Search

This study aims to execute machine learning methods to predict the mechanical properties containing TS and CS of HPC. They are essential parameters for the durability, workability, and efficiency of concrete structures in civil engineering. In this regard, obtaining the estimation of the mechanical properties of HPC is complex energy and time‐consuming. Due to this, an observed database was compiled, including 168 datasets for CS and 120 for TS. This database trained and validated two machine learning models: SVR and RT. The models combine the prediction outputs from the meta‐heuristic algorithms to build hybrid and ensemble‐hybrid models, which include dwarf mongoose optimization, PPSO, and moth flame optimization. According to the observed outputs, the ensemble models have great potential to be a recourse to deal with the overfitting problem of civil engineering, thus leading to the development of more supportable and less polluting concrete structures. This research significantly improves the efficiency and accuracy of predicting vital mechanical properties in high‐performance concrete by integrating machine learning and metaheuristic algorithms, offering promising avenues for enhanced concrete structure design and development. [ABSTRACT FROM AUTHOR]

The traditional CAPM explains the return on each security, while the current study suggests a new methodology for "picking" a broad index, based on regression trees. Analysts' recommendations on market prices are analyzed, and a one to three‐stage method is employed. The analysis suggests a few rules of thumb (only one to three stages) for buying or selling the CRSP US market index. The findings are robust, and the rules are reliable. Researchers and practitioners may benefit greatly from the new rules. [ABSTRACT FROM AUTHOR]

Summary: The increasing interest in renewable and sustainable energy production as a means of attaining net‐zero carbon emissions in the near future has spurred research attention in the development of fuel cells that convert chemical energy to electrical energy. In this study machine learning algorithms namely Support Vector Machine (SVM) regression, Regression Trees, and Gaussian Process Regression (GPR) were configured for modeling the effect of palladium supported on carbon nanotube used for formic acid electro‐oxidation. The effect of process parameters such as the amount of palladium, the amount of sodium tetrahydridoborate (NaBH4), amount of water, and the electro‐oxidation reaction time on the formic acid electro‐oxidation to generate current density was evaluated by the various models. The trained SVM regressions models incorporated with linear, quadratic, cubic, and fine Gaussian kernel functions, as well as the Boosted and the Bagged regression Trees, did not show impressive performance as indicated by a low coefficient of determination (R2) < 0.5 and high prediction errors. However, the SVM regression modeled with Median Gaussian kernel function, the GPR incorporated with rotational quadratic and squared exponential kernel functions displayed higher performance with R2 > 0.6 but less than 0.7. The optimization of the SVM, Ensemble Tree, and GPR models resulted in significant performance with R2 of 0.82, 0.83, and 0.85, respectively. The sensitivity analysis using modified Garson algorithm to determine how each of these parameters influences the predicted current density from the direct formic acid fuel cells showed that the level of importance of the input parameters on the predicted current density can be ranked as Pd composition > electro‐oxidation time > amount of water > NaBH4 proportion. [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]

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]

Questions: Inundation is an important feature linked to monodominance in tropical wetlands. The occurrence of neighbouring monodominant species indicates that soil can also have an important role. This study aimed to determine if variations in densities of three neighbouring monodominant species, Byrsonima cydoniifolia, Copernicia alba and Tabebuia aurea, are related primarily to variation of flooding patterns and secondarily to soil physicochemical variations in the Pantanal. Location: This study was performed in the southern Pantanal subregion of Miranda. Methods: We sampled 74 plots of 25 m × 25 m distributed among 15 patches of these species (five patches of each species). In each plot, we sampled all individuals of all shrub and tree species, checked the water mark left on tree trunks by the last flooding, and collected soil samples. Data were analyzed using canonical correspondence analysis (CCA) and regression trees. Results: We found that the main driver splitting these monodominant stands is soil, and that the secondary driver is inundation. The main drivers for Copernicia alba were higher soil pH, higher inundation and soil contents of Mg. For Byrsonima cydoniifolia, the main drivers were low Ca and Mg contents and high content of fine sand. Tabebuia aurea was the only species for which inundation was the main driver. Conclusions: We reject the hypothesis that inundation is the main driver splitting these monodominant stands. Differences in flooding levels were not crucial for two of the three species. Except for Tabebuia aurea, which was more influenced by inundation, soils were found to play an essential role in this spatial separation. [ABSTRACT FROM AUTHOR]

