Using an optimal CC-PLSR-RBFNN model and NIR spectroscopy for the starch content determination in corn

A three-stage wavelength selection algorithm for near-infrared spectroscopy calibration

The near-infrared spectral data is highly high dimensional and contains redundant information, it is necessary to identify the most representative characteristic wavelengths before modeling to improve model accuracy and reliability. At present, there are many methods for selecting the characteristic wavelengths of NIR spectroscopy, but the collinearity among wavelengths is still a main issue that leads to poor model effects. Therefore, this study proposes a three-stage wavelength selection algorithm (Stage III) to reduce redundancy in NIR spectral data and collinearity between wavelength variables, resulting in a simpler and more accurate predictive model. The research uses a public NIR data set of corn samples as its subject. Initially, the wavelengths with the higher correlation coefficients are chosen after calculating the relationship coefficients between every wavelength vector and the concentration vector. On this basis, the correlation coefficients between the vectors of each wavelength point are calculated, and those wavelength points with smaller correlation coefficients with other wavelength points are selected. Ultimately, the stepwise regression analysis selects the wavelengths that provide substantial value to the model as the variables for modeling, leading to the development of a multiple linear regression model. The results show that the model using the three-stage wavelength selection algorithm outperforms those using the full spectrum, Stages I and Stage II, and the coefficient of determination of the test set of the Stage III-MLR model achieved an accuracy of 0.9360. Instead of the successive projections algorithm (SPA), uninformative variable elimination (UVE), and competitive adaptive reweighted sampling (CARS), Stage III is better in the model prediction accuracy. Therefore, the three-stage wavelength selection algorithm is an effective wavelength selection algorithm that can effectively model NIR spectroscopy, reduce the collinearity between the wavelength variables, simplify the complexity of the model, and improve the prediction precision of the model.

Effect of organic acids on fermentation quality and microbiota of horseshoe residue and corn protein powder

This experiment aimed to investigate the impact of malic acid (MA) and citric acid (CA) on the nutritional composition, fermentation quality, rumen degradation rate, and microbial diversity of a mixture of apple pomace and corn protein powder during ensiling. The experiment used apple pomace and corn protein powder as raw materials, with four groups: control group (CON), malic acid treatment group (MA, 10 g/kg), citric acid treatment group (CA, 10 g/kg), and citric acid + malic acid treatment group (MA, 10 g/kg + CA, 10 g/kg). Each group has 3 replicates, with 2 repetitions in parallel, subjected to mixed ensiling for 60 days. The results indicated: (1) Compared to the CON group, the crude protein content significantly increased in the MA, CA, and MA + CA groups (p < 0.05), with the highest content observed in the MA + CA group. The addition of MA and CA effectively reduced the water-soluble carbohydrate (WSC) content (p < 0.05). Simultaneously, the CA group showed a decreasing trend in NDFom and hemicellulose content (p = 0.08; p = 0.09). (2) Compared to the CON group, the pH significantly decreased in the MA, CA, and MA + CA groups (p < 0.01), and the three treatment groups exhibited a significant increase in lactic acid and acetic acid content (p < 0.01). The quantity of lactic acid bacteria increased significantly (p < 0.01), with the MA + CA group showing a more significant increase than the MA and CA groups (p < 0.05). (3) Compared to the CON group, the in situ dry matter disappearance (ISDMD) significantly increased in the MA, CA, and MA + CA groups (p < 0.05). All three treatment groups showed highly significant differences in in situ crude protein disappearance (ISCPD) compared to the CON group (p < 0.01). (4) Good's Coverage for all experimental groups was greater than 0.99, meeting the conditions for subsequent sequencing. Compared to the CON group, the Shannon index significantly increased in the CA group (p < 0.01), and the Simpson index increased significantly in the MA group (p < 0.05). However, there was no significant difference in the Chao index among the three treatment groups and the CON group (p > 0.05). At the genus level, the abundance of Lentilactobacillus in the MA, CA, and MA + CA groups was significantly higher than in the control group (p < 0.05). PICRUSt prediction results indicated that the metabolic functional microbial groups in the CA and MA treatment groups were significantly higher than in the CON group (p < 0.05), suggesting that the addition of MA or CA could reduce the loss of nutritional components such as protein and carbohydrates in mixed ensilage. In conclusion, the addition of malic acid and citric acid to a mixture of apple pomace and corn protein powder during ensiling reduces nutritional losses, improves fermentation quality and rumen degradation rate, enhances the diversity of the microbial community in ensiled feed, and improves microbial structure. The combined addition of malic acid and citric acid demonstrates a superior effect.

