Search

The existence of time delay in complex industrial processes or dynamical systems is a common phenomenon and is a difficult problem to deal with in industrial control systems, as well as in the textile field. Accurate identification of the time delay can greatly improve the efficiency of the design of industrial process control systems. The time delay identification methods based on mathematical modeling require prior knowledge of the structural information of the model, especially for nonlinear systems. The neural network-based identification method can predict the time delay of the system, but cannot accurately obtain the specific parameters of the time delay. Benefit from the interpretability of machine learning, a novel method for delay identification based on an interpretable regression decision tree is proposed. Utilizing the self-explanatory analysis of the decision tree model, the parameters with the highest feature importance are obtained to identify the time delay of the system. Excellent results are gained by the simulation data of linear and nonlinear control systems, and the time delay of the systems can be accurately identified. [ABSTRACT FROM AUTHOR]

Short-term electric power load forecasting is a critical and essential task for utilities in the electric power industry for proper energy trading, which enables the independent system operator to operate the network without any technical and economical issues. From an electric power distribution system point of view, accurate load forecasting is essential for proper planning and operation. In order to build most robust machine learning model to forecast the load with a good accuracy irrespective of weather condition and type of day, features such as the season, temperature, humidity and day-status are incorporated into the data. In this paper, a machine learning model, namely a regression tree, is used to forecast the active power load an hour and one day ahead. Real-time active power load data to train and test the machine learning models are collected from a 33/11 kV substation located in Telangana State, India. Based on the simulation results, it is observed that the regression tree model is able to forecast the load with less error. [ABSTRACT FROM AUTHOR]

One primary goal of subgroup analysis is to identify subgroups of subjects with differential treatment effects. Existing methods have focused on the mean treatment effect and may be ineffective when the two distributions differ in scales or in the upper or lower tails. We develop a new generalized quantile tree method for subgroup identification. The method first uses quantile rank score tests to select split variables and then estimates the split point by minimizing a composite quantile loss. The proposed split rule is free of variable selection bias and robust against outliers and heavy-tailed distributions. In addition, we introduce a generalized quantile treatment effect estimator and a testing method for the selection and confirmation of predictive subgroups. Simulation shows that the proposed method gives more accurate subgroup identification than existing methods for cases with heteroscedastic or heavy-tailed errors. The practical value of the method is demonstrated through the analysis of an AIDS clinical trial data. for this article are available online. [ABSTRACT FROM AUTHOR]

Increasing nonresponse rates is a pressing issue for many longitudinal panel studies. Respondents frequently either refuse participation in single survey waves (temporary dropout) or discontinue participation altogether (permanent dropout). Contemporary statistical methods that are used to elucidate predictors of survey nonresponse are typically limited to small variable sets and ignore complex interaction patterns. The innovative approach of Bayesian additive regression trees (BART) is an elegant way to overcome these limitations because it does not specify a parametric form for the relationship between the outcome and its predictors. We present a BART event history analysis that allows identifying predictors for different types of nonresponse to anticipate response rates for upcoming survey waves. We apply our novel method to data from the German National Educational Panel Study including N = 4,559 students in Grade 5 that observed nonresponse rates of up to 36% across five waves. A cross-validation and comparison with logistic regression models with least absolute shrinkage and selection operator penalization underline the advantages of the approach. Our results highlight the potential of Bayesian discrete-time event modeling for the long-term projection of panel stability across multiple survey waves. Finally, potential applications of this approach for operational use in survey management are outlined. [ABSTRACT FROM AUTHOR]

Abstract Background Prevention of coronavirus (COVID-19) regarding households has many aspects, such as buying mask, hand sanitizer, face shield, and many others. As a result of buying the previous items, the household spending per month will increase during the COVID-19 pandemic period. This study aimed to calculate the average costs of each extra item involved in households spending during COVID-19 pandemic and to predict the total average extra costs spending by households. Results Most of the respondents were females (81%) and aged between 30 and 40 (56.3%). About 63.1% of families had the same monthly income while 35.4% had a decrease in monthly income. A significant reduction in days of leaving home before and after COVID-19 pandemic was observed (before; median = 6, after; median = 5, P = 15.65L.E.)) while the minimum average extra costs were 217 L.E./month (around 13.86$/month). Conclusions The effect of COVID-19 pandemic in households spending varies largely between households, it depends on what they do to prevent COVID-19.

The purpose of this study was to determine the factors affecting the 305-day milk yield of dairy cattle by using Regression Tree Analysis (RTA). The data set of this study consisted of 8 different cattle breeds grown in Turkey. Breed (B), Province (P), Lactation Length (LL), Service Period (SP), Dry Period (DP), Parity (PR), Calving Year (CY), Calving Age (CA) and Calving Month (CM) were used to predict the 305-day milk yield. Results of RTM showed that the usage of this method might be appropriate for determining the important factors that would be able to affect the 305-day milk yield (R2=71.3%). It was seen that the most important factors affecting the 305-day milk yield were the Breed, Lactation Length, Province, and Parity. Therefore, those selected factors were more efficient than the others in predicting the 305-day milk yield. RTA results also indicated that the lowest milk yield was estimated for Jersey, Jersey Crossbred, and Yerli Kara. Among the highest 305-day milk yield cows, the milk yield estimates of the cows in the second, third, fourth, fifth, and the sixth parities were found significantly higher than that of the cows in the first and seventh parities.

