Search

Gastrodia elata Blume (Tianma) is widely cultivated and consumed as a food and herbal material in China. With its increasing use as a functional food, Tianma is gaining popularity in the market. However, during the cultivation process, the harvest time affects its maturity and storage time, while the total content of gastrodin (GAS) and p -hydroxybenzyl alcohol (HA) affects its nutritional value, making it difficult to control the quality of Tianma. In this study, a combination of visible-near-infrared (Vis-NIR) spectroscopy and chemometrics was used to identify the harvest time and determine the quality indicator content. A Vis-NIRRamanNet modeling method based on the architecture of RamanNet was proposed and compared with harvest time discrimination models constructed using partial least squares discriminant analysis (PLS-DA), k-nearest neighbor (KNN), support vector machine (SVM), and one-dimensional convolutional neural network (1D-CNN). The results demonstrated that Vis-NIRRamanNet exhibited superior performance, achieving accuracy rates of 0.995 and 0.973 on the training and testing sets, respectively. Subsequently, Vis-NIR spectroscopy combined with support vector regression (SVR) was employed for quantitative analysis of quality indicator content. Wavelength selection methods such as uninformative variable elimination (UVE), genetic algorithm (GA), and competitive adaptive reweighted sampling (CARS) were utilized to optimize the model. The results indicated that the CARS-SVR model provided the best prediction of quality indicator content, with root mean square error of prediction (RMSEP) and coefficient of determination (R p 2) values of 0.257 and 0.901, respectively. Therefore, the combination of Vis-NIR spectroscopy and chemometrics shows significant potential in assisting the selection of high-quality Tianma. • Vis-NIR discriminates harvest time and predicts quality indicator contents. • An improved modeling method, Vis-NIRRamanNet, was developed. • Predictions by Vis-NIRRamanNet have superiority in discrimination models. • Exploring the optimization potential of wavelength selection methods in SVR models. [ABSTRACT FROM AUTHOR]

The present study investigated the feasibility of visible near-infrared (Vis-NIR) spectroscopy method as a low-cost, quick and reliable method for the prediction of qualitative characteristics (fruit juice percentage, soluble solids, acidity, taste index and vitamin C) of an export variety of Persian pomegranate. For this purpose, pomegranate samples were first analyzed by Vis-NIR spectroscopy, followed by destructive reference methods for quality determination. Subsequently, the data from Vis-NIR were evaluated with different pre-processing methods, among which the combination of the Savitzky–Golay (SG) smoothing model and standard normal variation (SNV) normalization model, generates the best outcomes in predicting six desired qualitative characteristics by partial least square regression (PLSR) model. Fruit juice percentage and pH presented the best prediction models with a correlation coefficient (r P) of 0.98 for both, and root mean square errors of prediction (RMSEP) equal to 0.036 and 0.041, respectively. The values of r p for all desired parameters in this study were higher than 0.95, which pointed to the excellent accuracy of the PLSR models in the prediction of pomegranate qualitative features. It can be concluded from the present study that, Vis-NIR spectroscopy using the PLSR model as a non-destructive functional approach is capable of verifying the quality of Persian export variety pomegranate as an online technique with the aim of grading products before the export phase in order to augment the product marketability. [Display omitted] • Twelve quality parameters of fruit determined through destructive tests. • The most important quality parameters were selected for non-destructive prediction. • Vis-NIR was able to predict selected quality parameters with excellent accuracy. • The fruit juice percentage was predicted for the first time as a quality parameter. • The proposed method can be utilized in the grading stage prior to the export phase. [ABSTRACT FROM AUTHOR]

Deoxynivalenol (DON) contamination of wheat grains is a serious problem in China, and it is necessary to remove contaminated wheat before it enters the consumer market. In this study, visible-near infrared (Vis-NIR) spectroscopy and computer vision techniques were combined to simulate online discrimination between normal and DON-contaminated wheat grains. Naturally growing wheat samples were collected from several of the main wheat-producing areas in China, the reference DON contents were measured by using liquid chromatography serial triple quadrupole mass spectrometer (LC-MS), and then wheat samples were divided into two categories according to the national standard of 1 mg kg−1. The characteristic spectral variables, colour and texture features were extracted and integrated for chemometric analysis. Principal component analysis based on fusion features indicated better clustering than with just spectral features. Subsequently, linear discriminant analysis modelling based on spectra and texture features achieved the best discrimination with an accuracy of 95.06% and 91.36% for calibration and validation sets respectively, which was 5% higher than with just spectral features, and the false positive rates (FPR) were the lowest: 3.41% and 10.42% for calibration and validation sets respectively. The internal scanning results of whole wheat flour indicated that the higher the content of DON, the looser the binding of starch granules, which could cause the textural change of wheat grains. The research showed that Vis-NIR spectroscopy combined with computer vision has the potential to be used in the non-destructive and online detection of DON-contaminated wheat grains; further study on the interference from complex environments is still need for actual online detection. • Vis-NIR spectroscopy and computer vision techniques were combined. • Spectral, texture, colour features were extracted and integrated for chemometric analysis. • Dynamically discrimination of the DON contaminated and normal wheat grains. • Naturally growing wheat grains were collected as samples. • Models based on integrated features provided more accurate discrimination results. [ABSTRACT FROM AUTHOR]

