Root Mean Square Error Of Prediction Research Articles

PROSAC as a selection tool for SO-PLS regression: A strategy for multi-block data fusion

BackgroundSpectral data from multiple sources can be integrated into multi-block fusion chemometric models, such as sequentially orthogonalized partial-least squares (SO-PLS), to improve the prediction of sample quality features. Pre-processing techniques are often applied to mitigate extraneous variability, unrelated to the response variables. However, the selection of suitable pre-processing methods and identification of informative data blocks becomes increasingly complex and time-consuming when dealing with a large number of blocks. The problem addressed in this work is the efficient pre-processing, selection, and ordering of data blocks for targeted applications in SO-PLS. ResultsWe introduce the PROSAC–SO–PLS methodology, which employs pre-processing ensembles with response-oriented sequential alternation calibration (PROSAC). This approach identifies the best pre-processed data blocks and their sequential order for specific SO-PLS applications. The method uses a stepwise forward selection strategy, facilitated by the rapid Gram-Schmidt process, to prioritize blocks based on their effectiveness in minimizing prediction error, as indicated by the lowest prediction residuals. To validate the efficacy of our approach, we showcase the outcomes of three empirical near-infrared (NIR) datasets. Comparative analyses were performed against partial-least-squares (PLS) regressions on single-block pre-processed datasets and a methodology relying solely on PROSAC. The PROSAC–SO–PLS approach consistently outperformed these methods, yielding significantly lower prediction errors. This has been evidenced by a reduction in the root-mean-squared error of prediction (RMSEP) ranging from 5 to 25 % across seven out of the eight response variables analyzed. SignificanceThe PROSAC–SO–PLS methodology offers a versatile and efficient technique for ensemble pre-processing in NIR data modeling. It enables the use of SO-PLS minimizing concerns about pre-processing sequence or block order and effectively manages a large number of data blocks. This innovation significantly streamlines the data pre-processing and model-building processes, enhancing the accuracy and efficiency of chemometric models.

An improved meteorological variables-based aerosol optical depth estimation method by combining a physical mechanism model with a two-stage model

A two-stage model integrating a spatiotemporal linear mixed effect (STLME) and a geographic weight regression (GWR) model is proposed to improve the meteorological variables-based aerosol optical depth (AOD) retrieval method (Elterman retrieval model-ERM). The proposed model is referred to as the STG-ERM model. The STG-ERM model is applied over the Beijing-Tianjin-Hebei (BTH) region in China for the years 2019 and 2020. The results show that data coverage increased by 39.0% in 2019 and 40.5% in 2020. Cross-validation of the retrieval results versus multi-angle implementation of atmospheric correction (MAIAC) AOD shows the substantial improvement of the STG-ERM model over earlier meteorological models for AOD estimation, with a determination coefficient (R2) of daily AOD of 0.86, root mean squared prediction error (RMSE) and the relative prediction error (RPE) of 0.10 and 36.14% in 2019 and R2 of 0.86, RMSE of 0.12 and RPE of 37.86% in 2020. The fused annual mean AOD indicates strong spatial variation with high value in south plain and low value in northwestern mountainous areas of the BTH region. The overall spatial seasonal mean AOD ranges from 0.441 to 0.586, demonstrating strongly seasonal variation. The coverage of STG-ERM retrieved AOD, as determined in this exercise by leaving out part of the meteorological data, affects the accuracy of fused AOD. The coverage of the meteorological data has smaller impact on the fused AOD in the districts with low annual mean AOD of less than 0.35 than that in the districts with high annual mean AOD of greater than 0.6. If available, continuous daily meteorological data with high spatiotemporal resolution can improve the model performance and the accuracy of fused AOD. The STG-ERM model may serve as a valuable approach to provide data to fill gaps in satellite-retrieved AOD products.

