Search

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 R p 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., (© 2024 Society of Chemical Industry.)

Total acid content (TAC) and reducing sugar content (RSC) are important evaluation indicators for the quality of fermented grains. In this study, the TAC and RSC of fermented grains were quantified using hyperspectral imaging (HSI). Two combined algorithms were used to extract the characteristic wavelengths of TAC and RSC. Nine color features of fermented grains were extracted based on H, S and V color channels. Multivariate analytical models were developed to predict TAC and RSC using full wavelengths, characteristic wavelengths, color features and fused data, respectively. The CF model established based on characteristic wavelengths extracted by CARS-SPA showed the best results in predicting TAC. Meanwhile, the PSO-SVR model built using fused data was the best model for predicting RSC. The visualization of the TAC and RSC was achieved using the optimal models. These results show that HSI can achieve non-destructive detection and visualization of TAC and RSC in fermented grains., (Copyright © 2022 Elsevier Ltd. All rights reserved.)

The contents of amylose and amylopectin in sorghum directly affects the quality and yield of liquor. Hyperspectral imaging (HSI) is an emerging technology widely applied in the content analysis of food ingredients. In this study, the effects of different preprocessing methods on visible-light and near-infrared spectral data were analyzed, and the prediction accuracies of these spectral data were compared. Principal components analysis (PCA) and successive projections algorithm (SPA) were combined to extract the characteristic wavelengths. Using both the full and characteristic wavelengths, partial least square regression (PLSR) and cascade forest (CF) models were developed to predict the contents of amylose and amylopectin in different varieties of sorghum. The average RPD values of the CF models established by the characteristic wavelengths were 4.7622 and 5.5889, respectively. These results corroborated the utility of HSI in achieving the rapid and nondestructive prediction of amylose and amylopectin contents in different varieties of sorghum., (Copyright © 2021 Elsevier Ltd. All rights reserved.)

Starch and alcohol serve as pivotal indicators in assessing the quality of lees fermentation. In this paper, two hyperspectral imaging (HSI) techniques (visible–near‐infrared (Vis–NIR) and NIR) were utilized to acquire separate HSI data, which were then fused and analyzed toforecast the starch and alcohol contents during the fermentation of lees. Five preprocessing methods were first used to preprocess the Vis–NIR, NIR, and the fused Vis–NIR and NIR data, after which partial least squares regression models were established to determine the best preprocessing method. Following, competitive adaptive reweighted sampling, successive projection algorithm, and principal component analysis algorithms were used to extract the characteristic wavelengths to accurately predict the starch and alcohol levels. Finally, support vector machine (SVM)‐AdaBoost and XGBoost models were built based on the low‐level fusion (LLF) and intermediate‐level fusion (ILF) of single Vis–NIR and NIR as well as the fused data. The results showed that the SVM‐AdaBoost model built using the LLF data afterpreprocessing by standard normalized variable was most accurate for predicting the starch content, with an RP2$\ R_P^2$ of 0.9976 and a root mean square error of prediction (RMSEP) of 0.0992. The XGBoost model built using ILF data was most accurate for predicting the alcohol content, with an RP2$R_P^2$ of 0.9969 and an RMSEP of 0.0605. In conclusion, the analysis of fused data from distinct HSI technologies facilitates rapid and precise determination of the starch and alcohol contents in fermented grains. [ABSTRACT FROM AUTHOR]

BACKGROUND: The purity of sorghum varieties is an important indicator of the quality of raw materials used in the distillation of liquors. Different varieties of sorghum may be mixed during the acquisition process, which will affect the flavor and quality of liquor. To facilitate the rapid identification of sorghum varieties, this study proposes a sorghum variety identification model using hyperspectral imaging (HSI) technology combined with convolutional neural network (AlexNet). RESULTS: First, the watershed algorithm, which was modified with the extended‐maxim transform, was used to segment the hyperspectral images of a single sorghum grain. The isolated forest algorithm was used to eliminate abnormal spectral data from the complete spectral data. Secondly, the AlexNet model of sorghum variety identification was established based on the two‐dimensional gray image data of sorghum grain in group 1. The effects of different preprocessing methods and different convolution kernel sizes on the performance of the AlexNet model were discussed. The eigenvalues of the last layer of the AlexNet model were visualized using the t‐distributed random neighborhood embedding method, which is used to evaluate the separability of features extracted by the AlexNet model. The performance differences between the optimal AlexNet model and traditional machine learning models for sorghum variety identification were compared. Finally, the varieties of sorghum grains in groups 2 and 3 were identified based on the optimal AlexNet model, and the average accuracy values of the test set reached 95.62% and 95.91% respectively. CONCLUSION: The results in this study demonstrated that HSI combined with the AlexNet model could provide a feasible technical approach for the detection of sorghum varieties. © 2022 Society of Chemical Industry. [ABSTRACT FROM AUTHOR]

