Evaluation of extractable polyphenols released to wine from cooperage byproduct by near infrared hyperspectral imaging

In-field and non-destructive determination of comprehensive maturity index and maturity stages of Camellia oleifera fruits using a portable hyperspectral imager

To efficiently detect the maturity stages of Camellia oleifera fruits, this study proposed a non-invasive method based on hyperspectral imaging technology. First, a portable hyperspectral imager was used for the in-field image acquisition of Camellia oleifera fruits at three maturity stages, and ten quality indexes were measured as reference standards. Then, factor analysis was performed to obtain the comprehensive maturity index (CMI) by analyzing the change trends and correlations of different indexes. To reduce the high dimensionality of spectral data, the successive projection algorithm (SPA) was employed to select effective feature wavelengths. The prediction models for CMI, including partial least squares regression (PLSR), support vector regression (SVR), extreme learning machine (ELM), and convolutional neural network regression (CNNR), were constructed based on full spectra and feature wavelengths; for CNNR, only the raw spectra were used as input. The SPA-CNNR model exhibited more promising performance (RP = 0.839, RMSEP = 0.261, and RPD = 1.849). Furthermore, PLS-DA models for maturity discrimination of Camellia oleifera fruits were developed using full wavelength, characteristic wavelengths and their fusion CMI, respectively. The PLS-DA model using the fused dataset achieved the highest maturity classification accuracy, with the best simplified model achieving 88.6 % accuracy in prediction set. This study indicated that a portable hyperspectral imager can be used for in-field determination of the internal quality and maturity stages of Camellia oleifera fruits. It provides strong support for non-destructive quality inspection and timely harvesting of Camellia oleifera fruits in the field.

Optimisation of the methodology for obtaining enzymatic protein hydrolysates from an industrial grape seed meal residue

The grape pomace industry produces large quantities of protein-rich seeds, which can be a sustainable non-animal protein source; their techno-functional properties could be exploited to improve the colour stabilisation and modulating the astringency of red wines in warm climates. This study aims to optimise the methodology of obtaining protein hydrolysates from defatted grape seed meal residue. Five assays using different quantities of enzyme and raw materials were considered. Based on the protein purity, hydrolysates yield, colour and molecular weight distribution achieved, optimal conditions were the hydrolysis of the alkaline protein concentrate with the highest amount of enzyme. The products obtained showed the lowest colour parameters, with the lightness contributing the most to the colour differences, which were visually perceptible (ΔE*_ab > 3). The hydrophobic amino acids remained within the peptide sequence, leaving polar and charged amino acids in terminal positions, which could affect the wine equilibrium related to colour stabilisation.

Identifying Individual Nutrient Deficiencies of Grapevine Leaves Using Hyperspectral Imaging

The efficiency of a vineyard management system is directly related to the effective management of nutritional disorders, which significantly downgrades vine growth, crop yield and wine quality. To detect nutritional disorders, we successfully extracted a wide range of features using hyperspectral (HS) images to identify healthy and individual nutrient deficiencies of grapevine leaves. Features such as mean reflectance, mean first derivative reflectance, variation index, mean spectral ratio, normalised difference vegetation index (NDVI) and standard deviation (SD) were employed at various stages in the ultraviolet (UV), visible (VIS) and near-infrared (N.I.R.) regions for our experiment. Leaves were examined visually in the laboratory and grouped as either healthy (i.e. control) or unhealthy. Then, the features of the leaves were extracted from these two groups. In a second experiment, features of individual nutrient-deficient leaves (e.g., N, K and Mg) were also analysed and compared with those of control leaves. Furthermore, a customised support vector machine (SVM) was used to demonstrate that these features can be utilised with a high degree of effectiveness to identify unhealthy samples and not only to distinguish from control and nutrient deficient but also to identify individual nutrient defects. Therefore, the proposed work corroborated that HS imaging has excellent potential to analyse features based on healthiness and individual nutrient deficiencies of grapevine leaves.

Comparison Performance of Visible-NIR and Near-Infrared Hyperspectral Imaging for Prediction of Nutritional Quality of Goji Berry (Lycium barbarum L.)

