Effect of variable selection algorithms on model performance for predicting moisture content in biological materials using spectral data

Advancements in Hyperspectral Imaging for Assessing Nutritional Parameters in Muscle Food: Current Research and Future Trends

Assessing the nutritional value of muscle food (MF) necessitates comprehensive component analysis. Traditional chemical analytical methods are often time-intensive, destructive, and environmentally detrimental, requiring specialized laboratory expertise. Hyperspectral imaging (HSI) emerges as an innovative technique that effectively integrates spectral and spatial information to enable rapid, nondestructive, and multidimensional predictions of nutritional parameters in MF. This Review examines the cutting-edge advancements in HSI technology, elucidating its novel technical and methodological dimensions. It systematically explores the principles and methodologies of HSI, presenting recent research and diverse applications in predicting MF nutritional parameters, and evaluates HSI's significant advantages and current limitations while addressing field-specific challenges and prospective research trends, ultimately positioning HSI as a potentially transformative tool in ensuring meat industry quality and safety.

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.

Detection of Pear Quality Using Hyperspectral Imaging Technology and Machine Learning Analysis

The non-destructive detection of fruit quality is indispensable in the agricultural and food industries. This study aimed to explore the application of hyperspectral imaging (HSI) technology, combined with machine learning, for a quality assessment of pears, so as to provide an efficient technical method. Six varieties of pears were used for inspection, including 'Sucui No.1', 'Zaojinxiang', 'Huangguan', 'Akizuki', 'Yali', and 'Hongli No.1'. Spectral data within the 398~1004 nm wavelength range were analyzed to compare the predictive performance of the Least Squares Support Vector Machine (LS-SVM) models on various quality parameters, using different preprocessing methods and the selected feature wavelengths. The results indicated that the combination of Fast Detrend-Standard Normal Variate (FD-SNV) preprocessing and Competitive Adaptive Reweighted Sampling (CARS)-selected feature wavelengths yielded the best improvement in model predictive ability for forecasting key quality parameters such as firmness, soluble solids content (SSC), pH, color, and maturity degree. They could enhance the predictive capability and reduce computational complexity. Furthermore, in order to construct a quality prediction model, integrating hyperspectral data from six pear varieties resulted in an RPD (Ratio of Performance to Deviation) exceeding 2.0 for all the quality parameters, indicating that increasing the fruit sample size and variety number further strengthened the robustness of the model. The Backpropagation Neural Network (BPNN) model could accurately distinguish six distinct pear varieties, achieving prediction accuracies of above 99% for both the calibration and test sets. In summary, the combination of HSI and machine learning models enabled an efficient, rapid, and non-destructive detection of pear quality and provided a practical value for quality control and the commercial processing of pears.

Optimizing feature selection with gradient boosting machines in PLS regression for predicting moisture and protein in multi-country corn kernels via NIR spectroscopy

Differences in moisture and protein content impact both nutritional value and processing efficiency of corn kernels. Near-infrared (NIR) spectroscopy can be used to estimate kernel composition, but models trained on a few environments may underestimate error rates and bias. We assembled corn samples from diverse international environments and used NIR with chemometrics and partial least squares regression (PLSR) to determine moisture and protein. The potential of five feature selection methods to improve prediction accuracy was assessed by extracting sensitive wavelengths. Gradient boosting machines (GBMs), particularly CatBoost and LightGBM, were found to effectively select crucial wavelengths for moisture (1409, 1900, 1908, 1932, 1953, 2174 nm) and protein (887, 1212, 1705, 1891, 2097, 2456 nm). SHAP plots highlighted significant wavelength contributions to model prediction. These results illustrate GBMs' effectiveness in feature engineering for agricultural and food sector applications, including developing multi-country global calibration models for moisture and protein in corn kernels.