Quantitative detection of multicomponent SF6 decomposition products based on Fourier transform infrared spectroscopy combined with SCARS-DNN

Accurate and efficient quantitative analysis of the decomposition products of the insulating medium SF6 in gas-insulated switchgear (GIS) is important for an effective assessment of its internal insulation status. In this work, a quantitative calibration model of Fourier Transform Infrared Spectroscopy (FTIR) combined with SCARS-DNN (Stability Competitive Adaptive Reweighted Sampling-Deep Neural Network) is proposed for the rapid non-destructive detection of SF6 decomposition products. First, the interference of the background gas SF6 on the absorption spectra of the decomposition products is eliminated according to the Lambert-Beer law, while baseline correction and Savitzky-Golay (S-G) smoothing are used to remove baseline drift and noise. Subsequently, a Monte Carlo cross-validation method is used to detect and eliminate the anomalous samples. Then feature selection is performed using uninformative variable elimination (UVE) and stability competitive adaptive reweighted sampling (SCARS), and finally quantitative calibration models of FULL-DNN (full spectral band), UVE-DNN, and SCARS-DNN are developed. For the quantitative detection of SF6 decomposition products, the SCARS-DNN model had the best prediction performance with a maximum reduction of 96.18% in the root mean square error (RMSE) and 96.11% in the mean absolute percentage error (MAPE). Results reveal that the relative errors are basically kept below 1.36% when predicting the three decomposition products, even in the presence of a high level of SF6 interference. Therefore, the SCARS-DNN model is suitable for high-precision quantitative detection of SF6 decomposition gas.

Exploring Deep Learning to Predict Coconut Milk Adulteration Using FT-NIR and Micro-NIR Spectroscopy

Accurately identifying adulterants in agriculture and food products is associated with preventing food safety and commercial fraud activities. However, a rapid, accurate, and robust prediction model for adulteration detection is hard to achieve in practice. Therefore, this study aimed to explore deep-learning algorithms as an approach to accurately identify the level of adulterated coconut milk using two types of NIR spectrophotometer, including benchtop FT-NIR and portable Micro-NIR. Coconut milk adulteration samples came from deliberate adulteration with corn flour and tapioca starch in the 1 to 50% range. A total of four types of deep-learning algorithm architecture that were self-modified to a one-dimensional framework were developed and tested to the NIR dataset, including simple CNN, S-AlexNET, ResNET, and GoogleNET. The results confirmed the feasibility of deep-learning algorithms for predicting the degree of coconut milk adulteration by corn flour and tapioca starch using NIR spectra with reliable performance (R2 of 0.886-0.999, RMSE of 0.370-6.108%, and Bias of -0.176-1.481). Furthermore, the ratio of percent deviation (RPD) of all algorithms with all types of NIR spectrophotometers indicates an excellent capability for quantitative predictions for any application (RPD > 8.1) except for case predicting tapioca starch, using FT-NIR by ResNET (RPD < 3.0). This study demonstrated the feasibility of using deep-learning algorithms and NIR spectral data as a rapid, accurate, robust, and non-destructive way to evaluate coconut milk adulterants. Last but not least, Micro-NIR is more promising than FT-NIR in predicting coconut milk adulteration from solid adulterants, and it is portable for in situ measurements in the future.

