Application of Competitive Adaptive Reweighted Sampling Method to Determine Effective Wavelengths for Prediction of Total Acid of Vinegar

Near-infrared spectroscopy: application in ensuring food quality and safety

In recent years, the demand for intelligent control of food quality during processing has been increasing in the food industry. As a practical analytical tool, near-infrared (NIR) spectroscopy has become a common detection method to ensure food quality and safety because of its advantages of continuous, rapid on-line determination and strong analytical performance. In the past 20 years, many attempts and research studies have been conducted on the applications of NIR spectroscopy. Based on this, this review focuses on the specific application of near-infrared technology in the field of food, highlighting its breakthrough and applicability. NIR spectroscopy is widely used for online quantitative analysis of beneficial food components to the human body, which include proteins, polysaccharides, and polyphenols. Additionally, this technology is applied to food microbiological analysis, food safety detection (such as food adulteration), and food origin prediction. This review discusses the existing challenges, future development directions, and opportunities for NIR spectroscopy technology.

A machine learning based variable selection algorithm for binary classification of perinatal mortality

The identification of significant predictors with higher model performance is the key objective in classification domain. A machine learning-based variable selection technique termed as CARS-Logistic model is proposed by coupling competitive adaptive re-weighted sampling(CARS) and logistic regression for binary classification. Based on five assessment criteria, the proposed method is found to be more efficient than Forward selection logistic regression model. The CARS-Logistic model is executed to determine the significant factors of perinatal mortality in Pakistan. The identified hazards communicated social, cultural, financial, and health-related characteristics which contain key information about perinatal mortality in Pakistan for policymakers.

An integrated CBLA-Net with fractional discrete wavelet transform and frequency-based CARS to predict heavy metal elements by XRF

BACKGROUND

X-ray fluorescence (XRF) emerges as a promising technique for estimating heavy metal elements. However, XRF spectra typically contain a significant amount of environmental information and signal noise, and the relationship between spectral intensity and element concentration is difficult to quantify using a single model, thereby reducing the predictive performance for low concentration elements.

RESULTS

This paper proposed a comprehensive framework for predicting elemental concentrations, encompassing preprocessing, variable selection, decision-making, to enable fast, non-destructive, and accurate estimation of element concentrations in soil. Firstly, an optimal denoising method based on fractional discrete wavelet transform (FDWT) was introduced to enhance signal quality. Furthermore, the frequency-based competitive adaptive reweighted sampling (FCARS) algorithm was employed for feature selection of XRF spectral variables, allowing extraction of the most informative features from the complex spectral data. Finally, a novel deep learning network, called ConvBiLSTM-Attention (CBLA-Net), was designed to achieve precise estimation of heavy metal elements concentration. Compared with other advanced algorithms, The CBLA-Net demonstrated the highest accuracy for V, Cr, Mn, Zn, Cd, and Pb, achieving the coefficient of determination (R2) of 0.9730, 0.9874, 0.9952, 0.9921, 0.9518, and 0.9741, respectively. The CBLA-Net not only effectively extract local features and capture global information, but also combines attention mechanism to focus on key information.

SIGNIFICANCE

The proposed novel deep learning quantitative framework, including preprocessing, feature selection, and CBLA-Net decision-making, significantly enhances the accuracy of elemental content prediction. It provides a new approach for accurately assessing the concentration of heavy metal elements in soil.

Auxiliary Diagnosis of Papillary Thyroid Carcinoma Based on Spectral Phenotype

Thyroid cancer, a common endocrine malignancy, is one of the leading death causes among endocrine tumors. The diagnosis of pathological section analysis suffers from diagnostic delay and cumbersome operating procedures. Therefore, we intend to construct the models based on spectral data that can be potentially used for rapid intraoperative papillary thyroid carcinoma (PTC) diagnosis and characterize PTC characteristics. To alleviate any concerns pathologists may have about using the model, we conducted an analysis of the used bands that can be interpreted pathologically. A spectra acquisition system was first built to acquire spectra of pathological section images from 91 patients. The obtained spectral dataset contains 217 spectra of normal thyroid tissue and 217 spectra of PTC tissue. Clinical data of the corresponding patients were collected for subsequent model interpretability analysis. The experiment has been approved by the Ethics Review Committee of the Wuhu Hospital of East China Normal University. The spectral preprocessing method was used to process the spectra, and the preprocessed signal respectively optimized by the first and secondary informative wavelengths selection was used to develop the PTC detection models. The PTC detection model using mean centering (MC) and multiple scattering correction (MSC) has optimal performance, and the reasons for the good performance were analyzed in combination with the spectral acquisition process and composition of the test slide. For model interpretable analysis, the near-ultraviolet band selected for modeling corresponds to the location of amino acid absorption peak, and this is consistent with the clinical phenomenon of significantly lower amino acid concentrations in PTC patients. Moreover, the absorption peak of hemoglobin selected for modeling is consistent with the low hemoglobin index in PTC patients. In addition, the correlation analysis was performed between the selected wavelengths and the clinical data, and the results show: the reflection intensity of selected wavelengths in normal cells has a moderate correlation with cell arrangement structure, nucleus size and free thyroxine (FT4), and has a strong correlation with triiodothyronine (T3); the reflection intensity of selected bands in PTC cells has a moderate correlation with free triiodothyronine (FT3).

