Application of unsupervised and supervised learning to a material attribute database of tablets produced at two different granulation scales

The purpose of this study is to demonstrate the usefulness of machine learning (ML) for analyzing a material attribute database from tablets produced at different granulation scales. High shear wet granulators (scale 30 g and 1000 g) were used and data were collected according to the design of experiments at different scales. In total, 38 different tablets were prepared, and the tensile strength (TS) and dissolution rate after 10 min (DS10) were measured. In addition, 15 material attributes (MAs) related to particle size distribution, bulk density, elasticity, plasticity, surface properties, and moisture content of granules were evaluated. By using unsupervised learning including principal component analysis and hierarchical cluster analysis, the regions of tablets produced at each scale were visualized. Subsequently, supervised learning with feature selection including partial least squares regression with variable importance in projection and elastic net were applied. The constructed models could predict the TS and DS10 from the MAs and the compression force with high accuracy (R²= 0.777 and 0.748, respectively), independent of scale. In addition, important factors were successfully identified. ML can be used for better understanding of similarity/dissimilarity between scales, for constructing predictive models of critical quality attributes, and for determining critical factors.

Determination of Bendamustine, Gemcitabine and Vinorelbine (BEGEV) regimen in spiked human plasma using multivariate model update chemometric methods

Combination of bendamustine (BEN), gemcitabine (GEM), and vinorelbine (VIB), (BEGEV) regimen, has been proved to be a tolerable, safe and effective regimen in relapsed/refractory classical hodgkin lymphoma (R/R cHL). Two chemometric models named principal component regression (PCR) and partial least squares (PLS) were established for determination and quantification of BEN, GEM and VIB simultaneously in the ranges of 5-25 µg/mL for each of BEN and VIB, while in the range of 10 -30 µg/mL for GEM in pure and spiked plasma using their UV absorbance. The updated methods have been proven their ability to predict the concentrations of the studied drugs and validated according to FDA guidelines showing good results. There was no significant difference between the developed methods and the reported LC-MS/MS method upon statistical comparison was applied. Furthermore, the updated chemometric methods have advantages of being sensitive, accurate and cost effective for estimation of BEN, GEM and VIB and monitoring their concentration.

Leveraging visible and near-infrared spectroelectrochemistry to calibrate a robust model for Vanadium(IV/V) in varying nitric acid and temperature levels

Spectroelectrochemistry and optimal design of experiments can be used to rapidly build accurate models for species quantification and enable a greater level of process awareness. Optical spectroscopy can provide vital elemental and molecular information, but several hurdles must be overcome before it can become a widely adopted analytical method for remote analysis in the nuclear field. Analytes with varying oxidation state, acid concentration, and fluctuating temperature must be efficiently accounted for to minimize time and resources in restrictive hot cell environments. The classic one-factor-at-a-time approach is not suitable for frequent calibration/maintenance operations in this setting. Therefore, a novel alternative was developed to characterize a system containing vanadium(IV/V) (0.01-0.1 M), nitric acid (0.1-4 M), and varying temperatures (20-45 °C). Spectroelectrochemistry methods were used to acquire a sample set selected by optimal design of experiments. This new approach allows for the accurate analysis of vanadium and HNO₃ concentration by leveraging UV-Vis-NIR absorption spectroscopy with robust and accurate chemometric models. The top model's root mean squared error of prediction percent values were 3.47%, 4.06%, 3.40%, and 10.9% for V(IV), V(V), HNO₃, and temperature, respectively. These models, efficiently developed using the designed approach, exhibited strong predictive accuracy for vanadium and acid with varying oxidation states and temperature using only spectrophotometry, which advances current technology for real-world hot cell applications. Additionally, Nernstian analysis of the V(IV/V) standard potential was performed using traditional absorbance methods and multivariate curve resolution (MCR). The successful tests demonstrated that MCR Nernst tests may be valuable in highly convoluted spectral systems to better understand the redox processes' behavior.