Upconversion and NIR-II luminescent rare earth nanoparticles combined with machine learning for cancer theranostics

How to develop contrast agents for cancer theranostics is a meaningful and challenging endeavor, and rare earth nanoparticles (RENPs) may provide a possible solution. In this study, we initially modified RENPs through the application of photodynamic agents (ZnPc) and targeted the bevacizumab antibody for cancer theranostics, which was aimed at improving the therapeutic targeting and efficacy. Subsequently, we amalgamated anthocyanin with the modified RENPs, creating a potential cancer diagnosis platform. When the spectral data were obtained from the composite of cells, the crucial information was extracted through a competitive adaptive reweighted sampling feature algorithm. Then, we employed a machine learning classification model and classified both the individual spectral data and fused spectral data to accurately predict distinctions between breast cancer and normal tissue. The results indicate that the amalgamation of fusion techniques with machine learning algorithms provides highly precise predictions for molecular-level breast cancer detection. Finally, in vitro and in vivo experiments were carried out to validate the near-infrared luminescence and therapeutic effectiveness of the modified nanomedicine. This research not only underscores the targeted effects of nanomedicine but also demonstrates the potent synergy between optical spectral technology and machine learning. This innovative approach offers a comprehensive strategy for the integrated treatment of breast cancer.

Towards Sustainable and Dynamic Modeling Analysis in Korean Pine Nuts: An Online Learning Approach with NIRS

Due to its advantages such as speed and noninvasive nature, near-infrared spectroscopy (NIRS) technology has been widely used in detecting the nutritional content of nut food. This study aims to address the problem of offline quantitative analysis models producing unsatisfactory results for different batches of samples due to complex and unquantifiable factors such as storage conditions and origin differences of Korean pine nuts. Based on the offline model, an online learning model was proposed using recursive partial least squares (RPLS) regression with online multiplicative scatter correction (OMSC) preprocessing. This approach enables online updates of the original detection model using a small amount of sample data, thereby improving its generalization ability. The OMSC algorithm reduces the prediction error caused by the inability to perform effective scatter correction on the updated dataset. The uninformative variable elimination (UVE) algorithm appropriately increases the number of selected feature bands during the model updating process to expand the range of potentially relevant features. The final model is iteratively obtained by combining new sample feature data with RPLS. The results show that, after OMSC preprocessing, with the number of features increased to 100, the new online model's R2 value for the prediction set is 0.8945. The root mean square error of prediction (RMSEP) is 3.5964, significantly outperforming the offline model, which yields values of 0.4525 and 24.6543, respectively. This indicates that the online model has dynamic and sustainable characteristics that closely approximate practical detection, and it provides technical references and methodologies for the design and development of detection systems. It also offers an environmentally friendly tool for rapid on-site analysis for nut food regulatory agencies and production enterprises.

Data fusion of near-infrared and Raman spectroscopy: An innovative tool for non-destructive prediction of the TVB-N content of salmon samples

Total volatile basic nitrogen (TVB-N) serves as a crucial indicator for evaluating the freshness of salmon. This study aimed to achieve accurate and non-destructive prediction of TVB-N content in salmon fillets stored in multiple temperature settings (-20, 0, -4, 20 °C, and dynamic temperature) using near-infrared (NIR) and Raman spectroscopy. A partial least square support vector machine (LSSVM) regression model was established through the integration of NIR and Raman spectral data using low-level data fusion (LLDF) and mid-level data fusion (MLDF) strategies. Notably, compared to a single spectrum analysis, the LLDF approach provided the most accurate prediction model, achieving an R2P of 0.910 and an RMSEP of 1.922 mg/100 g. Furthermore, MLDF models based on 2D-COS and VIP achieved R2P values of 0.885 and 0.906, respectively. These findings demonstrated the effectiveness of the proposed method for precise quantitative detection of salmon TVB-N, laying a technical foundation for the exploration of similar approaches in the study of other meat products. This approach has the potential to assess and monitor the freshness of seafood, ensuring consumer safety and enhancing product quality.

