Mean Squared Prediction Error Research Articles

Rapid determination of starch and alcohol contents in fermented grains by hyperspectral imaging combined with data fusion techniques.

Starch and alcohol serve as pivotal indicators in assessing the quality of lees fermentation. In this paper, two hyperspectral imaging (HSI) techniques (visible-near-infrared (Vis-NIR) and NIR) were utilized to acquire separate HSI data, which were then fused and analyzed toforecast the starch and alcohol contents during the fermentation of lees. Five preprocessing methods were first used to preprocess the Vis-NIR, NIR, and the fused Vis-NIR and NIR data, after which partial least squares regression models were established to determine the best preprocessing method. Following, competitive adaptive reweighted sampling, successive projection algorithm, and principal component analysis algorithms were used to extract the characteristic wavelengths to accurately predict the starch and alcohol levels. Finally, support vector machine (SVM)-AdaBoost and XGBoost models were built based on the low-level fusion (LLF) and intermediate-level fusion (ILF) of single Vis-NIR and NIR as well as the fused data. The results showed that the SVM-AdaBoost model built using the LLF data afterpreprocessing by standard normalized variable was most accurate for predicting the starch content, with an of 0.9976 and a root mean square error of prediction (RMSEP) of 0.0992. The XGBoost model built using ILF data was most accurate for predicting the alcohol content, with an of 0.9969 and an RMSEP of 0.0605. In conclusion, the analysis of fused data from distinct HSI technologies facilitates rapid and precise determination of the starch and alcohol contents in fermented grains.

Predicting grass proportion in fresh alfalfa: Grass mixtures using a hand‐held near‐infrared spectrometer

AbstractTechnological advancements have made hand‐held near infrared (NIR) spectrometers more affordable and more accurate, creating interest in on‐farm application for forage management. The objective of this study was to evaluate the ability of a hand‐held NIR spectrometer to predict grass percentage within fresh alfalfa (Medicago sativa L.):grass mixtures. Forage samples were collected at a range of maturities and varieties during the 2021 and 2022 growing seasons from multiple locations in New York. Fresh forage samples were chopped, and pure species were combined into known proportions on a dry matter basis, resulting in 534 samples. Analysis was carried out on NIR spectra collected from a hand‐held NeoSpectra spectrometer using stationary and sliding scanning techniques. Development of calibration models was completed using partial least squares regression with cross validation. The best performing calibration model using absorbance was from the sliding scanning technique with preprocessing consisting of mean‐centering (R2 = 0.89, root mean square error of prediction [RMSEP] = 13.7%, and ratio of prediction to deviation = 2.53). A total of 84% of the samples were correctly classified when the grass component was lower than 40%. For samples with the grass component above 40%, a total of 94% of the samples were correctly classified. Correct sample classification is critical considering that the extension recommendation in New York is to reseed alfalfa fields when the grass component exceeds 40% of the sward on a botanical composition basis. This research demonstrates that NIR technology has potential to provide the agricultural industry with rapid, non‐destructive, and affordable information to allow farmers and consultants to predict grass proportion within alfalfa:grass fresh forage mixtures in real time.

127 Utilizing predictive models for bone mineral content and bone mineral density as a tool to assess dietary phosphorous