A statistical machine learning approach linking molecular conformational changes to altered mechanical characteristics of skin due to thermal injury

This article develops statistical machine learning models to predict the mechanical properties of skin tissue subjected to thermal injury based on the Raman spectra associated with conformational changes of the molecules in the burned tissue. Ex vivo porcine skin tissue samples were exposed to controlled burn conditions at 200 °F for five different durations: (i) 10s, (ii) 20s, (iii) 30s, (iv) 40s, and (v) 50s. For each burn condition, Raman spectra of wavenumbers 500-2000 cm^-1 were measured from the tissue samples, and tensile testing on the same samples yielded their material properties, including, ultimate tensile strain, ultimate tensile stress, and toughness. Partial least squares regression models were established such that the Raman spectra, describing conformational changes in the tissue, could accurately predict ultimate tensile stress, toughness, and ultimate tensile strain of the burned skin tissues with R² values of 0.8, 0.8, and 0.7, respectively, using leave-two-out cross validation scheme. An independent assessment of the resultant models showed that amino acids, proteins & lipids, and amide III components of skin tissue significantly influence the prediction of the properties of the burned skin tissue. In contrast, amide I has a lesser but still noticeable effect. These results are consistent with similar observations found in the literature on the mechanical characterization of burned skin tissue.

Machine learning-assisted laser-induced breakdown spectroscopy for monitoring molten salt compositions of small modular reactor fuel under varying laser focus positions

Next-generation advanced nuclear reactors based on molten salts are interested to apply machine learning (ML) technology to minimize human error and realize effective autonomous operation. Owing to harsh environments with limited access to molten salts, laser-induced breakdown spectroscopy (LIBS) has been investigated as a possible option for remote online monitoring. However, the height of molten salts is easily fluctuated by vibration. In addition, the level of molten salts could change during normal operation through the insertion of a controlling structure. While these uncertainties should be considered, their effects have not been studied yet. In this study, LIBS has been actively coupled with ML to automate the online monitoring of difficult-to-access molten salt systems. To practically apply a prediction model with ML, we intentionally defocus the measurement by manipulating the sample position. This study investigates the focusing and defocusing spectra of Sr and Mo as fission products for constructing the two prediction models using partial least squares and artificial neural network methods. For each method, the prediction models trained with focusing spectra only or focusing and defocusing spectra simultaneously are constructed and compared to each other. While the prediction model using only focusing spectra resulted in a root mean square error of prediction (RMSEP) of 0.1943-0.2175 wt%, a prediction model using both spectra led to approximately 10 times enhanced RMSEP (0.0210-0.0316 wt%). This study implies that not only focusing data but also defocusing data are needed to construct the prediction model while considering its practical usage in a real system, especially in the complex processes of the nuclear industry.

Exploring quantitative structure-property relationship models for environmental fate assessment of petroleum hydrocarbons

The rate and extent of biodegradation of petroleum hydrocarbons in the different aquatic environments is an important element to address. The major avenue for removing petroleum hydrocarbons from the environment is thought to be biodegradation. The present study involves the development of predictive quantitative structure-property relationship (QSPR) models for the primary biodegradation half-life of petroleum hydrocarbons that may be used to forecast the biodegradation half-life of untested petroleum hydrocarbons within the established models' applicability domain. These models use easily computable two-dimensional (2D) descriptors to investigate important structural characteristics needed for the biodegradation of petroleum hydrocarbons in freshwater (dataset 1), temperate seawater (dataset 2), and arctic seawater (dataset 3). All the developed models follow OECD guidelines. We have used double cross-validation, best subset selection, and partial least squares tools for model development. In addition, the small dataset modeler tool has been successfully used for the dataset with very few compounds (dataset 3 with 17 compounds), where dataset division was not possible. The resultant models are robust, predictive, and mechanistically interpretable based on both internal and external validation metrics (R² range of 0.605-0.959. Q²_(Loo) range of 0.509-0.904, and Q²_F1 range of 0.526-0.959). The intelligent consensus predictor tool has been used for the improvement of the prediction quality for test set compounds which provided superior outcomes to those from individual partial least squares models based on several metrics (Q²_F1 = 0.808 and Q²_F2 = 0.805 for dataset 1 in freshwater). Molecular size and hydrophilic factor for freshwater, frequency of two carbon atoms at topological distance 4 for temperate seawater, and electronegative atom count relative to size for arctic seawater were found to be the most significant descriptors responsible for the regulation of biodegradation half-life of petroleum hydrocarbons.