The moisture content and distribution of Daqu significantly influences the quality of Daqu products. This work presents the visualization of the moisture content in Daqu using a combination of spectral and spatial information from hyperspectral imaging. The least squares support vector machine (LS-SVM) and partial least squares regression (PLSR) methods were adopted to establish the predictive models based on the full wavelengths and the 29 feature wavelengths combined with color features, respectively. The best prediction model was PLSR ( R p 2 = 0.9823 , RMSEP = 0.0109) based on feature wavelengths. The results showed that the combination of spectral and spatial information of hyperspectral imaging can accurately predict the moisture content in Daqu during different fermentation processes, and the visualization of the distribution map of moisture content in Daqu provided a more convenient and understandable assessment of moisture content. This work presents a novel, rapid, and nondestructive approach for moisture content detection in Daqu, and provides theoretical support and basis for intelligent adjustment of temperature, humidity and other environmental parameters of Daqu fermentation. [ABSTRACT FROM AUTHOR]

Sorghum is a type of brewing material. The starch content of different kinds of mixed sorghum affect the quality and yield of liquor. Therefore, an accurate and efficient detection of its starch content is of great significance to obtain high‐quality and high‐yield of liquor. Based on the data of single visible light (Vis), near‐infrared (NIR), and Vis and NIR fusion, this study develops a genetic algorithm optimization BP neural network (GA‐BPNN) model and a particle swarm optimization support vector machine model. It is deduced that the model based on the data from the Vis and NIR fusion has the highest performance in predicting the starch content of mixed sorghum. For the prediction of amylose, the GA‐BPNN model developed after using the Pearson correlation coefficient to select the characteristic wavelength for fusion, has the highest performance (RMSEP =.0298 and Rp2=.9948). For the prediction of amylopectin, the GA‐BPNN model developed after fusion of spectral features extracted by principal component analysis, has the highest performance (RMSEP =.0213 and Rp2=.9985). In conclusion, the hyperspectral imaging combined with data fusion can rapidly and accurately detect the starch content of mixed sorghum. Practical Applications: As the single raw material of Maotai‐flavor liquor and the main raw material of Luzhou‐flavor liquor, the amylopectin content of sorghum directly affects the quality of liquor. Its amylose content also affects the yield of liquor. Because the different varieties of sorghum have different amylose and amylopectin content, liquor manufacturers often use several mixed varieties of sorghum as a brewing material. In order to ensure the quality and yield of liquor, it is particularly crucial to detect the amylose and amylopectin content variables of blended sorghum. The traditional sorghum starch content determination methods, such as the chemical detection methods and near infrared spectroscopy, have the disadvantages of destructiveness, low efficiency, and low detection accuracy. In the process of liquor brewing, the traditional detection methods cannot guide the timely adjustment of brewing process parameters. The hyperspectral imaging technology is widely used in food material detection, due to its fast and nondestructive advantages. The data fusion technology can fuse data from different sources of the same object to be detected, in order to obtain more comprehensive data for the development of accurate prediction models. This study uses the hyperspectral imaging combined with data fusion in order to quickly and accurately predicts the starch content (amylose, amylopectin) of mixed sorghum, which has a guiding significance for the timely adjustment of process parameters in the brewing process of liquor. In addition, it provides an accurate method for the component detection of other grains. [ABSTRACT FROM AUTHOR]

