Search

In the emerging field of materials informatics, a fundamental task is to identify physicochemically meaningful descriptors, or materials genes, which are engineered from primary features and a set of elementary algebraic operators through compositions. Standard practice directly analyzes the high-dimensional candidate predictor space in a linear model; statistical analyses are then substantially hampered by the daunting challenge posed by the astronomically large number of correlated predictors with limited sample size. We formulate this problem as variable selection with operator-induced structure (OIS) and propose a new method to achieve unconventional dimension reduction by using the geometry embedded in OIS. Although the model remains linear, we iterate nonparametric variable selection for effective dimension reduction. This enables variable selection based on ab initio primary features, leading to a method that is orders of magnitude faster than existing methods, with improved accuracy. To select the nonparametric module, we discuss a desired performance criterion that is uniquely induced by variable selection with OIS; in particular, we propose to employ a Bayesian Additive Regression Trees (BART)-based variable selection method. Numerical studies show superiority of the proposed method, which continues to exhibit robust performance when the input dimension is out of reach of existing methods. Our analysis of single-atom catalysis identifies physical descriptors that explain the binding energy of metal-support pairs with high explanatory power, leading to interpretable insights to guide the prevention of a notorious problem called sintering and aid catalysis design. for this article are available online. [ABSTRACT FROM AUTHOR]

Children's health studies support an association between maternal environmental exposures and children's birth outcomes. A common goal is to identify critical windows of susceptibility—periods during gestation with increased association between maternal exposures and a future outcome. The timing of the critical windows and magnitude of the associations are likely heterogeneous across different levels of individual, family, and neighborhood characteristics. Using an administrative Colorado birth cohort we estimate the individualized relationship between weekly exposures to fine particulate matter (PM2.5) during gestation and birth weight. To achieve this goal, we propose a statistical learning method combining distributed lag models and Bayesian additive regression trees to estimate critical windows at the individual level and identify characteristics that induce heterogeneity from a high-dimensional set of potential modifying factors. We find evidence of heterogeneity in the PM2.5—birth weight relationship, with some mother—child dyads showing a three times larger decrease in birth weight for an IQR increase in exposure (5.9–8.5 μ g / m 3 PM2.5) compared to the population average. Specifically, we find increased vulnerability for non-Hispanic mothers who are either younger, have higher body mass index or lower educational attainment. Our case study is the first precision health study of critical windows. for this article are available online. [ABSTRACT FROM AUTHOR]

This article shows that decision trees constructed with Classification and Regression Trees (CART) and C4.5 methodology are consistent for regression and classification tasks, even when the number of predictor variables grows sub-exponentially with the sample size, under natural 0-norm and 1-norm sparsity constraints. The theory applies to a wide range of models, including (ordinary or logistic) additive regression models with component functions that are continuous, of bounded variation, or, more generally, Borel measurable. Consistency holds for arbitrary joint distributions of the predictor variables, thereby accommodating continuous, discrete, and/or dependent data. Finally, we show that these qualitative properties of individual trees are inherited by Breiman's random forests. A key step in the analysis is the establishment of an oracle inequality, which allows for a precise characterization of the goodness of fit and complexity tradeoff for a mis-specified model. for this article are available online. [ABSTRACT FROM AUTHOR]

Representative of the Slovak Republic M.S. in the years 2010-2016, she recorded a progressive growth of sports performance in swimming disciplines (50m butterfly 28.75 s, 100m butterfly 1:05.40 and 100m freestyle 55.86 s). In the 2012 annual training macrocycle, she achieved performances in the disciplines of 50m freestyle with a time of 25.53 and 100m freestyle with a time of 56.38. Retrospective analysis classified special and general training means that showed the highest tightness with sports performance in swimming. Non-parametric procedures such as Spearman's correlation coefficient and CHAID decision trees were used for interaction detection and prediction. When analyzing the data, we used the method of studying the training diaries from the 2012 annual training cycle. From the point of view of general training indicators, we focused on days of loading (GTI 110), the number of training units (GTI 111), the number of events (GTI 112), the total load time (GTI 113), regeneration time (GTI 114) and days of medical incapacity (GTI 115). Of the special training indicators, we focused on the total number of kilometers flown (STI 101), the volume of warm-up and swim-out (STI 102), the volume of aerobic endurance (STI 103), the volume of anaerobic endurance (STI 104), the volume of load swam in race pace (STI 105), elemental arm swimming (STI 106), elemental leg swimming (STI 107), technical exercises (STI 108). Among the special training indicators, the determinants of sports performance included the volume of warm-up and swim-out (STI 102) and elemental arm swimming (STI 106). Of the general training means, the number of events (GTI 112), days of loading (GTI 110) and the number of training units (GTI 111) determined the year-round sports performance. The exact identification of training means in terms of volume and intensity will allow us to rationalize the periodization of the training load, harmonize the conceptual starting points and improve the system of tuning the sports form of the observed swimmer for the next top world events. [ABSTRACT FROM AUTHOR]

Land subsidence (LS) due to natural and human-driven forces (e.g., earthquakes and overexploitation of groundwater) has detrimental and irreversible impacts on the environmental, economic, and social aspects of human life. Thus, LS hazard mapping, monitoring, and prediction are important for scientists and decision-makers. This study evaluated the performance of seven machine learning approaches (MLAs), comprising six classification approaches and one regression approach, namely (1) classification and regression trees (CARTs), (2) boosted regression tree (BRT), (3) Bayesian linear regression (BLR), (4) support vector machine (SVM), (5) random forest (RF), (6) logistic regression (LogR), and (7) multiple linear regression (MLR), in generating LS susceptibility maps and predicting LS in two case studies (Semnan Plain and Kashmar Plain in Iran) with varying intrinsic characteristics and available data points. Multiple input variables (slope, aspect, groundwater drawdown, distance from the river, distance from the fault, lithology, land use, topographic wetness index (TWI), and normalized difference vegetation index (NDVI)), were used as predictors. BRT outperformed the other classification approaches in both case studies, with accuracy rates of 75% and 74% for Semnan and Kashmar plains, respectively. The MLR approach yielded a Mean Square Error (MSE) of 0.25 for Semnan plain and 0.32 for Kashmar plain. According to the BRT approach, the variables playing the most significant role in LS in Semnan Plain were groundwater drawdown (20.31%), distance from the river (17.11%), land use (14.98%), NDVI (12.75%), and lithology (11.93%). Moreover, the three most important factors in LS in Kashmar Plain were groundwater drawdown (35.31%), distance from the river (23.1%), and land use (12.98%). The results suggest that the BRT method is not significantly affected by data set size, but increasing the number of training set data points in MLR results in a decreased error rate. [ABSTRACT FROM AUTHOR]

We introduce a three-step framework to determine at which pitches Major League batters should swing. Unlike traditional plate discipline metrics, which implicitly assume that all batters should always swing at (resp. take) pitches inside (resp. outside) the strike zone, our approach explicitly accounts not only for the players and umpires involved in the pitch but also in-game contextual information like the number of outs, the count, baserunners, and score. We first fit flexible Bayesian nonparametric models to estimate (i) the probability that the pitch is called a strike if the batter takes the pitch; (ii) the probability that the batter makes contact if he swings; and (iii) the number of runs the batting team is expected to score following each pitch outcome (e.g. swing and miss, take a called strike, etc.). We then combine these intermediate estimates to determine whether swinging increases the batting team's run expectancy. Our approach enables natural uncertainty propagation so that we can not only determine the optimal swing/take decision but also quantify our confidence in that decision. We illustrate our framework using a case study of pitches faced by Mike Trout in 2019. [ABSTRACT FROM AUTHOR]

Biogenic habitats are foundational habitats for species assemblages and drive a range of ecosystem functions. The Hauraki Gulf/Tiikapa Moana is the most intensively used coastal area in Aotearoa/New Zealand, and decades of commercial fishing, sedimentation and industrialization have degraded biogenic habitats in the Gulf. In response, the marine spatial plan 'Sea Change' includes proposals to create new and extend existing marine protected areas (MPAs) and restrict the area open to mobile bottom‐impact fishing methods to conserve and help the recovery of biogenic habitats.To assess the benefits of different spatial planning scenarios for biogenic habitats, information on their spatial distribution is needed, but data limitations are a significant challenge. Here, an approach is detailed that maximized the information extracted from limited species occurrence data, by incorporating expert knowledge to develop and evaluate models of biogenic habitat‐forming taxa.Ensemble habitat suitability models (using boosted regression tree and random forest models) were created for 20 biogenic habitat groups. Using withheld data for validation, area under curve (AUC) scores ranged from 0.58 to 0.95 and true skill statistics (TSS) ranged from 0.37 to 0.84, though three models were further evaluated as insufficient representations of known ecological habitats by expert assessors.Models produced here provide substantially increased information to inform progress on implementation of the Sea Change plan. Two stakeholder processes have been held, resulting in the development of spatial plans for bottom trawl mitigation that are currently under public consultation. Systematic surveys that gather abundance and high‐resolution environmental data should be a priority to improve the utility of predictive models and inform future management processes in the Hauraki Gulf, and funding has been allocated to support additional data collection to determine the effectiveness of spatial management measures in the Hauraki Gulf. [ABSTRACT FROM AUTHOR]