Quantitative analysis of three ingredients in Salvia miltiorrhiza by near infrared spectroscopy combined with hybrid variable selection strategy

Rosmarinic acid (RA), Tanshinone IIA (Tan IIA), and Salvianolic acid B (Sal B) are crucial compounds found in Salvia miltiorrhiza. Quickly predicting these components can aid in ensuring the quality of S. miltiorrhiza. Spectral preprocessing and variable selection are essential processes in quantitative analysis using near infrared spectroscopy (NIR). A novel hybrid variable selection approach utilizing iVISSA was employed in this study to enhance the quantitative measurement of RA, Tan IIA, and Sal B contents in S. miltiorrhiza. The spectra underwent 108 preprocessing approaches, with the optimal method being determined as orthogonal signal correction (OSC). iVISSA was utilized to identify the intervals (feature bands) that were most pertinent to the target chemical. Various methods such as bootstrapping soft shrinkage (BOSS), competitive adaptive reweighted sampling (CARS), genetic algorithm (GA), variable combination population analysis (VCPA), successive projections algorithm (SPA), iteratively variable subset optimization (IVSO), and iteratively retained informative variables (IRIV) were used to identify significant feature variables. PLSR models were created for comparison using the given variables. The results fully demonstrated that iVISSA-SPA calibration model had the best comprehensive performance for Tan IIA, and iVISSA-BOSS had the best comprehensive performance for RA and Sal B, and correlation coefficients of cross-validation (R2cv), root mean square errors of cross-validation (RMSECV), correlation coefficients of prediction (R2p), and root mean square errors of prediction (RMSEP) were 0.9970, 0.0054, 0.9990 and 0.0033, 0.9992, 0.0016, 0.9961 and 0.0034, 0.9998, 0.0138, 0.9875 and 0.1090, respectively. The results suggest that NIR spectroscopy, along with PLSR and a hybrid variable selection method using iVISSA, can be a valuable tool for quickly quantifying RA, Sal B, and Tan IIA in S. miltiorrhiza.

Predicting the evolution of pH and total soluble solids during coffee fermentation using near-infrared spectroscopy coupled with chemometrics

Currently, coffee fermentation is visually operated, which results in incomplete or excessive processes and coffees with undesirable characteristics. In front of it, pH and total soluble solids (TSS) have been shown to be good fermentation indicators, although this requires rapid, accurate, and chemical-free measurement techniques such as NIR spectroscopy. However, the complexity of the NIR spectra requires optimization steps in which variable selection techniques simplify profiles and subsequent models. This work tests a new covering array feature selection (CAFS) approach on NIR spectra to optimize prediction models in coffee samples during fermentation. Spectral profiles in the range 1100-2100 nm were extracted from coffee beans (Typica, Caturra, and Catimor varieties) raw and during fermentation (4, 8, 12, 16, 20, and 24 h). Partial least-squares regressions (PLSR) were performed using full spectra using a five-fold cross-validation strategy for training and validation. The relevant wavelengths were then selected using the β coefficients, the important projection of variables (VIP), and the CAFS method. Finally, optimized models were performed using the relevant wavelengths and compared among these using their statistical metrics. The models performed using the selected variables (22-47) of CAFS showed the best performance in predicting pH (R 2 = 0.825-0.903, RMSE = 0.096-0.158, RPD = 6.33-10.38) and TSS (R 2 = 0.865-0.922, RMSE = 0.688-1.059, RPD = 0.94-1.45) compared to the other methods. These findings suggest that simple and efficient models could be performed and implemented in routine analysis due to the maximum coverage and minimum cardinality of CAFS.