We model the conditional risk premium by combining principal component analysis and a statistical learning technique, known as boosted regression trees. The method is validated through various out‐of‐sample tests. We apply the estimates to test the positivity restriction on the risk premium and find evidence that the risk premium is negative in periods of low corporate and government bond returns, high inflation and downward‐sloping term structure. These periods are linked with changes in business cycles; the states when theories predict the existence of negative risk premium. Based on the evidence, we reject the conditional capital asset pricing model and raise a question over the practice of imposing the positive risk premium constraint in predictive models. [ABSTRACT FROM AUTHOR]

Typhoons have substantial impacts on power systems and may result in major power outages for distribution network users. Developing prediction models for the number of users going through typhoon power outages is a high priority to support restoration planning. This study proposes a data‐driven model to predict the number of distribution network users that may experience power outages when a typhoon passes by. To improve the accuracy of the prediction model, twenty six explanatory variables from meteorological factors, geographical factors and power grid factors are considered. In addition, the authors compared the application effect of five different machine learning regression algorithms, including linear regression, support vector regression, classification and regression tree, gradient boosting decision tree and random forest (RF). It turns out that the RF algorithm shows the best performance. The simulation indicates that the accuracy of the optimal model error within ±30% can reach up to 86%. The proposed method can improve the prediction accuracy through continuous learning on the existing basis. The prediction results can provide efficient guidance for emergency preparedness during typhoon disaster, and can be used as a basis to notify the distribution network users who are likely to lose power. [ABSTRACT FROM AUTHOR]

Summary: Graphics Processing Units (GPUs) are used as accelerators for improving performance while executing highly data parallel applications. The GPUs are characterized by a number of Streaming Multiprocessors (SM) and a large number of cores within each SM. In addition to this, a hierarchy of memories with different latencies and sizes is present in the GPUs. The program execution in GPUs is thus dependent on a number of parameter values, both at compile time and runtime. To obtain the optimal performance with these GPU resources, a large parameter space is to be explored, and this leads to a number of unproductive program executions. To alleviate this difficulty, machine learning–based autotuning systems are proposed to predict the right configuration using a limited set of compile‐time parameters. In this paper, we propose a two‐stage machine learning–based autotuning framework using an expanded set of attributes. The important parameters such as block size, occupancy, eligible warps, and execution time are predicted. The mean relative error in prediction of different parameters ranges from of 16% to 6.5%. Dimensionality reduction for the features set reduces the features by up to 50% with further increase in prediction accuracy. [ABSTRACT FROM AUTHOR]

Multiple imputation by chained equations (MICE) has emerged as a leading strategy for imputing missing epidemiological data due to its ease of implementation and ability to maintain unbiased effect estimates and valid inference. Within the MICE algorithm, imputation can be performed using a variety of parametric or nonparametric methods. Literature has suggested that nonparametric tree-based imputation methods outperform parametric methods in terms of bias and coverage when there are interactions or other nonlinear effects among the variables. However, these studies fail to provide a fair comparison as they do not follow the well-established recommendation that any effects in the final analysis model (including interactions) should be included in the parametric imputation model. We show via simulation that properly incorporating interactions in the parametric imputation model leads to much better performance. In fact, correctly specified parametric imputation and tree-based random forest imputation perform similarly when estimating the interaction effect. Parametric imputation leads to slightly higher coverage for the interaction effect, but it has wider confidence intervals than random forest imputation and requires correct specification of the imputation model. Epidemiologists should take care in specifying MICE imputation models, and this paper assists in that task by providing a fair comparison of parametric and tree-based imputation in MICE. [ABSTRACT FROM AUTHOR]

In this research we analyze a new approach for prediction of demand. In the studiedmarket of performing arts the observed demand is limited by capacity of the house. Then one needs to account for demand censorship to obtain unbiased estimates of demand function parameters. The presence of consumer segments with different purposes of going to the theater and willingness-to-pay for performance and ticket characteristics causes a heterogeneity in theater demand. We propose an estimator for prediction of demand that accounts for both demand censorship and preferences heterogeneity. The estimator is based on the idea of classification and regression trees and bagging prediction aggregation extended for prediction of censored data. Our algorithm predicts and combines predictions for both discrete and continuous parts of censored data. We show that our estimator performs better in terms of prediction accuracy compared with estimators which account either for censorship or heterogeneity only. The proposed approach is helpful for finding product segments and optimal price setting. [ABSTRACT FROM AUTHOR]

