RPD Values Research Articles

Regression prediction of tobacco chemical components during curing based on color quantification and machine learning

Color is one of the most important indicators to characteristic the quality of tobacco, which is strongly related to the variations of chemical components. In order to clarify the relationship between the changes of tobacco color and chemical components, here we established several prediction models of chemical components with the color values of tobacco based on machine learning algorithms. The results of correlation analysis showed that tobacco moisture content was highly significantly correlated with the parameters such as a*, H* and H°, the reducing sugar and total sugar content of tobacco was significantly correlated with the color values, and the starch content was highly significantly correlated with the color values except for b* and C*. The random forest models performed best in predicting tobacco moisture, reducing sugar, total sugar and starch constructed with the R2 of the model validation set was higher than 0.90, and the RPD value was greater than 2.0. The consistent between the predictions and measurements verified the availability and feasibility using color values to predict some chemical components of the tobacco leaves with high accuracy, and which has distinct advantages and potential application to realize the real-time monitoring of some chemical components in the tobacco curing process.

NIR spectroscopy prediction model for capsaicin content estimation in chilli: A rapid mining tool for trait-specific germplasm screening

Chilli is a widely produced crop, highly valued for its capsaicin content, a key economic trait. Traditional wet chemistry methods for estimating capsaicin are time-taking and laborious, while non-destructive methods like NIRS coupled with chemometrics, offer efficient alternatives, simplifying and accelerating biochemical assessments. This study is the first to develop and validate and tested for applicability of NIRS-based prediction model for capsaicin content in Indian chilli germplasm using MPLS regression. Various mathematical treatments were performed, and the most suited model was selected based on high RSQexternal, RPD and lower SEP values in the external validation set, indicating strong prediction accuracy and minimal error. The model achieved high RSQexternal value of 0.808, RPD value of 2.088 and low SEP value of 3.415 for capsaicin content, demonstrating excellent prediction performance. A paired sample t-test p-value of 0.757 (p > 0.05) showed non-significant difference between wet lab and predicted values, confirming the model’s accuracy. The applicability of the model was validated on fresh harvest germplasm the following year, showing a higher reliability score of 0.949, further confirming model’s reliability. This model would aid in high-throughput, accurate screening of chilli germplasm for capsaicin, accelerating chilli crop improvement programs and the development of new high-capsaicin varieties.

A Model for Fat Content Detection in Walnuts Based on Near-Infrared Spectroscopy

Near-infrared spectroscopy (NIR) is an efficient and accurate method for fat content detection in walnuts. ‘Wen 185’ walnut is grown in large quantities in southern Xinjiang, and its fat content is an important indicator for evaluating the intrinsic quality. The excessive pursuit of yield efficiency, combined with the neglect of quality, agricultural product safety and other factors, has led to the production of poor-quality walnuts. Moreover, research on predicting walnut kernel fat content based on near-infrared spectroscopy technology is rarely reported. Therefore, a technical framework for walnut kernel detection based on near-infrared spectroscopy and the technical standards for ‘Wen 185’ are urgently needed. After first optimizing the initial spectrum data using five preprocessing methods, we established separate prediction models for walnut kernel fat content based on either a back propagation neural network or a support vector regression (SVR) algorithm. The results show that the correction set and validation set coefficients of determination of the walnut kernel fat content prediction model using the back propagation neural network algorithm were 0.86 and 0.89, respectively, with root mean square errors of 1.56 and 1.58, and an RPD value of 2.57; the coefficients of determination for the calibration and validation sets of SVR were 0.90 and 0.83, respectively, with root mean square errors of 1.76 and 1.70, respectively, and an RPD value of 1.70. Thus, near-infrared spectroscopy can be used to establish a foundation for realizing the rapid detection of walnut kernel fat content.