Comparison of qualitative and quantitative performance of two portable near-infrared spectrometers for intact Rehmanniae Radix and calibration transfer

As a Chinese herbal medicine with high medical value, Rehmanniae Radix (RR) has a wide variety of geographical origins leading to distinctly diverse quality, and moisture content during storage affects the critical active ingredient content. In this work, two portable near-infrared (NIR) spectrometers, DLP NIRscan Nano (DLP) and VIAVI MicroNIR 1700 (M1700) were used for in-situ spectral acquisition from intact RR. The partial least squares-discriminant analysis (PLS-DA) was employed for three geographical sources (Shandong, Shanxi, Henan). After multiple pre-processing and wavelength selection, the M1700-based PLS-DA model, accuracy (Acc), sensitivity (Sen), and specificity (Spe), achieved 100 % accuracy. In contrast, model predictions using the low-cost instrument (DLP) was not satisfactory. The partial least squares regression (PLSR) was applied to predict the moisture content of RR. The best correlation coefficients in the prediction set (R2p), Root Mean Square Error of Prediction (RMSEP), and residual prediction deviation (RPD) values (0.98, 0.98, 4.98) were obtained by DLP and were also employed for comparison with the M1700 model (0.99, 0.70, 7.00). Therefore, to further improve the model prediction effect of the low-cost DLP, we employed the improved principal component analysis (IPCA), direct standardization (DS), and piecewise direct standardization (PDS) calibration transfer techniques. Unequivocally, IPCA optimized the origin identification model (Acc, Sen, and Spe were all 1.00), the moisture content prediction model RPD was increased by 23 %, and its RMSEP was reduced by 18 %, leading to the improvement in prediction accuracy of the DLP model. This study provides a portable and low-cost detection method for the in-situ evaluation of the quality of RR quality and a feasible solution for the NIR techniques to be used in the rapid and accurate in-situ analysis of RR.

Data Fusion of Acoustic and Optical Emission from Laser-Induced Plasma for In Situ Measurement of Rare Earth Elements in Molten LiCl-KCl.

Molten salts have a significant potential for use as next-generation nuclear reactor coolants and in pyroprocessing for the recycling of used nuclear fuel. However, the molten salt composition needs to be known at all times, and high temperatures and intense ionizing radiation pose challenges for the monitoring instrumentation. Although the technique of laser-induced breakdown spectroscopy (LIBS) has been studied for in situ measurements of molten salts, trials to improve its monitoring accuracy using chemometrics are lacking. In this study, a data fusion technique using the LIBS optical and laser-induced acoustic (LIA) signals was investigated to enhance the measurement accuracy for molten salt monitoring. Prediction models were constructed using the partial least-squares method, and the variable importance in projection scores was analyzed to evaluate the effect of incorporating the LIA signal into the analysis. This study investigates rare earth elements Eu, Er, and Pr found not only in nuclear but also in other settings such as laser and magnetic materials. The analysis of LIBS data without data fusion resulted in a root-mean-square error of prediction (RMSEP) of 0.0774-0.0913 wt %, whereas the prediction model using data fusion led to approximately 18-40% enhanced RMSEP (0.0461-0.0679 wt %). The results suggest that fusing the LIBS data with the simultaneously recorded LIA data can improve the monitoring accuracy of rare earth element composition in molten salts.

A comparative study of acoustic and ultrasonic nondestructive testing for evaluating melon quality

Abstract Melon (Cucumis melo L.) is a high-value agricultural commodity known worldwide for its sweet taste and crisp flesh texture, which are important factors for quality and consumer acceptance. Unfortunately, quality testing and determining the optimal harvest time for achieving desired melon characteristics are traditionally performed through destructive methods. The aim of this study was to explore the potential of acoustic and ultrasonic tests for predicting the physicochemical properties of Honey Globe melons (Cucumis melo L. var. inodorus). A total of 100 melon samples were used in this study. For the nondestructive ultrasonic testing, attenuation values served as its variable, whereas in acoustic testing, variables included frequency, magnitude, short-term energy, and zero-moment. Fruit’s flesh firmness and total soluble solids (TSS) as physicochemical quality properties were determined using destructive tests. The calibration phase involved 80 melon samples, employing a K-Fold Cross Validation approach with ten folds, done on Partial Least Square Regression (PLS) modeling. Another 20 melon samples were used for blind testing. Reliability evaluation was done on key metrics, consisting of R2 values, RMSEC (Root Mean Square Error of Calibration), RMSECV (Root Mean Square Error of Cross-Validation), RMSEP (Root Mean Square Error of Prediction), and RPD (Ratio of Performance to Deviation). Analysis results on these metrics collectively support the conclusion that both ultrasonic and acoustic methods exhibit their potential to predict the firmness properties of melon fruits. The best evaluation result that has been conducted for the ultrasonic test uses attenuation, age, and density as predictors to predict fruit firmness, with R2 = 0.763 and RPD = 2.945, while the acoustic test achieved the best result with magnitude used as a predictor to predict fruit firmness with R2 = 0.718 and RPD = 2.230. However, evaluation metrics on the prediction of total soluble solids for both nondestructive tests were still not good enough for application with low R2 and RPD value.