Factors that influence the impact of Chronic Non-Cancer Pain on daily life: A partial least squares modelling approach

BACKGROUND

Chronic Non-Cancer Pain is pain of more than three months' duration and is not associated with an oncological condition. There is ample literature that recognises that Chronic Non-Cancer Pain impacts numerous areas of the life of the person who suffers from it. This impact is difficult to determine and quantify because Chronic Pain is a subjective experience.

OBJECTIVE

The objective of this study was to test a recursive model of hypothesised factors that comprise the concept of Chronic Non-Cancer Pain Impact on daily life using Partial Least Squares-Structural Equation Modelling.

DESIGN

A cross-sectional study was carried out. The sample size was calculated using G*Power V.3.1.9.4 with five parameters (two-tailed, large effect size (f² = 0.35), power of 0.95, statistical significance of 95% (α = 0.05) and 36 predictors). The minimum number of subjects was considered to be 137.

METHODS

A recursive model was built based on data from a sample of 395 people over 18 years of age with Chronic Non-Cancer Pain. Data collection was conducted between January and March 2020 at Pain Units and Primary Healthcare Centres belonging to the Spanish Public Health System in the province of Seville (Spain). Analyses were based on Partial Least Squares-Structural Equation Modelling. The internal consistency, convergent validity and discriminant validity of the internal measurement model were assessed. For the external measurement model, global model adjustment and structural validity were assessed. The predictive capacity of the final model was also evaluated. All analyses were performed using SmartPLS version 3.3.2 in consistent mode.

RESULTS

Findings showed an adequate validity of the proposed model, which comprised nine factors: pain catastrophising, hopelessness due to pain, support network, proactivity, treatment compliance, self-care, mobility, resilience, and sleep. The internal validity of the model (Cronbach's alpha and rho_A > 0.70; Average Variance Extracted>0.50; standardised outer loadings>0.60; Heterotrait-Monotrait-Ratio < 0.85), goodness of fit (Standardised Root Mean Square Residuals<0.08; Geodesic and Euclidean distance p-value<0.05) and predictive power with out-of-sample values (Stone-Geisser test>0.5) were adequate. The hypothesised structure of the instrument has also been confirmed (path coefficients>0.3; R² > 0.1; f² > 0.2).

CONCLUSIONS

The results have shown an adequate internal consistency, convergent validity and discriminant validity of the model. Likewise, the model has shown an adequate goodness of fit, and the validity of its structure and the hypothesis have been confirmed. However, more research is needed in this regard as the possible interaction between the different factors evaluated in the model with the confounding or moderating variables that may exist.

Simultaneous quantitative Analysis of Salmeterol and Fluticasone in Inhalation Spray Using HPLC and Fast Spectrophotometric Technique Combined with Time Series Neural Network and Multivariate Calibration Methods

BACKGROUND

Chromatographic methods have been used for the simultaneous determination of salmeterol (SMT) and fluticasone (FLU), which take a lot of time to analyze, need large amount of solvents and sample pre-treatment, as well as it is costly.

OBJECTIVE

The aim of this paper was to propose a simple, quick, and low-cost method for the determination of SMT and FLU using time series neural network and multivariate calibration methods, including partial least squares (PLS) and principal component regression (PCR).

METHODS

The simultaneous spectrophotometric determination of SMT and FLU in binary mixtures and anti-asthma spray was performed by applying multivariate calibration methods and intelligent approach.

RESULTS

The coefficient of determination (R2) of the time series neural network was obtained 1 and 0.9997 for SMT and FLU, respectively. The mean recovery of PLS and PCR methods was found 99.29%, 99.84% and 102.05%, 103.72% for SMT and FLU, respectively. Furthermore, root mean square error (RMSE) of SMT and FLU were 0.187, 0.156 and 0.693, 0.714 for PLS and PCR, respectively.

CONCLUSION

The analyzing inhalation spray was assessed using high-performance liquid chromatography and its results were compared with chemometrics methods via analysis of variance (ANOVA) test.

HIGHLIGHTS

Intelligent and multivariate calibration methods were proposed.Simultaneous spectrophotometric determination of salmeterol and fluticasone was studied in the anti-asthma spray.HPLC as a reference method was performed and compared with chemometrics methods.Rapid, simple, low-cost, and accurate are the benefits of the proposed approaches.