Optimization of a tensile strength prediction model for compacted ribbons using NIR-HIS analysis

The tensile strength (TS) of compacted ribbon is a critical quality attribute in the roller compaction process that impacts the quality of the finished product. This study investigated the use of Near Infrared Hyperspectral Imaging Spectroscopy (NIR-HIS) technology for predicting TS of compacted ribbons, considering the effects of surface curvature, different spectral preprocessing methods, and variable selection methods on a predictive model based on Partial Least Squares regression (PLSr). The spectral preprocessing methods evaluated were Mean Centering (MC) and Standard Normal Variate (SNV). The variable selection methods were Filter by Regression Coefficient (REG), Variable Importance in Projection (VIP), Competitive Adaptive Reweighted Sampling (CARS), and Genetic Algorithm (GA). The results indicated that curved surfaces had no significant impact on the predictive performance of the model (p-value of 0.39 for RMSEP). The PLSr-CARS method, combined with MC spectral preprocessing, was successful in selecting and reducing the number of wavelengths from 182 to 5, as indicated by high values of R2pred and RPD, and a low RMSEP value (0.97, 5.75, and 7.60%, respectively). An MLR model using the 5 wavelengths was also developed, showing similar performance to the PLSr model. Both the MLR and PLSr models demonstrated high predictive accuracy and reliability. These models can perform well even when developed using only a few wavelengths, leading to significant reductions in processing time and measurement costs, making them valuable tools for quality control in the pharmaceutical industry.

Sentinel-2 Multispectral Satellite Remote Sensing Retrieval of Soil Cu Content Changes at Different pH Levels

With the development of multispectral imaging technology, retrieving soil heavy metal content using multispectral remote sensing images has become possible. However, factors such as soil pH and spectral resolution affect the accuracy of model inversion, leading to low precision. In this study, 242 soil samples were collected from a typical area of the Pearl River Delta, and the Cu content in the soil was detected in the laboratory. Simultaneously, Sentinel-2 remote sensing image data were collected, and two-dimensional and three-dimensional spectral indices were established. Constructing independent decision trees based on pH values, using the Successive Projections Algorithm (SPA) combined with the Boruta algorithm to select the characteristic bands for soil Cu content, and this was combined with Optuna automatic hyperparameter optimization for ensemble learning models to establish a model for estimating Cu content in soil. The research results indicated that in the SPA combined with the Boruta feature selection algorithm, the characteristic spectral indices were mainly concentrated in the spectral transformation forms of TBI2 and TBI4. Full-sample modeling lacked predictive ability, but after classifying the samples based on soil pH value, the R2 of the RF and XGBoost models constructed with the samples with pH values between 5.85 and 7.75 was 0.54 and 0.76, respectively, with corresponding RMSE values of 22.48 and 16.12 and RPD values of 1.51 and 2.11. This study shows that the inversion of soil Cu content under different pH conditions exhibits significant differences, and determining the optimal pH range can effectively improve inversion accuracy. This research provides a reference for further achieving the efficient and accurate remote sensing of heavy metal pollution in agricultural soil.

Potential of near-infrared spectroscopy (NIRS) for prediction of acrylamide formation in French fries in the potato breeding process

Breeding goals of potatoes for deep-frying purposes include high starch contents, good suitability for long-term storage, and low tendency to form reducing sugars as acrylamide precursors. Due to the extensive number of samples, an accurate analysis of acrylamide in French fries and its precursors in tubers is difficult to implement in the breeding process. Therefore, this study aimed to evaluate the suitability of NIRS measurements after minimal sample processing for the prediction of reducing sugar contents in the tubers or acrylamide contents in French fries. An external validation with more than 650 samples consisting of 194 potato genotypes resulted in a prediction accuracy of 51 % for acrylamide and 76 % for reducing sugar content. RPD values of less than 1.5 for acrylamide and between 1.64 and 2.23 for reducing sugar prediction rendered low medium to medium model quality. Nevertheless, acrylamide prediction models based on NIRS measurement of mashed tubers categorised over 80 % of unknown samples correctly as being below or above the European threshold value, indicating suitability as rapid test procedure in the breeding process.

An innovative variant based on generative adversarial network (GAN): Regression GAN combined with hyperspectral imaging to predict pesticide residue content of Hami melon

The rapid and non-destructive detection of pesticide residues in Hami melons plays substantial importance in protecting consumer health. However, the investment of time and resources needed to procure sample data poses a challenge, often resulting in limited data set and consequently leading insufficient accuracy of the established models. In this study, an innovative variant based on generative adversarial network (GAN) was proposed, named regression GAN (RGAN). It was used to synchronically extend the visible near-infrared (VNIR) and short-wave infrared (SWIR) hyperspectral data and corresponding acetamiprid residue content data of Hami melon. The support vector regression (SVR) and partial least squares regression (PLSR) models were trained using the generated data, and subsequently validate them with real data to assess the reliability of the generated data. In addition, the generated data were added to the real data to extend the dataset. The SVR model based on SWIR-HSI data achieved the optimal performance after data augmentation, yielding the values of Rp2, RMSEP and RPD were 0.8781, 0.6962 and 2.7882, respectively. The RGAN extends the range of GAN applications from classification problems to regression problems. It serves as a valuable reference for the quantitative analysis of chemometrics.

