multivariate calibration

BACKGROUND

The Enhanced Data Point Importance (EDPI) method, a systematic approach for evaluating the importance of data points in multivariate calibration, is introduced. Factor decomposition methods allow for the evaluation of the impact of variables on maintaining the structural pattern of data in the abstract space. Essential data points play a key role in these patterns and the method of Data Point Importance (DPI) aims to evaluate the essential data points in terms of their importance. All other points are rated by zero. In this contribution, DPI is extended to include inner points to evaluate the importance of these points in the absence of the essential points. The EDPI method employs convex peeling to sort data points systematically.

RESULTS

EDPI method was applied to near-infrared and Raman spectroscopy data sets, including corn and alcohol mixtures and simulated data, to rank and select important variables. EDPI effectively identified variables that contributed to the preservation of the data structure and highlighted key spectral regions with different degrees of selectivity. In the alcohol dataset, EDPI revealed important physicochemical insights by focusing on specific regions where non-analytes spectra overlapped. It performed in a similar way to the Variable Importance in Projection (VIP) method, but with fewer variables selected.

SIGNIFICANCE

The experimental results obtained from calibrating near-infrared and Raman spectroscopic datasets using partial least squares highlight the effectiveness of the proposed EDPI strategy when contrasted with the conventional variable importance in projection (VIP) method for variable selection.

A Nondestructive Detection Method for the Muti-Quality Attributes of Oats Using Near-Infrared Spectroscopy

This study aimed to achieve a precise and non-destructive quantification of the amounts of total starch, protein, β-glucan, and fat in oats using near-infrared technology in conjunction with chemometrics methods. Eight preprocessing methods (SNV, MSC, Nor, DE, FD, SD, BC, SS) were employed to process the original spectra. Subsequently, the optimal PLS model was obtained by integrating feature wavelength selection algorithms (CARS, SPA, UVE, LAR). After SD-SPA, total starch reached its optimal state (Rp2 = 0.768, RMSEP = 2.057). Protein achieved the best result after MSC-CARS (Rp2 = 0.853, RMSEP = 1.142). β-glucan reached the optimal value after BC-SPA (Rp2 = 0.759, RMSEP = 0.315). Fat achieved the optimal state after SS-SPA (Rp2 = 0.903, RMSEP = 0.692). The research has shown the performance of the portable FT-NIR for a rapid and non-destructive quantification of nutritional components in oats, holding significant importance for quality control and quality assessment within the oat industry.

Rapid Determination of Crude Protein Content in Alfalfa Based on Fourier Transform Infrared Spectroscopy

The crude protein (CP) content is an important determining factor for the quality of alfalfa, and its accurate and rapid evaluation is a challenge for the industry. A model was developed by combining Fourier transform infrared spectroscopy (FTIS) and chemometric analysis. Fourier spectra were collected in the range of 4000~400 cm-1. Adaptive iteratively reweighted penalized least squares (airPLS) and Savitzky-Golay (SG) were used for preprocessing the spectral data; competitive adaptive reweighted sampling (CARS) and the characteristic peaks of CP functional groups and moieties were used for feature selection; partial least squares regression (PLSR) and random forest regression (RFR) were used for quantitative prediction modelling. By comparing the combined prediction results of CP content, the predictive performance of airPLST-cars-PLSR-CV was the best, with an RP2 of 0.99 and an RMSEP of 0.053, which is suitable for establishing a small-sample prediction model. The research results show that the combination of the PLSR model can achieve an accurate prediction of the crude protein content of alfalfa forage, which can provide a reliable and effective new detection method for the crude protein content of alfalfa forage.

Detection of wheat saccharification power and protein content using stacked models integrated with hyperspectral imaging

BACKGROUND

Wheat is one of the key ingredients used to make Chinese liquor, and its saccharification power and protein content directly affect the quality of the liquor. In pursuit of a non-destructive assessment of wheat components and the optimization of raw material proportions in liquor, this study introduces a precise predictive model that integrates hyperspectral imaging (HSI) with stacked ensemble learning (SEL).

RESULTS

This study extracted hyperspectral information from 14 different varieties of wheat and employed various algorithms for preprocessing. It was observed that multiplicative scatter correction (MSC) emerged as the most effective spectral preprocessing method. The feature wavelengths were extracted from the preprocessed spectral data using three different feature extraction methods. Then, single models (support vector machine (SVM), backpropagation neural network (BPNN), random forest (RF), and gradient boosting tree (XGBoost)) and a SEL model were developed to compare the prediction accuracies of the SEL model and the single models based on the full-band spectral data and the characteristic wavelengths. The findings indicate that the MSC-competitive adaptive reweighted sampling-SEL model demonstrated the highest prediction accuracy, with Rp 2 (test set-determined coefficient) values of 0.9308 and 0.9939 for predicting the saccharification power and protein content and root mean square error of the test set values of 0.0081 U and 0.0116 g kg-1, respectively.

CONCLUSION

The predictive model established in this study, integrating HSI and SEL models, accurately detected wheat saccharification power and protein content. This validation underscores the practical potential of the SEL model and holds significant importance for non-destructive component analysis of raw materials used in liquor. © 2024 Society of Chemical Industry.

Establishment and comparison of in situ detection models for foodborne pathogen contamination on mutton based on SWIR-HSI

Introduction

Rapid and accurate detection of food-borne pathogens on mutton is of great significance to ensure the safety of mutton and its products and the health of consumers.

Objectives

The feasibility of short-wave infrared hyperspectral imaging (SWIR-HSI) in detecting the contamination status and species of Escherichia coli (EC), Staphylococcus aureus (SA) and Salmonella typhimurium (ST) contaminated on mutton was explored.

Materials and methods

The hyperspectral images of uncontaminated and contaminated mutton samples with different concentrations (108, 107, 106, 105, 104, 103 and 102 CFU/mL) of EC, SA and ST were acquired. The one dimensional convolutional neural network (1D-CNN) model was constructed and the influence of structure hyperparameters on the model was explored. The effects of different spectral preprocessing methods on partial least squares-discriminant analysis (PLS-DA), support vector machine (SVM) and 1D-CNN models were discussed. In addition, the feasibility of using the characteristic wavelength to establish simplified models was explored.

Results and discussion

The best full band model was the 1D-CNN model with the convolution kernels number of (64, 16) and the activation function of tanh established by the original spectra, and its accuracy of training set, test set and external validation set were 100.00, 92.86 and 97.62%, respectively. The optimal simplified model was genetic algorithm optimization support vector machine (GA-SVM). For discriminating the pathogen species, the accuracies of SVM models established by full band spectra preprocessed by 2D and all 1D-CNN models with the convolution kernel number of (32, 16) and the activation function of tanh were 100.00%. In addition, the accuracies of all simplified models were 100.00% except for the 1D-CNN models. Considering the complexity of features and model calculation, the 1D-CNN models established by original spectra were the optimal models for pathogenic bacteria contamination status and species. The simplified models provide basis for developing multispectral detection instruments.

Conclusion

The results proved that SWIR-HSI combined with machine learning and deep learning could accurately detect the foodborne pathogen contamination on mutton, and the performance of deep learning models were better than that of machine learning. This study can promote the application of HSI technology in the detection of foodborne pathogens on meat.