The potential of hyperspectral imaging for the prediction of the internal composition of goji berries was investigated. The prediction performances of models obtained in the Visible-Near Infrared (VIS-NIR) (400-1000 nm) and in the Near Infrared (NIR) (900-1700 nm) regions were compared. Analyzed constituents included Vitamin C, total antioxidant, phenols, anthocyanin, soluble solids content (SSC), and total acidity (TA). For vitamin C and AA, partial least square regression (PLSR) combined with different data pretreatments and wavelength selection resulted in a satisfactory prediction in the NIR region obtaining the R2pred value of 0.91. As for phenols, SSC, and TA, a better performance was obtained in the VIS-NIR region yielding the R2pred values of 0.62, 0.94, and 0.84, respectively. However, the prediction of total antioxidant and anthocyanin content did not give satisfactory results. Conclusively, hyperspectral imaging can be a useful tool for the prediction of the main constituents of the goji berry (Lycium barbarum L.).

Reduction of the Number of Samples for Cost-Effective Hyperspectral Grape Quality Predictive Models

Developing chemometric models from near-infrared (NIR) spectra requires the use of a representative calibration set of the entire population. Therefore, generally, the calibration procedure requires a large number of resources. For that reason, there is a great interest in identifying the most spectrally representative samples within a large population set. In this study, principal component and hierarchical clustering analyses have been compared for their ability to provide different representative calibration sets. The calibration sets generated have been used to control the technological maturity of grapes and total phenolic compounds of grape skins in red and white cultivars. Finally, the accuracy and precision of the models obtained with these calibration sets resulted from the application of the selection algorithms studied have been compared with each other and with the whole set of samples using an external validation set. Most of the standard errors of prediction (SEP) in external validation obtained from the reduced data sets were not significantly different from those obtained using the whole data set. Moreover, sample subsets resulting from hierarchical clustering analysis appear to produce slightly better results.

Assessment of the vigor of rice seeds by near-infrared hyperspectral imaging combined with transfer learning

Rice seed vigor plays a significant role in determining the quality and quantity of rice production. Thus, the quick and non-destructive identification of seed vigor is not only beneficial to fully obtain the state of rice seeds but also the intelligent development of agriculture by instant monitoring. Thus, herein, near-infrared hyperspectral imaging technology, as an information acquisition tool, was introduced combined with a deep learning algorithm to identify the rice seed vigor. Both the spectral images and average spectra of the rice seeds were sent to discriminant models including deep learning models and traditional machine learning models, and the highest accuracy of vigor identification reached 99.5018% using the self-built model. The parameters of the established deep learning models were frozen to be feature extractor for transfer learning. The identification results whose highest number also reached almost 98% indicated the possibility of applying transfer learning to improve the universality of the models. Moreover, by visualizing the output of convolutional layers, the progress and mechanism of spectral image feature extraction in the established deep learning model was explored. Overall, the self-built deep learning models combined with near-infrared hyperspectral images in the determination of rice seed vigor have potential to efficiently perform this task.

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.

Valorization of American Barrel-Shoot Wastes: Effect of Post Fermentative Addition and Readdition on Phenolic Composition and Chromatic Quality of Syrah Red Wines

The influence of post fermentative addition of American barrel-shoot wastes on phenolic composition and chromatic quality of Syrah red wines has been evaluated as an environmentally sustainable alternative to the conventional winemaking for avoiding the common color loss of red wines elaborated in warm climates. American oak wood byproducts added were previously classified by hyperspectral image analysis according to the amount of phenolic compounds transferred to the extraction media. After that, wines were elaborated under different maceration conditions by applying only one proportion of wood (12 g L^-1) and two different maceration procedures (simple and double addition) and were compared with a traditionally macerated Syrah red wine (CW, no wood addition). Results proved the effectiveness of the moderate postfermentative addition of oak wood byproducts to stabilize the color of wines and to provoke lower color modification along the time, producing color wines chromatically more stable for a better aging. In the case of double addition, the adsorption of the pigments during the maceration presents a stronger effect on the color than copigmentation and polymerization by cause of the copigments extracted from the wood.