The aim of this research was to examine the potential of visible and near infrared (Vis–NIR) spectroscopy for the prediction and mapping of sand and clay fractions of soils in one irrigated field having clay texture in Karacabey district of Bursa Province, Turkey. Eighty six soil samples, collected from the study area, were divided into calibration (80%) and validation (20%) sets. A partial least squares regression (PLSR) with leave-one-out cross-validation analysis was carried out using the calibration set, and the resulting model prediction ability was tested using the prediction set. Models developed were used to predict sand and clay content using laboratory spectra and spectra collected on-line from the field. Results showed an "excellent" laboratory prediction performance for both sand (regression coefficient (R 2) = 0.90, root mean square error of prediction (RMSEP) = 2.91% and ratio of prediction deviation (RPD) = 3.25 in cross-validation; R 2 = 0.81, RMSEP = 3.84% and RPD = 2.33 in the prediction set) and clay (R 2 = 0.91, RMSEP = 2.67% and RPD = 3.51 in cross validation; R 2 = 0.85, RMSEP = 3.40% and RPD = 2.66 in the prediction set). On-line predictions were less accurate than the laboratory results, although the on-line predictions were still very good (RPD = 2.25–2.31). Kappa statistics showed reasonable similarities between measured and predicted maps, particularly for those obtained with laboratory scanning. This study demonstrated that soil sand and clay can be successfully measured and mapped using Vis–NIR spectroscopy under both laboratory and on-line scanning conditions. Highlights • Vis–NIR spectroscopy evaluated for determining sand and clay content in field soil. • Successfully determined and mapped sand and clay content. • Vis–NIR-predicted maps showed significant similarity to lab-measured maps. • Spectroscopy could be extended to on-line measurement of sand and clay content. [ABSTRACT FROM AUTHOR]

Hyperspectral imaging (HSI) techniques using a newly-developed frame camera were applied to determine internal properties of mango fruits including firmness, total soluble solids (TSS) and titratable acidity (TA). Prediction models were developed using spectral data from relative surface reflectance of 160 fruits in the visible and near infrared (vis/NIR) region of 450–998 nm analysed by PLS regression. For data reduction, MLR analysis showed 16 significant factors for firmness, 17 for TA, and 20 for TSS. The results of MLR did not substantially affect the prediction performance as compared to PLS. An original approach with combined chemometric and HSI data analyses was applied using R programming. Significant correlations were found between HSI data and firmness (R 2 = 0.81 and RMSE = 2.83 N) followed by TA (R 2 = 0.81 and RMSE = 0.24%) and TSS (R 2 = 0.5 and RMSE = 2.0%). Prediction maps of physicochemical qualities were achieved by applying the prediction models to each pixel of HSI to visualise their spatial distribution. The variation of firmness, TSS, and TA within the fruit indicated fruit ripening started from shoulder toward to tip part. From these results, HSI can be used as a non-destructive technique for determining the quality of fruits which could potentially enhance grading capabilities in the industrial handling and processing of mango. [ABSTRACT FROM AUTHOR]