In this article, we propose a novel hybridization of regression trees (RTs) and radial basis function networks, namely, radial basis neural tree model, for waste recovery process (WRP) improvement in a paper industry. As a by‐product of the paper manufacturing process, a lot of waste along with valuable fibers and fillers come out from the paper machine. The WRP involves separating the unwanted materials from the valuable ones so that the recovered fibers and fillers can be further reused in the production process. This job is done by fiber‐filler recovery equipment (FFRE). The efficiency of FFRE depends on several crucial process parameters, and monitoring them is a difficult proposition. The proposed model can be useful to find the essential parameters from the set of available data and to perform prediction task to improve WRP efficiency. An idea of parameter optimization along with regularity conditions for the universal consistency of the proposed model is given. The proposed model has the advantages of easy interpretability and excellent performance when applied to the FFRE efficiency improvement problem. Improved waste recovery will help the industry to become environmentally friendly with less ecological damage apart from being cost‐effective. [ABSTRACT FROM AUTHOR]

The Atlantic Forest is the second most diverse forest system in South America, and only a fraction of its original distribution remains. In this study, we aim to use robust datasets of small mammals along the entire forest system to disentangle the main drivers for diversity along this gradient. More specifically, we aim to disentangle whether deforestation (recent), biogeographical variables, including 19 bioclimatic variables (historic), or historical trapping bias best describe patterns of taxonomic, functional, and phylogenetic diversities using small mammal assembles, from northeastern Brazil to eastern Paraguay. For that, we applied regression tree analyses to determine what environmental variables best describe each of the dimensions of diversity. Additionally, we implemented polynomial regression to test nonlinear relationships between biodiversity metrics and patch size. We found that patterns of overall taxonomic, functional, and phylogenetic diversities; rodent taxonomic diversity; and marsupial functional diversity were better explained by temperature variables. Meanwhile, marsupial taxonomic and phylogenetic diversities, and rodent functional and phylogenetic diversities were best explained by precipitation variables. Furthermore, patch area, trapping, and latitude were never the best descriptors for any of the diversity dimensions. Although all dimensions of biodiversity are correlated, they have unique information and should be considered individually to better understand biodiversity and inform conservation strategies. We found that fragmentation is impactful at a local scale and becomes less important at a biogeographical scale. Therefore, climatic variables drove biogeographical faunal patterns for all clades, probably reflecting important historical assembly process at large spatial scales. [ABSTRACT FROM AUTHOR]

Plant species recognition is performed using a dual deep learning architecture (DDLA) approach. DDLA consists of MobileNet and DenseNet‐121 architectures. The feature vectors obtained from individual architectures are concatenated to form a final feature vector. The extracted features are then classified using machine learning (ML) classifiers such as linear discriminant analysis, multinomial logistic regression (LR), Naive Bayes, classification and regression tree, k‐nearest neighbour, random forest classifier, bagging classifier and multi‐layer perceptron. The dataset considered in the studies is standard (Flavia, Folio, and Swedish Leaf) and custom collected (Leaf‐12) dataset. The MobileNet and DenseNet‐121 architectures are also used as a feature extractor and a classifier. It is observed that the DDLA architecture with LR classifier produced the highest accuracies of 98.71, 96.38, 99.41, and 99.39% for Flavia, Folio, Swedish leaf, and Leaf‐12 datasets. The observed accuracy for DDLA + LR is higher compared with other approaches (DDLA + ML classifiers, MobileNet + ML classifiers, DenseNet‐121 + ML classifiers, MobileNet + fully connected layer (FCL), DenseNet‐121 + FCL). It is also observed that the DDLA architecture with LR classifier achieves higher accuracy in comparable computation time with other approaches. [ABSTRACT FROM AUTHOR]