Online System for Monitoring the Degree of Fermentation of Oolong Tea Using Integrated Visible-Near-Infrared Spectroscopy and Image-Processing Technologies

During the fermentation process of Oolong tea, significant changes occur in both its external characteristics and its internal components. This study aims to determine the fermentation degree of Oolong tea using visible-near-infrared spectroscopy (vis-VIS-NIR) and image processing. The preprocessed vis-VIS-NIR spectral data are fused with image features after sequential projection algorithm (SPA) feature selection. Subsequently, traditional machine learning and deep learning classification models are compared, with the support vector machine (SVM) and convolutional neural network (CNN) models yielding the highest prediction rates among traditional machine learning models and deep learning models with 97.14% and 95.15% in the prediction set, respectively. The results indicate that VIS-NIR combined with image processing possesses the capability for rapid non-destructive online determination of the fermentation degree of Oolong tea. Additionally, the predictive rate of traditional machine learning models exceeds that of deep learning models in this study. This study provides a theoretical basis for the fermentation of Oolong tea.

Features in visible and Fourier transform infrared spectra confronting aspects of meat quality and fraud

Rapid assessment of microbiological quality (i.e., Total Aerobic Counts, TAC) and authentication (i.e., fresh vs frozen/thawed) of meat was investigated using spectroscopic-based methods. Data were collected throughout storage experiments from different conditions. In total 526 spectra (Fourier transform infrared, FTIR) and 534 multispectral images (MSI) were acquired. Partial Least Squares (PLS) was applied to select/transform the variables. In the case of FTIR data 30 % of the initial features were used, while for MSI-based models all features were employed. Subsequently, Support Vector Machines (SVM) regression/classification models were developed and evaluated. The performance of the models was evaluated based on the external validation set. In both cases MSI-based models (Root Mean Square Error, RMSE: 0.48-1.08, Accuracy: 91-97 %) were slightly better compared to FTIR (RMSE: 0.83-1.31, Accuracy: 88-94 %). The most informative features of FTIR for the case of quality were mainly in 900-1700 cm-1, while for fraud the features were more dispersed.

Tracking moisture contents in the pollution layer on a composite insulator surface using hyperspectral imaging technology

Electrical insulators used in transmission lines and outdoor substations are exposed to severe environmental pollution, which significantly increases the risk of power system failure, especially when the pollution layer is highly humid due to adverse weather conditions. The focus of this paper is to establish an effective method for assessing the moisture content (MC) in pollution layers as it serves as a crucial indicator for evaluating the risk of failure in insulators. Hyperspectral imaging (HSI) technology with a spectral range of 371.08-1037.89 nm was applied to determine significant changes in reflectance spectral characteristics in insulators during dynamic wetting and drying periods. Partial least squares regression (PLSR) models were utilized to evaluate the data presentation enhancement abilities of spectral transformation models and the data dimensionality reduction abilities of characteristic band selection methods. Furthermore, PLSR models were developed to calculate the MC along the pixel dimension to visually retrieve the dynamic wetting and drying processes of the pollution layer. The R-squared and root-mean-square error (RMSE) results in the cross-verification set and prediction set of the RE-RF(70%)-PLSR model with two characteristic bands with a wavelength of 543.28 nm and 848.01 nm were as follows: RCV2 = 0.9824, RMSECV = 0.0367, RP2 = 0.9818, RMSEP = 0.0369, respectively. This research contributes towards the visualization retrieval of the MC and offers an important technique for analyzing flashover evolution, optimizing insulator design, and preparing coating materials for insulators.

Visible and near-infrared spectroscopic determination of sugarcane chlorophyll content using a modified wavelength selection method for multivariate calibration

Spectroscopy in the visible and near-infrared region (Vis-NIR) region has proven to be an effective technique for quantifying the chlorophyll contents of plants, which serves as an important indicator of their photosynthetic rate and health status. However, the Vis-NIR spectroscopy analysis confronts a significant challenge concerning the existence of spectral variations and interferences induced by diverse factors. Hence, the selection of characteristic wavelengths plays a crucial role in Vis-NIR spectroscopy analysis. In this study, a novel wavelength selection approach known as the modified regression coefficient (MRC) selection method was introduced to enhance the diagnostic accuracy of chlorophyll content in sugarcane leaves. Experimental data comprising spectral reflectance measurements (220-1400 nm) were collected from sugarcane leaf samples at different growth stages, including seedling, tillering, and jointing, and the corresponding chlorophyll contents were measured. The proposed MRC method was employed to select optimal wavelengths for analysis, and subsequent partial least squares regression (PLSR) and Gaussian process regression (GPR) models were developed to establish the relationship between the selected wavelengths and the measured chlorophyll contents. In comparison to full-spectrum modelling and other commonly employed wavelength selection techniques, the proposed simplified MRC-GPR model, utilizing a subset of 291 selected wavelengths, demonstrated superior performance. The MRC-GPR model achieved higher coefficient of determination of 0.9665 and 0.8659, and lower root mean squared error of 1.7624 and 3.2029, for calibration set and prediction set, respectively. Results showed that the GPR model, a nonlinear regression approach, outperformed the PLSR model.