Performance Comparison of Two Portable Near-infrared Devices for Rapid Authentication of Aceh Aromatic Rice ‘Sigupai’

Sigupai rice, Indonesia local aromatic rice varieties grown in South-West region of Aceh, is highly valued for its fragrance and quality, making it susceptible to adulteration. This study compares the performance of two portable Near-infrared (NIR) devices, SCiO and NeoSpectra, for rapid authentication of Sigupai rice. We evaluated 86 samples for qualitative analysis (i.e. authentic vs adulterated rice) and 44 samples for quantitative analysis (i.e. the level of adulteration). For the qualitative analysis using partial least squares-discriminant analysis (PLS-DA), the best estimation model could differentiate authentic and adulterated samples with an accuracy, sensitivity, specificity, and false positive rates of 89.29%, 92.86%, 85.71% and 14.29% for the NeoSpectra and 97.44%, 100%, 94.87%, and 5.13% for the SCiO, respectively at the validation stage. For quantitative analysis using partial least squares-regression (PLS-R), the best estimation model could estimate the level of adulteration with a coefficient of determination (R²), RMSEP, RPD, and consistency values of 0.92, 1.50%, 5.93 and 100.69% for the NeoSpectra and 0.96, 1.31%, 6.83 and 104.78% for the SCiO. Both portable NIR devices could be used as a rapid analysis tool for the authenticity of Sigupai rice with high accuracy. However, in this study the SCiO device showed a better performance. Keywords: Portable NIR device, Authentication, Aromatic rice, Rapid analysis, Sigupai variety.

Determination of malathion content in sorghum grains using hyperspectral imaging technology combined with stacked machine learning models

The rapid and precise detection of pesticide residues remains a pressing safety issue in the food industry. In this study, a rapid method for analyzing pesticide residues in sorghum was developed, combining hyperspectral imaging (HSI) technology with stacking ensemble learning (SEL) models. The HSI spectral data were preprocessed using the multivariate scatter correction (MSC) algorithm. The gradient boosting decision tree (GBDT), extreme gradient boosting (XGBoost), light gradient boosting machine (LGBM), and categorical boosting (CatBoost) algorithms were employed to identify the feature wavelengths with high contributions to the predictive model, and the performances of SEL, GBDT, XGBoost, LGBM, and CatBoost to accurately predict the pesticide residues in sorghum samples were compared. The SEL model constructed using the characteristic wavelength selected by CatBoost has the best predictive performance, with RMSEP, RP2, and RPD values of 0.6940 mg/kg, 0.9798, and 7.029, respectively. The study demonstrated that the combination of HSI and SEL enabled the accurate analysis of pesticide residues in sorghum, providing a reference for the utilization of HSI methods to accurately measure the concentrations of pesticide residues in sorghum and other food products.

Discrimination of pressed sesame oil: A comparison study of non-targeted UV spectral fingerprints combined with different chemometric methods

This study explores the utilization of various chemometric analytical methods for determining the quality of pressed sesame oil with different adulteration levels of refined sesame oil using UV spectral fingerprints. The goal of this study was to provide a reliable tool for assessing the quality of sesame oil. The UV spectra of 51 samples of pressed sesame oil and 420 adulterated samples with refined sesame oil were measured in the range of 200–330 nm. Various classification and prediction methods, including linear discrimination analysis (LDA), support vector machines (SVM), soft independent modeling of class analogy (SIMCA), partial least squares regression (PLSR), support vector machine regression (SVR), and back-propagation neural network (BPNN), were employed to analyze the UV spectral data of pressed sesame oil and adulterated sesame oil. The results indicated that SVM outperformed the other classification methods in qualitatively identifying adulterated sesame oil, achieving an accuracy of 96.15%, a sensitivity of 97.87%, and a specificity of 80%. For quantitative analysis, BPNN yielded the best prediction results, with an R2 value of 0.99, RMSEP of 2.34%, and RPD value of 10.60 (LOD of 8.60% and LOQ of 28.67%). Overall, the developed models exhibited significant potential for rapidly identifying and predicting the quality of sesame oil.