Anthropogenic influences significantly modify the hydrochemical properties and material flow in riverine ecosystems across Asia, potentially accounting for 40–50% of global emissions. Despite the pervasive impact on Asian rivers, there is a paucity of studies investigating their correlation with carbon dioxide (CO 2) emissions. In this study, we computed the partial pressure of CO 2 (pCO 2) using the carbonate equilibria-based model (pCO 2 SYS) and examined its correlation with hydrochemical parameters from historical records at 91 stations spanning 2013–2021 in the Ganga River. The investigation unveiled substantial spatial heterogeneity in the pCO 2 across the Ganga River. The pCO 2 concentration varied from 1321.76 μatm, 1130.98 μatm, and 1174.33 μatm in the upper, middle, and lower stretch, respectively, with a mean of 1185.29 μatm. Interestingly, the upper stretch exhibited elevated mean pCO 2 and FCO 2 levels (fugacity of CO 2 : 3.63 gm2d−1) compared to the middle and lower stretch, underscoring the intricate interplay between hydrochemistry and CO 2 dynamics. In the context of pCO 2 fluctuations, nitrate concentrations in the upper segment and levels of biological oxygen demand (BOD) and dissolved oxygen (DO) in the middle and lower segments are emerging as crucial explanatory factors. Furthermore, regression tree (RT) and importance analyses pinpointed biochemical oxygen demand (BOD) as the paramount factor influencing pCO 2 variations across the Ganga River (n = 91). A robust negative correlation between BOD and FCO 2 was also observed. The distinct longitudinal patterns of both parameters may induce a negative correlation between BOD and pCO 2. Therefore, comprehensive studies are necessitated to decipher the underlying mechanisms governing this relationship. The present insights are instrumental in comprehending the potential of CO 2 emissions in the Ganga River and facilitating riverine restoration and management. Our findings underscore the significance of incorporating South Asian rivers in the evaluation of the global carbon budget. [Display omitted] • PCO 2 concentration higher in upstream region than downstream region of Ganges. • Nitrate predict pCO 2 well in upstream region. • BOD and DO are best predictors of pCO 2 in downstream regions. • BOD emerged as a crucial influencing factor for pCO 2 across the Ganga River. [ABSTRACT FROM AUTHOR]

Empirical studies have demonstrated associations between ten original adverse childhood experiences (ACEs) and multiple health outcomes. Identifying expanded ACEs can capture the burden of other childhood adversities that may have important health implications. We sought to identify childhood adversities that warrant consideration as expanded ACEs. We hypothesized that experiencing expanded and original ACEs would be associated with poorer adult health outcomes compared to experiencing original ACEs alone. The 11,545 respondents of the National Longitudinal Surveys (NLS) and Child and Young Adult Survey were 48.9 % female, 22.7 % Black, 15.8 % Hispanic, 36.1 % White, 1.7 % Asian/Native Hawaiian/Pacific Islander/Native American/Native Alaskan, and 7.5 % Other. This study used regression trees and generalized linear models to identify if/which expanded ACEs interacted with original ACEs in association with six health outcomes. Four expanded ACEs—basic needs instability, lack of parental love and affection, community stressors, and mother's experience with physical abuse during childhood —significantly interacted with general health, depressive symptom severity, anxiety symptom severity, and violent crime victimization in adulthood (all p -values <0.005). Basic needs instability and/or lack of parental love and affection emerged as correlates across multiple outcomes. Experiencing lack of parental love and affection and original ACEs was associated with greater anxiety symptoms (p = 0.022). This is the first study to use supervised machine learning to investigate interaction effects among original ACEs and expanded ACEs. Two expanded ACEs emerged as predictors for three adult health outcomes and warrant further consideration in ACEs assessments. [ABSTRACT FROM AUTHOR]

Neighborhood externalities influence residential land prices and housing prices simultaneously, contributing to a nexus relationship between them. Most existing studies have focused on the causal relationship between the two, with limited attention to their nexus. This research matched land parcel transactions from 2003 to 2015 and housing transaction records with purchasers' housing purchase records before 2019 to construct a spatial-temporal land-housing dataset in Shanghai. Both spatial statistical tools and regression tree models were employed to explore the underlying mechanism, focusing on proximity to industries. According to the modeling results, residential land prices and housing prices are highly sensitive to polluting industries and producer service industries. The impacts of polluting industries on residential land prices have intensified, but the impacts on housing prices have not. The regression tree models further showed that living service industries were the primary positive contributor to residential land and housing prices. Regarding the social environment, non-local people are taking over communities with high-priced housing on high-value residential land parcels. These research outcomes encourage more efforts to explore the determinants of the nexus between residential land prices and housing prices, rather than discussion of the causality relationship. • Analyzing the nexus between land and housing price using matched land and housing transaction records. • Construct a joint model to estimate the determinants of the nexus between land and housing prices. • Living service related industries could increase both land and housing price. • Non-local's communities are usually located on the high-value land parcels with higher housing price. [ABSTRACT FROM AUTHOR]