Purpose: Recognition of tool failure is an everlasting problem for the manufacturing industry, which leads to diminishing productivity and quality of the product. Much research has been conducted on intelligent tool condition monitoring (TCM) techniques. Machine-learning-based techniques comprise pattern recognition of signals to obtain intelligent decision-making. However, dealing with diversified data distributions' present and future moments is complex and needs robust models. This paper aims to develop a generalized statistical model of spindle vibrations trained using random forest. Methods: The real-time vibration evolved during machining was collected by performing experimentation considering different tool wear conditions of the face milling cutter. A thorough statistical analysis was undertaken considering hyperparameter tuning of the random forest—a multitude of decision trees, thereby attempting to provide generalization and robustness to the model. Results: Compared to various hyperparameters, the maximum depth of the tree showed a more significant influence on the performance of the vanilla model as it regulates its growth on a macro-level. While tuning the tree concerning minimum sample split, no notable splits were observed because the minimum splitting requirement of the node attained a peak and led to the underfitting of random forests. Thus, the allocation of the improvised value of minimum sample split eliminates the anomaly posed by underfitting. Conclusion: The robustness analysis of the random forest tree consisting of hyperparameter tuning has successfully eliminated the underfitting and overfitting of the model by showcasing an improvement and downfall in the performance, respectively. Here, the downfall in the accuracy indicates the ability of the tuned model to access unknown instances, thereby showing the generalization of the model concerning blind data. The results obtained using the overall framework indicate that the tuned random forest tree algorithm is appropriate and proficient for fault classification. This ML-based classification approach shall offer effective and optimum cutting tool usage and save considerable tooling costs. [ABSTRACT FROM AUTHOR]

The deep learning method has been widely used in the engineering field. The availability of the training dataset is one of the most important limitations of the deep learning method. Accurate prediction of pavement performance plays a vital role in road preventive maintenance (PM) and decision-making. Pavement performance prediction based on deep learning has been widely used around the world for its accuracy, robustness, and automation. However, most of the countries in the world have not built their pavement performance historical database, which prevents preventive maintenance using the deep learning method. This study presents an innovative particle swarm optimization (PSO) algorithm-enhanced two-stage TrAdaBoost.R2 transfer learning algorithm, which could significantly increase the pavement performance prediction database. The Long-Term Pavement Performance (LTPP) database is used as the source domain data, and one of the highways in China is chosen as the target domain to predict pavement performance. The results show that the proposed PSO-Two-stage TrAdaBoost.R2 model has the highest accuracy compared with AdaBoost.R2 model and traditional regression decision tree model. The validation case study shows significant consistency between the predicted International Roughness Index (IRI) and the whole-year measurement data with an R2 of 0.7. This study demonstrates the great potential of the innovative instance-based transfer learning method in pavement performance prediction of a region's lack of data. This study also contributes to other engineering fields that could greatly increase the universality of deep learning. [ABSTRACT FROM AUTHOR]

Bangladesh's remarkable achievements in economic and social progress have placed the country in a position that was unimaginable just 20 years ago. However, has such improvement in development outcomes been equal across all areas within the country? We aim to address this question by analyzing district-level income per capita derived from the 2000 and 2016 rounds of the Household Income and Expenditure Survey. Using models based on standard neoclassical economic convergence theory, which may also account for natural disasters, we find little evidence of convergence. This suggests that income differentials among Bangladesh's 64 districts persist. We also examined the possibility of multiple steady states by estimating models with a three-club structure based on income percentiles as registered in 2000. However, we found no evidence of conditional convergence. Additionally, we explored the potential for endogenous club formation using regression trees and machine learning algorithms. Yet, once again, the results did not support convergence. Overall, our findings reveal no evidence of conditional convergence in income among Bangladesh's districts. This implies that policy implications might vary, with targeted interventions possibly necessary to address the specific factors hindering convergence among similar regions. [ABSTRACT FROM AUTHOR]

Machine learning algorithms often require large training sets to perform well, but labeling such large amounts of data is not always feasible, as in many applications, substantial human effort and material cost is needed. Finding effective ways to reduce the size of training sets while maintaining the same performance is then crucial: one wants to choose the best sample of fixed size to be labeled among a given population, aiming at an accurate prediction of the response. This challenge has been studied in detail in classification, but not deeply enough in regression, which is known to be a more difficult task for active learning despite its need in practice. Few model-free active learning methods have been proposed that detect the new samples to be labeled using unlabeled data, but they lack the information of the conditional distribution between the response and the features. In this paper, we propose a standard regression tree-based active learning method for regression that improves significantly upon existing active learning approaches. It provides impressive results for small and large training sets and an appreciably low variance within several runs. We also exploit model-free approaches, and adapt them to our algorithm to utilize maximum information. Through experiments on numerous benchmark datasets, we demonstrate that our framework improves existing methods and is effective in learning a regression model from a very limited labeled dataset, reducing the sample size for a fixed level of performance, even with many features. [ABSTRACT FROM AUTHOR]

This paper proposes a new method for network screening on rural low-volume roads. These roads are important as they provide critical access to agricultural land and tourist attractions. Most low-volume roads belong to the lowest functional class (local rural roads) and thus are built to lower design standards. Conventional hot spot network screening techniques may not be appropriate for low-volume roads due to the sporadic nature of crashes occurring on these roads. Conversely, sophisticated network screening approaches require extensive roadway and traffic data that are often unavailable to local agencies due to a lack of resources, and/or a lack of technical expertise. This research attempts to address these obstacles to low-volume road network screening which aims to identify candidate sites for safety improvements. The research used an extensive low-volume road sample from the state of Oregon and Empirical Bayes expected number of crashes in developing the proposed models for network screening. The proposed models do not require exact measurements of roadway geometric features as all geometric variables were classified into categories that are easy to compile by local agencies. Further, the method could be used with and without traffic data, without compromising the effectiveness of the network screening process. [ABSTRACT FROM AUTHOR]

Forensic psychiatric hospitals regularly monitor the mental health and forensic risk factors of their patients. As part of this monitoring, staff score patients on various items. Common practice is to aggregate these scores across staff members. However, this is suboptimal because it assumes that assessors are interchangeable and that patients are independent. An improvement over averaging scores is the use of Cultural Consensus Theory (CCT), which imposes a hierarchical model across patients, staff members, and items. While accounting for differences between patients and staff members, CCT estimates a 'true' score for each patient on each item based on the consensus among staff members. Here, we apply a CCT model to data from a Dutch maximum-security forensic psychiatric centre and use the inferences to predict violent behaviour in patients. The CCT model outpredicts several alternatives, such as random forest and boosted regression trees, albeit by a small margin. We discuss practical limitations and directions for how future monitoring of patients could be adapted to maximize the added value of a CCT-based approach. [ABSTRACT FROM AUTHOR]

Consider the problem of determining the Bayesian credibility mean $E(X_{n+1}|X_1,\cdots, X_n),$ whenever the random claims $X_1,\cdots, X_n,$ given parameter vector $\boldsymbol{\Psi},$ are sampled from the K-component mixture family of distributions, whose members are the union of different families of distributions. This article begins by deriving a recursive formula for such a Bayesian credibility mean. Moreover, under the assumption that using additional information $Z_{i,1},\cdots,Z_{i,m},$ one may probabilistically determine a random claim $X_i$ belongs to a given population (or a distribution), the above recursive formula simplifies to an exact Bayesian credibility mean whenever all components of the mixture distribution belong to the exponential families of distributions. For a situation where a 2-component mixture family of distributions is an appropriate choice for data modelling, using the logistic regression model, it shows that: how one may employ such additional information to derive the Bayesian credibility model, say Logistic Regression Credibility model, for a finite mixture of distributions. A comparison between the Logistic Regression Credibility (LRC) model and its competitor, the Regression Tree Credibility (RTC) model, has been given. More precisely, it shows that under the squared error loss function, it shows the LRC's risk function dominates the RTC's risk function at least in an interval which about $0.5.$ Several examples have been given to illustrate the practical application of our findings. [ABSTRACT FROM AUTHOR]