Quantitative determination of oxides in cement raw meal based on near-infrared spectroscopy and hybrid feature selection strategy

Determining the content of components in cement raw meal is vital in Portland cement manufacturing. Near-infrared spectroscopy (NIRS)enables rapid, safe, and accurate quantitative analysis of the primary constituents of cement raw meal (CaO, SiO2, Al2O3, and Fe2O3), thereby assisting the cement industry in reducing the time delay in raw meal proportioning control and enhancing the quality of the raw meal. This study employed a hybrid feature selection strategy to identify effective feature points in the NIRS of raw meal samples. Effective feature points from the raw meal were integrated with partial least squares (PLS) to develop a regression model. Initially, NIRS data from raw meal samples were obtained using a Fourier NIR spectrometer. Subsequently, sample set partitioning based on joint X-Y distance (SPXY) was utilized to divide the samples into a calibration set (70 samples) and a validation set (22 samples). Next, A backward interval partial least squares (BiPLS) approach, along with various preprocessing algorithms, was then employed to initially screen the optimal waveband combinations of the NIRS. Within these combinations, effective feature points were further identified using competitive adaptive reweighted sampling (CARS), variable combined population analysis (VCPA) and weighted fusion variable space shrinkage approach (WFVSSA). Finally, we developed and compared PLS models based on the full spectrum and three hybrid feature selection methods. The results demonstrated that.WFVSSA offers a comprehensive assessment of wavelength importance, effectively preserving feature points while eliminating redundant information. BiPLS-WFVSSA-PLS outperformed BiPLS-CARS-PLS and BiPLS-VCPAPLS on the validation set, with R2, RMSEP, and RPD values of 0.8676, 0.1431, and 2.8129 for CaO; 0.9212, 0.1216, and 3.6461 for SiO2; 0.9198, 0.0607, and 3.5618 for Al2O3; and 0.8717, 0.0166, and 2.8614 for Fe2O3, respectively. These findings underscore the superior accuracy and stability of BiPLS-WFVSSA-PLS in determining cement raw meal component contents.

Glycogen Quantification and Gender Identification in Di-, Tri-, and Tetraploid Crassostrea gigas Using Portable Near-Infrared Spectroscopy.

Near-infrared spectroscopy (NIR) has become an essential tool for non-destructive analysis in various fields, including aquaculture. This study presents a pioneering application of portable NIR spectrometers to analyze glycogen content in the gonadal tissues of the Pacific oyster (Crassostrea gigas), marking the first instance of developing quantitative models for glycogen in tetraploid C. gigas. The research also provides a comparative analysis with models for diploid and triploid oysters, underscoring the innovative use of portable NIR technology in aquaculture. Two portable NIR spectrometers were employed: the Micro NIR 1700 (908-1676 nm) and the Micro PHAZIR RX (1624-2460 nm). Near-infrared spectra were acquired from the gonadal tissues of diploid, triploid, and tetraploid C. gigas. Quantitative models for glycogen content were developed and validated using cross-validation methods. Additionally, qualitative models for different ploidies and genders were established. For the Micro NIR 1700, the cross-validation correlation coefficients (Rcv) and cross-validation relative predictive errors (RPDcv) for glycogen were 0.949 and 3.191 for diploids, 0.915 and 2.498 for triploids, and 0.902 and 2.310 for tetraploids. The Micro PHAZIR RX achieved Rcv and RPDcv values of 0.781 and 2.240 for diploids, 0.839 and 2.504 for triploids, and 0.717 and 1.851 for tetraploids. The Micro NIR 1700 demonstrated superior quantitative performance, with RPD values exceeding 2, indicating its effectiveness in predicting glycogen content across different ploidy levels. Qualitative models showed a performance index of 91.6 for diploid and 95 for tetraploid genders using the Micro NIR 1700, while the Micro PHAZIR RX achieved correct identification rates of 99.79% and 100% for diploid and tetraploid genders, respectively. However, differentiation of ploidies was less successful with both instruments. This study's originality lies in establishing the first quantitative models for glycogen content in tetraploid C. gigas using portable NIR spectrometers, highlighting the significant advancements in non-destructive glycogen analysis. The applicability of these findings is substantial for oyster breeding programs focused on enhancing meat quality traits. These models provide a valuable phenotyping tool for selecting oysters with optimal glycogen content, demonstrating the practical utility of portable NIR technology in aquaculture.