Abstract Dietary phosphorous is a necessary nutrient for bone development in pigs at all stages of its growing. Deficiencies in phosphorous decrease bone mineral content (BMC) and bone mineral density (BMD) and may be a causative of lameness. However, the normal range expected in whole body (WB) and individual bones for BMC and BMD in commercial pigs has been poorly defined. Therefore, our objectives were to 1) model normal WB bone density at multiple timepoints in wean to finish pigs, and 2) determine the extent to which individual bone (femur and 3rd metatarsal) BMC and BMD could predict WB BMC and BMD. Mixed sex pigs [Camborough (1050) x 337, PIC] were utilized and included freshly weaned ~21 d (n = 8), ~44 d of age (n = 24), ~84 d of age (n = 24) and ~154 d of age (n = 24). Pigs were individually penned. Excluding weaning age, at each age group pigs were randomly assigned to diets adequate, marginally deficient, or deficient in available phosphorus (avP) and fed for 3, 4, and 6 wk (age group 44, 84, 154, respectively). Within each age group, diets were formulated to meet nutrient and energy requirements except for avP and pigs fed ad libitum. On-test and off-test body weight (BW) and feed intake and gain to feed ratio were assessed for each age group. At the end of each feeding period, all pigs were euthanized and WB, femur (F) and 3rd metatarsal (M) BMC and BMD determined by dual X-ray absorptiometry (DXA). Data were analyzed using linear and generalized additive models that predicted response variables (BMC or BMD) as a function of BW or age. Only pigs fed adequate avP diets were used in the model fit. Pigs fed adequate avP diets increased BMD with age (0.22, 0.42, 0.84 and 1.10 g/cm2, days of age 21, 44, 84 and 154 respectively, P < 0.001). Within day of age 84, marginally and deficient avP diets reduced BMC and BMD by 21 to 41% (P = 0.002) and 12 to 25% (P = 0.006), respectively. Within day of age 154, marginally and deficient avP diets reduced BMC and BMD by 9% (P = 0.05) and 6 to 8% (P = 0.06), respectively. Body weight record and individual bone (F and M) BMC and BMD from pigs fed deficient avP diets were used to predict WB BMC and BMD and the mean square error of prediction was selected as a criterion to evaluate the ability of the models to detect these inadequately fed pigs. Using the selected models, pigs fed nutritionally deficient diets were detected due to 2- to 7-fold increase in MSE of predicted WBMD or WBMC compared with pigs fed adequate diets. These models can be used to assess bone development and strength in growing pigs and to infer the adequacy of avP level supplied in their diets.

Near-infrared spectroscopy in resin transfer molding—determination of the degree of cure

Near-infrared (NIR) spectroscopy is employed to directly monitor the degree of cure of composite material during the curing phase in the resin transfer molding (RTM) process. The composite material consists of natural fibers and an epoxy-amine resin system. The quantitative determination of the degree of cure, α, from the NIR spectra is realized by partial least square (PLS) regression in conjunction with various pre-treatments of the spectral data. As a reference, the degree of cure is determined by isothermal differential scanning calorimetry (DSC) experiments. The best PLS model that could be obtained for α is characterized by a determination coefficient of prediction (R²P) of 0.980 and root mean square error of prediction (RMSEP) of 4.4 %. While the spectra change during curing according to the literature for each RTM trial, significant differences can be observed between the spectra of different RTM trials. The reasons for this are discussed in detail. The findings show the potential of inline NIR spectroscopy for monitoring α in the RTM process.

Rapid determination of residual pefloxacin in mutton based on hyperspectral imaging and data fusion

Non-destructive detection of veterinary drug residues in meat products is critical for ensuring food safety and human health. The feasibility of using visible near-infrared (Vis-NIR) and near-infrared (NIR) hyperspectral imaging (HSI) system combined with data fusion for the prediction of pefloxacin residues in mutton was investigated in this study. A partial least squares regression optimization model was developed by multivariate data processing methods. The results showed that the low-level fusion (LLF) produced better results with R2P = 0.907 and RMSEP = 0.462 as compared to individual data blocks. Furthermore, intermediate-level fusion (ILF) based on iterative retention of informative variables algorithm showed the best results with R2P = 0.940 and RMSEP = 0.375. Finally, the visualized distributions of Vis-NIR and NIR based on the optimal model combination were mapped. The results have demonstrated that a combination of HSI with data fusion may be applied to rapidly and non-destructively detect pefloxacin residues in mutton.

Vis-NIR spectroscopic discriminant analysis of aflatoxin B1 excessive standard in peanut meal as feedstuff materials