PLS-DA and Vis-NIR spectroscopy based discrimination of abdominal tissues of female rabbits

Using Vis-NIR spectroscopy to distinguish gestational sac from other abdominal tissues is the key to diagnosing female rabbits' pregnancy by optical means. This study aims to demonstrate the gestational sac and other abdominal tissues (hair, skin, breast, muscle, cecum, small intestine) of rabbits can be identified using Vis-NIR spectroscopy in vitro. These tissues' raw NIR spectra were recorded in the Vis-NIR range (490-940 nm) with interactive mode. The raw spectra of tissues were analyzed by the principal component analysis (PCA), and were pre-processed using five spectral pre-processing techniques (moving average filter (MF), De-trending (DT), first-order derivative (D1), Multivariate scattering correction (MSC), and standard normal variate (SNV)) to reduce signal noises. The raw and pre-processed spectra were classified using partial least squares discrimination analysis (PLS-DA). Two-way and multi-way PLS-DA model was conducted to understand the classification of each tissue from the gestational sac and to understand the classification of all tissues from the gestational sac, respectively. SNV-PLS-DA model had the best performance, and its multi-way accuracy (Ac), determination coefficients (R²), and Q² were 0.89, 0.91, 0.77, respectively. The successive projection algorithm (SPA) and competitive adaptive reweighted sampling (CARS) were used to select characteristic wavelengths (CWs). The SNV-SPA-PLS-DA model with eighteen CWs was better than the SNV-CARS-PLS-DA model. The results showed that Vis-NIR spectroscopy technology combined with PLS-DA could discriminate the gestational sac from the abdominal tissues. This study may help develop an optical diagnosis system for pregnant rabbits.

Use of Artificial Neural Networks and NIR Spectroscopy for Non-Destructive Grape Texture Prediction

In this article, a combination of non-destructive NIR spectroscopy and machine learning techniques was applied to predict the texture parameters and the total soluble solids content (TSS) in intact berries. The multivariate models obtained by building artificial neural networks (ANNs) and applying partial least squares (PLS) regressions showed a better prediction ability after the elimination of uninformative spectral ranges. A very good prediction was obtained for TSS and springiness (R² 0.82 and 0.72). Qualitative models were obtained for hardness and chewiness (R² 0.50 and 0.53). No satisfactory calibration model could be established between the NIR spectra and cohesiveness. Textural parameters of grape are strictly related to the berry size. Before any grape textural measurement, a time-consuming berry-sorting step is compulsory. This is the first time a complete textural analysis of intact grape berries has been performed by NIR spectroscopy without any a priori knowledge of the berry density class.

Early pregnancy diagnosis of rabbits: A non-invasive approach using Vis-NIR spatially resolved spectroscopy

Pregnancy diagnosis is essential for rabbit's reproductive management. The early identification of non-pregnant rabbits allows for earlier re-insemination, increases the service rate, and reduces the laboring interval in commercial operations. The objective of this study was to establish the feasibility of using a Vis-NIR spatially resolved spectroscopy for diagnosing pregnancy in female rabbits. A total of 141 female rabbits, including 67 pregnant female rabbits (PRs) and 74 non-pregnant female rabbits (NPRs), were measured spectrally between 350 and 1000 nm with different source-detector distances (SDD). Different preprocessing methods were used to transform and enhance the spectral signal. A partial least squares-discriminant analysis (PLS-DA) classification model of the original and preprocessed spectra was established. The highest accuracy of the calibration set and prediction set was 91.75% and 86.05%, respectively. Competitive adaptive reweighted sampling (CARS) and successive projection algorithm (SPA) were used to select characteristic wavelengths from the variables of VIP > 1 (Variable importance in projection),and four classification models were established based on selected wavelengths, including PLS-DA, support vector machine (SVM), K-Nearest Neighbor (KNN) and Naïve Bayes. SPA-SVM was the optimal classification model, the sensitivity, specificity, and accuracy of the validation set and prediction set were 93.18%, 94.44%, 93.88%, 86.96%, 90.00%, 90.69% respectively. The results showed that Vis-NIR spatially resolved spectroscopy combined with classification models could discriminate the PRs and NPRs.