Accurate prediction of runoff signatures is important for numerous hydrological and water resources applications. However, there are lack of comprehensive evaluations of various approaches for predicting hydrological signatures. This study, for the first time, introduces regression tree ensemble approach and compares it with other three widely used approaches (multiple linear regression, multiple log‐transformed linear regression, and hydrological modeling) for assessing prediction accuracy of 13 runoff characteristics or signatures, using a large data set from 605 catchments across Australia. The climate, in particular, mean annual precipitation and aridity index, has the most significant influence on the runoff signatures. Physical catchment attributes including forest ratio, slope, and soil water holding capacity also have significant influence (p < 0.05) on the runoff signatures. All four approaches can predict the long‐term average and high flow signatures accurately. The regression approaches can also well predict majority of the other runoff signatures, with the Nash‐Sutcliffe Efficiency larger than 0.60. The regression tree ensemble outperforms the two linear regressions in predicting signatures of flow dynamics. The hydrological models, calibrated to one specific objective criterion, cannot predict many of the runoff signatures, particularly those reflecting low flows and flow dynamics. This is because in most hydrological model applications, the simulations allow satisfactory predictions of long‐term average and high flow signatures. In applications where a specific runoff signature is needed, regression relationships that directly relate that runoff signature to catchment attributes give the best predictions. Here the regression tree ensemble is overall best and offers significant potential, being able to predict most of the runoff signatures very well. Key Points: Four approaches are compared for predicting 13 runoff signatures for 605 catchments across AustraliaThe regression tree ensemble approach is overall best; the linear regressions are intermediate and only marginally different from each otherHydrological modeling can predict reasonably well the average and high flow signatures, but in general not the low flow and flow dynamic signatures [ABSTRACT FROM AUTHOR]

Abstract: Classification of particles as gunshot residues (GSRs) is conducted using a semiautomatic approach in which the system first classifies particles based on an automatic elemental analysis, and then, examiners manually analyze particles having compositions which are characteristic of or consistent with GSRs. Analyzing all the particles in the second stage is time consuming with many particles classified by the initial automated system as being potentially GSRs excluded as such by the forensic examiner. In this paper, a new algorithm is developed to improve the initial classification step. The algorithm is based on a binary tree that was trained on almost 16,000 particles from 43 stubs used to sample hands of suspects. The classification algorithm was tested on 5,900 particles from 23 independent stubs and performed very well in terms of false positive and false negative rates. A routine use of the new algorithm can reduce significantly the analysis time of GSRs. [ABSTRACT FROM AUTHOR]

The evaluation of ecosystem quality is important for land-management and land-use planning. Evaluation is unavoidably subjective, and robust metrics must be based on consensus and the structured use of observations. We devised a transparent and repeatable process for building and testing ecosystem metrics based on expert data. We gathered quantitative evaluation data on the quality of hypothetical grassy woodland sites from experts. We used these data to train a model (an ensemble of 30 bagged regression trees) capable of predicting the perceived quality of similar hypothetical woodlands based on a set of 13 site variables as inputs (e.g., cover of shrubs, richness of native forbs). These variables can be measured at any site and the model implemented in a spreadsheet as a metric of woodland quality. We also investigated the number of experts required to produce an opinion data set sufficient for the construction of a metric. The model produced evaluations similar to those provided by experts, as shown by assessing the model's quality scores of expert-evaluated test sites not used to train the model. We applied the metric to 13 woodland conservation reserves and asked managers of these sites to independently evaluate their quality. To assess metric performance, we compared the model's evaluation of site quality with the managers' evaluations through multidimensional scaling. The metric performed relatively well, plotting close to the center of the space defined by the evaluators. Given the method provides data-driven consensus and repeatability, which no single human evaluator can provide, we suggest it is a valuable tool for evaluating ecosystem quality in real-world contexts. We believe our approach is applicable to any ecosystem. [ABSTRACT FROM AUTHOR]

Risk equalization formulas have been refined since their introduction about two decades ago. Because of the complexity and the abundance of possible interactions between the variables used, hardly any interactions are considered. A regression tree is used to systematically search for interactions, a methodologically new approach in risk equalization. Analyses are based on a data set of nearly 2.9 million individuals from a major German social health insurer. A two-step approach is applied: In the first step a regression tree is built on the basis of the learning data set. Terminal nodes characterized by more than one morbidity-group-split represent interaction effects of different morbidity groups. In the second step the 'traditional' weighted least squares regression equation is expanded by adding interaction terms for all interactions detected by the tree, and regression coefficients are recalculated. The resulting risk adjustment formula shows an improvement in the adjusted R2 from 25.43% to 25.81% on the evaluation data set. Predictive ratios are calculated for subgroups affected by the interactions. The R2 improvement detected is only marginal. According to the sample level performance measures used, not involving a considerable number of morbidity interactions forms no relevant loss in accuracy. Copyright © 2015 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