Quantitative and qualitative detection of target heavy metals using anti-interference colorimetric sensor Array combined with near-infrared spectroscopy

An anti-interference colorimetric sensor array (CSA) technique was developed for the qualitative and quantitative detection of target heavy metals in corn oil. This method involves a binding mechanism that triggers changes in atomic energy levels and visible color changes. A custom-built olfactory visualization device was employed to gather spectral data, revealing distinct CSA color difference patterns. Subsequently, three pattern recognition algorithms were used to create an identification model for the target heavy metals. The results showed that the ACO-KNN (Ant Colony Optimization-K-Nearest Neighbor) model outperformed the other models, achieving accuracy rates of 90.28% and 89.58% for the calibration and prediction sets, respectively. The ACO-PLS (Partial Least Square) model was more stable with the lowest root mean square error of prediction (RMSEP), which were 0.1730 and 0.1180, respectively. The limit of detection (LOD) and quantification (LOQ) of Pb and Hg were (0.3, 0.6, 1.1 and 2.2) x 10−3 mg/L, respectively.

Incorporating empirical knowledge into data-driven variable selection for quantitative analysis of coal ash content by laser-induced breakdown spectroscopy

Laser-induced breakdown spectroscopy (LIBS) has become a widely used atomic spectroscopic technique for rapid coal analysis. However, the vast amount of spectral information in LIBS contains signal uncertainty, which can affect its quantification performance. In this work, we propose a hybrid variable selection method to improve the performance of LIBS quantification. Important variables are first identified using Pearson’s correlation coefficient, mutual information, least absolute shrinkage and selection operator (LASSO) and random forest, and then filtered and combined with empirical variables related to fingerprint elements of coal ash content. Subsequently, these variables are fed into a partial least squares regression (PLSR). Additionally, in some models, certain variables unrelated to ash content are removed manually to study the impact of variable deselection on model performance. The proposed hybrid strategy was tested on three LIBS datasets for quantitative analysis of coal ash content and compared with the corresponding data-driven baseline method. It is significantly better than the variable selection only method based on empirical knowledge and in most cases outperforms the baseline method. The results showed that on all three datasets the hybrid strategy for variable selection combining empirical knowledge and data-driven algorithms achieved the lowest root mean square error of prediction (RMSEP) values of 1.605, 3.478 and 1.647, respectively, which were significantly lower than those obtained from multiple linear regression using only 12 empirical variables, which are 1.959, 3.718 and 2.181, respectively. The LASSO-PLSR model with empirical support and 20 selected variables exhibited a significantly improved performance after variable deselection, with RMSEP values dropping from 1.635, 3.962 and 1.647 to 1.483, 3.086 and 1.567, respectively. Such results demonstrate that using empirical knowledge as a support for data-driven variable selection can be a viable approach to improve the accuracy and reliability of LIBS quantification.

Quality assessment of Gastrodia elata Blume (Tianma) based on Vis-NIR spectroscopy: Discrimination of harvest times and prediction of quality indicator contents

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 (Rp2) 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.

Impact of external moisture on quantitative analysis of coal and rapid drying by a CO2 laser to improve prediction accuracy based on laser induced breakdown spectroscopy.

For high-accuracy determination of ash, fixed carbon, and volatile matter in coal, generally, the impact of external moisture content in coal must be considered and removed in quantitative modeling based on laser-induced breakdown spectroscopy (LIBS). Herein, the ash, fixed carbon, and volatile of coals with moisture contents from 3% to 15% are quantitatively assessed using partial least squares based on principal component analysis (PCA-PLS), and the predictive limit of this model for moist coals is explored based on LIBS. To validate the industrial feasibility of the method, an infrared CO2 laser based heating technique is employed to rapidly dry the moist coals before laser ablation. The results demonstrate that root mean square error of prediction (RMSEP) of all ash, volatile carbon, and fixed carbon become higher with moisture content increase. Nevertheless, as the moisture content reaches 3%, the prediction model retains an acceptable predictive capability with mean absolute error (MAE) of ash, volatile matter, and fixed carbon of 1.85%, 1.5%, and 1.79%, respectively. When the IR laser for drying is employed to irradiating for 40 ms, external water in coal with an original moisture content of 15% can be quickly removed, resulting in a decrease in RMSEP of ash, volatile matter, and fixed carbon from 3.06%, 5.42%, and 6.22% to 1.47%, 3.16%, and 3.34%, respectively. This method provides a potential technical solution for the use of infrared laser-assisted LIBS real-time online rapid detection of indicators in raw coal with high moisture content.