Soil organic carbon (SOC) is one of the key soil components for cultivated soils. SOC is regularly monitored and mapped to improve the quality, health, and productivity of the soil. However, traditional SOC-level monitoring is expensive for land managers and farmers. Estimating SOC using satellite imagery provides an easy, efficient, and cost-effective way to monitor surface SOC levels. The objective of this study was to estimate the surface SOC distribution in selected soils of Major Land Resource Areas (MLRA), 102A (Rolling Till Plain, Brookings County, SD), and 103 (Central Iowa and Minnesota Till Prairies, Lac qui Parle County, MN), using satellite imagery with different resolutions (Landsat 8 and PlanetScope). The dominant soils in the study area are Haplustolls, Calciustolls, and Endoaquolls, which are formed in silty sediments, local silty alluvium, and till. Landsat 8 and PlanetScope spectral bands were used to develop SOC prediction models. Parametric and data-driven methods were employed to predict the SOC. Multiple linear regression and Linear Spatial Mixed Model (LSMM) were used on the Landsat 8 and PlanetScope data. In addition to the parametric models, Regression Trees and Random Forest were also employed on both satellite data. The results showed that reduced LSMM provided the lowest RMSE, which are 0.401 and 0.367 for Landsat 8 and PlanetScope, respectively. Furthermore, the random forest has the highest RPD and RPIQ for Landsat 8 (RPD of 2.67 and RPIQ of 2.49) and PlanetScope (RPD of 2.85 and RPIQ of 3.7). In all cases, models obtained from PlanetScope are better than those obtained from Landsat 8. [ABSTRACT FROM AUTHOR]

Objective: To operationalize an intersectionality framework using a novel statistical approach and with these efforts, improve the estimation of disparities in access (i.e., wait time to treatment entry) to opioid use disorder (OUD) treatment beyond race. Data source Sample of 941,286 treatment episodes collected in 2015–2017 in the United States from the Treatment Episodes Data Survey (TEDS‐A) and a subset from California (n = 188,637) and Maryland (n = 184,276), states with the largest sample of episodes. Study design This retrospective subgroup analysis used a two‐step approach called virtual twins. In Step 1, we trained a classification model that gives the probability of waiting (1 day or more). In Step 2, we identified subgroups with a higher probability of differences due to race. We tested three classification models for Step 1 and identified the model with the best estimation. Data collection: Client data were collected by states during personal interviews at admission and discharge. Principal findings: Random forest was the most accurate model for the first step of subgroup analysis. We found large variation across states in racial disparities. Stratified analysis of two states with the largest samples showed critical factors that augmented disparities beyond race. In California, factors such as service setting, referral source, and homelessness defined the subgroup most vulnerable to racial disparities. In Maryland, service setting, prior episodes, receipt of medication‐assisted opioid treatment, and primary drug use frequency augmented disparities beyond race. The identified subgroups had significantly larger racial disparities. Conclusions: The methodology used in this study enabled a nuanced understanding of the complexities in disparities research. We found state and service factors that intersected with race and augmented disparities in wait time. Findings can help decision makers target modifiable factors that make subgroups vulnerable to waiting longer to enter treatment. [ABSTRACT FROM AUTHOR]

The measurement of efficiency of water utilities has been traditionally carried out using econometric methods or linear programming techniques. Alternatively, in this study a data mining non-parametric method is used, such as an artificial neural network (ANN) approach, to predict the efficiency of several water companies in England and Wales. The further use of a regression tree model allowed us to visualize and quantify the impact of operating characteristics on efficiency. The average efficiency score for the water industry was 0.411. Average scores for water only companies and waterand sewerage companies were 0.210 and 0.626, respectively. Only one water company was identified as being fully efficient. This indicates that most of the English and Welsh water companies need to make substantial improvements in their managerial practices to catch-up with the most efficient ones in the industry. Several operating characteristics such as water leakage, water taken from different sources and population density were found to influence efficiency. The percentage of water leakage was identified as the most relevant operational variable influencing the efficiency of water companies. The findings of our study aim to support benchmarking analysis in regulated industries and to get a better insight on what drives efficiency. [ABSTRACT FROM AUTHOR]

Quantifying forest systems is of importance for ecological services and economic benefits in ecosystem models. This study aims to map the percent tree cover (PTC) of various forest stands in the Buyuk Menderes Basin, located in the western part of Turkey with different characteristics in the Mediterranean and Terrestrial transition regions Sentinel-2 data with 10-m spatial resolution. In recent years, some researches have been carried out in different fields to show the capabilities and potential of Sentinel-2 satellite sensors. However, the limited number of PTC researches conducted with Sentinel-2 images reveals the importance of this study. This study aimed to demonstrate reliable PTC data in landscape planning or ecosystem modeling by introducing an advanced approach with high spatial, spectral, and temporal resolution and more cost-effective. In this study, a regression tree algorithm, one of the popular machine learning techniques for ecological modeling, was used to estimate the tree cover's dependent variable based on high-resolution monthly metrics' spectral signatures. Six frames of TripleSat images were used as training data in the regression tree. Monthly Sentinel-2 bands and produced metrics including NDVI, LAI, fCOVER, MSAVI2, and MCARI were almost the first time used as predictor variables. Stepwise linear regression (SLR) was applied to select these predictor bands in the regression tree and a correlation coefficient of 0.83 was obtained. Result PTC maps were produced and the results were evaluated based on coniferous and broadleaf. The results were tested using high spatial resolution TripleSat images and higher model accuracy was determined in both forest types. The high correlation is due to the Sentinel 2 satellite's band characteristics and the metrics are directly related to the tree cover. As a result, the high-accuracy availability of the Sentinel2 satellite is seen to map the PTC on a regional scale, including complex forest types between the Mediterranean and terrestrial transition climates. [ABSTRACT FROM AUTHOR]