Application of artificial intelligence combined with near infrared spectroscopy in the continuous counter-current extraction process of Angelica dahurica formula granules

The establishment of near infrared (NIR) spectroscopy model mostly relies on chemometrics, and spectral analysis combined with artificial intelligence (AI) provides a new way of thinking for pharmaceutical quality inspection, new algorithms such as back propagation artificial neural networks (BP-ANN) and swarm intelligence optimization algorithms such as sparrow search algorithm (SSA) provide core technical support. In order to explore the application of AI in the pharmaceutical field, in this study, Angelica dahurica formula granules with a relatively complex system were selected as the research object. Quantitative analysis models were established by using partial least squares regression (PLSR) with a micro-NIR spectrometer, and BP-ANN modeling results were compared. For the best PLSR models of six characteristic components in the continuous counter-current extract of Angelica dahurica, R2v of imperatorin was lower than 0.90, and the RPD values of imperatorin, phellopterin, and isoimperatorin were even lower than 1. When the prediction model established by SSA-BP-ANN was used for quantitative analysis, R2v of six components were all higher than 0.92, and the RPD values all higher than 1.5, which proved that the BP-ANN method was better than PLSR. This study confirmed that in the continuous counter-current extraction progress of Angelica dahurica formula granules, the use of micro-NIR spectrometer combined with AI could realize the rapid prediction of the contents of six characteristic components. The comparison results provided a scientific reference for the process analysis and on-line monitoring in the production process of traditional Chinese medicine by micro-NIR spectrometer combined with AI.

Continental-scale mapping of soil pH with SAR-optical fusion based on long-term earth observation data in google earth engine

The advent of cloud computing platforms (e.g., Google Earth Engine (GEE)) and the massive amounts of optical and radar Earth Observation (EO) data hosted by these platforms present new opportunities for mapping soil pH at large scales. However, existing studies generally lack consensus on the effects of satellite and radar sensor parameters on GEE-based soil pH prediction models. In this study, we assessed the suitability of long-term radar (C-band Sentinel-1 and L-band PALSAR-1/2) and optical (Sentinel-2) EO data on GEE for the digital mapping of soil pH on a continental (Europe) scale and determined the most appropriate radar sensor parameters. Thirteen scenarios with different data configurations were simulated and combined with the 2018 LUCAS soil database and two machine learners (boosted regression trees and extreme gradient boosting) to develop soil prediction models. Results showed that the selection of modeling techniques, satellite sensors and radar system parameters largely affected the model output. Models involving a single polarization mode of PALSAR-1/2 data performed the worst (RPD = 1.24). Models based on Sentinel-1 data performed better than those built using PALSAR-1/2 data. The model performance was improved when a model involved more polarization bands, orbital directions, and band frequencies. The multiband model built using the two radar datasets achieved a comparable accuracy to the model based on optical data. Moreover, the model that fused radar-optical data achieved better results, with RPD values of 1.56 and 1.46 for the models with and without radar data, respectively; its performance was comparable to that of models built with commonly used variables (topography and climate). The analysis of importance indicated that long-term optical and radar EO data on GEE were important in our model. The modelling of soil pH at the continental scale largely benefits from GEE. The predicted maps exhibited strong spatial heterogeneity among different biogeographic regions, with similar spatial patterns under different modelling scenarios.

Potential of hyperspectral imaging for nondestructive determination of α-farnesene and conjugated trienol content in ‘Yali’ pear