Non-destructive optical sensing technologies for advancing the egg industry toward Industry 4.0: A review

The egg is considered one of the best sources of dietary protein, and has an important role in human growth and development. With the increase in the world's population, per capita egg consumption is also increasing. Ground-breaking technological developments have led to numerous inventions like the Internet of Things (IoT), various optical sensors, robotics, artificial intelligence (AI), big data, and cloud computing, transforming the conventional industry into a smart and sustainable egg industry, also known as Egg Industry 4.0 (EI 4.0). The EI 4.0 concept has the potential to improve automation, enhance biosecurity, promote the safeguarding of animal welfare, increase intelligent grading and quality inspection, and increase efficiency. For a sustainable Industry 4.0 transformation, it is important to analyze available technologies, the latest research, existing limitations, and prospects. This review examines the existing non-destructive optical sensing technologies for the egg industry. It provides information and insights on the different components of EI 4.0, including emerging EI 4.0 technologies for egg production, quality inspection, and grading. Furthermore, drawbacks of current EI 4.0 technologies, potential workarounds, and future trends were critically analyzed. This review can help policymakers, industrialists, and academicians to better understand the integration of non-destructive technologies and automation. This integration has the potential to increase productivity, improve quality control, and optimize resource management toward sustainable development of the egg industry.

A Monte Carlo resampling based multiple feature-spaces ensemble (MFE) strategy for consistency-enhanced spectral variable selection

BACKGROUND

Variable selection has gained significant attention as a means to enhance spectroscopic calibration performance. However, existing methods still have certain limitations. Firstly, the selection results are sensitive to the choice of training samples, indicating that the selected variables may not be truly relevant. Secondly, the number of the selected variables is still too large in some situations, and modelling with too many predictors may lead to over-fitting issues. To address these challenges, we propose and implement a novel multiple feature-spaces ensemble (MFE) strategy with the least absolute shrinkage and selection operator (LASSO) method.

RESULTS

The MFE strategy synergizes the advantages of LASSO regression and ensemble strategy, thereby facilitating a more robust identification of key variables. We demonstrated the efficacy of our approach through extensive experimentation on publicly available datasets. The results not only demonstrate enhanced consistency in variable selection but also manifest improved prediction performance compared to benchmark methods.

SIGNIFICANT

The MFE strategy provided a comprehensive framework for conducting variable importance analysis, leading to robust and consistent variable selection. Furthermore, the improved consistency in variable selection contributes to enhanced prediction performance for spectroscopic calibration, making it more robust and accurate.

Semi-Supervised Deep Learning-Based Multi-component Spectral Calibration Modeling for UV-vis and Near-Infrared Spectroscopy without Information Loss