Post-stratification is applied when the subpopulation membership is observed only for sampled values and the goal is to estimate stratum-specific parameters which leads the survey statisticians towards primary goals i.e., classification of non-sampled units into different strata and prediction of the values of the study variables. Regression models, on one side, optimize the prediction of the study variable's non-sampled values while the classification algorithms, on the other side, look for the classification of non-sampled cases into different strata. Hence, it is crucial to deal with these two goals simultaneously for the estimation of stratum-specific parameters. This study introduces the idea of a double-objective classification and regression trees (CARTs) approach for estimating stratum-specific parameters. Theoretical properties of the total estimator are derived. An application on the estimation of health outcomes in different domains is given to delineate the practical significance as well as the efficiency of the proposed CART-based method. The proposed estimator of population total performs better than the existing stratum-specific estimator in terms of relative efficiency for all choices of parameters. As an ensemble model, the random forest CART outperforms the other competing tree-based models and homogenous population model without using any auxiliary variable. [ABSTRACT FROM AUTHOR]

The prediction of flight delays is one of the important and challenging issues in the field of scheduling and planning flights by airports and airlines. Therefore, in recent years, we have witnessed various methods to solve this problem using machine learning techniques. In this article, a new method is proposed to address these issues. In the proposed method, a group of potential indicators related to flight delay is introduced, and a combination of ANOVA and the Forward Sequential Feature Selection (FSFS) algorithm is used to determine the most influential indicators on flight delays. To overcome the challenges related to large flight data volumes, a clustering strategy based on the DBSCAN algorithm is employed. In this approach, samples are clustered into similar groups, and a separate learning model is used to predict flight delays for each group. This strategy allows the problem to be decomposed into smaller sub-problems, leading to improved prediction system performance in terms of accuracy (by 2.49%) and processing speed (by 39.17%). The learning model used in each cluster is a novel structure based on a random forest, where each tree component is optimized and weighted using the Coyote Optimization Algorithm (COA). Optimizing the structure of each tree component and assigning weighted values to them results in a minimum 5.3% increase in accuracy compared to the conventional random forest model. The performance of the proposed method in predicting flight delays is tested and compared with previous research. The findings demonstrate that the proposed approach achieves an average accuracy of 97.2% which indicates a 4.7% improvement compared to previous efforts. [ABSTRACT FROM AUTHOR]

Background: Infectious diarrhea remains a major public health problem worldwide. This study used stacking ensemble to developed a predictive model for the incidence of infectious diarrhea, aiming to achieve better prediction performance. Methods: Based on the surveillance data of infectious diarrhea cases, relevant symptoms and meteorological factors of Guangzhou from 2016 to 2021, we developed four base prediction models using artificial neural networks (ANN), Long Short-Term Memory networks (LSTM), support vector regression (SVR) and extreme gradient boosting regression trees (XGBoost), which were then ensembled using stacking to obtain the final prediction model. All the models were evaluated with three metrics: mean absolute percentage error (MAPE), root mean square error (RMSE), and mean absolute error (MAE). Results: Base models that incorporated symptom surveillance data and weekly number of infectious diarrhea cases were able to achieve lower RMSEs, MAEs, and MAPEs than models that added meteorological data and weekly number of infectious diarrhea cases. The LSTM had the best prediction performance among the four base models, and its RMSE, MAE, and MAPE were: 84.85, 57.50 and 15.92%, respectively. The stacking ensembled model outperformed the four base models, whose RMSE, MAE, and MAPE were 75.82, 55.93, and 15.70%, respectively. Conclusions: The incorporation of symptom surveillance data could improve the predictive accuracy of infectious diarrhea prediction models, and symptom surveillance data was more effective than meteorological data in enhancing model performance. Using stacking to combine multiple prediction models were able to alleviate the difficulty in selecting the optimal model, and could obtain a model with better performance than base models. [ABSTRACT FROM AUTHOR]

Background: The incidence of Antimicrobial Resistance (AMR) in uropathogens varies between countries and over time. We aim to study the patterns and potential predictors of AMR among patients with UTIs admitted to the Urology Department at Alexandria University Hospital. Methods: An observational retrospective record-based study was conducted on all patients admitted to the Urology department from October 2018 to October 2020. Data collected from patients' records included: demographic data, diagnosis on admission, history of chronic diseases, duration of hospital stay, insertion of a urinary catheter, duration of the catheter in days, history of the use of antibiotics in the previous three months, and history of urinary tract operations. If UTI was documented, we abstracted data about urine culture, use of antibiotics, results of urine cultures, type of organism isolated, and sensitivity to antibiotics. We conducted a multivariable logistic regression model. We performed Classification and Regression Tree Analysis (CART) for predicting risk factors associated with drug resistance among patients with UTI. Data were analyzed using SPSS statistical package, Version 28.0, and R software (2022). Results: This study encompassed 469 patients with UTIs. The most commonly isolated bacterium was Escherichia coli, followed by Klebsiella pneumoniae. Multidrug resistance (MDR) was found in 67.7% (149/220) of patients with hospital-acquired UTIs and in 49.4% (83/168) of patients with community-acquired UTIs. Risk factors independently associated with antimicrobial resistance according to logistic regression analysis were the use of antibiotics within three months (AOR = 5.2, 95% CI 2.19–12.31), hospital-acquired UTI (AOR = 5.7, 95% CI 3.06–10.76), diabetes mellitus (AOR = 3.8, 95% CI 1.24–11.84), age over 60 years (AOR = 2.9, 95% CI 1.27–6.72), and recurrent UTI (AOR = 2.6, 95% CI 1.08–6.20). Classification and regression tree (CART) analysis revealed that antibiotic use in the previous three months was the most significant predictor for developing drug resistance. Conclusion: The study concluded a high level of antimicrobial resistance as well as significant MDR predictors among hospitalized patients with UTIs. It is vital to assess resistance patterns in our hospitals frequently to improve rational antibiotic treatment as well as to sustain antimicrobial stewardship programs and a rational strategy in the use of antibiotics. Empirical therapy for UTI treatment should be tailored to the potential pathogens' susceptibility to ensure optimal treatment. Strategic antibiotic use is essential to prevent further AMR increases. Further research should focus on suggesting new biological systems or designed drugs to combat the resistance of UTI pathogens. [ABSTRACT FROM AUTHOR]

The conventional method for the color-matching process involves the compounding of polymers with pigments and then preparing plaques by using injection molding before measuring the color by an offline spectrophotometer. If the color fails to meet the L*, a*, and b* standards, the color-matching process must be repeated. In this study, the aim is to develop a machine learning model that is capable of predicting offline color using data from inline color measurements, thereby significantly reducing the time that is required for the color-matching process. The inline color data were measured using an inline process spectrophotometer, while the offline color data were measured using a bench-top spectrophotometer. The results showed that the Bagging with Decision Tree Regression and Random Forest Regression can predict the offline color data with aggregated color differences (dE) of 10.87 and 10.75. Compared to other machine learning methods, Bagging with Decision Tree Regression and Random Forest Regression excel due to their robustness, ability to handle nonlinear relationships, and provision of insights into feature importance. This study offers valuable guidance for achieving Bagging with Decision Tree Regression and Random Forest Regression to correlate inline and offline color data, potentially reducing time and material waste in color matching. Furthermore, it facilitates timely corrections in the event of color discrepancies being observed via inline measurements. [ABSTRACT FROM AUTHOR]

Background: To investigate the accuracy of an F22 Aligner system, considering the amount of prescribed movement, tooth type, grip points, sex and age. Methods: Digital models of 120 patients (64 females and 56 males; mean age 35.2 years ± 7.4) affected by mild-to-moderate Class I malocclusion and treated via F22 Aligners, retrospectively selected from the University of Ferrara Orthodontics Clinic's electronic database; post-treatment models were generated, and three angular values per tooth and four linear intra-arch measurements per arch were acquired. For angular measurements, planned (T1) and achieved (T2) values were obtained thorough digital model superimpositions. Linear measurements were acquired from pre-treatment, reference and post-treatment models. Statistical comparisons were performed to assess accuracy among tooth types and prescribed movements, tooth type, grip points, sex and age were investigated via chi-squared automatic interaction detection regression trees. Results: Mean accuracy for inclination and angulation were 86.76% and 88.01%, respectively, whereas rotation was less accurate (61.59%), especially for rounded teeth. All variables investigated influenced accuracy, with the exception of inclination, which was only influenced by age. Regarding linear measurements, good expansive capacity was shown, except for the distance between mandibular second premolars. Conclusions: F22 aligners are a viable solution for the treatment of Class I malocclusion of mild-to-moderate complexity, although clinicians should bear in mind the lower predictability of rotation, as well as the influence of the variables investigated. [ABSTRACT FROM AUTHOR]