The sesquiterpene α-farnesene and its corresponding oxidation products, namely conjugated trienols (CTols) is well known to be correlated with the development of superficial scald, a typical physiological disorder after a long term of cold storage in pear fruit. In this work, hyperspectral imaging (HSI) technology was used for nondestructive predicting of α-farnesene and CTols [CT258, CT281 and CT(281-290)] content in ‘Yali’ pear. In order to obtain the best performance of calibration model and simplify the calibration model further, various preprocessing methods together with their combinations and different wavelength selection algorithms, including successive projections algorithm (SPA), competitive adaptive reweighted sampling (CARS) and uninformative variable elimination (UVE), were investigated and compared based on linear partial least square regression (PLSR) and nonlinear least square support vector machine (LS-SVM) models, respectively. In conclusion, compared to the PLSR models, the results of LS-SVM models based on original and preprocessing methods performed better for the prediction of α-farnesene and CTols, while the performance of LS-SVM models based on the selected characteristic wavelengths were worse. For α-farnesene, the best result was obtained by LS-SVM model based on MSC-FD pretreatment with the RPD value of 2.6, Rp = 0.925 and RMSEP = 4.387 nmol cm−2. And for CTols, CT281 performed better compared with CT258 and CT(281-290), achieving the result with RPD = 2.4, Rp = 0.913 and RMSEP = 2.734 nmol cm−2 based on LS-SVM model combined with SD pretreatment. The overall results illustrated HSI technology could be used for rapid and nondestructive prediction of α-farnesene and CTols in ‘Yali’ pear, which would be helpful for supporting postharvest decision systems.

Estimation of human bloodstains time since deposition using ATR-FTIR spectroscopy and chemometrics in simulated crime conditions

Blood in the form of stains is one of the most frequently encountered fluid in crime scene. Estimation of the time since deposition (TSD) is of great importance to guide the police investigation and the clarification of criminal offences. The time elapsed since deposition is usually estimated by modelling the physicochemical degradation of blood biomolecules over time. This work shows an ATR-FTIR spectroscopy and chemometrics study to estimate TSD of bloodstains on various surfaces and under different ambient conditions (indoor and outdoor). For a period from 0 to 212 days, a total of 960 stains were analyzed. Most of the eleven partial least squares regression (PLSR) models obtained showed a good prediction capacity, with a Residual Predictive Deviation (RPD) value higher than 3, and R2 higher than 0.90. Models for non-rigid supports showed better predictive capacity than those for rigid ones. A non-rigid surface model including the various non-rigid surfaces and ambient conditions was elaborated, which might be the most useful one from the criminalistic point of view. These results show that this technique can be a rapid, robust, and trustable tool for in situ determination of the TSD of bloodstains at crime scenes.

Estimating Soil Erodible Fraction Using Multivariate Regression and Proximal Sensing Data in Arid Lands, South Egypt

Estimating soil erodible fraction based on basic soil properties in arid lands is a valuable research topic in the field of soil science and land management. The Proximal Sensing (PS) technique offers a non-destructive and efficient method to assess wind erosion potential in arid regions. By using Partial Least Squares Regression (PLSR) and Support Vector Machine (SVM) models and combining soil texture and chemical properties, determined through Visible-Near Infrared (vis-NIR) spectroscopy in 96 soil samples, this study aims to predict soil erodibility, soil organic matter (SOM), and calcium carbonate equivalent (CaCO3) in arid lands located in Elkobaneyya Valley, Aswan Governorate, Egypt. Results showed that the soil erodibility fraction (EF-Factor) had the highest values and possessed a strong relationship between slope and SOM of 0.01% in determining soil erodibility. The PLSR model performed better than SVM for estimating SOM, CaCO3, and EF-Factor. Furthermore, the results showed that the spectral responses of CaCO3 were observed in separate places in the wavelengths of 570, 649, 802, 1161, 1421, 1854, and 2362 nm, and the wavelengths with SOM parameter were 496, 658, 779, 1089, 1417, 1871, and 2423 nm. The EF-factor shows the highest significant correlation with spectral reflectance values at 526, 688, 744, 1418, 1442, 2292, and 2374 nm. The accuracy and performance of the PLSR model in estimating the EF-Factor using spectral reflectance data and the distribution of data points for both the calibration and validation data-sets indicate a good accuracy of the PLSR model, with RMSE values of 0.0921 and 0.0836 Mg h MJ−1 mm−1, coefficient of determination (R2) values of 0.931 and 0.76, and RPD values of 2.168 and 2.147, respectively.

Fast detection of moisture content and freshness for loquats using optical fiber spectroscopy.