A fast, simple and reagent-free detection method for aflatoxin B1 (AFB1) is of great significance to food safety and human health. Visible and near-infrared (Vis-NIR) spectroscopy was applied to the discriminant analysis of AFB1 excessive standard of peanut meal as feedstuff materials. Two types of excessive standard discriminant models based on spectral quantitative analysis with partial least squares (PLS) and direct pattern recognition with partial least squares-discrimination analysis (PLS-DA) were established, respectively. Multi-parameter optimization of Norris derivative filtering (NDF) was used for spectral preprocessing; the two-stage wavelength screening method based on equidistant combination-wavelength step-by-step phase-out (EC-WSP) was used for wavelength optimization. A rigorous sample experimental design of calibration-prediction-validation was utilized. The calibration and prediction samples were used for modeling and parameter optimization, and the selected model was validated using the independent validation samples. For quantitative analysis-based, the positive, negative and total recognition-accuracy rates in validation (RARV+, RARV-, and RARV) were 84.8 %, 74.6 % and 79.8 %, respectively; but, the relative root mean square error of prediction was as high as 51.0 %. For pattern recognition-based, the RARV+, RARV-, and RARV were 93.3 %, 90.5 % and 91.9 %, respectively. Moreover, the number of wavelengths N was drastically reduced to 17, and the discrete wavelength combination was in NIR overtone frequency region. The results indicated that, the EC-WSP-PLS-DA model achieved significantly better discrimination effect. Thus demonstrated that Vis-NIR spectroscopy has feasibility for the excessive standard discrimination of aflatoxin B1 in feedstuff materials.

Species-Specific quantification of bioactive boswellic acids in Boswellia resin using NIR spectroscopy, HPLC and Multivariate data analysis

The bioactive compounds Acetyl-11-keto-β-boswellic acid (AKBA) and 11-keto-β-boswellic acid (KBA), found in the resin of the Boswellia tree, exhibit anti-inflammatory properties, rendering Boswellia resin an intriguing natural medicinal products. However, the content of boswellic acids varies across different Boswellia species and proper knowledge of its species-dependent nature, as well as alternatives to the resource- and time-intensive HPLC analysis, are lacking. Here we present a comprehensive investigation into the boswellic acid content of seven Boswellia species from ten countries and introduce a novel and non-destructive Near-Infrared spectroscopy method for predicting boswellic acid concentrations in solid resin samples. The HPLC-UV reference analysis revealed AKBA concentrations of up to 7.27 % (w/w) with KBA concentrations reaching up to 1.28 % (w/w). Principal Component Analysis of the HPLC and NIR spectroscopy data unveiled species-specific variations, facilitating differentiation based on boswellic acid content, characteristic chromatograms and NIR spectra. Using the HPLC-UV quantification as reference, we developed a Partial Least Squares regression model based on NIR spectra of the resin samples. This model demonstrated highly satisfactory predictive capabilities for AKBA content, achieving a root mean square error of prediction of 0.74 % (w/w) and an R2val of 0.79 in independent test set validation. Although the model was less effective for predicting KBA content, it still offered valuable estimates. The spectroscopic method introduced in this study provides a cost-effective and solvent-free approach for predicting boswellic acid content, demonstrating the potential for application in non-laboratory settings through the use of miniaturized NIR spectrometers. Consequently, this method aligns well with the principles of green chemistry and addresses the growing demand for alternative analytical techniques.

Confocal controlled laser-induced breakdown spectroscopy for quantitative detection of cadmium in soil

Soil, one of the most precious natural resources on Earth, gradually accumulates heavy metals, inevitably causing significant damage to the ecological environment. Here, we introduce confocal controlled laser induced breakdown spectroscopy (CCLIBS) technology for the quantitative analysis of the heavy metal cadmium in soil for the first time. CCLIBS offers better spatial consistency and stable plasma temperature during sample ablation compared to traditional LIBS, thereby reducing matrix effects to improve the accuracy of the quantitative results. The fluctuation of the spectrum and limit of detection are reduced by 0.6 times and 0.39 times, respectively. An effective prediction model was established using the partial least squares method, with a determination coefficient increased to 0.96. The root mean square error of prediction and average relative error are reduced to 67.67 and 0.20, respectively. These results indicate that CCLIBS provides consistent ablation conditions for elemental quantification and yields reliable test results, which is significant for monitoring heavy metals in the ecological environment and effectively intervene and mitigate environmental contamination.