An effective moisture interference correction method for maize powder NIR spectra analysis

The detection of maize starch content is of great significance for maize processing industry and near-infrared spectroscopy (NIRS) is an ideal rapid detection technology. However, the interference of moisture in maize is a bottleneck problem that affects the accuracy of NIRS quantitative analysis. In this study, we proposed methods based on external parameter orthogonalization (EPO) combined with wavelength selection algorithms to bring more accurate analytical results. Two groups of maize starch samples with different moisture content distributions were investigated to compare the predictive performance of NIRS models. The results showed that the model built using EPO combined with the synergy interval partial least squares (EPO-siPLS) algorithm exhibited the superior prediction accuracy, whose RMSEP/RMSEPck is improved by 9.7 % compared with that of siPLS model, 25.3 % compared with that of EPO-PLS, and 45.8 % compared with that of the PLS model. This study provides a more accurate and robust new method for rapid detection of maize starch and offers new insights for its application.

Quantitative assessment of wheat quality using near-infrared spectroscopy: A comprehensive review

Wheat is one of the most widely cultivated crops throughout the world. A great need exists for wheat quality assessment for breeding, processing, and products production purposes. Near-infrared spectroscopy (NIRS) is a rapid, low-cost, simple, and nondestructive assessment method. Many advanced studies associated with NIRS for wheat quality assessment have been published recently, either introducing new chemometrics or attempting new assessment parameters to improve model robustness and accuracy. This review provides a comprehensive overview of NIRS methodology including its principle, spectra pretreatments, spectral wavelength selection, outlier disposal, dataset division, regression methods, and model evaluation. More importantly, the applications of NIRS in the determination of analytical parameters, rheological parameters, and end product quality of wheat are summarized. Although NIRS showed great potential in the quantitative determination of analytical parameters, there are still challenges in model robustness and accuracy in determining rheological parameters and end product quality for wheat products. Future model development needs to incorporate larger databases, integrate different spectroscopic techniques, and introduce cutting-edge chemometrics methods. In addition, calibration based on external factors should be considered to improve the predicted results of the model. The NIRS application in micronutrients needs to be extended. Last, the idea of combining standard product sensory attributes and spectra for model development deserves further study.

Evaluation of high-linearity bone radiation detectors exposed to gamma-rays via FTIR measurements

In radiation physics, the study of new alternative dosimeters is of interest to the growing branch of dosimetric characterization for radiotherapy applications. The goal of this work was to expose bone samples to high doses and evaluate their linearity response to gamma rays. The Fourier Transform Infrared (FTIR) spectrophotometry technique was employed as the evaluation technique, and based on the spectrophotometry absorbance profiles the linearity was assessed based on the following methods: Area Under the Curve (AUC), Wavenumber Method (WM), Partial Component Regression (PCR) and Partial Least-Square Regression (PLSR) methods. The bone samples were irradiated with absorbed doses of 10 Gy up to 500 Gy using a ⁶⁰Co Gamma Cell-220 system. The results showed, for the calibration curves of the system, adequate linearity on all methods. In conclusion, the results indicate a good linear response and therefore an interesting potential radiation detector.

Advances in infrared spectroscopy combined with artificial neural network for the authentication and traceability of food

The authentication and traceability of food attract more attention due to the increasing consumer awareness regarding nutrition and health, being a new hotspot of food science. Infrared spectroscopy (IRS) combined with shallow neural network has been widely proven to be an effective food analysis technology. As an advanced deep learning technology, deep neural network has also been explored to analyze and solve food-related IRS problems in recent years. The present review begins with brief introductions to IRS and artificial neural network (ANN), including shallow neural network and deep neural network. More notably, it emphasizes the comprehensive overview of the advances of the technology combined IRS with ANN for the authentication and traceability of food, based on relevant literature from 2014 to early 2020. In detail, the types of IRS and ANN, modeling processes, experimental results, and model comparisons in related studies are described to set forth the usage and performance of the combined technology for food analysis. The combined technology shows excellent ability to authenticate food quality and safety, involving chemical components, freshness, microorganisms, damages, toxic substances, and adulteration. As well, it shows excellent performance in the traceability of food variety and origin. The advantages, current limitations, and future trends of the combined technology are further discussed to provide a thoughtful viewpoint on the challenges and expectations of online applications for the authentication and traceability of food.