Daqu, a Chinese liquor fermentation starter, contains all kinds of microorganisms and enzymes for Chinese liquor fermentation. The moisture content of Daqu significantly influence on the reproduction of microorganisms in Daqu. This work presents for the first time that determination of moisture content of Daqu with hyperspectral imaging. The characteristic spectrum of water is extracted based on comparative experiments with varying moisture content. The molds based on the full bands and feature bands were established by the support vector regression (SVR) method, which is used to predict moisture content of Daqu during fermentation process. The performance of the model based on the feature bands (R2 = 0.9870, root mean square error (RMSE) = 0.0091) is comparable to the full bands and the dimensions of the spectral information were significantly reduced. This work presents a novel, rapid and nondestructive approach for detecting the moisture content in Daqu and lays a foundation for the application of hyperspectral imaging. [ABSTRACT FROM AUTHOR]

• A robust model was developed and validated for evaluation of sorghum quality. • Isolated forest and CARS-SPA were conducive to the optimization of the model. • The average CRR of the model in identifying sorghum varieties was greater than 91%. • The deviation of the predicted mixing ratio of adulterated samples was less than 4%. This study combined hyperspectral imaging (HSI) and deep forest (DF) to develop a reliable model for conducting a rapid and nondestructive determination of sorghum purity. Isolated forest (IF) algorithm and principal component analysis (PCA) were used to remove the abnormal data of sorghum grains. Competitive adaptive reweighted sampling (CARS) algorithm and successive projections algorithm (SPA) were combined and used to extract the characteristic wavelengths. Gray-level co-occurrence matrix (GLCM) was used to extract the textural features. DF models were established based on the different types of data. Specifically, the DF models established using the characteristic spectra produced the best recognition results: the average correct recognition rate (CRR) of the models was greater than 91%. In addition, the average CRR of validation set Ⅰ was 88.89%. These results show that a combination of HSI and DF could be used for the rapid and nondestructive determination of sorghum purity. [ABSTRACT FROM AUTHOR]

• The R P 2 values of the CF models were greater than 98.00 %. • PCA-SPA was used to extract characteristic wavelengths. • The distribution map of the substance content was obtained via visualization. • This study provides a new method for obtaining real-time index data on Daqu. In this research, the hyperspectral imaging technique was employed to realize the rapid and accurate detection of the reducing sugar and amino acid nitrogen contents of Daqu during fermentation. Different preprocessed data were employed to establish cascade forest (CF) models to determine the best preprocessing method. Principal component analysis (PCA) and the successive projection algorithm (SPA) were then combined to extract the characteristic wavelengths. Four types of models (CF, BPNN, SVR, and PLSR) were established based on the full and characteristic wavelengths, respectively. Among all the models, the CF model established by the characteristic wavelengths was determined to be superior for the detection of the reducing sugar and amino acid nitrogen contents: for reducing sugar, R P 2 = 0.9862, RMESP = 0.0812 g/100 g, and RPD = 6.0402; for amino acid nitrogen, R P 2 = 0.9876, RMSEP = 0.0500 g/100 g, and RPD = 6.3698. The best model achieved the visualization of the reducing sugar and amino acid nitrogen contents in the region of interest. The satisfactory detection results demonstrate that the hyperspectral imaging technique can be used to realize the rapid and accurate detection of the reducing sugar and amino acid nitrogen contents of Daqu during fermentation. [ABSTRACT FROM AUTHOR]

• First time HSI was used to detect adulterated sorghum. • Watershed algorithm could effectively segment sorghum grains. • PCA and CA could effectively find abnormal samples in a single sorghum variety. • PLS-DA model could rapidly and nondestructively detect sorghum adulteration. • The distribution map of the sorghum was obtained through visualization. This paper proposes a sorghum adulteration detection model using hyperspectral imaging technology (HSI), image processing technology, and multivariate analysis technology. The model used a watershed algorithm to extract hyperspectral data from sorghum grains. Principal component analysis (PCA) and clustering analysis (CA) were used to remove abnormal samples of sorghum. Partial least squares discriminant analysis (PLS-DA) was used to identify the variety of sample, and a sorghum distribution map and adulteration ratios were obtained by marking varieties with different colors. This paper presents, for the first time, HSI use for identification of adulteration in sorghum using PCA and CA. Accuracy of the model identification for the validation set reached 96%, and for the adulterated samples reached 91%, and comprehensive accuracy of the model could reach more than 90%. These results show that the model can rapidly and nondestructively detect sorghum adulteration. [ABSTRACT FROM AUTHOR]