Fast detection of volatile fatty acids in biogas slurry using NIR spectroscopy combined with feature wavelength selection

To analyze the state of anaerobic digestion (AD), fast detection models of volatile fatty acids (VFAs) were constructed using near-infrared transmission spectroscopy combined with partial least squares regression to measure concentrations of the acetic acid (AA), propionic acid (PA) and total acid (TA) in biogas slurry. CARS-SA-BPSO algorithm was proposed based on competitive adaptive reweighted sampling (CARS) and simulated annealing binary particle swarm optimization algorithm (SA-BPSO) for selecting feature wavelengths of the AA, PA and TA. Regression models were established with the determination coefficient of prediction (R_p²) of 0.989, root mean squared error of prediction (RMSEP) of 0.111 and residual predictive deviation (RPD) of 9.706 for AA; R_p² of 0.932, RMSEP of 0.116 and RPD of 3.799 for PA; R_p² of 0.895, RMSEP of 0.689 and RPD of 3.676 for TA. It is sufficient to meet the fast detection needs of the AA and PA concentrations in biogas slurry, and basically meet the measuring demand of the TA concentration. CARS-SA-BPSO effectively improves the performance of the calibration model using sensitive wavelength selections, which provides theoretical support for establishing the spectral quantitative regression model to meet the requirements of practical application.

Online quantitative substrate, product, and cell concentration in citric acid fermentation using near-infrared spectroscopy combined with chemometrics

As a mature platform compound, citric acid (CA) is mainly produced by Aspergillus niger (A. niger) through submerged fermentation. However, the CA fermentation process is still regulated based on experience and limited offline data, so real-time monitoring and intelligent precise control of the fermentation process cannot be carried out. In this study, near-infrared (NIR) spectroscopy combined with different chemometrics methods was used to quantify the substrate, product, and cell concentration of CA fermentation online. The predictive performance of total sugar (TS), CA, and dry cell weight (DCW) concentrations were compared between traditional partial least squares (PLS) and intelligent stacked auto-encoder (SAE) modeling methods. Theresults showed that both PLS and SAE models had good performance in predicting TS and CA. The performance, accuracy, and precision of the PLS models are slightly better than those of the SAE models in predicting TS and CA. SAE model was superior to the PLS model in predicting DCW concentration. The SAE modeling method has advantages in predicting the concentration of complex components. In this study, the multi-parameter online prediction was realized in the complex system of CA fermentation, which provided the basis for real-time intelligent control of the fermentation process.

Morphable models of the lumbar spine to vary geometry based on pathology, demographics, and anatomical measurements

The shape of the lumbar spine influences its function and dysfunction. Yet examining the influence of geometric differences associated with pathology or demographics on lumbar biomechanics is challenging in vivo where these effects cannot be isolated, and the use of simple anatomical measurements does not fully capture the complex three-dimensional geometry. The goal of this work was to develop and share morphable models of the lumbar spine that allow geometry to be varied according to pathology, demographics, or anatomical measurements. Partial least squares regression was used to generate statistical shape models that quantify geometric differences associated with pathology, demographics, and anatomical measurements from the lumbar spines of 87 patients. To determine if the morphable models detected meaningful geometric differences, the ability of the morphable models to classify spines was compared with models generated from random labels. The models for disc herniation (p < 0.04), spondylolisthesis (p < 0.001), and sex (p < 0.01) all performed significantly better than the random models. Age was predicted with a root mean square error of 14.1 years using the age-based model. The morphable models for anatomical measurements were able to produce instances with root mean square errors less than 0.8°, 0.3 cm², and 0.7 mm between desired and resulting measurements. This method can be used to produce morphable models that enable further analysis of the relationship among shape, pathology, demographics, and function through computational simulations. The morphable models and code are available at https://github.com/aclouthier/morphable-lumbar-model.

Automated malarial retinopathy detection using transfer learning and multi-camera retinal images

Cerebral malaria (CM) is a fatal syndrome found commonly in children less than 5 years old in Sub-saharan Africa and Asia. The retinal signs associated with CM are known as malarial retinopathy (MR), and they include highly specific retinal lesions such as whitening and hemorrhages. Detecting these lesions allows the detection of CM with high specificity. Up to 23% of CM, patients are over-diagnosed due to the presence of clinical symptoms also related to pneumonia, meningitis, or others. Therefore, patients go untreated for these pathologies, resulting in death or neurological disability. It is essential to have a low-cost and high-specificity diagnostic technique for CM detection, for which We developed a method based on transfer learning (TL). Models pre-trained with TL select the good quality retinal images, which are fed into another TL model to detect CM. This approach shows a 96% specificity with low-cost retinal cameras.