Determination of time since deposition of bloodstains through NIR and UV–Vis spectroscopy – A critical comparison

Time elapsed since bloodstain deposition is a crucial aspect in forensic investigations, where non-destructive spectroscopic methods play a pivotal role. While extensive research has been conducted by UV–Vis spectroscopy, showcasing its utility in specific cases, there is still a paucity of studies based on NIR spectroscopy, which has the potential to overcome the limitations of the UV–Vis-based methods. To compensate for this disequilibrium, the present study aimed to evaluate the NIR applicability for estimating the age of forensic bloodstains and develop a performance comparison with UV–Vis spectroscopy methods. Capillary blood was sampled and subjected to a 16-day aging, during which it was repeatedly analyzed using both spectroscopic methods. Subsequently, chemometric analysis was applied to process the spectral data and independently assess the methods’ performance. Classical preprocessing transforms (i.e., Savitzky-Golay derivatives and SNV transform) were used together with more targeted strategies, such as class centering, whose benefit was highlighted by PCA. Lastly, PLS regression models were computed to evaluate the effectiveness of both spectroscopic methods in estimating the time elapsed since blood trace deposition. Comparable root mean square errors in prediction (RMSEP) – 40 and 55 h for UV–Vis and NIR spectroscopy, respectively – were observed for both techniques, featuring an improvement with respect to the existing literature for NIR spectroscopy. Data fusion strategies for a multi-instrumental platform were also explored, evaluating advantages and disadvantages of low-level and mid-level approaches. The results indicated that NIR spectroscopy integrated with adequate chemometric strategies deserves increased appreciation in forensic bloodstain dating.

Simple Method for Calcium Determination in Crude Oil Emulsion Using Digital Image Colorimetry

A portable device for digital image colorimetry (DIC) is reported for the determination of Ca in crude oil emulsions. ASTM D4807 was used for sample preparation for the isolation of saline species containing Ca. DIC was evaluated based on the complexation reactions with Ca using calcein, murexide, and calcon. Partial least squares (PLS) provided the best determination coefficients (higher than 0.990) for all complexing reagents. Significant interference of Mg was observed for the determination of Ca using calcein. PLS models with the lowest root mean square error of cross validation (RMSECV) values were obtained for murexide and calcon for a concentration of 0.250 mmol L−1 at pH of 13. The best conditions for camera focal length were 11 and 2 mm for murexide and calcon. For light intensity, the optimized conditions for murexide and calcon was 180 lux. Stabilities of color complexes over the time were 30 and 15 min for murexide and calcon, respectively. DIC/murexide provided the lowest root mean square error of prediction (RMSEP) and a linear response was observed from 0.5 to 10 mg L−1 Ca and the relative standard deviation (RSD) was lower than 10%. Significant differences were not observed between the results obtained by DIC/murexide and those obtained by microwave-assisted wet digestion (MAWD) with determination by inductively coupled plasma-optical emission spectrometry (ICP-OES). A limit of quantification of 0.50 mg kg−1 Ca were obtained using DIC/murexide. This approach is an alternative and useful method for the determination of Ca in crude oil samples, with advantages of miniaturization, low cost, and ease of operation.