Accurately quantifying the relative effects of climate change and human activities on soil carbon, nitrogen, and phosphorus in alpine grasslands and their feedback is an important aspect of global change, and high-precision models are the key to solving this scientific problem with high quality. Therefore, nine models, the random forest model (RFM), generalized boosted regression model (GBRM), multiple linear regression model (MLRM), support vector machine model (SVMM), recursive regression tree model (RRTM), artificial neural network model (ANNM), generalized linear regression model (GLMR), conditional inference tree model (CITM), and eXtreme gradient boosting model (eXGBM), were used for modeling soil organic carbon (SOC), total nitrogen (TN), total phosphorus (TP), the ratio of SOC to TN (C:N), the ratio of SOC to TP (C:P), and the ratio of TN to TP (N:P) at depths of 0-10, 10-20, and 20-30 cm under non-grazing and free-grazing scenarios in the Xizang grasslands. Annual radiation (ARad), annual precipitation (AP), and annual temperature (AT) were used as independent variables under non-grazing scenarios, whereas ARad, AP, AT, and growing season maximum normalized difference vegetation index (NDVImax) were used as independent variables under free-grazing scenarios. Overall, the RFM and GBRM were more accurate than the other seven models. However, the tree numbers of the GBRM were much larger than those of the RFM, indicating that the GBRM may have a greater model complexity and lower running speed. Therefore, the RFM had the best performance among the nine models in modeling SOC, TN, TP, C:N, C:P, and N:P in the Xizang grasslands. The RFM established in this study can not only help scientists save time and money on massive sampling and analysis, but can also be used to construct a database of SOC, TN, and TP, and their ratios, and further scientific research related to ecological and environmental issues (e.g., examining whether soil systems intensified global warming over the past few decades by exploring whether climate change and human activities altered soil organic carbon) in the grasslands of Xizang Plateau. [ABSTRACT FROM AUTHOR]

Introduction: Increased mortality after acute and chronic spinal cord injury (SCI) remains a challenge and mandates a better understanding of the factors contributing to survival in these patients. This study investigated whether body mass index (BMI) measured after acute traumatic SCI is associated with a change in mortality. Methods: A prospective longitudinal cohort study was conducted with 742 patients who were admitted to the Acute Spine Unit of the Vancouver General Hospital between 2004 and 2016 with a traumatic SCI. An investigation of the association between BMI on admission and long-term mortality was conducted using classification and regression tree (CART) and generalized additive models (spline curves) from acute care up to 7.7 years after SCI (chronic phase). Multivariable models were adjusted for (i) demographic factors (e.g., age, sex, and Charlson Comorbidity Index) and (ii) injury characteristics (e.g., neurological level and severity and Injury Severity Score). Results: After the exclusion of incomplete datasets (n = 602), 643 patients were analyzed, of whom 102 (18.5%) died during a period up to 7.7 years after SCI. CART identified three distinct mortality risk groups: (i) BMI: > 30.5 kg/m2, (ii) 17.5-30.5 kg/m2, and (iii) < 17.5 kg/m2. Mortality was lowest in the high BMI group (BMI > 30.5 kg/m2), followed by the middle-weight group (17.5-30.5 kg/m2), and was highest in the underweight group (BMI < 17.5 kg/m2). High BMI had a mild protective effect against mortality after SCI (hazard ratio 0.28, 95% CI: 0.09-0.88, p = 0.029), concordant with a modest "obesity paradox". Moreover, being underweight at admission was a significant risk factor for mortality up to 7.7 years after SCI (hazard ratio 5.5, 95% CI: 2.34-13.17, p < 0.001). Discussion: Mortality risk (1 month to 7.7 years after SCI) was associated with differences in BMI at admission. Further research is needed to better understand the underlying mechanisms. Given an established association of BMI with metabolic determinants, these results may suggest unknown neuro-metabolic pathways that are crucial for patient survival. [ABSTRACT FROM AUTHOR]

This study utilized a remotely sensed dataset with a high spatial resolution of 3 m to predict species diversity in the Bobiri Forest Reserve (BFR), a moist semi-deciduous tropical forest in Ghana. We conducted a field campaign of tree species measurements to achieve this objective for species diversity estimation. Thirty-five field plots of 50 m × 20 m were established, and the most dominant tree species within the forest were identified. Other measurements, such as diameter at breast height (DBH ≥ 5 cm), tree height, and each plot's GPS coordinates, were recorded. The following species diversity indices were estimated from the field measurements: Shannon–Wiener (H′), Simpson diversity index (D2), species richness (S), and species evenness (J′). The PlanetScope surface reflectance data at 3 m spatial resolution was acquired and preprocessed for species diversity prediction. The spectral/pixel information of all bands, except the coastal band, was extracted for further processing. Vegetation indices (VIs) (NDVI—normalized difference vegetation index, EVI—enhanced vegetation index, SRI—simple ratio index, SAVI—soil adjusted vegetation index, and NDRE—normalized difference red edge index) were also calculated from the spectral bands and their pixel value extracted. A correlation analysis was then performed between the spectral bands and VIs with the species diversity index. The results showed that spectral bands 6 (red) and 2 (blue) significantly correlated with the two main species diversity indices (S and H′) due to their influence on vegetation properties, such as canopy biomass and leaf chlorophyll content. Furthermore, we conducted a stepwise regression analysis to investigate the most important spectral bands to consider when estimating species diversity from the PlanetScope satellite data. Like the correlation results, bands 6 (red) and 2 (blue) were the most important bands to be considered for predicting species diversity. The model equations from the stepwise regression were used to predict tree species diversity. Overall, the study's findings emphasize the relevance of remotely sensed data in assessing the ecological condition of protected areas, a tool for decision-making in biodiversity conservation. [ABSTRACT FROM AUTHOR]

Now a days, secure data communication over computer network system is a major issue in which impact of feature reduction plays a vital role to secure network by early detection of intrusion. It not only keeps a deep impact on the performance of existing Intrusion Detection System (IDS) algorithms but also affects the computational complexity. Although lots of techniques have been offered for feature reduction by researchers and they have their own perks and quirks, but still they are several flows. To manipulate the same dataset for different classifiers and to select different number of features for the detection of attacks are not only having too much computational cost but also time consuming. The experiments have been carried out using "Python" programming language based library "Scikit‐Learn" software on "Kddcup99" dataset from UCI machine learning repository as a test bed. In this article a classification and regression trees (CART) based feature selection algorithm has been proposed which offers optimum set of features. Further optimum set of features has been offered by our proposed work passed over various classifiers for training and testing to establish network intrusion detection system (NIDS). We have compared the performance accuracy of various existing machine learning (ML) based classification algorithms and obtained higher performance accuracy with lower computational cost. The proposed algorithm having optimum time complexity and accuracy in designing of IDS. [ABSTRACT FROM AUTHOR]

Rental bike sharing is an urban mobility model that is affordable and ecofriendly. The public bike sharing model is widely used in several cities across the world over the past decade. Because bike use is rising constantly, understanding the system demand in prediction is important to boost the operating system readiness. This article presents a prediction model to meet user demands and efficient operations for rental bikes using Random Forest (RF), which is a homogeneous ensemble method. The approach is carried out in Seoul, South Korea to predict the hourly use of rental bikes. RF is compared with Support Vector Machine with Radial Basis Function Kernel, k‐nearest neighbor and Classification and Regression Trees to verify RF supremacy in rental bike demand prediction. Performance Index measures the efficiency of RF compared to the other predictive models. Also, the variable importance analysis is performed to assess the most important characteristics during different seasons by creating a predictive model using RF for each season. The results show that the influence of variables changes depending on the seasons that suggest different operating conditions. RF models trained with yearly and seasonwise models show that bike sharing demand can be further improved by considering seasonal change. [ABSTRACT FROM AUTHOR]

Background: Acute kidney injury (AKI) is prevalent in hospitalized patients with traumatic brain injury (TBI), and increases the risk of poor outcomes. We designed this study to develop a visual and convenient decision-tree-based model for predicting AKI in TBI patients. Methods: A total of 376 patients admitted to the emergency department of the West China Hospital for TBI between January 2015 and June 2019 were included. Demographic information, vital signs on admission, laboratory test results, radiological signs, surgical options, and medications were recorded as variables. AKI was confirmed since the second day after admission, based on the Kidney Disease Improving Global Outcomes criteria. We constructed two predictive models for AKI using least absolute shrinkage and selection operator (LASSO) regression and classification and regression tree (CART), respectively. Receiver operating characteristic (ROC) curves of these two predictive models were drawn, and the area under the ROC curve (AUC) was calculated to compare their predictive accuracy. Results: The incidence of AKI on the second day after admission was 10.4% among patients with TBI. Lasso regression identified five potent predictive factors for AKI: glucose, serum creatinine, cystatin C, serum uric acid, and fresh frozen plasma transfusions. The CART analysis showed that glucose, serum uric acid, and cystatin C ranked among the top three in terms of the feature importance of the decision tree model. The AUC value of the decision-tree predictive model was 0.892, which was higher than the 0.854 of the LASSO regression model, although the difference was not statistically significant. Conclusion: The decision tree model is valuable for predicting AKI among patients with TBI. This tree-based flowchart is convenient for physicians to identify patients with TBI who are at high risk of AKI and prompts them to develop suitable therapeutic strategies. [ABSTRACT FROM AUTHOR]