Rapid determination of polysaccharides and antioxidant activity of Poria cocos using near-infrared spectroscopy combined with chemometrics

This study evaluates the feasibility of near-infrared (NIR) spectroscopy combined with chemometrics as a fast and efficient technique to predict the polysaccharide content and antioxidant activity of Poria cocos. The reference values of polysaccharide content were determined by the phenol-sulfuric acid method, and the antioxidant activities were determined by the DPPH scavenge assay, FRAP scavenge assay and ABTS scavenge assay, respectively. The partial least squares regression algorithm was used to relate the spectra to the reference values. Various methods for spectra pretreatment and variable selection were optimized to improve the predictability and stability of the models. As a result, the best models yielded very satisfying results, of which the values of coefficients of determination were all >0.94, and the values of residual predictive deviation were all >4. Such results confirmed that the present method is robust and applicable, and thus has good potential for rapid quality evaluation of Poria cocos.

Feasibility study on prediction of gasoline octane number using NIR spectroscopy combined with manifold learning and neural network

Octane number is an anti-knock index of fuel gasoline, which has an important impact on the service life of engine components and the safety of vehicles. Therefore, it is a basic work involving safety to predict the gasoline octane number accurately. This work was aimed to predict the octane number of near infrared (NIR) spectroscopy by combining dimension reduction algorithm with neural network. Covariance matrix estimation (CME), known as a mathematical statistic tool, was applied to estimating the intrinsic dimensions of octane spectrum dataset. Landmark-Isometric feature mapping (L-Isomap), as a novel manifold learning algorithm, was used for dimensionality reduction of spectral data. A new method, beetle antennae search optimization BP neural network (BAS-BP), was proposed to realize the prediction of octane number. In order to verify the performance of CME-L-Isomap-BAS-BP model presented in this paper, it is compared with other models. The results showed that when CME-L-Isomap was combined with BAS-BP, the average recovery rate (AR), mean square error (MSE), mean absolute percentage error (MAPE), correlation coefficient (R) and running time were superior than other models. The satisfying results demonstrated that the CME-L-Isomap-BAS-BP model is more suitable for prediction of gasoline octane number.

Identification of Rice Varieties and Transgenic Characteristics Based on Near-Infrared Diffuse Reflectance Spectroscopy and Chemometrics

Background: In recent years, genetically modified technology has developed rapidly, and the potential impact of genetically modified foods on human health and the ecological environment has received increasing attention. The currently used methods for testing genetically modified foods are cumbersome, time-consuming, and expensive. This paper proposed a more efficient and convenient detection method. Methods: Near-infrared diffuse reflectance spectroscopy (NIRDRS) combined with multivariate calibration methods, including principal component analysis (PCA), partial least squares discriminant analysis (PLS-DA), and support vector machines (SVM), were used for identification of different rice varieties and transgenic (Bt63)/non-transgenic rice. Spectral pretreatment methods, including Norris–Williams smooth (NWS), standard normal variate (SNV), multiplicative scatter correction (MSC), and Savitzky–Golay 1st derivative (SG 1st-Der), were used for spectral noise reduction and effective information enhancement. Accuracy was used to evaluate the qualitative discriminant models. Results: The results showed that the SG 1st-Der pretreatment method, combined with the SVM, provided the optimal model to distinguish different rice varieties. The accuracy of the optimal model was 98.33%. For the discrimination model of transgenic/non-transgenic rice, the SNV-SVM model, MSC-SVM model, and SG 1st-Der-PLS-DA model all achieved good analysis results with the accuracy of 100%. Conclusion: The results showed that portable NIR spectroscopy combined with chemometrics methods could be used to identify rice varieties and transgenic characteristics (Bt63) due to its fast, non-destructive, and accurate advantages.