Real-time determination of combustion degree by laser-induced breakdown spectroscopy

The combustion of fuels in industries is one of the sources of greenhouse gases, posing a considerable threat to human health and the natural environment. The monitoring of the combustion process and the measurement of combustion degrees, therefore, are crucial and significant. In this work, an experimental system was developed based on Laser-induced breakdown spectroscopy (LIBS). Charcoals with different combustion degrees were taken as samples, and in the LIBS spectra of charcoals, the characteristic line of C and the molecular bands of CN and CaO were observed. Moreover, a univariate calibration model based on the exponential fitting curve was constructed to predict the combustion degree according to the variation of the C I line intensity under different combustion degrees. Furthermore, different algorithms including support vector machine (SVM), partial least squares (PLS), random forest (RF), and convolutional neural network (CNN) were applied to establish the multivariate calibration model, and the prediction performance was compared according to the 10-fold cross-validation. Particle swarm optimization (PSO) was used to optimize hyperparameters of the selected SVM-based multivariate calibration model. Principal component analysis (PCA) and linear discriminant analysis (LDA) were employed to extract spectral features and reduce dimensions for the improvement of the model's performance, with the final root mean square error of prediction (RMSEP) and mean relative error (MRE) of the LDA-PSO-SVM calibration model of 0.035 and 3.877%, respectively. Finally, c. The results prove feasible to realize the real-time determination of combustion degree to control carbon emissions and monitor carbon concentration through the LIBS-based method with machine learning, which also provides new ideas for the application of LIBS in the atmospheric field.

Rapid pH Value Detection in Secondary Fermentation of Maize Silage Using Hyperspectral Imaging

As pH is a key factor affecting the quality of maize silage, its accurate detection is essential to ensuring product quality. Although traditional methods for testing the pH of maize silage feed are widely used, the procedures are often complex and time-consuming and may damage the sample. This study presents a non-destructive hyperspectral imaging (HSI) technology that provides a more efficient and cost-effective method of monitoring pH by capturing the spectral information of samples and analyzing their chemical and physical properties rapidly and without contact. We applied four spectral preprocessing methods, among which the multiplicative scatter correction (MSC) preprocessing method yielded the best results. To minimize model redundancy and enhance predictive performance, we utilized six feature extraction methods for characteristic wavelength extraction, integrating these with partial least squares (PLS), non-linear support vector machine regression (SVR), and extreme learning machine (ELM) algorithms to construct a quantitative pH value prediction model. The results showed that the model based on the bootstrapping soft shrinkage (BOSS) feature wavelength extraction method outperformed the other feature extraction methods, selecting 20 pH value-related feature wavelengths from 256 bands and building a stable BOSS–ELM model with prediction set determination coefficient (RP2), root-mean-square error of prediction (RMSEP), and relative percentage deviation (RPD) values of 0.9241, 0.4372, and 3.6565, respectively. To further optimize the model for precisely predicting pH at each pixel in hyperspectral images, we employed three algorithms: the genetic algorithm (GA), whale optimization algorithm (WOA), and bald eagle search (BES). These algorithms optimized and compared the BOSS–ELM model to obtain the best model for predicting maize silage pH: the BOSS–BES–ELM model. This model achieved a determination coefficient (RP2) of 0.9598, an RMSEP of 0.3216, and an RPD of 5.1448. We generated a visualized distribution map of pH value variation in maize silage using the BOSS–BES–ELM model. This study provides strong technical support and a reference for the rapid, non-destructive detection of maize silage pH from an image, an advancement of great significance to ensuring the quality of maize silage.

Primary investigation of an innovative method for milk authenticity using two handheld spectrometers and chemometrics: Comparison with portable ATR-FTIR

This study advocates the use of handheld spectrometers, spanning the visible-near-infrared (Vis-NIR, 400–1000 nm) and near-infrared (NIR, 900–1700 nm) ranges, alongside a portable attenuated total reflection-Fourier transform infrared (ATR-FTIR) instrument, for discerning water adulteration in raw bovine milk. Samples with water adulteration levels ranging from 0 % to 30 % underwent direct analysis without additional preparation. Principal component analysis was utilized for differentiation, while quantification was achieved using partial least squares regression (PLSR) and radial basis function-artificial neural network (ANN) models. The ATR-FTIR instrument displayed remarkable performance, achieving regression coefficients of prediction (R2p) of 0.99 and 0.99, with root mean square error of prediction (RMSEP) values of 0.20 % and 0.53 % in PLS and ANN regression models, respectively. Similarly, handheld NIR spectrometer yielded robust results, with R2p values of 0.99 and 0.99 and RMSEP values of 1.28 % and 1.12 % in PLS and ANN models, respectively. Vis-NIR spectrometer also demonstrated commendable performance, with R2p values of 0.92 and 0.94 and RMSEP values of 4.53 % and 4.83 % in PLS and ANN models, respectively. ATR-FTIR showed the best performance followed by handheld NIR and Vis-NIR spectrometers. All instruments can be used potentially for screening and/or quality control in the dairy industry.