Vis-NIR hyperspectral imaging coupled with independent component analysis for saffron authentication

In the present contribution, visible-near infrared hyperspectral imaging (Vis-NIR-HSI) combined with a novel chemometric approach based on mean-filed independent component analysis (MF-ICA) followed by multivariate classification techniques is proposed for saffron authentication and adulteration detection. First, MF-ICA was used to exploit pure spatial and spectral profiles of the components. Then, principal component analysis (PCA) and hierarchical cluster analysis (HCA) were used to find patterns of authentic samples based on their distribution maps. Then, detection of five common plant-derived adulterants of saffron including safflower, saffron style, calendula, rubia and turmeric were investigated. For this purpose, partial least squares-discriminant analysis (PLS-DA) for supervised classification to find a boundary between authentic and adulterated saffron samples. Classification accuracies for all models for calibration and prediction sets were 100 %. Finally, a mixed dataset was prepared and analyzed using the proposed strategy which again 100 % of accuracies for calibration and prediction sets were obtained. At the end, data driven soft independent modelling of class analogy (dd-SIMCA) was used to evaluate model for class modeling. Sensitivity was 95% for authentic class and specificities for all adulterants were 100%.

Classification of local diesel fuels and simultaneous prediction of their physicochemical parameters using FTIR-ATR data and chemometrics

Class identification and prediction of physicochemical variables of eight diesel fuel brands collected from several stations within the Atlanta metropolitan area in the State of Georgia were investigated using principal component analysis (PCA), partial least squares discriminant analysis (PLS2-DA), and partial least squares regression (PLSR) as modeling techniques. The fuels were from a common pipeline, therefore, assumed to have very similar characteristics. Ten FTIR-ATR spectra per fuel brand were collected over the 650 - 4000 cm^-1 mid-infrared region, and the 80 x 3351 matrix was submitted to PCA to determine if there were any clusters. Following PCA, the 80 x 3351 matrix was split into a training matrix (56x3351) and a test matrix (24x3351). PLS2-DA models were built and evaluated for class identification using dummy variables (I,0) as input matrix. For physicochemical variable predictions, models were developed via PLSR using the FTIR-ATR spectra training matrix and physicochemical variables obtained from the Georgia Department of Agriculture Labs as input. Correlation coefficients of the eight fuels ranged from 0.9960 to 0.9998. PCA revealed all eight clusters of the diesel fuels, regardless of the tight correlation coefficients range. With a 1.0 ± 0.1 cut-off for fuel identification, the PLS2-DA models showed 100% correct predictions for four or five fuel brands, and 75% correct prediction for all eight fuel brands. PLSR predicted 100% correct physicochemical variables, with a RMSEP range of 0.019 to 1.132 for all 80 variables targeted.

Topic based quality indexes assessment through sentiment

This paper proposes a new methodology called TOpic modeling Based Index Assessment through Sentiment (TOBIAS). This method aims at modeling the effects of the topics, moods, and sentiments of the comments describing a phenomenon upon its overall rating. TOBIAS is built combining different techniques and methodologies. Firstly, Sentiment Analysis identifies sentiments, emotions, and moods, and Topic Modeling finds the main relevant topics inside comments. Then, Partial Least Square Path Modeling estimates how they affect an overall rating that summarizes the performance of the analyzed phenomenon. We carried out TOBIAS on a real case study on the university courses' quality evaluated by the University of Cagliari (Italy) students. We found TOBIAS able to provide interpretable results on the impact of discussed topics by students with their expressed sentiments, emotions, and moods and with the overall rating.