Spectral analysis is an important method for characterizing and identifying chemical species. However, quantitative spectral analysis of multiple chemical properties in the real world has always been a challenging problem due to the strong correlation, massive noise, and serious information overlapping of the spectral features. Here, we present a new semi-supervised spectral calibration method based on information lossless decoupling of spectral features named NICEM. To realize the separation and extraction of key latent features, the method uses the flow-based model non-linear independent component estimation (NICE) to learn the sample distribution. The spectral data information is transformed into independent latent variables obeying Gaussian distribution by the reversible structure of deep network without information loss, so as to find the essential properties and realize the feature nonlinear decomposition. Moreover, the association between the input latent feature variables and attributes is evaluated by the maximum mutual information coefficient to eliminate the adverse effects of irrelevant information in the latent variable space and mine key information. Since the latent variables are independent in each dimension, the NICEM method is easier to establish an accurate semi-supervised multi-component calibration model even for high overlapping and complex spectral data. The applicability of the proposed spectral modeling method is demonstrated by using three ultraviolet-visible and near-infrared spectral data sets with 15 physical and chemical properties including diesel fuels, corn, and multi-metal ions solution. Results show that the proposed NICEM method has the highest determination coefficient (R2) and significantly improves extrapolation compared with the seven state-of-the-art methods. The proposed method is intuitive because it obviates complex feature engineering and prior knowledge and is a promising spectral calibration tool for quantitative analysis in other spectroscopy applications.

Improving the monitoring of root zone soil salinity under vegetation cover conditions by combining canopy spectral information and crop growth parameters

Soil salinization is one of the main causes of land degradation in arid and semi-arid areas. Timely and accurate monitoring of soil salinity in different areas is a prerequisite for amelioration. Hyperspectral technology has been widely used in soil salinity monitoring due to its high efficiency and rapidity. However, vegetation cover is an inevitable interference in the direct acquisition of soil spectra during crop growth period, which greatly limits the monitoring of soil salinity by remote sensing. Due to high soil salinity could lead to difficulty in plants' water absorption, and inhibit plant dry matter accumulation, a method for monitoring root zone soil salinity by combining vegetation canopy spectral information and crop aboveground growth parameters was proposed in this study. The canopy spectral information was acquired by a spectroradiometer, and then variable importance in projection (VIP), competitive adaptive reweighted sampling (CARS), and random frog algorithm (RFA) were used to extract the salinity spectral features in cotton canopy spectrum. The extracted features were then used to estimate root zone soil salinity in cotton field by combining with cotton plant height, aboveground biomass, and shoot water content. The results showed that there was a negative correlation between plant height/aboveground biomass/shoot water content and soil salinity in 0-20, 0-40, and 0-60 cm soil layers at different growth stages of cotton. Spectral feature selection by the three methods all improved the prediction accuracy of soil salinity, especially CARS. The prediction accuracy based on the combination of spectral features and cotton growth parameters was significantly higher than that based on only spectral features, with R² increasing by 10.01%, 18.35%, and 29.90% for the 0-20, 0-40, and 0-60 cm soil layer, respectively. The model constructed based on the first derivative spectral preprocessing, spectral feature selection by CARS, cotton plant height, and shoot water content had the highest accuracy for each soil layer, with R² of 0.715,0.769, and 0.742 for the 0-20, 0-40, 0-60 cm soil layer, respectively. Therefore, the method by combining cotton canopy hyperspectral data and plant growth parameters could significantly improve the prediction accuracy of root zone soil salinity under vegetation cover conditions. This is of great significance for the amelioration of saline soil in salinized farmlands arid areas.

Non-destructive discrimination of homochromatic foreign materials in cut tobacco based on VIS-NIR hyperspectral imaging

BACKGROUND

The presence of foreign materials (FM) not only reduces the commercial value of tobacco and the quality of cigarette products, but also affects the aroma and flavor of cigarettes. Existing tobacco deblending equipment has received little study with respect to homochromatic FM. In the present study, visible-near infrared (VIS-NIR) hyperspectral imaging technique combined with chemometrics were used to identify and visualize the homochromatic FM on the surface of thining tobacco. A comparison with conventional vision method was made to analyze the feasibility of the method. The importance of detecting FM in cut tobacco was further demonstrated by first studying the volatile organic compounds produced in cigarette mixed FM smoke and their effects on human health before conducting hyperspectral experiments.