As one of the important flood control engineering measures, reservoirs play an important role in ensuring the sustainable growth of national economy, maintaining social stability and alleviating the contradiction between supply and demand of water resources. Meanwhile, scientific and reasonable reservoir flood control operation can effectively promote its role. In order to solve the problem of insufficient utilization of historical flood operation data, this paper proposes a new method of using random forest (RF) regression algorithm to formulate reservoir flood control operation scheme. First of all, the optimal flood operation data set is generated by optimizing the historical flood data, and the main factors affecting the reservoir discharge are determined by the RF regression algorithm. Then, the main influencing factors and discharges of the training sample flood processes are input into the RF regression algorithm to construct the discharge regression trees. Finally, the discharges of the verification sample flood processes are determined by regression trees. The example of Tianzhuang Reservoir in Shandong Province proves the operability and rationality of this method. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Agriculture & Nature / Kahramanmaraş Sütçü İmam Üniversitesi Tarım & Doğa Dergisi is the property of Kahramanmaras Sutcu Imam Universitesi and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

During the process of deep drawing of cylindrical thin-walled products from aluminum sheets, the occurrence of product defects in the form of breaking the material continuity is observed. This has a very large impact on the efficiency of production lines and the number of generated scraps. The number of defects depends on many factors, including the material and the process properties. Because the problem appears after changing one material to another, while the process parameters do not change, it was assumed that the material has the main influence on the number of defects. To reduce the number of defects, a tool is needed to predict threats to the process. Decision tree models were used for this purpose. Using the tree interaction algorithms, the influence of the chemical composition and strength parameters of the 3xxx series aluminum alloy on the number of generated defects was investigated. Increased Silicon (Si) and Iron (Fe) values generated a higher number of defects. Increased yield strength (YS) and decreased elongation (E) also generated a higher number of defects. Based on the results, a defect prediction tool was created, where after entering the parameters of the material, it is possible to predict production hazards. [ABSTRACT FROM AUTHOR]

Effective rock fragmentation is the main target of blasting operations in production blasting and is usually determined using empirical or image analysis methods. However, the cost of performing image analysis, expertise required, and impossibility of using it to pre-control blast design parameters result to the use of empirical model. The empirical model has been found to be inaccurate, and this necessitated the use of novel response surface method (RSM), artificial neural network (ANN), regression tree (RT), and gene expression programming (GEP) to predict the mean fragment size (X50). The performances of the proposed models were compared using graphical presentation and statistical indices such as the coefficient of determination (R2), residual sum of squares (RSS), and root mean squared error (RMSE) in OriginPro software. The ANN model has R2 values of 0.956, 0.970, and 0.932; RSS values of 0.089, 0.023, and 0.024; and RMSE values of 0.036, 0.042, and 0.043 for training, testing, and validation of the datasets, respectively. The RT model has R2 values of 0.956, 0.832, and 0.334; RSS values of 0.09, 0.098, and 0.246; and RMSE values of 0.037, 0.087, and 0.138. The GEP model has R2 values of 0.859, 0.714, and 0.357; RSS values are 0.272, 0.109, and 0.229; and RMSE values of 0.065, 0.092, and 0.133, respectively. Based on the RSS, which is an optimal statistical criterion in model selection, ANN performs better, followed by RT and GEP. In addition, this study established that the proposed models can be used in Monte Carlo simulation (MCS) to estimate large number of X50 values. [ABSTRACT FROM AUTHOR]

Moving towards a circular and sustainable economy requires improving the management of municipal solid waste (MSW) increasing recycling rates while minimising unsorted waste and operational costs. It is essential to evaluate the economic and environmental efficiency of MSW services. Previous studies focused on developed countries and employed radial parametric and non-parametric methods. By contrast, this study assessed the technical efficiency, environmental efficiency and eco-efficiency of several Chilean municipalities employing the non-radial range adjusted measure approach. A second stage of assessment was conducted to explore the influence of a set of environmental variables on efficiency scores. Results revealed that the evaluated Chilean municipalities performed poorly from a technical perspective since the average technical efficiency score was 0.484. By contrast, average environmental efficiency and eco-efficiency scores were 0.899 and 0.922, respectively. Nevertheless, the percentage of eco-efficient municipalities was lower than 1%. It was also found that tourism had a major and negative impact on all types of efficiency. By contrast, population density had a significant and positive impact on environmental efficiency. The assessment of three types of efficiency provides relevant information to policymakers to define specific strategies to improve MSW management according to sustainability and circular economic objectives. [ABSTRACT FROM AUTHOR]

Background: Every year, volunteers of the Belgian Red Cross provide onsite medical care at more than 8000 mass gathering events and other manifestations. Today standardized planning tools for optimal preventive medical resource use during these events are lacking. This study aimed to develop and validate a prediction model of patient presentation rate (PPR) and transfer to hospital rate (TTHR) at mass gatherings in Belgium.Methods: More than 200,000 medical interventions from 2006 to 2018 were pooled in a database. We used a subset of 28 different mass gatherings (194 unique events) to develop a nonlinear prediction model. Using regression trees, we identified potential predictors for PPR and TTHR at these mass gatherings. The additional effect of ambient temperature was studied by linear regression analysis. Finally, we validated the prediction models using two other subsets of the database.Results: The regression tree for PPR consisted of 7 splits, with mass gathering category as the most important predictor variable. Other predictor variables were attendance, number of days, and age class. Ambient temperature was positively associated with PPR at outdoor events in summer. Calibration of the model revealed an R2 of 0.68 (95% confidence interval 0.60-0.75). For TTHR, the most determining predictor variables were mass gathering category and predicted PPR (R2 = 0.48). External validation indicated limited predictive value for other events (R2 = 0.02 for PPR; R2 = 0.03 for TTHR).Conclusions: Our nonlinear model performed well in predicting PPR at the events used to build the model on, but had poor predictive value for other mass gatherings. The mass gathering categories "outdoor music" and "sports event" warrant further splitting in subcategories, and variables such as attendance, temperature and resource deployment need to be better recorded in the future to optimize prediction of medical usage rates, and hence, of resources needed for onsite emergency medical care. [ABSTRACT FROM AUTHOR]