Formative-reflective scheme for the assessment of tourism destination competitiveness: an analysis of Italian municipalities

In this article, we propose a formative-reflective scheme for the assessment of Tourism Destination Competitiveness (TDC) based on a combined use of Partial Least Squares-Path Modelling (PLS-PM) and the method recently proposed by Fattore, Pelagatti, and Vittadini (FPV). TDC is conceived as a construct reflecting the tourism performance of a destination, and several determinants are considered, including endowed resources, created resources, and supporting factors. The proposed scheme is applied to a case study on 1575 Italian municipalities for which the Italian National Institute of Statistics released data on tourist flows. Our contribution is innovative for three aspects: (i) the consistency of the formative-reflective scheme for TDC assessment is discussed on a theoretical basis; (ii) an empirical comparison between PLS-PM and the FPV method is performed; (iii) data with higher granularity than most studies on TDC assessment are employed. Our findings highlight that endowed resources are the primary driver of TDC, followed by created resources and supporting factors, and emphasize that the best ranked destinations are big cities with a multifaceted tourism alongside sea and mountain destinations with cultural attractions.

A study on water quality parameters estimation for urban rivers based on ground hyperspectral remote sensing technology

The purpose of this research is to seek a better inversion algorithm. And on this basis, it explores the feasibility of using hyperspectral monitoring technology instead of laboratory physical and chemical index test and evaluates the prediction effect of inversion model on water quality change. So as to be more convenient, more economical and extensive monitoring methods for water quality monitoring of urban internal river are provided. This paper takes the water samples collected in Fuyang River in downtown Handan as the research object and obtains original spectral data of the samples by the ASD FieldSpec 4 field hyperspectral spectrometer. After the smoothing filter pretreatment by the Savitzky-Golay (SG) method and specified mathematical transformations, the modeling spectral indicators of various water quality parameters are selected and determined by calculating the maximum mean of absolute values for correlation coefficients of various spectral indicators and measured values in the wavelength range from 400 to 950 nm. By introducing partial least squares (PLS), random forest (RF), and Lasso (least absolute shrinkage and selection operator), six water quality parameter fitting models were constructed including turbidity (Turb), suspended substance (SS), chemical oxygen demand (COD), NH4-N, total nitrogen (TN), and total phosphorus (TP), which are also testified and evaluated through hyperspectral data. The results show that different spectral transformation methods highlight different information inversion effects. The first derivative of reciprocal logarithm of spectral data after SG smoothing has a good modeling effect on four water quality parameters including Turb, COD, NH₄-N, and TP; and the first derivative of smoothed spectral data has a good modeling effect on both water quality parameters of SS and TN. Among the three models, the PLS model has a good prediction effect, with the [Formula: see text] for COD, TN, and TP ranging from 0.74 to 0.80, while that for Turb and SS shows relatively poorer prediction effect, followed by even worse effect on HN₄-H. Both machine learning algorithms of RF and Lasso have respectively obtained the best prediction models for different water quality parameters. The Lasso model has a [Formula: see text] value above 0.8 for water body organic pollutants COD, TN, and TP, and the decrease value for [Formula: see text] and [Formula: see text] is below 0.1, which indicates that the model has high prediction accuracy and strong generalization ability, but the results of SS and NH₄-N do not meet the expected accuracy. In the inversion model of RF for COD, [Formula: see text] is higher than [Formula: see text], which shows excellent performance, and has certain prediction ability for SS and NH₄-N. The RF model and Lasso model complement each other effectively in applicability and prediction accuracy. Compared with the traditional regression model PLS, machine learning has obvious overall advantages, making it more suitable for classified inversion prediction of urban river water quality parameters.

Evaluation of an individualized facial growth prediction model based on the multivariate partial least squares method

OBJECTIVES

To develop a facial growth prediction model incorporating individual skeletal and soft tissue characteristics.

MATERIALS AND METHODS

Serial longitudinal lateral cephalograms were collected from 303 children (166 girls and 137 boys), who had never undergone orthodontic treatment. A growth prediction model was devised by applying the multivariate partial least squares (PLS) algorithm, with 161 predictor variables. Response variables comprised 78 lateral cephalogram landmarks. Multiple linear regression analysis was performed to investigate factors influencing growth prediction errors.

RESULTS

Using the leave-one-out cross-validation method, a PLS model with 30 components was developed. Younger age at prediction resulted in greater prediction error (0.03 mm/y). Further, prediction error increased in proportion to the growth prediction interval (0.24 mm/y). Girls, subjects with Class II malocclusion, growth in the vertical direction, skeletal landmarks, and landmarks on the maxilla were associated with more accurate prediction results than boys, subjects with Class I or III malocclusion, growth in the anteroposterior direction, soft tissue landmarks, and landmarks on the mandible, respectively.