RESULTS

The results indicated that solid-phase microextraction and gas chromatography mass spectrometry could detect volatile organic compounds in mainstream cigarette smoke that were not cigarette components and affected consumer health. Then, spectral features of the samples were extracted from hyperspectral images for building identification models to distinguish FM from cut tobacco. The visual RGB values of cut tobacco and FM were also used for the analysis of the recognition models. The results showed that the accuracy, precision and recall reached 100.00% using the back propagation artificial neural network classification model based on the principal component analysis raw wavelengths. The visualization results based on the optimal model produced clearer localization than conventional computer vision method.

CONCLUSION

The present study revealed that the VIS-NIR hyperspectral imaging technology had advantage in the detection and localization of FM on the surface of thinning tobacco, which provided a foundation for improving the quality and safety of cut tobacco production. © 2023 Society of Chemical Industry.

Global calibration for non-targeted fraud detection in quinoa flour using portable hyperspectral imaging and chemometrics

Quinoa is one of the highest nutritious grains, and global consumption of quinoa flour has increased as people pay more attention to health. Due to its high value, quinoa flour is susceptible to adulteration. Cross-contamination between quinoa flour and other flour can be easily neglected due to their highly similar appearance. Therefore, detecting adulteration in quinoa flour is important to consumers, industries, and regulatory agencies. In this study, portable hyperspectral imaging in the visible near-infrared (VNIR) spectral range (400-1000 nm) was applied as a rapid tool to detect adulteration in quinoa flour. Quinoa flour was adulterated with wheat, rice, soybean, and corn in the range of 0-98% with 2% increments. Partial least squares regression (PLSR) models were developed, and the best model for detecting the % authentic flour (quinoa) was obtained by the raw spectral data with R2p of 0.99, RMSEP of 3.08%, RPD of 8.77, and RER of 25.32. The model was improved, by selecting only 13 wavelengths using bootstrapping soft shrinkage (BOSS), to R2p of 0.99, RMSEP of 2.93%, RPD of 9.18, and RER of 26.60. A visualization map was also generated to predict the level of quinoa in the adulterated samples. The results of this study demonstrate the ability of VNIR hyperspectral imaging for adulteration detection in quinoa flour as an alternative to the complicated traditional method.

Hyperspectral Imaging Combined with Chemometrics Analysis for Monitoring the Textural Properties of Modified Casing Sausages with Differentiated Additions of Orange Extracts

The textural properties (hardness, springiness, gumminess, and adhesion) of 16-day stored sausages with different additions of orange extracts to the modified casing solution were estimated by response surface methodology (RSM) and a hyperspectral imaging system in the spectral range of 390-1100 nm. To improve the model performance, normalization, 1st derivative, 2nd derivative, standard normal variate (SNV), and multiplicative scatter correction (MSC) were applied for spectral pre-treatments. The raw, pretreated spectral data and textural attributes were fit to the partial least squares regression model. The RSM results show that the highest R² value achieved at adhesion (77.57%) derived from a second-order polynomial model, and the interactive effects of soy lecithin and orange extracts on adhesion were significant (p < 0.05). The adhesion of the PLSR model developed from reflectance after SNV pretreatment possessed a higher calibration coefficient of determination (0.8744) than raw data (0.8591). The selected ten important wavelengths for gumminess and adhesion can simplify the model and can be used for convenient industrial applications.

Identification of aged-rice adulteration based on near-infrared spectroscopy combined with partial least squares regression and characteristic wavelength variables

The long-term storage of rice will inevitably be involved in the deterioration of edible quality, and aged rice poses a great threat to food safety and human health. The acid value can be employed as a sensitive index for the determination of rice quality and freshness. In this study, near-infrared spectra of three kinds of rice (Chinese Daohuaxiang, southern japonica rice, and late japonica rice) mixed with different proportions of aged rice were collected. The partial least squares regression (PLSR) model with different preprocessing was constructed to identify the aged rice adulteration. Meanwhile, a competitive adaptive reweighted sampling (CARS) algorithm was used to extract the optimization model of characteristic variables. The constructed CARS-PLSR model method could not only reduce greatly the number of characteristic variables required by the spectrum but also improve the identification accuracy of three kinds of aged-rice adulteration. As above, this study proposed a rapid, simple, and accurate detection method for aged-rice adulteration, providing new clues and alternatives for the quality control of commercial rice.