The contents of amylopectin and amylose are important indicators to evaluate the quality of sorghum. Hyperspectral imaging (HSI) is a technology based on machine vision and spectroscopy that has been widely used in the quality evaluation of various foods. Three combined algorithms were used to extract the characteristic wavelengths. The gray-level co-occurrence matrix (GLCM) was used to extract the textural features. Based on the spectra, textures, and fusion data, genetic algorithm-optimized back propagation neural network (BPNN-GA), cascade forest (CF), and partial least square regression (PLSR) models were established to predict the amylopectin and amylose contents. The BPNN-GA and CF models established using the characteristic wavelengths of visible-light were determined to be the best model, with RPD values of 8.2352 and 26.7308, respectively. These results demonstrated that HSI combined with machine learning algorithms could be used to enable the rapid and nondestructive prediction of amylopectin and amylose contents in sorghum. • The RPD values of the best models were both greater than 8. • The fusion data of the characteristic spectra and texture features was employed. • Three different combined algorithms were used to extract characteristic wavelengths. • This study provides a new method for obtaining the content of starch in sorghum. [ABSTRACT FROM AUTHOR]

This study sought to develop a hyperspectral imaging (HSI)- and machine learning (mL)-based method to quantitatively analyze the composition of alcohols and esters of Soy Sauce-Aroma Type Baijiu (SSAB). First, preprocessed the spectral data in the 900–1700 nm NIR range using various algorithms. Then, particle swarm optimization-support vector regression (PSO-SVR) and random forest (RF) models were established based on the full wavelength and the feature wavelength spectral data. In the preprocessing method, the external parameter orthogonalization (EPO) method demonstrated superior modeling performance in most cases. Spearman correlation analysis revealed a significant positive correlation between the concentrations of ethanol and alcohols in the SSAB samples, with an r-value of 0.93. Ethyl acetate and ethyl lactate also showed a significant positive correlation with esters, with r-values of 0.87 and 0.88, respectively. Combining the relevant compounds with feature wavelengths as input yields a model with high accuracy, with an R p 2 of 0.997 and RMSEP of 0.118 mg/L for alcohols and an R p 2 of 0.996 and RMSEP of 0.017 mg/L for esters. The results indicate that HSI can achieve non-destructive and accurate detection of alcohols and esters in the aroma of SSAB, providing a new method for aroma analysis in Baijiu. [Display omitted] • Quantitative analysis of the aroma of Soy Sauce-Aroma Type Baijiu. • Comparison of various preprocessing methods and feature extraction methods. • Fusion modeling of Spearman correlation and feature extraction methods. • Achieving non-destructive and accurate detection of aroma components. [ABSTRACT FROM AUTHOR]

The rapid and precise detection of pesticide residues remains a pressing safety issue in the food industry. In this study, a rapid method for analyzing pesticide residues in sorghum was developed, combining hyperspectral imaging (HSI) technology with stacking ensemble learning (SEL) models. The HSI spectral data were preprocessed using the multivariate scatter correction (MSC) algorithm. The gradient boosting decision tree (GBDT), extreme gradient boosting (XGBoost), light gradient boosting machine (LGBM), and categorical boosting (CatBoost) algorithms were employed to identify the feature wavelengths with high contributions to the predictive model, and the performances of SEL, GBDT, XGBoost, LGBM, and CatBoost to accurately predict the pesticide residues in sorghum samples were compared. The SEL model constructed using the characteristic wavelength selected by CatBoost has the best predictive performance, with RMSEP, R P 2, and RPD values of 0.6940 mg/kg, 0.9798, and 7.029, respectively. The study demonstrated that the combination of HSI and SEL enabled the accurate analysis of pesticide residues in sorghum, providing a reference for the utilization of HSI methods to accurately measure the concentrations of pesticide residues in sorghum and other food products. • Utilization of HSI for measuring malathion residue levels in sorghum. • Stacking ensemble learning (SEL) models for predicting malathion content in sorghum. • CatBoost-SEL models showed the best prediction results in modeling. [ABSTRACT FROM AUTHOR]