CONCLUSIONS

The prediction error of the prediction model was proportional to the remaining growth potential. PLS growth prediction seems to be a versatile approach that can incorporate large numbers of predictor variables to predict numerous landmarks for an individual subject.

Comprehensive examination and comparison of machine learning techniques for the quantitative determination of adulterants in honey using Fourier infrared spectroscopy with attenuated total reflectance accessory

Facile, robust, and accurate analyses of honey adulterants are required in the honey industry to assess its purity for commercialization purposes. A stacked regression ensemble approach using Fourier transform infrared spectroscopic method was developed for the quantitative determination of corn, cane, beet, and rice syrup adulterants in honey. A training set (n=81) was used to predict the percent adulterant composition of the aforementioned constituents in an independent test set (n=32). A comprehensive comparison of the performance of various machine learning techniques including support vector regression using linear function, least absolute shrinkage and selection operator, ride regression, elastic net, partial least squares, random forests, recursive partitioning and regression trees, gradient boosting, and gaussian process regression was assessed. The predictive performance of the aforementioned machine learning approaches was then compared with stacked regression, an ensemble learning technique which collates the performance of the various abovementioned techniques. Results show that stacked regression did not primarily outperform other techniques across all four syrup adulterant constituents in the testing set data. Further, elastic net generalized linear model generated the optimum results (Rootmeansquareerrorofprediction(RMSEP)_average=0.0107,R_average²=0.809) across all four honey adulterant constituents. Elastic net coupled with Fourier transform infrared spectroscopy may offer a novel, direct, and accurate method of simultaneously quantifying corn, cane, beet, and rice syrup adulterants in honey.

A stacked regression ensemble approach for the quantitative determination of biomass feedstock compositions using near infrared spectroscopy

Rapid, robust, and accurate biomass compositional analyses are required in the bioenergy industry to accurately determine the chemical composition of biomass feedstocks. A stacked regression ensemble approach using near infrared spectroscopic method was developed for the quantitative determination of glucan, xylan, lignin, ash, and extract in biomass feedstocks. A comprehensive comparison of the performance of various machine learning techniques including support vector regression (linear and radial), least absolute shrinkage and selection operator (LASSO), ridge regression, elastic net, partial least squares, random forests, recursive partitioning and regression trees, gradient boosting, and gaussian process regression was assessed in the training set data (n = 188). The predictive performance of the aforementioned machine learning approaches was then compared with stacked regression, an ensemble learning algorithm which collates the performance of the abovementioned machine learning regression techniques. Results show that the stacked regression primarily outperformed other machine learning techniques (Root mean square error of prediction (RMSEP)_average=1.660%wt,R²=0.907) across all five constituents in the validation set data (n = 81). Further results also show that the RMSEP of the stacked ensemble technique is significantly different than that of the partial least squares (PLS) approach in predicting glucan, ash, lignin, and extract components in biomass samples. The stacked ensemble learning approach offers an alternative method for a more accurate prediction of biomass compositions than the traditional PLS technique.

Sex-specific associations in verbal memory brain circuitry in early psychosis

Hippocampal circuitry and related cortical connections are altered in first episode psychosis (FEP) and are associated with verbal memory deficits, as well as positive and negative symptoms. There are robust sex differences in the clinical presentation of psychosis, including poorer verbal memory in male patients. Consideration of sex differences in hippocampal-cortical circuitry and their associations with different behavioral dimensions may be useful for understanding the underlying pathophysiology of verbal memory deficits and related symptomatology in psychosis. Here, we use a data-driven approach to simultaneously capture the complex links between sex, verbal memory, symptoms, and cortical-hippocampal brain metrics in FEP. Structural magnetic resonance imaging and behavioral data were acquired from 100 FEP patients (75 males, 25 females) and 87 controls (55 males, 32 females). Multivariate brain-behavior associations were examined in FEP using partial least squares to map sociodemographic, verbal memory, and clinical data onto brain morphometry. The analysis identified two sex-dependent patterns of verbal memory, symptoms, and brain structure. In male patients, verbal memory deficits and core psychotic symptoms were associated with both increased and decreased frontal and temporal cortical thickness and reductions in CA2/3 hippocampal subfield and fornix volumes. In female patients, fewer negative/depressive symptoms were associated with a more attenuated cortical thickness pattern and more diffuse reductions in hippocampal white matter regions. Taken together, the results contribute towards better understanding the underlying pathophysiology of psychosis by highlighting the unique contribution of specific hippocampal subfields and surrounding white matter and their connections with broader cortical networks in a sex-dependent manner.