Three-dimensional imaging to estimate in vivo body and carcass chemical composition of growing beef-on-dairy crossbred bulls

The dynamics of cattle body chemical composition during growth and fattening periods determine animal performance and beef carcass quality. The aim of this study was to estimate the empty body (EB) and carcass chemical composition of growing beef-on-dairy crossbred bulls (Brown Swiss breed as dam with Angus, Limousin or Simmental as sire) using three-dimensional (3D) imaging. The 3D images of the cattle’s external body shape were recorded in vivo on 48 bulls along growth trajectory (75–520 kg BW and 34–306 kg hot carcass weight [HCW]; set 1) and on 70 bulls at target market slaughter weight, including 18 animals from set 1 (average 517 ± 10 kg BW and 289 ± 10 kg HCW; set 2). The linear, circumference, curve, surface and volume measurements on the 3D body shape were determined. Those predictive variables were used in partial least square regressions, together with the effect of the sire breed whenever significant (P < 0.05), with leave-one-out cross-validation to estimate water, lipid, protein, mineral and energy mass or proportions in the EB and carcass. Mass and proportions were determined directly from postmortem grinding and chemical analyses (set 1) or indirectly using the 11th rib dissection method (set 2). In set 1, bulls’ BW and HCW were estimated via 3D imaging, with root mean square error of prediction (RMSEP) of 12 kg and 6 kg, respectively. The EB and carcass chemical component proportions were estimated with RMSEP from 0.2% for EB minerals (observed mean 3.7 ± 0.2%) to 1.8% for EB lipid (11.6 ± 4.2%), close to the RMSEP found for the carcass. In set 2, the RMSEP for estimation via 3D imaging was 9 kg for BW and 6 kg for HCW. The EB energy and protein proportions were estimated, with RMSEP of 0.5 MJ/kg fresh matter (10.1 ± 0.8 MJ/DM) and 0.2% (18.7 ± 0.7%), respectively. Overall, the estimations of chemical component proportions from 3D imaging were slightly less precise for both sets than the mass estimations. The morphological traits from the 3D images appeared to be precise estimators of BW, HCW as well as EB and carcass chemical component masses and proportions.

Prediction of the protein and lipid content of Coalho cheese using spectroscopy

Coalho cheese is a traditional dairy product consumed in Brazil. Official methodologies for determining the cheese composition have disadvantages related to costs and analysis time, but Near Infrared Region Spectroscopy (NIRS), a faster methodology, is an alternative that can be used to obtain fast and reliable data. The aim of this study was to use NIRS associated with multivariate analysis to predict the content of proteins and lipids in Coalho cheese. 80 samples of the product were submitted to the official analysis methods and NIRS. The spectra were obtained in the region 10000 - 4000 cm-1, in reflectance mode. The multivariate calibration method used was partial least squares regression (PLS) with PLS interval algorithm. It was found that the mean square error of prediction for the chosen model for lipids was 1.39% and, for proteins, 2.73%. The NIRS showed imprecision for protein prediction in Coalho cheese, but, for the lipid content, the NIRS-PLS methodology showed satisfactory prediction results, which shows its potential for the Dairy Industries.

From Organelle Morphology to Whole-Plant Phenotyping: A Phenotypic Detection Method Based on Deep Learning.

The analysis of plant phenotype parameters is closely related to breeding, so plant phenotype research has strong practical significance. This paper used deep learning to classify Arabidopsis thaliana from the macro (plant) to the micro level (organelle). First, the multi-output model identifies Arabidopsis accession lines and regression to predict Arabidopsis's 22-day growth status. The experimental results showed that the model had excellent performance in identifying Arabidopsis lines, and the model's classification accuracy was 99.92%. The model also had good performance in predicting plant growth status, and the regression prediction of the model root mean square error (RMSE) was 1.536. Next, a new dataset was obtained by increasing the time interval of Arabidopsis images, and the model's performance was verified at different time intervals. Finally, the model was applied to classify Arabidopsis organelles to verify the model's generalizability. Research suggested that deep learning will broaden plant phenotype detection methods. Furthermore, this method will facilitate the design and development of a high-throughput information collection platform for plant phenotypes.