Warm mix asphalt (WMA) has recently gained popularity as a pavement engineering alternative because it has the potential to significantly reduce energy utilization and the carbon footprint of the pavement industry. However, due to lower mixing and compaction temperatures, concerns have been raised about the material's durability and the possibility of water damage. The current research evaluates the effect of the simultaneous usage of two additives [styrene–butadiene rubber (SBR), and polyphosphoric acid (PPA)] on the moisture damage resistance of warm-stone matrix asphalt (SMA) mixtures containing anti-tripping agents (ASAs). Different mixture tests were performed to investigate the moisture susceptibility of the samples. A two-way analysis of variance was performed to investigate whether additives have a significant effect or not. The outcomes show that the combination of two polymers improves the indirect tensile strength, fracture energy, and resilient modulus of samples. Also, the combination of Sasobit and Zycotherm and ASAs enhances the performance of samples, and among mixtures containing ASAs, specimens containing ASA (B) have the best moisture strength performance. In addition, a numerical method through a regression tree ensemble (RTE) model was designed to estimate the resilient modulus ratio (RMR), fracture energy ratio (FER), and tensile strength ratio (TSR) values. The outcomes indicated the high accuracy of this model in predicting the mentioned values. [ABSTRACT FROM AUTHOR]

Introduction: Cytomegalovirus (CMV)‐infection and reactivation remain a relevant complication after liver transplantation (LT). The recipient and donor serum CMV‐IgG‐status has been established for risk stratification when choosing various pharmaceutical regimens for CMV‐prophylaxis in the last two decades. However, factors influencing course of CMV‐infection in LT remain largely unknown. In this study, the impact of immunosuppressive regimen was examined in a large cohort of patients. Methods: All patients that underwent primary LT between 2006 and 2018 at the Charité–Universitaetsmedizin, Berlin, were included. Clinical course as well as histological and laboratory findings of patients were analyzed our prospectively maintained database. Univariate and multivariate regression analysis for impact of variables on CMV‐occurrence was conducted, and survival was examined using Kaplan–Meier analysis. Results: Overall, 867 patients were included in the final analysis. CMV‐infection was diagnosed in 325 (37.5%) patients after transplantation. Significantly improved overall survival was observed in these patients (Log rank = 0.03). As shown by correlation and regression tree classification and regression tree analysis, the recipient/donor CMV‐IgG‐status with either positivity had the largest influence on CMV‐occurrence. Analysis of immunosuppressive burden did not reveal statistical impact on CMV‐infection, but statistically significant inverse correlation of cumulative tacrolimus trough levels and survival was found (Log rank <.001). Multivariate analysis confirmed these findings (p =.02). Discussion: CMV‐infection remains of clinical importance after LT. Undergone CMV‐infection of either recipient or donor requires prophylactic treatment. Additionally, we found a highly significant, dosage‐dependent impact of immunosuppression (IS) on long‐term outcomes for these patients, underlying the importance of minimization of IS in liver transplant recipients. [ABSTRACT FROM AUTHOR]

The rockburst hazard induced by the extreme release of the stress concentrated in rock mass in deep underground mines poses a significant threat to the safety and economy of the mining projects. Therefore, properly managing this hazard is critical for ensuring rock engineering projects' sustainability. This study proposes comprehensible and practical classifiers for rockburst risk level appraisal by hybridizing K-means clustering with gene expression programming, GEP, logistic regression, LR, and classification and regression tree, CART (i.e., K-mean-GEP-LR and K-means-CART classifiers). A database containing 246 rockburst events with four risk levels of none, light, moderate, and severe was compiled from previous practices. Preliminary statistical analyses were conducted to detect the extreme outliers and determine the critical rockburst indicators. The K-means clustering analysis was performed to identify the main clusters within the database and relabel the rockburst events. The GEP algorithm was then utilized to develop binary models for predicting the occurrence of each class. Then, the likelihood of each class occurrence was determined using LR. Furthermore, the K-means clustering was combined with the CART algorithm to provide another visual tree structure model. The classifiers' performance evaluation showed 96% and 95% accuracy values in the training and testing stages, respectively, for the K-means-GEP-LR model, while the accuracy values of 98.8% and 93.0% were obtained for the foregoing stages for the K-means-CART classifier. The results showed the robustness and high classification capability of both models. MatLab codes were also provided for the K-means-GEP-LR model, which assists other researchers/engineers in implementing the model in practice. [ABSTRACT FROM AUTHOR]

Ensemble methods, such as Bagging, Boosting, or Random Forests, often enhance the prediction performance of single learners on both classification and regression tasks. In the context of regression, we propose a gradient boosting‐based algorithm incorporating a diversity term with the aim of constructing different learners that enrich the ensemble while achieving a trade‐off of some individual optimality for global enhancement. Verifying the hypotheses of Biau and Cadre's theorem (2021, Advances in contemporary statistics and econometrics—Festschrift in honour of Christine Thomas‐Agnan, Springer), we present a convergence result ensuring that the associated optimization strategy reaches the global optimum. In the experiments, we consider a variety of different base learners with increasing complexity: stumps, regression trees, Purely Random Forests, and Breiman's Random Forests. Finally, we consider simulated and benchmark datasets and a real‐world electricity demand dataset to show, by means of numerical experiments, the suitability of our procedure by examining the behavior not only of the final or the aggregated predictor but also of the whole generated sequence. [ABSTRACT FROM AUTHOR]

Context: Globally, plant species are facing numerous threats; an issue particularly acute for island floras, which often exhibit high levels of endemism. Ex situ conservation in seed banks is an important tool for plant conservation. However not all species' seeds can be stored in conventional seed banks. Data on seed storage behaviour are therefore vital for conservation decision making. Aims: To review available seed storage information for the New Zealand (NZ) indigenous seed plant flora, 86% of which are endemic. Methods: We compiled seed storage information for the NZ flora from databases and existing literature, and used boosted regression trees models to investigate predictors of seed storage behaviour for NZ woody plants. We used existing global models to predict the likely storage behaviour for the NZ woody flora where this was unknown, to examine the overall contribution that conventional seed banking could make towards NZ plant conservation. Key results: Data were available for 412 of 1823 seed plants, of which 83% produced orthodox seeds that can be stored in a conventional seed bank. Of the woody flora, the incidence of non-orthodox seeds was positively correlated with seed mass, plant height, biotic dispersal, and habitat diurnal temperature range. Eighty-one percent of the woody flora are predicted to produce orthodox seeds. Conclusions and implications: Conventional seed banking is likely to be suitable for a high proportion of the NZ flora. However, work is required to gain further seed storage behaviour data for NZ species, and to develop protocols for alternative ex situ conservation strategies for non-orthodox species, especially those facing in situ conservation threats. Seed banks are an important tool for plant conservation. However not all species can be stored. We compiled information on seed storage for New Zealand plants, finding that 83% could be stored in a seed bank. Plants unable to be banked are generally bird-dispersed canopy trees, including some threatened species. [ABSTRACT FROM AUTHOR]

Snow cover information is essential for pursuing seasonal variation studies in Himalayan river basins. This study aims to investigate the seasonal variation of snow cover in the Sutlej river basin (Tibet to Bhakra dam in India) over three different seasons: Monsoon (June–September), winter (October-January), and summer (February-May) during the period 2010–2021. Landsat 7 and 8 Surface Reflectance (SR) data is used to develop 108 land use land cover (LULC) maps for 12 years, with three seasons per year and three machine-learning models. The study has conducted on the Google Earth Engine (GEE) platform, employing Random Forest (RF), Classification and Regression Trees (CART), and Support Vector Machine (SVM) models to classify the Landsat satellite data and assess the seasonal snow cover variation during the three seasons. The results show that among the three machine learning models, the RF model exhibits the highest average overall accuracy at 98.75%, followed by the CART model at 98.10%, and the SVM model with the lowest accuracy at 97.15%. In terms of snow cover area variability; there is a decline trend in summer snow cover and an increase in monsoon snow cover over the past three years (2019–2021). However, an increasing trend emerges when considering the decadal changes in all three seasons. In addition, the maximum percentages of snow cover area observed as 67.61%, 46.78%, and 30.58% in the summer period of 2013, the winter period of 2019, and the monsoon period of 2021, respectively. Similarly, the minimum percentage of snow cover is 23.22%, 11.36%, and 13.01%, observed in the summer period of 2014, the winter period of 2011, and the monsoon period of 2012, respectively. A comprehensive assessment procedure on temporal and seasonal snow cover variation in a large river basin have been presented in this work, which will help to plan and manage the sustainable water resources in study region. [ABSTRACT FROM AUTHOR]