It is widely known that the visible and near infrared (VIS-NIR) spectroscopy has the potential of estimating soil total nitrogen (TN), organic carbon (OC) and moisture content (MC) due to the direct spectral responses these properties have in the near infrared (NIR) region. However, improving the prediction accuracy requires advanced modelling techniques, particularly when measurement is planned for fresh (wet and un-processed) soil samples. The aim of this work is to compare the predictive performance of two linear multivariate and two machine learning methods for TN, OC and MC. The two multivariate methods investigated included principal component regression (PCR) and partial least squares regression (PLSR), whereas the machine learning methods included least squares support vector machines (LS-SVM), and Cubist. A mobile, fibre type, VIS-NIR spectrophotometer was utilised to collect soil spectra (305–2200 nm) in diffuse reflectance mode from 140 wet soil samples collected from one field in Germany. The results indicate that machine learning methods are capable of tackling non-linear problems in the dataset. LS-SVMs and the Cubist method out-performed the linear multivariate methods for the prediction of all three soil properties studied. LS-SVM provided the best prediction for MC (root mean square error of prediction (RMSEP) = 0.457% and residual prediction deviation (RPD) = 2.24) and OC (RMSEP = 0.062% and RPD = 2.20), whereas the Cubist method provided the best prediction for TN (RMSEP = 0.071 and RPD = 1.96). [ABSTRACT FROM AUTHOR]

This study was undertaken to investigate the application of visible and near infrared (vis–NIR) spectroscopy for determining soil cation exchange capacity (CEC) under laboratory and on-line field conditions. Measurements were conducted in two fields with clay texture in field 1 (F1) and clay-loam texture in field 2 (F2) both in Turkey. Partial least squares (PLS) regression analyses with full cross-validation were carried out to establish CEC models using three datasets of F1, F2 and F1 + F2. Analytically-measured, laboratory vis–NIR and on-line vis–NIR predicted maps were produced and compared statistically by kappa coefficient. Results of the CEC prediction using laboratory vis–NIR data gave good prediction results, with averaged r 2 values of 0.92 and 0.72, root mean squared errors of prediction (RMSEP) of 1.89 and 1.54 cmol kg −1 and residual prediction deviations (RPD) of 3.69 and 1.89 for F1 and F2, respectively. Less successful predictions were obtained for the on-line measurement with r 2 of 0.75 and 0.7, RMSEP of 4.79 and 1.76 cmol kg −1 and RPD of 1.45 and 1.56 for F1 and F2, respectively. Comparisons using kappa statistics test indicated a significant agreement (κ = 0.69) between analytically-measured and laboratory vis–NIR predicted CEC maps of F1, while poorer agreement was found for F2 (κ = 0.43). A moderate spatial similarity was also found between analytically-measured and on-line vis–NIR predicted CEC maps in F1 (κ = 0.50) and F2 (κ = 0.49). This study suggests that soil CEC can be satisfactorily analysed using vis–NIR spectroscopy under laboratory conditions and with somewhat less precision under on-line scanning conditions. [ABSTRACT FROM AUTHOR]

Identifying the geographic origin of peaches will not only help producers obtain higher economic benefits, but also enable consumers to buy the most satisfactory fruits. In this study, the feasibility of distinguishing the geographic origin of four traditional famous peaches in China by visible-near infrared spectroscopy, fluorescence spectroscopy and image processing technology was explored. Visible-near infrared spectra and fluorescence spectra of 397–1175 nm and color characteristics extracted from images were used to establish the support vector machine, k-nearest neighbor, random forest and extreme learning machine classification models. The factors most related to the geographic origin were found by decision tree analysis. The results showed that the support vector machine models had the highest classification accuracy, some reaching 100%. In order to improve the calculation speed, the spectral principal components were used, resulting in the accuracy of support vector machine, k-nearest neighbor and random forest models more than 95%. The decision tree showed that R value, the first principal component of fluorescence spectra and H value played a decisive role in identifying the geographic origin, leading to the accuracy of support vector machine, k-nearest neighbor and random forest models more than 95%. This study compared the advantages and disadvantages of visible-near infrared spectroscopy, fluorescence spectroscopy and image processing technology in identifying geographic origin, and found that the combination of these three methods could effectively distinguished the geographic origin of peaches. • The quality attributes of peaches from different geographic origins were compared. • Three non-destructive methods were compared in identifying the geographic origins. • The SVM models based on spectral and image data had the highest accuracy. • Three factors most related to geographic origin of peaches were found. [ABSTRACT FROM AUTHOR]