Data-Driven Identification of Crane Dynamics Using Regularized Genetic Programming

The meaningful problem of improving crane safety, reliability, and efficiency is extensively studied in the literature and targeted via various model-based control approaches. In recent years, crane data-driven modeling has attracted much attention compared to physics-based models, particularly due to its potential in real-time crane control applications, specifically in model predictive control. This paper proposes grammar-guided genetic programming with sparse regression (G3P-SR) to identify the nonlinear dynamics of an underactuated crane system. G3P-SR uses grammars to bias the search space and produces a fixed number of candidate model terms, while a local search method based on an l0-regularized regression results in a sparse solution, thereby also reducing model complexity as well as reducing the probability of overfitting. Identification is performed on experimental data obtained from a laboratory-scale overhead crane. The proposed method is compared with multi-gene genetic programming (MGGP), NARX neural network, and Takagi-Sugeno fuzzy (TSF) ARX models in terms of model complexity, prediction accuracy, and sensitivity. The G3P-SR algorithm evolved a model with a maximum mean square error (MSE) of crane velocity and sway prediction of 1.1860 × 10−4 and 4.8531 × 10−4, respectively, in simulations for different testing data sets, showing better accuracy than the TSF ARX and MGGP models. Only the NARX neural network model with velocity and sway maximum MSEs of 1.4595 × 10−4 and 4.8571 × 10−4 achieves a similar accuracy or an even better one in some testing scenarios, but at the cost of increasing the total number of parameters to be estimated by over 300% and the number of output lags compared to the G3P-SR model. Moreover, the G3P-SR model is proven to be notably less sensitive, exhibiting the least deviation from the nominal trajectory for deviations in the payload mass by approximately a factor of 10.

Enhancing corn quality prediction: Variable selection and explainable AI in spectroscopic analysis

This study addresses the challenge of effectively selecting relevant variables and providing interpretable insights in spectroscopic analysis (1100–2498 nm) of corn quality (moisture, fat, protein, and starch), incorporating variable selection techniques and explainable artificial intelligence (AI). Three variable selection algorithms were used to select 36 important variables, and through combinatorial optimization, only 11 common wavelengths were chosen. Partial least squares regression (PLSR) models were developed using the full spectral range, individual variables, and common variables. Based on the root mean square errors of prediction (RMSEP), the PLSR models with common variables outperformed individual feature variables for starch (0.22 % vs. 0.24 %) and were comparable for oil (0.05 % vs. 0.05 %), water (0.02 % vs. 0.01 %) and protein (0.12 % vs. 0.09 %). The SHapley Additive exPlanation (SHAP) method was employed to explain the PLSR model and assess the contribution of common variables. This combined approach significantly improved the accuracy and interpretability of corn prediction models, providing trust in the results and facilitating the understanding of the relationship between spectral features and corn quality attributes.

Quantitative analysis of three ingredients in Salvia miltiorrhiza by near infrared spectroscopy combined with hybrid variable selection strategy

Rosmarinic acid (RA), Tanshinone IIA (Tan IIA), and Salvianolic acid B (Sal B) are crucial compounds found in Salvia miltiorrhiza. Quickly predicting these components can aid in ensuring the quality of S. miltiorrhiza. Spectral preprocessing and variable selection are essential processes in quantitative analysis using near infrared spectroscopy (NIR). A novel hybrid variable selection approach utilizing iVISSA was employed in this study to enhance the quantitative measurement of RA, Tan IIA, and Sal B contents in S. miltiorrhiza. The spectra underwent 108 preprocessing approaches, with the optimal method being determined as orthogonal signal correction (OSC). iVISSA was utilized to identify the intervals (feature bands) that were most pertinent to the target chemical. Various methods such as bootstrapping soft shrinkage (BOSS), competitive adaptive reweighted sampling (CARS), genetic algorithm (GA), variable combination population analysis (VCPA), successive projections algorithm (SPA), iteratively variable subset optimization (IVSO), and iteratively retained informative variables (IRIV) were used to identify significant feature variables. PLSR models were created for comparison using the given variables. The results fully demonstrated that iVISSA-SPA calibration model had the best comprehensive performance for Tan IIA, and iVISSA-BOSS had the best comprehensive performance for RA and Sal B, and correlation coefficients of cross-validation (R2cv), root mean square errors of cross-validation (RMSECV), correlation coefficients of prediction (R2p), and root mean square errors of prediction (RMSEP) were 0.9970, 0.0054, 0.9990 and 0.0033, 0.9992, 0.0016, 0.9961 and 0.0034, 0.9998, 0.0138, 0.9875 and 0.1090, respectively. The results suggest that NIR spectroscopy, along with PLSR and a hybrid variable selection method using iVISSA, can be a valuable tool for quickly quantifying RA, Sal B, and Tan IIA in S. miltiorrhiza.