Objective: Given the limited information on population dynamics of Gafftopsail Catfish Bagre marinus in the western Gulf of Mexico, the objectives of this study were to determine the status of this species in Texas estuaries by assessing trends in relative abundance, length, and habitat preferences from fishery‐independent trawl (juvenile) and gill‐net (adult) data, as well as angler harvest trends from fishery‐dependent creel surveys collected in all Texas estuaries. Methods: Fishery‐independent and ‐dependent monitoring data were collected by the Texas Parks and Wildlife Department in all major bay systems of the Texas coast from 1983 to 2022. Linear trend analysis was used to assess trends across the full time series and all major bay systems for both juvenile and adult specimens and for total recreational harvest. Boosted regression tree analysis was used to assess habitat preference for both juveniles and adults. Result: Both juvenile and adult catch rates consistently increased in most Texas estuaries, with the most extreme increases occurring in central Texas coast estuaries beginning in the early 2000s. During the same time frame, mean lengths of adult specimens significantly decreased in many of the same estuaries. Habitat suitability analysis suggested that Gafftopsail Catfish were primarily influenced by salinity, though they still exist across a very broad range of salinity conditions. Angler catch rates showed some localized patterns of increasing or decreasing trends, though they generally did not follow fishery‐independent trends for most estuaries. Conclusion: These trends interpreted in the context of the known trophic role of Gafftopsail Catfish imply the potential for larger ecosystem‐level effects on both prey organisms and competitors. A more thorough awareness of these trends and potential interactions should help fisheries managers operate in an ecosystem‐based context when investigating population dynamics and recommending management strategies. Impact statementGafftopsail Catfish abundance is increasing in most Texas estuaries. They have few documented predators and limited fishery interest. Given their trophic role as generalist predators, they may significantly impact populations of prey species, including blue crabs and penaeid shrimp, which have high economic value. [ABSTRACT FROM AUTHOR]

Objective: Crevalle Jack Caranx hippos are important coastal predators and support an increasingly popular catch‐and‐release sport fishery. However, population declines have recently been perceived by stakeholders in parts of the species' range. Here, we aimed to provide distribution and harvest trends for Crevalle Jack in the northwestern Gulf of Mexico. Methods: Long‐term fishery‐independent and fishery‐dependent data were collected by the Texas Parks and Wildlife Department from 1983 to 2021. Bag seine, bay trawl, and gill‐net samples were collected in conjunction with angler creel surveys. Crevalle Jack that were observed in fishery‐independent sampling were used to assess patterns in both juvenile and adult relative abundance, distribution, and seasonality. In addition, boosted regression tree models were used to highlight important predictors of Crevalle Jack presence. Crevalle Jack harvest observed during angler surveys was used to describe the fishery, including differences in inshore and offshore catch patterns. Relative abundance of both juveniles and adults was variable across years but displayed no trend throughout the time series. Result: Crevalle Jack of all sizes were found within inshore waters, with subadults and large adults particularly reliant on estuarine systems. Recruitment peaked in early summer, with juveniles occupying all major estuaries along the coast. Shifts in recruitment were evident in bag seines, as the mean date of catch trended almost 2 weeks earlier over the study period. The Crevalle Jack fishery was spread across inshore and offshore waters, with significantly larger fish harvested offshore during summer. The majority of anglers who harvested Crevalle Jack stated that they were specifically targeting other species, thus supporting the notion that the targeted fishery is mainly catch and release. Conclusion: As Crevalle Jack declines have been noted elsewhere in the species' range, these results could help to inform future management decisions in Texas. Impact statementCrevalle Jack are an important sport fish in the eastern Gulf of Mexico. However, anglers have noted population declines in parts of their range. Here, we examined seasonality, distribution, and recruitment of Crevalle Jack in Texas. Results indicate that populations are stable and provide important insights into Crevalle Jack ecology. While the fishery is largely catch and release, the reliance of large Crevalle Jacks on estuaries and nearshore waters could see them increase in popularity as an accessible sport fish. These findings will be important to inform future management decisions. [ABSTRACT FROM AUTHOR]

The latest development in empirical Asset Pricing is the use of Machine Learning methods to address the problem of the factor zoo. These techniques offer great flexibility and prediction accuracy but require special care as they strongly depart from traditional Econometrics. We review and critically assess the most recent and relevant contributions in the literature grouping them into five categories defined by the Machine Learning (ML) approach they employ: regularization, dimension reduction, regression trees/random forest (RF), neural networks (NNs), and comparative analyses. We summarize the empirical findings with particular attention to their economic interpretation providing hints for future developments. [ABSTRACT FROM AUTHOR]

Purpose: We built Bayesian Network (BN) models to explain roles of different patient-specific factors affecting racial differences in breast cancer stage at diagnosis, and to identify healthcare related factors that can be intervened to reduce racial health disparities. Methods: We studied women age 67–74 with initial diagnosis of breast cancer during 2006–2014 in the National Cancer Institute's SEER-Medicare dataset. Our models included four measured variables (tumor grade, hormone receptor status, screening utilization and biopsy delay) expressed through two latent pathways-a tumor biology path, and health-care access/utilization path. We used various Bayesian model assessment tools to evaluate these two latent pathways as well as each of the four measured variables in explaining racial disparities in stage-at-diagnosis. Results: Among 3,010 Black non-Hispanic (NH) and 30,310 White NH breast cancer patients, respectively 70.2% vs 76.9% were initially diagnosed at local stage, 25.3% vs 20.3% with regional stage, and 4.56% vs 2.80% with distant stage-at-diagnosis. Overall, BN performed approximately 4.7 times better than Classification And Regression Tree (CART) (Breiman L, Friedman JH, Stone CJ, Olshen RA. Classification and regression trees. CRC press; 1984) in predicting stage-at-diagnosis. The utilization of screening mammography is the most prominent contributor to the accuracy of the BN model. Hormone receptor (HR) status and tumor grade are useful for explaining racial disparity in stage-at diagnosis, while log-delay in biopsy impeded good prediction. Conclusions: Mammography utilization had a significant effect on racial differences in breast cancer stage-at-diagnosis, while tumor biology factors had less impact. Biopsy delay also aided in predicting local and regional stages-at-diagnosis for Black NH women but not for white NH women. [ABSTRACT FROM AUTHOR]

Pan evaporation modeling and forecasting are needed to provide timely, continuous, and valuable information to support water management. This study aimed to overcome the constraints identified in traditional regression techniques and less explored machine learning models—the CatBoost, to enhance the precision and comprehensiveness of pan evaporation estimation. Additionally, the CatBoost model was compared with other machine-learning approaches, viz., multiple linear regression (MLR), multiple non-linear least-squares regression (MNLSR), multivariate adaptive regression splines (MARS), random forest regression (RF), and M5 model tree (M5Tree). The algorithms were developed using data obtained from the Crop Research Center, Pantnagar- Uttarakhand, India. Stepwise regression was used as an input variable selection algorithm for selecting the best relevant input from several meteorological variables. For the model's development, data were split into two subsets: the first three years were reserved for model calibration, while the fourth-year data was used for model validation. Statistical analyses, namely root mean square error (RMSE), Nash–Sutcliffe efficiency (NSE), Willmott index of agreement (WI), Pearson correlation coefficient (PCC), coefficient of determination (R2), and mean absolute error (MAE) were used to assess the effectiveness of weekly pan evaporation estimation models. Findings indicated that the CatBoost model, based on four predictors, was the most accurate at Pantnagar station, with NSE, WI, MAE, RMSE, PCC and R2 ranging from 0.9838 to 0.9877, 0.9960–0.9968, 0.1991–0.2078, 0.3643–0.3650–0.9955, 0.9925 and 0.9851–0.9911, respectively. RF model was found to be the second-most best-performing model in terms of in accuracy and effectiveness for mapping weekly pan evaporation, followed by MARS, MNLSR, MLR, and M5Tree. In conclusion, CatBoost's approach of considering combinations greedily implies a thoughtful and cautious selection of features during the modeling process. This can enhance the model's robustness and generalization capability, contributing to more accurate predictions in diverse environmental conditions in subtropical and sub-humid regions. [ABSTRACT FROM AUTHOR]

This study analyzes oil price movements through the lens of an agnostic random forest model, which is based on 1000 regression trees. It shows that this highly disciplined, yet flexible computational model reduces in-sample root-mean-square errors (RMSEs) by 65% relative to a standard linear least square model that uses the same comprehensive set of 11 high-frequency explanatory factors. In 1–3 months ahead price forecasting exercises the RMSE reduction relative to OLS ranges exceeds 50%, highlighting the relevance of non-linearities in oil markets. The results underscore the importance of incorporating financial factors into oil models: US interest rates, the dollar and the VIX together account for 39% of the models' RMSE reduction in the post-2010 sample, rising to 48% in the post-2020 sample. [ABSTRACT FROM AUTHOR]