Diatom cell-size composition as a novel tool for quantitative estimates of the water table in peatlands.

Diatom cell-size composition is an indicator of aquatic environmental changes but has been rarely investigated, especially in semi-terrestrial peatlands. In this study, both taxonomic composition and cell-size composition of diatoms were analysed in 41 samples from two montane peatlands, northeastern China. Redundancy analyses revealed that diatom taxonomic composition was significantly related to the depth to the water table (DWT) and Ca2+, while cell-size composition was significantly associated with DWT and Si. DWT was the most important factor and its sole effect explained 26.2% and 17.9% of the total variance in taxonomic composition and cell-size composition, respectively. Accordingly, diatom-based water-table transfer functions were developed based on taxonomic composition and cell-size composition, respectively. The maximum-likelihood (ML) model based on diatom taxonomic composition had the best performance, with a correlation coefficient value (R2) of 0.78 and the root mean squared error of prediction (RMSEP) of 6.66 cm. The ML model based on cell-size composition had similar performance, with an R2 of 0.78 and the RMSEP of 6.87 cm, suggesting that diatom cell-size composition can be a new quantitative means to track past water-table changes. This method requires further appraisal with palaeoecological data but offers a new option that deserves exploration.

Identifying uncertainty in physical–chemical property estimation with IFSQSAR

This study describes the development and evaluation of six new models for predicting physical–chemical (PC) properties that are highly relevant for chemical hazard, exposure, and risk estimation: solubility (in water SW and octanol SO), vapor pressure (VP), and the octanol–water (KOW), octanol–air (KOA), and air–water (KAW) partition ratios. The models are implemented in the Iterative Fragment Selection Quantitative Structure–Activity Relationship (IFSQSAR) python package, Version 1.1.0. These models are implemented as Poly-Parameter Linear Free Energy Relationship (PPLFER) equations which combine experimentally calibrated system parameters and solute descriptors predicted with QSPRs. Two other ancillary models have been developed and implemented, a QSPR for Molar Volume (MV) and a classifier for the physical state of chemicals at room temperature. The IFSQSAR methods for characterizing applicability domain (AD) and calculating uncertainty estimates expressed as 95% prediction intervals (PI) for predicted properties are described and tested on 9,000 measured partition ratios and 4,000 VP and SW values. The measured data are external to IFSQSAR training and validation datasets and are used to assess the predictivity of the models for “novel chemicals” in an unbiased manner. The 95% PI intervals calculated from validation datasets for partition ratios needed to be scaled by a factor of 1.25 to capture 95% of the external data. Predictions for VP and SW are more uncertain, primarily due to the challenges in differentiating their physical state (i.e., liquids or solids) at room temperature. The prediction accuracy of the models for log KOW, log KAW and log KOA of novel, data-poor chemicals is estimated to be in the range of 0.7 to 1.4 root mean squared error of prediction (RMSEP), with RMSEP in the range 1.7–1.8 for log VP and log SW. Scientific contributionNew partitioning models integrate empirical PPLFER equations and QSARs, allowing for seamless integration of experimental data and model predictions. This work tests the real predictivity of the models for novel chemicals which are not in the model training or external validation datasets.Graphical

Relationship between body weight and hip width in dairy buffaloes (Bubalus bubalis).

The objective of the present study was to evaluate the relationship between body weight (BW) and hip width (HW) in dairy buffaloes (Bubalus bubalis). HW was measured in 215 Murrah buffaloes with a BW of 341 ± 161.6 kg, aged between three months and five years, and raised in southeastern Mexico. Linear and non-linear regressions were used to construct the prediction models. The goodness of fit of the models was evaluated using the Akaike information criterion (AIC), Bayesian information criterion (BIC), coefficient of determination (R2), mean squared error (MSE), and root MSE (RMSE). Additionally, the developed models were evaluated through internal and external cross-validation (k-folds) using independent data. The ability of the fitted models to predict the observed values was assessed based on the root mean square error of prediction (RMSEP), R2, and mean absolute error (MAE). The relationship between BW and HW showed a high correlation coefficient (r = 0.96, P < 0.001). The chosen fitted model to predict BW was: -176.33 (± 40.83***) + 8.74 (± 1.79***) × HW + 0.04 (± 0.01*) × HW2, because it presented the lowest MSE, RMSE, and AIC values, which were 1228.64, 35.05 and 1532.41, respectively. Therefore, with reasonable accuracy, the quadratic model using hip width may be suitable for predicting body weight in buffaloes.