The mean squared prediction error paradox

AbstractIn this paper, we show that traditional comparisons of mean squared prediction error (MSPE) between two competing forecasts may be highly controversial. This is so because when some specific conditions of efficiency are not met, the forecast displaying the lowest MSPE will also display the lowest correlation with the target variable. Given that violations of efficiency are usual in the forecasting literature, this opposite behavior in terms of accuracy and correlation with the target variable may be a fairly common empirical finding that we label here as “the MSPE paradox.” We characterize “paradox zones” in terms of differences in correlation with the target variable and conduct some simple simulations to show that these zones may be non‐empty sets. Finally, we illustrate the relevance of the paradox with a few empirical applications.

Machine learning-enhanced drug testing for simultaneous morphine and methadone detection in urinary biofluids

The simultaneous identification of drugs has considerable difficulties due to the intricate interplay of analytes and the interference present in biological matrices. In this study, we introduce an innovative electrochemical sensor that overcomes these hurdles, enabling the precise and simultaneous determination of morphine (MOR), methadone (MET), and uric acid (UA) in urine samples. The sensor harnesses the strategically adapted carbon nanotubes (CNT) modified with graphitic carbon nitride (g-C3N4) nanosheets to ensure exceptional precision and sensitivity for the targeted analytes. Through systematic optimization of pivotal parameters, we attained accurate and quantitative measurements of the analytes within intricate matrices employing the fast Fourier transform (FFT) voltammetry technique. The sensor’s performance was validated using 17 training and 12 test solutions, employing the widely acclaimed machine learning method, partial least squares (PLS), for predictive modeling. The root mean square error of cross-validation (RMSECV) values for morphine, methadone, and uric acid were significantly low, measuring 0.1827 µM, 0.1951 µM, and 0.1584 µM, respectively, with corresponding root mean square error of prediction (RMSEP) values of 0.1925 µM, 0.2035 µM, and 0.1659 µM. These results showcased the robust resiliency and reliability of our predictive model. Our sensor’s efficacy in real urine samples was demonstrated by the narrow range of relative standard deviation (RSD) values, ranging from 3.71 to 5.26%, and recovery percentages from 96 to 106%. This performance underscores the potential of the sensor for practical and clinical applications, offering precise measurements even in complex and variable biological matrices. The successful integration of g-C3N4-CNT nanocomposites and the robust PLS method has driven the evolution of sophisticated electrochemical sensors, initiating a transformative era in drug analysis.

Pulpwood holocellulose model transfer based on screening with consistent and stable signals algorithm.

In this study, in order to realize the sharing of the near-infrared analysis model of holocellulose between three spectral instruments of the same type, 84 pulp samples and their content of holocellulose were taken as the research objects. The effects of 10 pre-processing methods, such as 1st derivative (D1st), 2nd derivative (D2nd), multiplicative scatter correction (MSC), standard normal variable transformation (SNV), autoscaling, normalization, mean centering and pairwise combination, on the transfer effect of the stable wavelength selected by screening wavelengths with consistent and stable signals (SWCSS) were discussed. The results showed that the model established by the wavelength selected by the SWCSS algorithm after the autoscaling pre-processing method had the best analysis effect on the two target samples. Root mean square error of prediction (RMSEP) decreased from 2.4769 and 2.3119 before the model transfer to 1.2563 and 1.2384, respectively. Compared with the full-spectrum model, the value of AIC decreased from 3209.83 to 942.82. Therefore, the autoscaling pre-processing method combined with SWCSS algorithm can significantly improve the accuracy and efficiency of model transfer and provide help for the application of SWCSS algorithm in the rapid determination of pulp properties by near-infrared spectroscopy (NIRS).