Detection of the moisture content (MC) and freshness for loquats is crucial for achieving optimal taste and economic efficiency. Traditional methods for evaluating the MC and freshness of loquats have disadvantages such as destructive sampling and time-consuming. To investigate the feasibility of rapid and non-destructive detection of the MC and freshness for loquats, optical fiber spectroscopy in the range of 200-1000 nm was used in this study. The full spectra were pre-processed using standard normal variate method, and then, the effective wavelengths were selected using competitive adaptive weighting sampling (CARS) and random frog algorithms. Based on the selected effective wavelengths, prediction models for MC were developed using partial least squares regression (PLSR), multiple linear regression, extreme learning machine, and back-propagation neural network. Furthermore, freshness level discrimination models were established using simplified k nearest neighbor, support vector machine (SVM), and partial least squares discriminant analysis. Regarding the prediction models, the CARS-PLSR model performed relatively better than the other models for predicting the MC, with R 2 P and RPD values of 0.84 and 2.51, respectively. Additionally, the CARS-SVM model obtained superior discrimination performance, with 100% accuracy for both calibration and prediction sets. The results demonstrated that optical fiber spectroscopy technology is an effective tool to fast detect the MC and freshness for loquats.

Rapid non-destructive evaluation of texture properties changes in crispy tilapia during crispiness using hyperspectral imaging and data fusion

In this study, two distinct hyperspectral imaging systems, the Visible and Near-Infrared Spectroscopy (VNIR) and the Short-Wave Infrared Spectroscopy (SWIR), were employed in combine with chemometric techniques to examine the alterations in the texture properties (hardness, resilience, chewiness, and cohesiveness) of tilapia during the crispy process. Partial least squares regression (PLSR) was used to establish a linear relationship between the spectral reflectance values and the different texture parameters of tilapia, and various preprocessing, variable selection, and data fusion (Low-Level Fusion (LLF) and Mid-Level Fusion (MLF)) methods were considered to optimize the calibration model. For hardness, with RP, RMSEP, %RMSEP and RPD values of 0.63, 5.84, 21.65% and 1.26 respectively. For resilience, the LLF presented superior performance, with RP, RMSEP, %RMSEP and RPD values of 0.92, 0.03, 6.8% and 2.52 respectively. For chewiness, the MLF presented superior performance, with RP, RMSEP, %RMSEP and RPD values of 0.68, 4.03, 23.05% and 1.36. For cohesiveness, the MLF exhibited the best performance, with RP, RMSEP, %RMSEP and RPD values of 0.82, 0.03, 4.85% and 1.65 respectively. It was demonstrated that the fusion of both hyperspectral datasets provides a promising method for non-destructive texture measurement of tilapia at different stages of crispiness.

Near-Infrared Spectroscopy Modeling of Combustion Characteristics in Chip and Ground Biomass from Fast-Growing Trees and Agricultural Residue

This study focuses on the investigation and comparison of combustion characteristic parameters and combustion performance indices between fast-growing trees and agricultural residues as biomass sources. The investigation is conducted through direct combustion in an air environment using a thermogravimetric analyzer (TGA). Additionally, partial least squares regression (PLSR)-based models were developed to assess combustion performance indices via near-infrared spectroscopy (NIRS), serving as a non-destructive alternative method. The results obtained through the TGA reveal that, specifically, fast-growing trees display higher average ignition temperature (227 °C) and burnout temperature (521 °C) in comparison to agricultural residues, which exhibit the values of 218 °C and 515 °C, respectively. Therefore, fast-growing trees are comparatively difficult to ignite, but sustain combustion over extended periods, yielding higher temperatures. However, despite fast-growing trees having a high ignition index (Di) and burnout index (Df), the comprehensive combustion performance (Si) and flammability index (Ci) of agricultural residue are higher, indicating the latter possess enhanced thermal and combustion reactivity, coupled with improved combustion stability. Five distinct PLSR-based models were developed using 115 biomass samples for both chip and ground forms, spanning the wavenumber range of 3595–12,489 cm−1. The optimal model was selected by evaluating the coefficients of determination in the prediction set (R2P), root mean square error of prediction (RMSEP), and RPD values. The results suggest that the proposed model for Df, obtained through GA-PLSR using the first derivative (D1), and Si, achieved through full-PLSR with MSC, both in ground biomass, is usable for most applications, including research. The model yielded, respectively, an R2P, RMSEP, and RPD, which are 0.8426, 0.4968 wt.% min⁻4, and 2.5; and 0.8808, 0.1566 wt.%2 min⁻2 °C⁻3, and 3.1. The remaining models (Di in chip and ground, Df, and Si in chip, and Ci in chip and ground biomass) are primarily applicable only for rough screening purposes. However, including more representative samples and exploring a more suitable machine learning algorithm are essential for updating the model to achieve a better nondestructive assessment of biomass combustion behavior.