Abstract: Various α-Fe2O3 haematite samples were synthesized by precipitation routes (under standard or hydrothermal conditions) followed by thermal treatments under air. The trigonal distortion (C 3 v point group) of the Fe3+ octahedral sites, which depends on the synthesis route and thermal treatment, was investigated by X-ray diffraction, Mössbauer spectroscopy and visible–near infrared (Vis–NIR) spectroscopy. The correlation between diffuse reflectance spectra and structural features of the haematite samples is reported and discussed herein. The slight increase of the average distortion of the Fe3+ octahedral sites, which depends on the annealing temperature of the precipitated sample, directly linked to the crystallite size, contrasts with the larger reduction of the sites distortion for the compound prepared by hydrothermal route due to the occurrence of hydroxyl groups substituted for O2− anions as well as Fe3+ cationic vacancies. On a local point of view, as shown by Mössbauer spectroscopy, the Fe3+ octahedral sites distortion decreases from the centre towards the surface of the grains. Then the smaller the grain size, the lower the average site distortion. Finally, the reduction of the octahedral distortion was directly correlated to the two Fetransfer bands in the visible range and the colour of as-prepared haematites. [Copyright &y& Elsevier]

Tea plants that have a large leaf area mainly suffer from heavy metal accumulation in the above-ground parts through foliar uptake. With the world rapid industrialization, this pollution in tea is considered a crucial challenge due to its potential health risks. The present study proposes an innovative approach based on visible and near-infrared (Vis-NIR) spectroscopy coupled with chemometrics for the characterization of tea chemical indicators under airborne lead stress, which can be performed fast and in situ. The effects of lead stress on chemical indicators and accumulation in leaves of the two tea varieties at different time intervals and levels of treatment were investigated. In addition, changes in cell structure and leaf stomata were monitored during foliar uptake of aerosol particles by transmission electron microscopy (TEM) and scanning electron microscopy (SEM). The spectral variation was able to classify the tea samples into the Pb treatment groups through the linear discriminant analysis (LDA) model. Two machine learning techniques, namely, partial least squares (PLS) and radial basis function neural network (RBFNN), were evaluated and compared for building the quantitative determination models. The RBFNN models combined with correlation-based feature selection (CFS) and PLS data compression methods were used to optimize the prediction performance. The results demonstrated that the PLS–RBFNN as a non-linear model outperformed the PLS model and provided the R-value of 0.944, 0.952, 0.881, 0.937, and 0.930 for prediction of MDA, starch, sucrose, fructose, glucose, respectively. It can be concluded that the proposed approach has strong application potential in monitoring the quality and safety of plants under airborne heavy metal stress. [Display omitted] • Effects of Pb pollution on tea quality and safety were explored by Vis-NIR spectra. • Leaf microstructure changes during uptake of atmospheric aerosols were studied. • Spectral differences can distinguish samples into airborne Pb treatment groups. • PLS–RBFNN performed better than PLS in predicting the chemical indicators of tea. • The spectra coupled with nonlinear models yielded high accuracy for Pb monitoring. [ABSTRACT FROM AUTHOR]

The composition of Solar System surfaces can be inferred through reflectance and emission spectroscopy, by comparing these observations to laboratory measurements and radiative transfer models. While several populations of objects appear to be covered by sub-micrometre sized particles (D < 1 μm) (referred to as hyperfine), there are limited studies on reflectance and emission of particulate surfaces composed of particles smaller than the visible and infrared wavelengths. We have undertaken an effort to determine the reflectance of hyperfine particulate surfaces in conjunction with high-porosity, in order to simulate the physical state of cometary surfaces and their related asteroids (P- and D-types). In this work, we present a technique developed to produce hyperfine particles of astrophysical relevant materials (silicates, sulphides, macromolecular organics). This technique is used to prepare hyperfine powders that were measured in reflectance in the 0.4–2.6 μm range. These powders were then included in water ice particles, sublimated under vacuum, in order to produce a hyperporous sample of hyperfine material (refers as to sublimation residue). When grinded below one micrometre, the four materials studied (olivine, smectite, pyroxene and amorphous silica), show strong decrease of their absorption features together with a blueing of the spectra. This "small grain degeneracy" implies that surfaces covered by hyperfine grains should show only shallow absorption features if any (in the case of moderately absorbing particles as studied here). These two effects, decrease of band depth and spectral blueing, appear magnified when the grains are incorporated in the hyperporous residue. We interpret the distinct behaviour between hyperporous and more compact surfaces by the distancing of individual grains and a decrease in the size of the elemental scatterers. This work implies that hyperfine grains are unabundant at the surfaces of S- or V-type asteroids, and that the blue nature of B-type may be related to a physical effect rather than a compositional effect. • A protocol for production of sub-μm grains in hyperporous surfaces was developed • Reflectance of sub-μm grains shows attenuated absorptions and blue spectral slope • Increasing porosity of a surface of sub-μm grains increases these spectral effects • Consequently, spectra of primitive bodies need to be interpreted with caution [ABSTRACT FROM AUTHOR]