The tunnel advance (pull) per blast considerably influences the time and expenditure incurred to construct tunnels using conventional drill and blast methods. Blasts with high pull efficiency can considerably lessen the construction time by reducing the number of drilling, blasting and mucking cycles. Researchers have developed some empirical and theoretical models for determining pull. However, these models are based upon hit and trial techniques. The previous works on the similar subject suggest that the pull efficiency cannot be correlated to a variable. Nevertheless, the literature suggests that the soft computing techniques can be used for solving such non-linear problems. The present study aims to develop a classification and regression tree (CART) model to predict the pull using various blast design parameters, such as cross-sectional area, number of blast holes, hole diameter, hole depth, charge per hole, maximum charge per delay, total charge and charge factor. A dataset comprising of 100 data points was compiled from tunnelling sites of Karcham Wangtoo Hydroelectric Project for model formulation. The dataset was divided in a ratio of 80:20 for training and testing, respectively. The coefficient of determination (R2) and root mean square error (RMSE) of the CART model and multivariate regression analysis were compared for the validation. The suitability of the CART model was further verified by conducting statistical hypothesis tests. [ABSTRACT FROM AUTHOR]

In this study, box and whisker and principal component analysis, as well as classification and regression tree modeling as a part of machine learning were performed on a database constructed on PEM (polymer electrolyte membrane) electrolysis with 789 data points from 30 recent publications. Box whisker plots discovered that pure Pt at the cathode surface, Ti at the anode support, the existence of Pt, Ir, Co, Ru at the anode surface, Ti porous structures at the electrodes, pure water-electrolyte and Nafion and Aquivion type membranes in proton exchange electrolyzer provide the highest performances. Principal component analysis indicated that when cathode surface consists of mostly pure Ni, when anode electrode has no support or vanadium (10–20%) doped TiO 2 support and when anode electrode surface consists of cobalt-iron alloys (0.5:0.5 and 0.333:0.666 mol ratio) or RuO 2 , there is a risk for low-performance. Classification trees revealed that other than current density and potential, cathode surface Ni mole fraction, anode surface Co mole fraction are the most important variables for the performance of an electrolyzer. Finally, the regression tree technique successfully modeled the polarization behavior with a RMSE (root mean square error) value of 0.18. [Display omitted] • Carbon, Pt and Ti based materials have high PEM electrolyzer performance. • Proton conductor electrolyzers are superior to anion exchange electrolyzers. • Ni, unsupported or vanadium doped TiO 2 , CoFe and RuO 2 have performance risks. • Ni and Co mole fractions are the most important input variables. • Regression tree modeling can predict PEM electrolyzer polarization. [ABSTRACT FROM AUTHOR]

This paper examines a novel gradient boosting framework for regression. We regularize gradient boosted trees by introducing subsampling and employ a modified shrinkage algorithm so that at every boosting stage the estimate is given by an average of trees. The resulting algorithm, titled "Boulevard", is shown to converge as the number of trees grows. This construction allows us to demonstrate a central limit theorem for this limit, providing a characterization of uncertainty for predictions. A simulation study and real world examples provide support for both the predictive accuracy of the model and its limiting behavior. [ABSTRACT FROM AUTHOR]

Meteorological parameters modulate transmission of the SARS-Cov-2 virus, the causative agent related to coronavirus disease-2019 (COVID-19) development. However, findings across the globe have been inconsistent attributed to several confounding factors. The aim of the present study was to investigate the relationship between reported meteorological parameters from July 1 to October 31, 2020, and the number of confirmed COVID-19 cases in 4 Brazilian cities: São Paulo, the largest city with the highest number of cases in Brazil, and the cities with greater number of cases in the state of Parana during the study period (Curitiba, Londrina and Maringa). The assessment of meteorological factors with confirmed COVID-19 cases included atmospheric pressure, temperature, relative humidity, wind speed, solar irradiation, sunlight, dew point temperature, and total precipitation. The 7- and 15-day moving averages of confirmed COVID-19 cases were obtained for each city. Pearson's correlation coefficients showed significant correlations between COVID-19 cases and all meteorological parameters, except for total precipitation, with the strongest correlation with maximum wind speed (0.717, <0.001) in São Paulo. Regression tree analysis demonstrated that the largest number of confirmed COVID-19 cases was associated with wind speed (between ≥0.3381 and <1.173 m/s), atmospheric pressure (<930.5mb), and solar radiation (<17.98e+3). Lower number of cases was observed for wind speed <0.3381 m/s and temperature <23.86°C. Our results encourage the use of meteorological information as a critical component in future risk assessment models. [ABSTRACT FROM AUTHOR]