Imperfect detection of individuals within an animal population can bias estimates of abundance and other population metrics. However, detectability may be improved by timing surveys with conditions that increase detection among individuals of the population. We explored the weather conditions that promote surface activity in a burrowing desert lizard, Slater's skink Liopholis slateri, with the aim of increasing detectability in observational surveys for this endangered species. We matched repeated count data ( n = 126) of individuals within a population of Slater's skink sampled across four survey years with corresponding weather observations. We used classification and regression tree (CART) models to determine the environmental conditions that promoted high skink counts, and by inference high levels of surface activity. We also investigated how individual activity patterns varied over a day-night cycle through the course of a survey year using remote infrared cameras at burrow entrances set to capture images every 30 min. We found that two weather variables, air temperature and humidity, influenced activity levels, but there was no consistent single covariate, or set of covariates that explained surface activity. Variation in results of analysis between morning and evening datasets suggests that lizards respond to different weather conditions at different times of the day. We also found evidence of previously unreported nocturnal activity during the hottest months of the year. [ABSTRACT FROM AUTHOR]

We describe and evaluate a regression tree algorithm for finding subgroups with differential treatments effects in randomized trials with multivariate outcomes. The data may contain missing values in the outcomes and covariates, and the treatment variable is not limited to two levels. Simulation results show that the regression tree models have unbiased variable selection and the estimates of subgroup treatment effects are approximately unbiased. A bootstrap calibration technique is proposed for constructing confidence intervals for the treatment effects. The method is illustrated with data from a longitudinal study comparing two diabetes drugs and a mammography screening trial comparing two treatments and a control. Copyright © 2016 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

BACKGROUND The western corn rootworm ( WCR) is economically the most important pest of maize in Croatia. To predict WCR adult population abundance and variability, traditional, genetic and morphometric monitoring of populations was conducted over time through each phase of the WCR invasion process in Croatia. RESULTS Through traditional monitoring it was shown that WCR established their current population and reached economic densities after 14 years persisting in the study area. Regression-tree-based modelling showed that the best predictor of WCR adult abundance was the total amount of rainfall. Genetic monitoring indicated that genetic differentiation increased over time at the intrapopulation level, and morphometric monitoring indicated that wing morphotypes varied according to edaphic landscape changes. CONCLUSION Traditional population metric surveys are important in WCR integrated pest management ( IPM), as such surveys can be effectively used to predict population abundances. Novel-use monitoring techniques such as genetics and geometric morphometrics can be used to provide valuable information on variation within and among populations. The monitoring techniques presented herein provide sound data to assist in the understanding of both WCR ecology and population genetics and may provide more information than that currently available using traditional techniques (e.g. sticky traps), and as such these additional techniques should be written into IPM for WCR. © 2015 Society of Chemical Industry [ABSTRACT FROM AUTHOR]

This study proposes a content‐based image retrieval system for skin lesion images as a diagnostic aid. Effectiveness is measured by the rate of correct retrieval of images from skin lesions. The proposed architecture is used to retrieve digital images and the name of the disease category from an image data repository by the contents in the image, such as shape, texture and colour that is extracted from the image. The author's proposed algorithm used feature vector, classification and regression tree to retrieve comprehensive reference sources for diagnostic purpose. The results proved using a receiver operating characteristic curve that the proposed architecture has high contribute to computer‐aided diagnosis of skin lesions. Experiments on a set of 1210 images yielded a specificity of 97.25% and a sensitivity of 91.24%. Their empirical evaluation has a superior retrieval and diagnosis performance when compared to the performance of other works. The authors present explicit combinations of feature vectors corresponding to healthy and lesion skin. [ABSTRACT FROM AUTHOR]