Geometallurgical Characterisation with Portable FTIR: Application to Sediment-Hosted Cu-Co Ores

Cobalt (Co) mine production primarily originates from the sediment-hosted copper (Cu) deposits of the Democratic Republic of Congo (DRC). These deposits usually consist of three ore zones with a supergene oxide ore blanket overlying a transition zone which grades into a sulphide zone at depth. Each of these zones display a mineral assemblage with varying gangue mineralogy and, most importantly, a distinct state of oxidation of the mineralisation. This has direct implications for Cu and Co extraction during mineral processing as it dictates which processing method is to be used (i.e., leaching vs. flotation) and affects the performance of these. To optimise resource efficiency, reduce technical risks and environmental impacts, comprehensive understanding of variation of ore mineralogy and texture in the deposit is essential. By defining geometallurgical ore types according to their inferred metallurgical behaviour, this information can serve to classify the resources and improve resource management. To obtain insight into the spatial distribution of mineral grades, it is necessary to develop techniques that have the potential to measure rapidly and, preferably, within the mine at relatively low-cost. In this study, the application of portable Fourier transformed infrared (FTIR) spectroscopy is investigated to measure the mineralogy of drill core samples. A set of samples from a sediment-hosted Cu-Co deposit in DRC was selected to test this approach. Results were validated using automated mineralogy (QEMSCAN). Prediction of gangue and target mineral grades from the FTIR spectra was achieved through partial least squares regression (PLS-R) combined with competitive adaptive reweighted sampling (CARS). It is shown that the modal mineralogy obtained from FTIR can be used to classify the ore according to type of mineralisation and gangue mineralogy into geometallurgical ore types. This classification supports selection of a suitable processing route and is likely to affect the overall process performance.

Multiple rounds of Aspergillus niger biofortification confer relatively stable quality with minor changes of microbial community during industrial-scale Baoning vinegar production

Vinegar is consumed worldwide as a food condiment, especially in the Chinese diet. The present study optimized the addition of A. niger biofortified-bran Qu (0.3%, 0.45%, and 0.6%) as additional starter to improve total acid content and starch utilization rate in industrial-scale Baoning vinegar production. In addition, this novel study determined the quality and microbial community changes of Baoning vinegar during three-round biofortification in industrial scale. Our results indicated that A. niger biofortified-bran Qu added at 0.6% resulted in higher total acid content and starch utilization rate of vinegar Pei. Biofortification imposed minor changes in the microbial community during three-round biofortification, and more variation was observed in fungal community than that in bacterial community. Most importantly, the quality of Baoning vinegar remained relatively stable. This information further confirmed the feasibility of multiple rounds of A. niger biofortification, and can be used to provide theoretical basis for industrial-scale production.

Fast monitoring total acids and total polyphenol contents in fermentation broth of mulberry vinegar using MEMS and optical fiber near-infrared spectrometers

This study evaluated the potential of Micro-Electro-Mechanical System (MEMS) and optical fiber Near-Infrared (NIR) spectrometers as a rapid method for monitoring total acids (TA) and total polyphenol content (TPC) in the fermentation process of mulberry vinegar. The NIR spectrometers Digital Light Processing (DLP) NIRscan Nano EVM (MEMS instrument) were used for this purpose, and another NIR spectrometer NIRQuest 512 was used for comparison. The standard Normal Variate (SNV) was selected as the best method used to pre-process spectra, and the competitive adaptive reweighted sampling (CARS) was applied to optimize wavelength variables, which were then subjected to partial least squares (PLS) regression. The results showed that TA and TPC could be determined. For TA, NIRQuest 512 provided a good predictive performance with the root-mean-square error of prediction set (RMSEP) of 0.22% and the R-squared of prediction set (R²_P) of 0.977, whiles DLP NIRscan Nano EVM obtained the RMSEP of 0.32% and R²p of 0.950. For TPC, the NIRQuest 512 provided a predictive performance with the RMSEP of 8.11 mgGAE/L (mg gallic acid equivalent/L) and R²_P of 0.820, and DLP NIRscan Nano EVM had the RMSEP of 8.22 mg GAE/L and R²p of 0.800. In conclusion, the low-price MEMS NIR instruments DLP NIRscan Nano EVM can be applied to monitor TA and TPC in the fermentation broth of mulberry vinegar.