With the emergence of telematics car driving data, insurance companies have started to boost classical actuarial regression models for claim frequency prediction with telematics car driving information. In this paper, we propose two data-driven neural network approaches that process telematics car driving data to complement classical actuarial pricing with a driving behavior risk factor from telematics data. Our neural networks simultaneously accommodate feature engineering and regression modeling which allows us to integrate telematics car driving data in a one-step approach into the claim frequency regression models. We conclude from our numerical analysis that both classical actuarial risk factors and telematics car driving data are necessary to receive the best predictive models. This emphasizes that these two sources of information interact and complement each other. [ABSTRACT FROM AUTHOR]

Reference evapotranspiration (ET0) is a crucial element for deriving irrigation scheduling of major crops. Thus, precise projection of ET0 is essential for better management of scarce water resources in many parts of the globe. This study evaluates the potential of a Hierarchical Fuzzy System (HFS) optimized by Particle Swarm Optimization (PSO) algorithm (PSO-HFS) to predict daily ET0. The meteorological variables and estimated ET0 (using FAO-56 Penman–Monteith equation) were employed as inputs and outputs, respectively, for the PSO-HFS model. The prediction accuracy of PSO-HFS was compared with that of a Fuzzy Inference System (FIS), M5 Model Tree (M5Tree), and a Regression Tree (RT) model. Ranking of the models was performed using the concept of Shannon's Entropy that accounts for a set of performance evaluation indices. Results revealed that the PSO-HFS model performed better (with Entropy weight = 0.93) than the benchmark models (Entropy weights of 0.77, 0.74, and 0.90 for the FIS, RT, and M5Tree, respectively). Furthermore, the generalization capabilities of the proposed models were evaluated using the dataset from a test station. Generalization performances revealed that the models performed equally well with the unseen test dataset and that the PSO-HFS model provided superior performance (with R = 0.93, RMSE = 0.59 mm d−1 and IOA = 0.94) while the RT model (with R = 0.82, RMSE = 0.90 mm d−1, and IOA = 0.83) exhibited the worst performance for the test dataset. The overall results imply that the PSO-HFS model could effectively be utilized to model ET0 quite efficiently and accurately. [ABSTRACT FROM AUTHOR]

Abstract In veneer-drying facilities, controllers face many challenges to maintain desired parameters in the final product based on customer’s needs. The major challenge is setting process parameters to control the temperature and humidity within the various sections in the drying machine to obtain the desired properties of the final product. The regression tree approach can be used to simplify the complex relationship among process and product variables for identifying critical factors for drying veneer and achieving the desired range of veneer temperature. In this study, we investigated veneer-drying conditions and the short-term effect of climatic variables on veneer temperature. We have shown a three-step process to develop an optimal regression tree for veneer temperature. From the developed optimal tree, we are able to identify the most important threshold points of predictor space and adjustment for the climatic variables on the temperature of veneer sheets. The findings of this study were further investigated in an industrial setting and the desired veneer temperatures were attained for the final product. This application shows that we can follow the path of the optimal tree to pinpoint the most desired veneer temperature outcome. The developed optimal tree is relatively easy to use and interpret to estimate the average response of veneer temperature.

Background: Reducing health disparities is a public health issue. Identification of low-health-interest populations is important, but a definition of people with low health interest has not yet been established. We aimed to quantitatively define low-health-interest populations., Methods: A nationwide cross-sectional internet survey was conducted in 2022. We compiled regression tree (RT) analyses with/without adjustment for age, sex, and socioeconomic status with the 12-item Interest in Health Scale (IHS, score range 12-48) as an explanatory variable and the 10 composite health behaviors as a dependent variable. We defined the first IHS branching condition from the root node as a lower-health-interest group and the terminal node with the lowest health behaviors as the lowest-health-interest group., Results: The mean IHS value of 22,263 analyzed participants was 32.1 ± 5.6; it was higher in females and in those who were aged over 45 years, had a high education, a high income, or a spouse. The first branching condition was IHS 31.5, and the terminal node branched at 24.5, before/after adjustment for covariates., Conclusions: We determined the cutoff values of the IHS as <32 for a lower-health-interest group and <25 for the lowest-health-interest group. Using these cutoffs might enable us to reveal the characteristics of low-health-interest populations.

The aim of this study was to evaluate the potential of the machine learning technique of decision trees to understand the relationships among furnace design, process parameters, crystal quality, and yield in the case of the Czochralski growth of germanium. The ultimate goal was to provide the range of optimal values of 13 input parameters and the ranking of their importance in relation to their impact on three output parameters relevant to process economy and crystal quality. Training data were provided by CFD modelling. The variety of data was ensured by the Design of Experiments method. The results showed that the process parameters, particularly the pulling rate, had a substantially greater impact on the crystal quality and yield than the design parameters of the furnace hot zone. Of the latter, only the crucible size, the axial position of the side heater, and the material properties of the radiation shield were relevant.