Rice is one of the main raw materials used in the brewing of Chinese liquor. The fatty acid content of rice is one of the most important indicators of the degree of aging of rice, which greatly influences the flavor of the liquor. In this study, hyperspectral imaging (HSI) was used in combination with an integrated learning model to predict the fatty acid content in rice. Spectral, textural, and color information were extracted from the hyperspectral images of the rice grains derived from at different levels of aging. After analyzing, the best preprocessing method was determined to be SG-SNV. Principal component analysis with different kernel functions (KPCA) was used to extract the characteristic wavelengths, and PSO-SVR, SSA-KELM, and SVM-AdaBoost models were developed to predict the fatty acid content of rice based on full-wavelength spectral data, feature wavelengths, feature wavelengths combined with texture information, and feature wavelengths combined with color information. Comparison of model performance showed that the SVM-AdaBoost model, which was built by combining the texture information of the rice grains with the feature wavelengths, had the highest performance of all the models, with a RPD value of 22.3663. These results showed that combining HSI with an integrated learning model can be effective for the rapid and accurate prediction of fatty acid content in rice. [Display omitted] [ABSTRACT FROM AUTHOR]

Tannins are one of the key components that constitute the nutritional structure of grains, and have a significant impact on the quality of grain products. The detection of tannins by chemical methods is both time- and manpower-consuming. In this study, hyperspectral imaging (HSI) technology was combined with an optimized algorithm, iteratively variable subset optimization (IVSO), in conjunction with the variable importance in projection (VIP) method to rapidly detect the tannin content of grains (sorghum, rice, glutinous rice, wheat, and corn). The IVSO algorithm and VIP method were employed to extract characteristic wavelengths. Subsequently, three tannin content prediction models based on full and characteristic wavelengths (BPNN, PSO-LSSVM, and DF) were respectively established. A comparative analysis demonstrated that the DF model based on the characteristic wavelengths had the best effect (R p 2 = 0.9922 g/100 g, RPD = 11.3), and the tannin content of grain particles was visually analyzed by using the best prediction model. The results show that HSI can realize the rapid non-destructive detection of the tannin content of grain particles, which provides a new technical reference for the food industry to improve product quality. [Display omitted] • Detection and Visualization of the tannin content in five grains: sorghum, rice, glutinous rice, wheat, and corn. • The optimized algorithm (IVSO-VIP) was employed to select feature wavelengths that are more representative. • The coefficient of determination for deep forest on the prediction of tannin content in grain reached 0.9922. [ABSTRACT FROM AUTHOR]

Wheat is the main raw material for brewing Chinese liquor, and differences in the wheat varieties and mixing ratio will affect its quality and flavor. In this study, hyperspectral imaging (HSI) was combined with ensemble learning models for the classification and determination of the mixing ratio of wheat. The spectral information and textural and shape features of each wheat grain were respectively extracted. The density-based spatial clustering of applications with noise (DBSCAN) algorithm was used to remove abnormal data, and Savitzky-Golay combined multiplicative scatter correction (SG-MSC) was used to pre-process the spectra of the wheat samples. The characteristic wavelengths were then extracted using the competitive adaptive reweighted sampling (CARS) algorithm, and the classification effects of BP-Adaboost models were compared when using feature spectral data, image features, and fusion data as the input. The recognition effects and visualization of the validation set proved the optimal classification of feature spectral data fused with shape features; the average accuracy was 92.29% and the maximum deviation range of mixing ratio prediction was 5%. With the addition of wheat classification categories, this method still achieved excellent results. The results prove the feasibility of using fusion data with HSI combined with ensemble learning models for the classification and mixing ratio detection of wheat. • Classification and determination of the adulteration ratio of wheat by fusing HSI spectral and image features. • An ensemble learning model was developed and validated for identification of wheat varieties. • The average ACC of the model in identifying 3 varieties of wheat grains was greater than 92%. • The deviation of the predicted mixing ratio of adulterated samples was less than 5%. [ABSTRACT FROM AUTHOR]