Synchronous spectrofluorimetry and chemometric modeling: A synergistic approach for analyzing simeprevir and daclatasvir, with application to pharmacokinetics evaluation

Simeprevir and daclatasvir represent a cornerstone in the management of Hepatitis C Virus infection, a global health concern that affects millions of people worldwide. In this study, we propose a synergistic approach combining synchronous spectrofluorimetry and chemometric modeling i.e. Partial Least Squares (PLS-1) for the analysis of simeprevir and daclatasvir in different matrices. Moreover, the study employs firefly algorithms to further optimize the chemometric models via selecting the most informative features thus improving the accuracy and robustness of the calibration models. The firefly algorithm was able to reduce the number of selected wavelengths to 47–44% for simeprevir and daclatasvir, respectively offering a fast and sensitive technique for the determination of simeprevir and daclatasvir. Validation results underscore the models' effectiveness, as evidenced by recovery rates close to 100% with relative root mean square error of prediction (RRMSEP) of 2.253 and 2.1381 for simeprevir and daclatasvir, respectively. Moreover, the proposed models have been applied to determine the pharmacokinetics of simeprevir and daclatasvir, providing valuable insights into their distribution and elimination patterns. Overall, the study demonstrates the effectiveness of synchronous spectrofluorimetry coupled with multivariate calibration optimized by firefly algorithms in accurately determining and quantifying simeprevir and daclatasvir in HCV antiviral treatment, offering potential applications in pharmaceutical formulation analysis and pharmacokinetic studies for these drugs.

Quantitative determination of the carbonyl value in frying oils based on LF-NMR combined with chemometrics

Low-field nuclear magnetic resonance (LF-NMR) combined with chemometrics was used for the rapidly and nondestructively quantitative determination of carbonyl value (CV) of frying oils during frying process. The quality indices of frying oils during frying process were analyzed as well as the changes of its LF-NMR signal, followed by exploring the correlation between the quality indices of frying oils and the relaxation-characteristic indices and investigating the influences of modeling data and preprocessing methods on the modeling performance. Based on the echo decay curves data of LF-NMR and the relaxation-characteristic indices data, the prediction model of CV was established by partial least square (PLS), principal component regression (PCR), multiple linear regression (MLR), and support vector machine regression (SVR). Results showed that there was a significant correlation between CV and relaxation-characteristic indices (p < 0.01) with both modeling data and preprocessing methods affecting the model performance. The prediction performance of non-linear SVR model was significantly superior to that of linear modeling methods (PLS, PCR, and MLR). The best prediction model of CV was built using the SVR method based on echo decay curves data. The root mean square error of prediction and coefficient of determination were 2.599 mmol/kg and 0.9873, respectively.

Hologram quantitative structure-activity relationship on the gas chromatographic retention index of plant essential oil constituents

The gas chromatography retention index (RI) is an important parameter for the identification of different types of compounds in the field of chromatographic analysis; however, the experimental collection of RI values is a extremely cumbersome process. Thus, there is an urgent need for the establishment of a simple, efficient, and accurate model for the prediction of the RI values of compounds. In this study, first, the experimental RI values for 60 plant essential oil constituents were obtained. Next, a model describing the hologram quantitative structure-activity relationship (HQSAR) between the structural properties of the essential oil constituents and their RI values was investigated and constructed. The optimal HQSAR model was established by setting the model parameters "fragment size", "fragment distinction", "hologram length" and "principal components" to "1-4", "C, Ch", "199", and "4", respectively. Finally, the predictive ability of the model was verified using external test set validation and leave-one-out cross-validation (LOO-CV). The experimental results were as follows, the root mean square error of prediction (RMSEP), predictive determination coefficient ([Formula: see text]), concordance correlation coefficient (CCC), and mean relative error (MRE) for external test set validation were 40.45, 0.984, 0.968, and 2.20%, respectively. Meanwhile, the root mean square error of cross validation (RMSECV) and MRE for LOO-CV were 72.56 and 4.17%, respectively. These findings demonstrate that the established HQSAR model has a good predictive ability and can accurately predict the RI values of plant essential oil constituents. In addition, the molecular contribution maps of the HQSAR model revealed that the RI values of aromatic compounds increase when hydroxyl groups are connected to their alkyl chains. Aliphatic compounds feature long chain alkyl groups, which can lead to an increase in RI values. The above phenomena highlight the promising application prospects of HQSAR for studying the RI values of plant essential oil constituents. Therefore, this study provides a reliable theoretical basis for predicting the RI values of other essential oil constituents.