Thinning of semi‐arid forests to reduce wildfire risk is believed to improve forest health by increasing soil moisture. Increased snowpack, reduced transpiration and reduced rainfall interception are frequently cited mechanisms by which reduced canopy density may increase soil moisture. However, the relative importance of these factors has not been rigorously evaluated in field studies. We measured snow depth, snow water equivalent (SWE) and the spatial and temporal variation in soil moisture at four experimental paired treatment‐control thinning sites in high elevation ponderosa pine forest northern Arizona, USA. We compared snow and soil moisture measurements with forest structure metrics derived from aerial imagery and 3‐dimensional lidar data to determine the relationship between vegetation structure, snow and soil moisture throughout the annual hydrologic cycle. Soil moisture was consistently and significantly higher in thinned forest plots, even though the treatments were performed 8–11 years before this study. However, we did not find evidence that SWE was higher in thinned forests across a range of snow conditions. Regression tree analysis of soil moisture and vegetation structure data provided some evidence that localized differences in transpiration and interception of precipitation influence the spatial pattern of soil moisture at points in the annual hydrologic cycle when the system is becoming increasingly water limited. However, vegetation structure explained a relatively low amount of the spatial variance (R2 < 0.23) in soil moisture. Continuous measurements of soil moisture in depth profiles showed stronger attenuation of soil moisture peaks in thinned sites, suggesting differences in infiltration dynamics may explain the difference in soil moisture between treatments as opposed to overlying vegetation alone. Our results show limited support for commonly cited relationships between vegetation structure, snow and soil moisture and indicate that future research is needed to understand how reduction in tree density alters soil hydraulic properties. [ABSTRACT FROM AUTHOR]

In this paper, a new tree-structured regression model—the projection pursuit regression tree—is proposed. It combines the projection pursuit classification tree with the projection pursuit regression. The main advantage of the projection pursuit regression tree is exploring the independent variable space in each range of the dependent variable. Additionally, it retains the main properties of the projection pursuit classification tree. The projection pursuit regression tree provides several methods of assigning values to the final node, which enhances predictability. It shows better performance than CART in most cases and sometimes beats random forest with a single tree. This development makes it possible to find a better explainable model with reasonable predictability. [ABSTRACT FROM AUTHOR]

Identifying areas prone to flooding is a key step in flood risk management. The purpose of this study is to develop and present a novel flood susceptibility model based on Bayesian Additive Regression Tree (BART) methodology. The predictive performance of the new model is assessed via comparison with the Naïve Bayes (NB) and Random Forest (RF) based methods that were previously published in the literature. All models were tested on a real case study based in the Kan watershed in Iran. The following fifteen climatic and geo-environmental variables were used as inputs into all flood susceptibility models: altitude, aspect, slope, plan curvature, profile curvature, drainage density, distance from river distance from road, stream power index (SPI), topographic wetness index (TPI), topographic position index (TPI), curve number (CN), land use, lithology and rainfall. Based on the existing flood field survey and other information available for the analyzed area, a total of 118 flood locations were identified as potentially prone to flooding. The data available were divided into two groups with 70% used for training and 30% for validation of all models. The receiver operating characteristic (ROC) curve parameters were used to evaluate the predictive accuracy of the new and existing models. Based on the area under curve (AUC) the new BART (86%) model outperformed the NB (80%) and RF (85%) models. Regarding the importance of input variables, the results obtained showed that the location's altitude and distance from the river are the most important variables for assessing flooding susceptibility. [ABSTRACT FROM AUTHOR]

The acetylcholinesterase (AChE) and butyrylcholinesterase (BuChE) inhibitors play a key role in treating Alzheimer's disease. This study proposes an approach that integrates a modified binary particle swarm optimization (PSO) with a machine learning algorithm for building QSAR models to predict the activity of inhibitors for AChE and BuChE enzymes. More precisely, it uses a transfer function to convert the continuous search space of PSO to binary. Furthermore, it utilizes the concepts of catfish effect and chaotic map to improve exploration ability in searching for an optimum subset of descriptors for QSAR model constructions. Then, through a statistical method, it employs a machine learning algorithm to evaluate the fitness value of each candidate subset of features. Different combinations of four transfer functions with four machine learning algorithms, including K-nearest neighbour, multiple linear regression, support vector machine, and regression tree, were used to build several variants of the proposed algorithm. QSAR models constructed by each version were verified by internal and external validations. The best variants were selected based on a method called sum of ranking differences. [ABSTRACT FROM AUTHOR]

BRAF and MEK inhibitors combination, including dabrafenib (D) and trametinib (T) have transformed the treatment of BRAF V600 -mutant advanced melanoma patients, including patients with brain metastasis (BM). In a large phase IIIb, single-arm, open-label, multicenter French study, we assessed safety, response to treatment, progression-free survival (PFS) and factors associated with progression, and stratified the population into risk groups. Patients with unresectable, advanced, BRAF V600 -mutant melanoma were included, including those with the presence of BM, Eastern Cooperative Oncology Group Performance Status (ECOG PS) ≤2, elevated lactate dehydrogenase (LDH) or previous melanoma treatments. Responses were determined locally, without central review. PFS was estimated using the Kaplan–Meier analysis and modelled with multivariate Cox model. Risk subgroups were identified using a regression tree analysis. Between March 2015 and November 2016, 856 patients received at least one D + T dose. Overall, 92% had stage IV melanoma, 38% ECOG PS ≥1, 32% BM and 37.5% elevated LDH. Median PFS was 8.02 months (95% confidence interval [CI] 7.33–8.77). Significant factors associated with lower PFS were ECOG PS ≥1, elevated LDH, ≥3 metastatic sites and presence of BM. Patients with <3 metastatic sites, ECOG = 0 and no BM had the highest probability of PFS at 6 months (83%, 95% CI 76–87) and 12 months (56%, 95% CI 47–64), respectively. This is the largest prospective study in advanced BRAF V600 -mutant melanoma patients treated with D + T, conducted in conditions close to 'real-world practice'. We confirm previous findings that LDH, ECOG PS and ≥3 metastatic sites are associated with shorter PFS, but the real-world setting introduces BM as a major prognostic factor. • This is the largest close to real-word study on BRAF V600-mutant melanoma patients. • The study included the largest population of melanoma patients with brain metastases. • The results confirm the clinical activity of trametinib associated to dabrafenib. • LDH, ECOG, number of metastatic sites and presence of brain metastases associated with PFS. [ABSTRACT FROM AUTHOR]