Interactions between predictors play an important role in many applications. Popular and successful tree-based supervised learning methods such as random forests or logic regression can incorporate interactions associated with the considered outcome without specifying which variables might interact. Nonetheless, these algorithms suffer from certain drawbacks such as limited interpretability of model predictions and difficulties with negligible marginal effects in the case of random forests or not being able to incorporate interactions with continuous variables, being restricted to additive structures between Boolean terms, and not directly considering conjunctions that reveal the interactions in the case of logic regression. We, therefore, propose a novel method called logic decision trees (logicDT) that is specifically tailored to binary input data and helps to overcome the drawbacks of existing methods. The main idea consists of considering sets of Boolean conjunctions, using these terms as input variables for decision trees, and searching for the best performing model. logicDT is also accompanied by a framework for estimating the importance of identified terms, i.e., input variables and interactions between input variables. This new method is compared to other popular statistical learning algorithms in simulations and real data applications. As these evaluations show, logicDT is able to yield high prediction performances while maintaining interpretability. [ABSTRACT FROM AUTHOR]

One of the main methods for determining coagulant dosage (CD) is the jar test. However, this method is expensive, time-consuming, and requires laboratory equipment. In this situation, machine learning, especially hybrid machine learning, is suitable to estimate the CD without requiring a jar test. To this end, a hybrid model based on a combination of the M5 and the gorilla troops optimizer (GTO) algorithm was introduced as the M5-GTO model. Nine different parameters, including raw water production (RWP), turbidity of water, Conductivity, TDS, Salinity, pH, water temperature (WT), SM, and O2, were also utilized as inputs in the CD modeling. The results of comparing the proposed model with the multiple linear regression, multiple nonlinear regression, artificial neural network, multivariate adaptive regression splines, M5 model tree, k-nearest neighbor, least-squares support vector machine, general regression neural network, and random forest (RF) showed that this model is more accurate in CD modeling. Besides, the M5-GTO well estimated the distribution of observational data. For example, the values of the mean absolute error, root mean square error (RMSE), relative RMSE, normalized RMSE, and correlation coefficient criteria for the M5-GTO were equal to 0.562, 1.172, 0.257, 0.170, and 0.967, which were up to 73%, 54.9%, 54.8%, 55%, and 4% are more accurate than LSSVM (worst algorithm), respectively. In addition, the M5 and RF algorithms were also in the second and third ranks. The partial dependence plots results showed that the RWP and WT had the most significant effects on CD changes. Increasing the RWP reduced the amount of CD, while increasing the WT increased the CD. The algorithm introduced in the present study has a high potential for modeling various parameters in water treatment plants. [ABSTRACT FROM AUTHOR]

The drying process of polymeric coatings, particularly in the presence of surfactants, poses a complex challenge due to its intricate dynamics involving simultaneous heat and mass transfer. This study addresses the inherent complexity by employing Artificial Neural Networks (ANNs) to model the surfactant-enhanced drying of poly(styrene)-p-xylene coatings. A substantial dataset of 16,258 experimentally obtained samples forms the basis for training the ANN model, showcasing the suitability of this approach when ample training data is available. The chosen single-layer feed-forward network with backpropagation adeptly captures the non-linear relationships within the drying data, providing a predictive tool with exceptional accuracy. Our results demonstrate that the developed ANN model achieves a precision level exceeding 99% in predicting coating weight loss for specified input values of time, surfactant amount, and initial coating thickness. The model's robust generalization capability eliminates the need for additional experiments, offering reliable predictions for both familiar and novel conditions. Comparative analysis reveals the superiority of the ANN over the regression tree, emphasizing its efficacy in handling the intricate dynamics of polymeric coating drying processes. In conclusion, this study contributes a valuable tool for optimizing polymeric coating processes, reducing production defects, and enhancing overall manufacturing quality and cost-effectiveness. [ABSTRACT FROM AUTHOR]

One challenging task in analyzing environmental data is how to achieve better prediction in presence of outliers, which is inevitable, especially in environmental modeling. The purpose of prediction is to draw valid conclusions and provide useful advices in environmental management. Robust approach is often desirable when there exist outliers. Robust nonparametric regression methods have attracted much attention from a practical point of view. As a nonparametric Bayesian approach, Bayesian additive regression trees (BART) provides a flexible regression that captures potential nonlinear relationships and complex interactions via the framework including sum-of-trees model, regularization prior and Bayesian backfitting MCMC algorithm (hereafter backfitting MCMC). When outliers are present in the data, we find out that BART has the highest prediction performance in simulation studies which are carried out in a variety of cases, compared to the well-known machine learning methods: random forest, support vector machine, extreme gradient boosting. The findings of this study demonstrate that BART approach is seen to be remarkably robust to outliers. For illustration, we also analyze two datasets which exist many underlying outliers: one from a study of forest fires related factors and the other from a study of biomass fuels. [ABSTRACT FROM AUTHOR]

Coronavirus disease 2019 (COVID-19) has strained healthcare systems worldwide. Predicting COVID-19 severity could optimize resource allocation, like oxygen devices and intensive care. If machine learning model could forecast the severity of COVID-19 patients, hospital resource allocation would be more comfortable. This study evaluated machine learning models using electronic records from 3,996 COVID-19 patients to forecast mild, moderate, or severe disease up to 2 days in advance. A deep neural network (DNN) model achieved 91.8% accuracy, 0.96 AUROC, and 0.90 AUPRC for 2-day predictions, regardless of disease phase. Tree-based models like random forest achieved slightly better metrics (random forest: 94.1% of accuracy, 0.98 AUROC, 0.95 AUPRC; Gradient boost: 94.1% of accuracy, 0.98 AUROC, 0.94 AUPRC), prioritizing treatment factors like steroid use. However, the DNN relied more on fixed patient factors like demographics and symptoms in aspect to SHAP value importance. Since treatment patterns vary between hospitals, the DNN may be more generalizable than tree-based models (random forest, gradient boost model). The results demonstrate accurate short-term forecasting of COVID-19 severity using routine clinical data. DNN models may balance predictive performance and generalizability better than other methods. Severity predictions by machine learning model could facilitate resource planning, like ICU arrangement and oxygen devices. [ABSTRACT FROM AUTHOR]

What dataset features affect machine learning (ML) performance has primarily been unknown in the current literature. This study examines the impact of tabular datasets' different meta-level and statistical features on the performance of various ML algorithms. The three meta-level features this study considered are the dataset size, the number of attributes and the ratio between the positive (class 1) and negative (class 0) class instances. It considered four statistical features for each dataset: mean, standard deviation, skewness and kurtosis. After applying the required scaling, this study averaged (uniform and weighted) each dataset's different attributes to quantify its four statistical features. We analysed 200 open-access tabular datasets from the Kaggle (147) and UCI Machine Learning Repository (53) and developed ML classification models (through classification implementation and hyperparameter tuning) for each dataset. Then, this study developed multiple regression models to explore the impact of dataset features on ML performance. We found that kurtosis has a statistically significant negative effect on the accuracy of the three non-tree-based ML algorithms of the Support vector machine (SVM), Logistic regression (LR) and K-nearest neighbour (KNN) for their classical implementation with both uniform and weighted aggregations. This study observed similar findings in most cases for ML implementations through hyperparameter tuning, except for SVM with weighted aggregation. Meta-level and statistical features barely show any statistically significant impact on the accuracy of the two tree-based ML algorithms (Decision tree and Random forest), except for implementation through hyperparameter tuning for the weighted aggregation. When we excluded some datasets based on the imbalanced statistics and a significantly higher contribution of one attribute compared to others to the classification performance, we found a significant effect of the meta-level ratio feature and statistical mean and standard deviation features on SVM, LR and KNN accuracy in many cases. Our findings open a new research direction in understanding how dataset characteristics affect ML performance and will help researchers select appropriate ML algorithms for a possible optimal accuracy outcome. [ABSTRACT FROM AUTHOR]

The degradation of bus system attractiveness is primarily caused by low‐level service quality and reliability. As an essential technology for bus operation management, online bus speed control has proven to be a flexible and effective solution to mitigate bus bunching and enhance the service level of bus operation systems. In this study, we propose a robust nonlinear decision mapping (RNDM) approach that uses real‐time key bus system states to control bus speeds and accounts for uncertainties associated with passenger demands at stations and traffic speeds of interstation links. We develop this approach through a design process that involves learning the input–output mapping relation of a nonlinear programming simulation‐based optimization (NLPSO) method using regression tree with AdaBoost. Critical parameters of the fitted regression tree with AdaBoost are then optimized offline using a distributionally robust simulation‐based optimization (DRSO) model that is solved by a simulation‐based optimization (SO) algorithm. The resulting RNDM method effectively handles two types of uncertainties, expressed by two ambiguity sets of probability distributions, and ensures good bus operation performance even under worst‐case uncertainty levels. Numerical experiments reveal that the RNDM, NLPSO, and integer programming SO (IPSO) methods successfully mitigate bus bunching and improve service efficiency and robustness, compared to the no‐control scenario. Furthermore, the RNDM method outperforms NLPSO and IPSO in terms of comprehensive performance under uncertainties and demonstrates practical operability. In conclusion, this study presents an innovative general framework that uses a nonlinear decision mapping optimized offline by an SO approach to address online simulation‐based optimal decision‐making problems under uncertainties, which can be applied to solve similar problems. [ABSTRACT FROM AUTHOR]