Increases in atmospheric temperature and nutrients from land are thought to be promoting the expansion of harmful cyanobacteria in lakes worldwide, yet to date there has been no quantitative synthesis of long-term trends. To test whether cyanobacteria have increased in abundance over the past ~ 200 years and evaluate the relative influence of potential causal mechanisms, we synthesised 108 highly resolved sedimentary time series and 18 decadal-scale monitoring records from north temperate-subarctic lakes. We demonstrate that: (1) cyanobacteria have increased significantly since c. 1800 ce, (2) they have increased disproportionately relative to other phytoplankton, and (3) cyanobacteria increased more rapidly post c. 1945 ce. Variation among lakes in the rates of increase was explained best by nutrient concentration (phosphorus and nitrogen), and temperature was of secondary importance. Although cyanobacterial biomass has declined in some managed lakes with reduced nutrient influx, the larger spatio-temporal scale of sedimentary records show continued increases in cyanobacteria throughout the north temperate-subarctic regions. [ABSTRACT FROM AUTHOR]

BACKGROUND Central European outbreak populations of the bank vole ( Myodes glareolus Schreber) are known to cause damage in forestry and to transmit the most common type of Hantavirus (Puumala virus, PUUV) to humans. A sound estimation of potential effects of future climate scenarios on population dynamics is a prerequisite for long-term management strategies. Historic abundance time series were used to identify the key weather conditions associated with bank vole abundance, and were extrapolated to future climate scenarios to derive potential long-term changes in bank vole abundance dynamics. RESULTS Classification and regression tree analysis revealed the most relevant weather parameters associated with high and low bank vole abundances. Summer temperatures 2 years prior to trapping had the highest impact on abundance fluctuation. Extrapolation of the identified parameters to future climate conditions revealed an increase in years with high vole abundance. CONCLUSION Key weather patterns associated with vole abundance reflect the importance of superabundant food supply through masting to the occurrence of bank vole outbreaks. Owing to changing climate, these outbreaks are predicted potentially to increase in frequency 3-4-fold by the end of this century. This may negatively affect damage patterns in forestry and the risk of human PUUV infection in the long term. © 2014 Society of Chemical Industry [ABSTRACT FROM AUTHOR]

An adaptive damping control scheme based on classification and regression tree (CART) using wide‐area signals is proposed in this study. A family of robust controllers is designed off‐line and are used in real‐time after the corresponding operating point is retrieved from phasor measurement unit (PMU) data with CART interpolation. When the power system is operating precisely at a pre‐selected operating point, only the corresponding controller is active. When the power system is not exactly at the operating point, a combined controller is formed for damping. A 68‐bus, 16‐generator system is used as a test system. A thyristor‐controlled series capacitor, a static var compensator and an energy storage device are used as actuators, and remote PMUs frequencies as added inputs are employed as the example control. The simulation results demonstrate the effectiveness and robustness against the wider range of operating changes even without knowing precisely the model of disturbances that occurred in the dynamic system. [ABSTRACT FROM AUTHOR]

We introduce a new statistical method to select which morphological characters are most useful to identify monogenean species. The method estimates the average size overlap of candidate diagnostic structures among a set of species to individuate those that mostly differ between the species. To demonstrate our approach, we report a comprehensive analysis conducted on two of the most species-rich monogenean genera: Dactylogyrus Diesing, 1850 and Gyrodactylus von Nordmann, 1832. We demonstrate that, in contrast to common taxonomic practice, very few but highly diagnostic measurements are necessary to correctly identify a specimen. In particular, we found that most of Dactylogyrus and Gyrodactylus species can be classified on the basis of the width of the supplementary connecting bar and of the length of the hook sickle, respectively. [ABSTRACT FROM AUTHOR]

We investigate the usefulness of complex flood damage models for predicting relative damage to residential buildings in a spatial and temporal transfer context. We apply eight different flood damage models to predict relative building damage for five historic flood events in two different regions of Germany. Model complexity is measured in terms of the number of explanatory variables which varies from 1 variable up to 10 variables which are singled out from 28 candidate variables. Model validation is based on empirical damage data, whereas observation uncertainty is taken into consideration. The comparison of model predictive performance shows that additional explanatory variables besides the water depth improve the predictive capability in a spatial and temporal transfer context, i.e., when the models are transferred to different regions and different flood events. Concerning the trade-off between predictive capability and reliability the model structure seem more important than the number of explanatory variables. Among the models considered, the reliability of Bayesian network-based predictions in space-time transfer is larger than for the remaining models, and the uncertainties associated with damage predictions are reflected more completely. [ABSTRACT FROM AUTHOR]