Time series forecasting has been the area of intensive research for years. Statistical, machine learning or mixed approaches have been proposed to handle this one of the most challenging tasks. However, little research has been devoted to tackle the frequently appearing assumption of normality of given data. In our research, we aim to extend the time series forecasting models for heavy-tailed distribution of noise. In this paper, we focused on normal and Student's t distributed time series. The SARIMAX model (with maximum likelihood approach) is compared with the regression tree-based method—random forest. The research covers not only forecasts but also prediction intervals, which often have hugely informative value as far as practical applications are concerned. Although our study is focused on the selected models, the presented problem is universal and the proposed approach can be discussed in the context of other systems. [ABSTRACT FROM AUTHOR]

Random forest (RF) is one of the most popular machine learning (ML) models used for both classification and regression problems. As an ensemble model, it demonstrates high predictive accuracy and low variance, while being easy to learn and optimize. In this study, we use RF for short-term load forecasting (STLF), focusing on data representation and training modes. We consider seven methods of defining input patterns and three training modes: local, global and extended global. We also investigate key RF hyperparameters to learn about their optimal settings. The experimental part of the work demonstrates on four STLF problems that our model, in its optimal variant, can outperform both statistical and ML models, providing the most accurate forecasts.

As the spatial carrier of carbon emission from land ecosystems and human activities, land use plays an important role in representing the spatial distribution of carbon emissions and carbon sinks. The intension of CO2 emission is closely attached to the fundamental unit of urban form—land use patterns. The exploration of the low-carbon oriented spatial optimization provides new scope for solving the high carbon emission in the urban area through spatial planning. In this paper, Eindhoven in the Netherlands was selected as the case study to implement spatial optimization. A set of parameters containing the spatial attributes of buildings and vegetation were introduced to classify the land use patterns into six categories through a combined random forest algorithm and regression tree approach. The results show the geographic features of vegetation are the crucial factors for the carbon emission. The multi-objective spatial optimization model integrated carbon emission, population, and constraint conditions. It is solved with non-dominated sorting genetic algorithm-II (NSGA-II), in which each gene represents a specific type of land use category. The optimal solutions were incorporated with a regression model to analyze the impact of the variation in each land use category. Three categories were proved to be more influential on carbon emission performance. The optimized land use structure shows the potential to reduce the carbon emission and offer valuable consults to low carbon land use plan.

The present study was conducted to evaluate the comparative predictive performances of Classification and Regression trees (CART), Chi Squared Automatic Interaction Detector (CHAID) and Exhausted CHAID algorithms used to predict body weights of Awassi lambs at 60-d (W60) and 90-d (W90) of age. For this purpose, 730 Awassi lamb records were collected from 3 base flocks in Turkey in 2014-2016. The potential predictors included in this study were dam age, sex, birth type, flock, lambing season and birth year. In order to determine the best one among these decision tree algorithms, model evaluation criteria i.e RMSE, MAPE, RAE, SDratio, MAD, Pearson coefficient, Coefficient of determination (푅 2) and adjusted coefficient of variation (푅 2Adj) values were calculated. For the prediction of W60 and W90, the best decision tree algorithm was found to be the CART algorithm. 푅 2 for W60 and W90 were 0.614 and 0.978 and RMSE estimates for W60 and W90 were 0.94 and 0.321, respectively. The influential predictors affecting W90 were flock and W60. However, flock, birth weight (BW), birth type and birth year were found as significant factors for W60. In conclusion, CART algorithm may be a useful tool in describing breed standards of the Awassi for selection purposes in animal breeding. Also, it outperformed Exhausted CHAID and CHAID decision tree algorithms in predictive performance to predict W60 and W90 of Awassi lambs. [ABSTRACT FROM AUTHOR]

Background: Prevention of coronavirus (COVID-19) regarding households has many aspects, such as buying mask, hand sanitizer, face shield, and many others. As a result of buying the previous items, the household spending per month will increase during the COVID-19 pandemic period. This study aimed to calculate the average costs of each extra item involved in households spending during COVID-19 pandemic and to predict the total average extra costs spending by households. Results: Most of the respondents were females (81%) and aged between 30 and 40 (56.3%). About 63.1% of families had the same monthly income while 35.4% had a decrease in monthly income. A significant reduction in days of leaving home before and after COVID-19 pandemic was observed (before; median = 6, after; median = 5, P = < 0.001). The extra spending in grocery was the dominated item compared to other items (mean = 707.2 L.E./month, SD = 530.7). Regarding regression tree, the maximum average extra costs due to COVID-19 pandemic were 1386 L.E./month (around 88.56$/month (1$—> 15.65L.E.)) while the minimum average extra costs were 217 L.E./month (around 13.86$/month). Conclusions: The effect of COVID-19 pandemic in households spending varies largely between households, it depends on what they do to prevent COVID-19. [ABSTRACT FROM AUTHOR]