Identification and quantification of adulterated honey by Raman spectroscopy combined with convolutional neural network and chemometrics

In this study, Raman spectroscopy combined with convolutional neural network (CNN) and chemometrics was used to achieve the identification and quantification of honey samples adulterated with high fructose corn syrup, rice syrup, maltose syrup and blended syrup, respectively. The shallow CNNs utilized to analyze honey mixed with single-variety syrup classified samples into four categories by the adulteration concentration with more than 97% accuracy, and the general CNN model for simultaneously detecting honey adulterated with any type of syrup obtained an accuracy of 94.79%. The established CNNs had the best performance compared with several chemometric classification algorithms. In addition, partial least square regression (PLS) successfully predicted the purity of honey mixed with single syrup, while coefficients of determination and root mean square errors of prediction were greater than 0.98 and less than 3.50, respectively. Therefore, the proposed methods based on Raman spectra have important practical significance for food safety and quality control of honey products.

Social support as a mediator in the relationship between perceived stress and nomophobia: An Investigation among Malaysian university students during the COVID-19 pandemic

This study examined the mediating role of social support in the relationship between perceived stress and nomophobia among Malaysian university students during the COVID-19 pandemic. A cross-sectional study was conducted with N = 547 university students. Participants answered a self-administered questionnaire measuring nomophobia, social support, and perceived stress. Exploratory analyses were conducted using partial least square structural equation modelling. We found that perceived stress was positively associated with nomophobia during the COVID-19 pandemic, whilst social support partially mediated the relationship between perceived stress and nomophobia. The results of this study indicated that stress may be buffered by social support in individuals with higher levels of nomophobia.

Effect of lean manufacturing tools on sustainability: the case of Mexican maquiladoras

The Mexican maquiladora industry is applying Lean Manufacturing Tools (LMT) in its production lines; however, few studies have investigated its relationship with sustainability (social, economic, and environmental). This paper presents a second-order structural equation model (SEM) relating 8 LMT integrated into three independent latent variables: continuous improvement (Kaizen and Gemba), supporting tools (Andon, visual management, and Poka-yoke), and machinery and equipment (total productive maintenance, overall equipment effectiveness, and Jidoka) that are related to social, economic, and environmental sustainability as dependent variables. The model is validated with information obtained from 249 companies using partial least squares. Findings show that the application of LMT in the Mexican maquiladora industry avoids the generation of waste and reprocessing. Likewise, the improvement of production processes reduces the waste emitted into the environment and reduces energy consumption. Also, when companies have environmental programs, the work environment is safe, and labor relations are improved, increasing morale and the commitment to work for the company, gaining economic and ecological benefits.

Scale invariance in fNIRS as a measurement of cognitive load

Scale invariant neural dynamics are a relatively new but effective means of measuring changes in brain states as a result of varied cognitive load and task difficulty. This study tests whether scale invariance (as measured by the Hurst exponent, H) can be used with functional near-infrared spectroscopy (fNIRS) to quantify cognitive load, paving the way for scale-invariance to be measured in a variety of real-world settings. We analyzed H extracted from the fNIRS time series while participants completed an N-back working memory task. Consistent with what has been demonstrated in fMRI, the current results showed that scale-invariance analysis significantly differentiated between task and rest periods as calculated from both oxy- (HbO) and deoxy-hemoglobin (HbR) concentration changes. Results from both channel-averaged H and a multivariate partial least squares approach (Task PLS) demonstrated higher H during the 1-back task than the 2-back task. These results were stronger for H derived from HbR than from HbO. This suggests that scale-free brain states are a robust signature of cognitive load and not limited by the specific neuroimaging modality employed. Further, as fNIRS is relatively portable and robust to motion-related artifacts, these preliminary results shed light on the promising future of measuring cognitive load in real life settings.