A residual dense comprehensively regulated convolutional neural network to identify spectral information for egg quality traceability

In the egg market, due to the different nutritional values of eggs laid by hens under different feeding conditions, it is common for low-quality eggs to be counterfeited as high-quality eggs. This paper proposes a residual dense comprehensively regulated convolutional neural network (RDCR-Net) to identify the quality of eggs laid by hens under different feeding conditions. Firstly, a hyperspectral system is used to obtain the spectral information of eggs. Secondly, due to the complex structure of the spectral information, a comprehensively regulated convolution (CRConv) is proposed to extract features hidden in the spectral information through feature transformation in multiple spaces. Thirdly, due to the limited availability of spectral information training samples, deep networks may suffer from feature degradation. The residual dense comprehensively regulated block (RDCR-Block) is proposed to tightly connect multiple CRConv layers with residual dense connections. Finally, the RDCR-Block is taken as the central unit, and the RDCR-Net is designed to identify egg spectral information. In the comparison of multi-model results, the RDCR-Net obtains the best classification performance with 96.29% accuracy, 97.53% precision, 97.14% recall, and 96.19% kappa coefficient. In summary, the RDCR-Net effectively extracts the deep features of spectral information, achieves high accuracy in identifying eggs laid by hens under different feeding conditions, and provides a new method for egg quality traceability.

Evaluation of pH in Sausages Stuffed in a Modified Casing with Orange Extracts by Hyperspectral Imaging Coupled with Response Surface Methodology

The pH values of sausages stuffed in natural hog casings with different modifications (soy lecithin, soy oil, orange extracts (OE) from waste orange peels, lactic acid in slush salt, and treatment time) after 16-day 4 °C storage were evaluated for the first time by hyperspectral imaging (350−1100 nm) coupled with response surface methodology (RSM). A partial least squares regression (PLSR) model was developed to relate the spectra to the pH of sausages. Spectral pretreatment, including first derivative, second derivative, multiplicative scatter correction (MSC), standard normal variate (SNV), normalization, and normalization, with different combinations was employed to improve model performance. RSM showed that only soy lecithin and OE interactively affected the pH of sausages (p < 0.05). The pH value decreased when the casing was treated with a higher concentration of soy lecithin with 0.26% OE. As the first and second derivatives are commonly used to eliminate the baseline shift, the PLSR model derived from absorbance pretreated by the first derivative in the full wavelengths showed a calibration coefficient of determination (R2) of 0.73 with a root mean square error of calibration of 0.4283. Twelve feature wavelengths were selected with a comparable R2 value compared with the full wavelengths. The prediction map enables the visualization of the pH evolution of sausages stuffed in the modified casings added with OE.

Multispectral Wavebands Selection for the Detection of Potential Foreign Materials in Fresh-Cut Vegetables

Ensuring the quality of fresh-cut vegetables is the greatest challenge for the food industry and is equally as important to consumers (and their health). Several investigations have proven the necessity of advanced technology for detecting foreign materials (FMs) in fresh-cut vegetables. In this study, the possibility of using near infrared spectral analysis as a potential technique was investigated to identify various types of FMs in seven common fresh-cut vegetables by selecting important wavebands. Various waveband selection methods, such as the weighted regression coefficient (WRC), variable importance in projection (VIP), sequential feature selection (SFS), successive projection algorithm (SPA), and interval PLS (iPLS), were used to investigate the optimal multispectral wavebands to classify the FMs and vegetables. The application of selected wavebands was further tested using NIR imaging, and the results showed good potentiality by identifying 99 out of 107 FMs. The results indicate the high applicability of the multispectral NIR imaging technique to detect FMs in fresh-cut vegetables for industrial application.