This study aims to understand the dynamic changes in the coral reef habitats of Derawan Island over two decades (2003, 2011, and 2021) using advanced machine learning classification techniques. The motivation stems from the urgent need for accurate, detailed environmental monitoring to inform conservation strategies, particularly in ecologically sensitive areas like coral reefs. We employed non-parametric machine learning algorithms, including Random Forest (RF), Support Vector Machine (SVM), and Classification and Regression Tree (CART), to assess spatial and temporal changes in coral habitats. Our analysis utilized high-resolution data from Landsat 9, Landsat 7, Sentinel-2, and Multispectral Aerial Photos. The RF algorithm proved to be the most accurate, achieving an accuracy of 71.43% with Landsat 9, 73.68% with Sentinel-2, and 78.28% with Multispectral Aerial Photos. Our findings indicate that the classification accuracy is significantly influenced by the geographic resolution and the quality of the field and satellite/aerial image data. Over the two decades, there was a notable decrease in the coral reef area from 2003 to 2011, with a reduction to 16 hectares, followed by a slight increase in area but with more heterogeneous densities between 2011 and 2021. The study underscores the dynamic nature of coral reef habitats and the efficacy of machine learning in environmental monitoring. The insights gained highlight the importance of advanced analytical methods in guiding conservation efforts and understanding ecological changes over time. [ABSTRACT FROM AUTHOR]

The demand for high-performance displays is driving the development of glass substrates with extremely low strain variation during manufacturing. To achieve the necessary balance of physical properties to resist strain, the traditional compositional design methods for glass substrates like trial-and-error and classical computational techniques should be optimized. As an alternative approach, machine learning (ML) algorithms have emerged for designing new glass compositions. In this work, we conduct ML research focused on the compositional design for high-performance glass substrates. We employ three ML algorithms i.e., Random Forest (RF), Classification And Regression Tree (CART) and k-Nearest Neighbors (k-NN) to predict five physical properties that are key to the performance of alkaline-free aluminosilicate glass substrates. By using only small-to-medium dataset sizes, our model reaches a high coefficient of determination of 0.9879. Furthermore, our model achieves an accurate generalized prediction of 50 experimental data and enables the prediction and design of glass substrate compositions with advanced comprehensive properties. [ABSTRACT FROM AUTHOR]

Mayaro virus (MAYV) is a mosquito-borne Alphavirus that is widespread in South America. MAYV infection often presents with non-specific febrile symptoms but may progress to debilitating chronic arthritis or arthralgia. Despite the pandemic threat of MAYV, its true distribution remains unknown. The objective of this study was to clarify the geographic distribution of MAYV using an established risk mapping framework. This consisted of generating evidence consensus scores for MAYV presence, modeling the potential distribution of MAYV in select countries across Central and South America, and estimating the population residing in areas suitable for MAYV transmission. We compiled a georeferenced compendium of MAYV occurrence in humans, animals, and arthropods. Based on an established evidence consensus framework, we integrated multiple information sources to assess the total evidence supporting ongoing transmission of MAYV within each country in our study region. We then developed high resolution maps of the disease's estimated distribution using a boosted regression tree approach. Models were developed using nine climatic and environmental covariates that are related to the MAYV transmission cycle. Using the output of our boosted regression tree models, we estimated the total population living in regions suitable for MAYV transmission. The evidence consensus scores revealed high or very high evidence of MAYV transmission in several countries including Brazil (especially the states of Mato Grosso and Goiás), Venezuela, Peru, Trinidad and Tobago, and French Guiana. According to the boosted regression tree models, a substantial region of South America is suitable for MAYV transmission, including north and central Brazil, French Guiana, and Suriname. Some regions (e.g., Guyana) with only moderate evidence of known transmission were identified as highly suitable for MAYV. We estimate that approximately 58.9 million people (95% CI: 21.4–100.4) in Central and South America live in areas that may be suitable for MAYV transmission, including 46.2 million people (95% CI: 17.6–68.9) in Brazil. Our results may assist in prioritizing high-risk areas for vector control, human disease surveillance and ecological studies. Author summary: We used a comprehensive, georeferenced compendium of Mayaro virus (MAYV) occurrence to model the suitability for MAYV in Central and South America. Our boosted regression tree model incorporated 195 MAYV occurrence locations and 9 gridded environmental covariates to generate a 5 x 5 km continuous surface of MAYV suitability across Central and South America. Using this distribution model, we estimated the total population residing in areas that are suitable for MAYV transmission. Furthermore, we developed evidence consensus scores for each country in our study region that synthesized a variety of sources to assess the overall evidence of known MAYV transmission. Our study provides a contemporary estimate of MAYV distribution using a well-established disease mapping framework. This information provides an evidence base that can guide disease surveillance (including human cases and ecological studies) and vector control efforts in Central and South America. This is especially useful in regions with high predicted MAYV suitability but only moderate evidence of current MAYV transmission (e.g., Guyana and Suriname). [ABSTRACT FROM AUTHOR]

The increasing importance of uncertainty quantification in the regulatory evaluation of pharmaceutical products has triggered an explosion of Bayesian methods in recent years. In biomarker discovery and early clinical development, Bayesian methods have established a foothold in developing new drugs, in part due to the increasing availability of greater computational power, often complementing both traditional pharmaceutical statistics and classical statistical methods. In this paper, we present a selective survey of the recent efforts that have been made toward the development and application of effective statistical and computational models in early development statistics. The survey introduces four such case studies and methods that can be used for end-to-end biomarker discovery that includes pre-clinical and early clinical development, from unsupervised clustering to supervised machine learning to modern statistical inference, including but not limited to Bayesian clustering, Bayesian additive regression trees, Bayesian neural networks, and empirical Bayes procedures with the overarching goal of promoting their use and applications among pharmaceutical statisticians. Finally, we present some open issues in Bayesian early clinical methods to help guide the future advancement and wide adoption of Bayesian applications in early clinical pharmaceutical statistics. [ABSTRACT FROM AUTHOR]

Background: Objective prognostic information is essential for good clinical decision making. In case of unknown diseases, scarcity of evidence and limited tacit knowledge prevent obtaining this information. Prediction models can be useful, but need to be not only evaluated on how well they predict, but also how stable these models are under fast changing circumstances with respect to development of the disease and the corresponding clinical response. This study aims to provide interpretable and actionable insights, particularly for clinicians. We developed and evaluated two regression tree predictive models for in-hospital mortality of COVID-19 patient at admission and 24 hours (24 h) after admission, using a national registry. We performed a retrospective analysis of observational routinely collected data. Methods: Two regression tree models were developed for admission and 24 h after admission. The complexity of the trees was managed via cross validation to prevent overfitting. The predictive ability of the model was assessed via bootstrapping using the Area under the Receiver-Operating-Characteristic curve, Brier score and calibration curves. The tree models were assessed on the stability of their probabilities and predictive ability, on the selected variables, and compared to a full-fledged logistic regression model that uses variable selection and variable transformations using splines. Participants included COVID-19 patients from all ICUs participating in the Dutch National Intensive Care Evaluation (NICE) registry, who were admitted at the ICU between February 27, 2020, and November 23, 2021. From the NICE registry, we included concerned demographic data, minimum and maximum values of physiological data in the first 24 h of ICU admission and diagnoses (reason for admission as well as comorbidities) for model development. The main outcome measure was in-hospital mortality. We additionally analysed the Length-of-Stay (LoS) per patient subgroup per survival status. Results: A total of 13,369 confirmed COVID-19 patients from 70 ICUs were included (with mortality rate of 28%). The optimism-corrected AUROC of the admission tree (with seven paths) was 0.72 (95% CI: 0.71–0.74) and of the 24 h tree (with 11 paths) was 0.74 (0.74–0.77). Both regression trees yielded good calibration and variable selection for both trees was stable. Patient subgroups comprising the tree paths had comparable survival probabilities as the full-fledged logistic regression model, survival probabilities were stable over six COVID-19 surges, and subgroups were shown to have added predictive value over the individual patient variables. Conclusions: We developed and evaluated regression trees, which operate at par with a carefully crafted logistic regression model. The trees consist of homogenous subgroups of patients that are described by simple interpretable constraints on patient characteristics thereby facilitating shared decision-making. [ABSTRACT FROM AUTHOR]