NIR spectroscopy in conjunction with multivariate analysis for non-destructive characterization of Xuan paper

In the process of conservation mounting, starch paste made from wheat flour is the glue of choice to paste reinforcing strips and backing papers, often Xuan paper, for mending and decorating aged and damaged paper-based Chinese artworks. To keep objects intact and select appropriate conservation materials, this research explored the applicability of near-infrared (NIR) spectroscopy coupled with multivariate analysis for the characterization of contemporary unsized Xuan paper with and without starch. In particular, partial least squares (PLS) regression was used to predict the degree of polymerization (DP) of the paper, i.e., one of the most important properties of paper materials, and principal component analysis (PCA) was used to detect starch and to distinguish between papers with different amounts of starch. Using 12 contemporary unsized Xuan papers, the NIR-PLS method for DP prediction was validated, and the best-performed model was generated using the logarithmic transformation of DP−1 as a response variable, with root mean square error of prediction (RMSEP) of DP 128. The NIR-PCA method was also found to be applicable to separate starch-free papers and papers treated with starch, and the results indicate that the higher the content of starch, the better PCA classification performs. This research provides supporting data for the non-destructive characterization of Xuan paper-based objects and differentiates between Xuan paper before and after treatment with starch.

Dynamic Nondestructive Detection Models of Apple Quality in Critical Harvest Period Based on Near-Infrared Spectroscopy and Intelligent Algorithms.

Apples are usually bagged during the growing process, which can effectively improve the quality. Establishing an in situ nondestructive testing model for in-tree apples is very important for fruit companies in selecting raw apple materials for valuation. Low-maturity apples and high-maturity apples were acquired separately by a handheld tester for the internal quality assessment of apples developed by our group, and the effects of the two maturity levels on the soluble solids content (SSC) detection of apples were compared. Four feature selection algorithms, like ant colony optimization (ACO), were used to reduce the spectral complexity and improve the apple SSC detection accuracy. The comparison showed that the diffuse reflectance spectra of high-maturity apples better reflected the internal SSC information of the apples. The diffuse reflectance spectra of the high-maturity apples combined with the ACO algorithm achieved the best results for SSC prediction, with a prediction correlation coefficient (Rp) of 0.88, a root mean square error of prediction (RMSEP) of 0.5678 °Brix, and a residual prediction deviation (RPD) value of 2.466. Additionally, the fruit maturity was predicted using PLS-LDA based on color data, achieveing accuracies of 99.03% and 99.35% for low- and high-maturity fruits, respectively. These results suggest that in-tree apple in situ detection has great potential to enable improved robustness and accuracy in modeling apple quality.

Prediction of freezing point and moisture distribution of beef with dual freeze-thaw cycles using hyperspectral imaging

The freezing point (FP) is an important quality indicator of the superchilled meat. Currently, the potential of hyperspectral imaging (HSI) for predicting beef FP as affected by multiple freeze-thaw (F-T) cycles was explored. Correlation analysis revealed that the FP had a negative correlation with the proportion of bound water (P21) and a positive correlation with the proportion of immobilized water (P22). Moreover, the optimal wavelengths were selected by principal component analysis (PCA). Principal component regression (PCR) and partial least squares regression (PLSR) models were successfully developed based on the optimal wavelengths for predicting FP with determination coefficient in prediction (RP2) of 0.76, 0.76 and root mean square errors in prediction (RMSEP) of 0.12, 0.12, respectively. Additionally, PLSR based on full wavelengths was established for predicting P21 with RP2 of 0.80 and RMSEP of 0.67, and PLSR based on the optimal wavelengths was established for predicting P22 with RP2 of 0.87 and RMSEP of 0.66. The results show the potential of hyperspectral technology to predict the FP and moisture distribution of meat as a nondestructive method.