Identification of antibiotic mycelia residues in cottonseed meal using Fourier transform near-infrared microspectroscopic imaging

Near-infrared microscopy (NIRM) technology can analyze different components within a sample while also obtaining spatial information about the sample. No rapid detection methods are available for effectively identifying antibiotic mycelia residues (AMRs) in protein feeds materials to date. In this study, the feasibility of using NIRM to identify AMRs (oxytetracycline residue, streptomycin sulfate residue and clay colysin sulfate residue) mixed in cottonseed meals was studied. The samples were scanned by NIRM, then the spectra of images were analyzed by principal component analysis (PCA) to select characteristic bands for further identification with one-class partial least squares analysis (OCPLS). The results showed that: a) AMRs were effectively identified in cottonseed meal; b) screening characteristic bands and increasing the spectral number of the calibration set improved the identification results of the model; and c) the sensitivity, specificity, accuracy and class error of the method were 100%, 95.93%, 99.01% and 2.03%, respectively.

Potential of Cooperage Byproducts Rich in Ellagitannins to Improve the Antioxidant Activity and Color Expression of Red Wine Anthocyanins

Cooperage byproducts are an important source of phenolic compounds that could be used for wine technology applications. The effects of the addition of two types of oak wood shavings (American, AOW, and Ukrainian, UOW) on the antioxidant activity and color of red wine anthocyanins, in a wine model solution, were evaluated by spectrophotometric and colorimetric analyses. Phenolic compounds from shavings, mainly ellagitannins, were determined by ultra-high-performance liquid chromatography/mass spectrometry (UHPLC/MS). Antioxidant and copigmentation effects varied depending on the type of shavings (AOW and UOW) and the phenolic concentration (100, 400, and 500 mg/L). Phenolic compounds from shavings improved the color characteristics (darker and more bluish color) and the copigmentation effect of red wine anthocyanins, being UOW a better source of copigments than AOW shavings. The best antioxidant activity was found for the 400 and 500 mg/L model solutions for both types of shavings. Results show a winemaking technological application based on the repurposing of cooperage byproducts, which could improve color and antioxidant characteristics of red wines.

Impact of a post-fermentative maceration with overripe seeds on the color stability of red wines

With the purpose of modulating the copigmentation equilibria of red wines, an environmentally sustainable process was performed based on post-fermentative addition of overripe seeds (OS). Simple (SW) and double (DW) addition were performed to produce different enrichment of phenolics from seeds, hence different copigmentation/polymerization ratios. The determination of the phenolic composition showed different global increases in OS-macerates wines (catechin, epicatechin, gallic acid and procyanidins B1 and B2). The double post-maceration (DW) was more effective than the simple post-maceration addition to improve the phenolic structure of wines. The application of Differential Tristimulus Colorimetry could assess the effects of this practice on the color characteristics and stability of wines. Results highlighted that both simple and double assays underwent colorimetric improvements against the control wines (CW, no seeds addition). DW led to the highest chromatic stability, showing lower lightness, higher chroma values and bluish hues than CW. This color difference was visually detectable.

Potential of UV and SWIR hyperspectral imaging for determination of levels of phenolic flavour compounds in peated barley malt

In this study, ultra-violet (UV) and short-wave infra-red (SWIR) hyperspectral imaging (HSI) was used to measure the concentration of phenolic flavour compounds on malted barley that are responsible for smoky aroma of Scotch whisky. UV-HSI is a relatively unexplored technique that has the potential to detect specific absorptions of phenols. SWIR-HSI has proven to detect phenols in previous applications. Support Vector Machine Classification and Regression was applied to classify malts with ten different concentration levels of the compounds of interest, and to estimate the concentration respectively. Results reveal that UV-HSI is at its current development stage unsuitable for this task whereas SWIR-HSI is able to produce robust results with a classification accuracy of 99.8% and a squared correlation coefficient of 0.98 with a Root Mean Squared Error of 0.32 ppm for regression. The results indicate that with further testing and development, HSI may potentially be exploited in an industrial production environment.