Quantitative analysis of yeast fermentation process using Raman spectroscopy: Comparison of CARS and VCPA for variable selection

Yeast is one of the most widely used microbial species in the field of microbiology, and it is crucial that rapid and accurate monitoring of its process. Therefore, this study presents a method using Raman spectroscopy for quantitative analysis of yeast fermentation process. First, a ProSP-Micro2000K Raman measuring system used to obtain the Raman spectra of eight batches of yeast samples during fermentation, and the spectra obtained were pretreated using Savitzky-Golay (SG) smoothing filter and standard normal variate (SNV). Then, two variable selection methods, which were competitive adaptive reweighted sampling (CARS) and variable combination population analysis (VCPA), were compared to search the preprocessed Raman spectroscopy characteristic wavenumber. Finally, support vector machine (SVM) was employed to construct a quantitative monitoring model of yeast fermentation process based on variables from the selected characteristic wavenumbers. The results revealed that the VCPA-SVM model showed the best prediction result with 14 selected characteristic wavelength variables. The coefficient of determination (R_P²) of the optimal model was 0.979, while the root mean square error of prediction (RMSEP) was 0.108 in the validation set. The overall results demonstrate that the Raman spectroscopy integrated with chemometric approaches could be utilized as a rapid method to monitor the process of yeast cultivations.

Developing deep learning based regression approaches for determination of chemical compositions in dry black goji berries (Lycium ruthenicum Murr.) using near-infrared hyperspectral imaging

Black goji berry (Lycium ruthenicum Murr.) has great commercial and nutritional values. Near-infrared hyperspectral imaging (NIR-HSI) was used to determine total phenolics, total flavonoids and total anthocyanins in dry black goji berries. Convolutional neural networks (CNN) were designed and developed to predict the chemical compositions. These CNN models and deep autoencoder were used as supervised and unsupervised feature extraction methods, respectively. Partial least squares (PLS) and least-squares support vector machine (LS-SVM) as modelling methods, successive projections algorithm and competitive adaptive reweighted sampling (CARS) as wavelength selection methods, and principal component analysis (PCA) and wavelet transform (WT) as feature extraction methods were studied as conventional approaches for comparison. Deep learning approaches as modelling methods and feature extraction methods obtained good and equivalent performances to the conventional methods. The results illustrated that deep learning had great potential as modelling and feature extraction methods for chemical compositions determination in NIR-HSI.

Rapid Screen of the Color and Water Content of Fresh-Cut Potato Tuber Slices Using Hyperspectral Imaging Coupled with Multivariate Analysis

Color index and water content are important indicators for evaluating the quality of fresh-cut potato tuber slices. In this study, hyperspectral imaging combined with multivariate analysis was used to detect the color parameters (L*, a*, b*, Browning index (BI), L*/b*) and water content of fresh-cut potato tuber slices. The successive projections algorithm (SPA) and competitive adaptive reweighted sampling (CARS) were used to extract characteristic wavelengths, partial least squares (PLS) and least squares support vector machine (LS-SVM) were utilized to establish regression models. For color prediction, R²_c, R²_p and RPD of all the LSSVM models established for the five color indicators L*, a*, b*, BI, L*/b* were exceeding 0.90, 0.84 and 2.1, respectively. For water content prediction, R²_c, R²_p, and RPD of the LSSVM models were over 0.80, 0.77 and 1.9, respectively. LS-SVM model based on full spectra was used to reappear the spatial distribution of color and water content in fresh-cut potato tuber slices by pseudo-color imaging since it performed best in most cases. The results illustrated that hyperspectral imaging could be an effective method for color and water content prediction, which could provide solid theoretical basis for subsequent grading and processing of fresh-cut potato tuber slices.

Uninformative Biological Variability Elimination in Apple Soluble Solids Content Inspection by Using Fourier Transform Near-Infrared Spectroscopy Combined with Multivariate Analysis and Wavelength Selection Algorithm

Uninformative biological variability elimination methods were studied in the near-infrared calibration model for predicting the soluble solids content of apples. Four different preprocessing methods, namely, Savitzky-Golay smoothing, multiplicative scatter correction, standard normal variate, and mean normalization, as well as their combinations were conducted on raw Fourier transform near-infrared spectra to eliminate the uninformative biological variability. Subsequently, robust calibration models were established by using partial least squares regression analysis and wavelength selection algorithms. Results indicated that the partial least squares calibration models with characteristic variables selected by CARS method coupled with preprocessing of Savitzky-Golay smoothing and multiplicative scatter correction had a considerable potential for predicting apple soluble solids content regardless of the biological variability.

Estimation of the critical quality attributes for hydroxypropyl methylcellulose with near-infrared spectroscopy and chemometrics

With the implementation of quality by design (QbD), critical attributes of raw material (drug substance and excipients) are of significantly importance in pharmaceutical manufacturing process. It is desirable for the quality control of critical material attributes (CMAs) of excipients to ensure the quality of end product. This paper explored the feasibility of an at-line method for the quantitative analysis of hydroxypropoxy group in hydroxypropyl methylcellulose (HPMC) with near infrared spectroscopy (NIRS). Hydroxypropoxy group content can be seen as a CMA of HPMC for quality control. The partial least squares (PLS) model was built with 61 samples including 47 samples as calibration set, 14 samples as validation set by sample set partitioning based on joint x-y distances (SPXY) method. Multiplicative scattering correction (MSC) combined with Savitzkye-Golay (SG) smoothing with first derivative was used as the appropriate pretreatment method. Three variable selection methods including interval partial least-squares (iPLS), competitive adaptive reweighted Sampling (CARS), and the combination of the two methods (iPLS-CARS) were performed for optimizing the model. The results indicated that NIRS could predict rapidly and effectively the content of hydroxypropoxy group in HPMC. NIRS could be a potential method for the quality control of CMAs.

Quantitative analysis of yeast growth process based on FT-NIR spectroscopy integrated with Gaussian mixture regression

To improve the yield of industrial fermentation, herein, we report a method based on Fourier-transform near-infrared spectroscopy (FT-NIR) to predict the growth of yeast.

A new spectral variable selection pattern using competitive adaptive reweighted sampling combined with successive projections algorithm

The competitive adaptive reweighted sampling-successive projections algorithm (CARS-SPA) method was proposed as a novel variable selection approach to process multivariate calibration. The CARS was first used to select informative variables, and then SPA to refine the variables with minimum redundant information. The proposed method was applied to near-infrared (NIR) reflectance data of nicotine in tobacco lamina and NIR transmission data of active ingredient in pesticide formulation. As a result, fewer but more informative variables were selected by CARS-SPA than by direct CARS. In the system of pesticide formulation, a multiple linear regression (MLR) model using variables selected by CARS-SPA provided a better prediction than the full-range partial least-squares (PLS) model, successive projections algorithm (SPA) model and uninformative variables elimination-successive projections algorithm (UVE-SPA) processed model. The variable subsets selected by CARS-SPA included the spectral ranges with sufficient chemical information, whereas the uninformative variables were hardly selected.

Characterizing and authenticating Montilla-Moriles PDO vinegars using near infrared reflectance spectroscopy (NIRS) technology

This study assessed the potential of near infrared (NIR) spectroscopy as a non-destructive method for characterizing Protected Designation of Origin (PDO) “Vinagres de Montilla-Moriles” wine vinegars and for classifying them as a function of the manufacturing process used. Three spectrophotometers were evaluated for this purpose: two monochromator instruments (Foss NIRSystems 6500 SY-I and Foss NIRSystems 6500 SY-II; spectral range 400–2,500 nm in both cases) and a diode-array instrument (Corona 45 VIS/NIR; spectral range 380–1,700 nm). A total of 70 samples were used to predict major chemical quality parameters (total acidity, fixed acidity, volatile acidity, pH, dry extract, ash, acetoin, methanol, total polyphenols, color (tonality and intensity), and alcohol content), and to construct models for the classification of vinegars as a function of the manufacturing method used. The results obtained indicate that this non-invasive technology can be used successfully by the vinegar industry and by PDO regulators for the routine analysis of vinegars in order to authenticate them and to detect potential fraud. Slightly better results were achieved with the two monochromator instruments. The findings also highlight the potential of these NIR instruments for predicting the manufacturing process used, this being of particular value for the industrial authentication of traditional wine vinegars.

A Review of Optical Nondestructive Visual and Near-Infrared Methods for Food Quality and Safety

This paper is a review of optical methods for online nondestructive food quality monitoring. The key spectral areas are the visual and near-infrared wavelengths. We have collected the information of over 260 papers published mainly during the last 20 years. Many of them use an analysis method called chemometrics which is shortly described in the paper. The main goal of this paper is to provide a general view of work done according to different FAO food classes. Hopefully using optical VIS/NIR spectroscopy gives an idea of how to better meet market and consumer needs for high-quality food stuff.