This article presents a regression-tree-based meta-analysis of rodent pulmonary toxicity studies of uncoated, nonfunctionalized carbon nanotube (CNT) exposure. The resulting analysis provides quantitative estimates of the contribution of CNT attributes (impurities, physical dimensions, and aggregation) to pulmonary toxicity indicators in bronchoalveolar lavage fluid: neutrophil and macrophage count, and lactate dehydrogenase and total protein concentrations. The method employs classification and regression tree (CART) models, techniques that are relatively insensitive to data defects that impair other types of regression analysis: high dimensionality, nonlinearity, correlated variables, and significant quantities of missing values. Three types of analysis are presented: the RT, the random forest (RF), and a random-forest-based dose-response model. The RT shows the best single model supported by all the data and typically contains a small number of variables. The RF shows how much variance reduction is associated with every variable in the data set. The dose-response model is used to isolate the effects of CNT attributes from the CNT dose, showing the shift in the dose-response caused by the attribute across the measured range of CNT doses. It was found that the CNT attributes that contribute the most to pulmonary toxicity were metallic impurities (cobalt significantly increased observed toxicity, while other impurities had mixed effects), CNT length (negatively correlated with most toxicity indicators), CNT diameter (significantly positively associated with toxicity), and aggregate size (negatively correlated with cell damage indicators and positively correlated with immune response indicators). Increasing CNT N2-BET-specific surface area decreased toxicity indicators. [ABSTRACT FROM AUTHOR]

The purpose of this study was to develop a preliminary decision algorithm predicting functional performance outcomes to aid in the decision of when to undergo total knee arthroplasty (TKA). One hundred and nineteen patients undergoing primary unilateral TKA were evaluated before and 6 months after TKA. A regression tree analysis using a recursive partitioning function was performed with the Timed Up and Go (TUG) time, Six-Minute Walk (6MW) distance, and Stair Climbing Test (SCT) time as measured 6 months after TKA as the primary outcomes. Preoperative measures of functional performance, joint performance, anthropometrics, demographics, and self-reported status were evaluated as predictors of the primary outcomes 6 months after surgery. Individuals taking ≥10.1 s on the TUG and aged 72 years or older before surgery had the poorest performance on the TUG 6 months after surgery. Individuals walking <314 meters on the 6MW before surgery had the poorest performance on the 6MW test 6 months after surgery. Individuals taking ≥17 s to complete the SCT and scoring <40 on the SF-36 mental component score before surgery had the poorest performance on the SCT 6 months after surgery. Poorer performance preoperatively on the 6MW, SCT, and TUG, was related to poorer performance in the same measure after TKA. Age and decreased mental health were secondary predictors of poorer performance at 6 months on the TUG and SCT, respectively. These measures may help further develop models predicting thresholds for poor outcomes after TKA. © 2012 Orthopaedic Research Society. Published by Wiley Periodicals, Inc. J Orthop Res 30:1805-1810, 2012 [ABSTRACT FROM AUTHOR]

Question How do multivariate methods perform in relating species- and community-level trait responses to the environment? Location (1) Field data from grazed semi-natural grasslands, NE Germany; (2) artificial data. Methods Research questions associated with trait-environment relationships were briefly reviewed and seven available methods evaluated. The main distinction between research questions is whether trait-environment relationships should be addressed at community or species level. A redundancy analysis ( RDA) of mean trait values of species in a plot weighted by their abundances ( CWM- RDA) is exclusively suitable for the community level. The other six methods address the species level. A double inertia analysis of two arrays ( RLQ) and double canonical correspondence analysis (double CCA) use combinations of ordinations to simultaneously analyse species and trait responses to the environment. A combination of the outlying mean index with generalized additive models ( OMI- GAM) predicts the response of species to environmental variables on trait gradients. RDA-RegTree first analyses species responses to the environment with RDA and then uses a regression tree to classify trait expressions according to scores of species responses on the ordination axes. Cluster regression uses cluster analyses and logistic regression to search for trait combinations with the best response to the environmental variables. This method models the distribution of functional groups on environmental gradients. All methods and data are available as R scripts. Results All methods consistently revealed the main trait responses to environment in the field data set, namely that life history was associated with available phosphorus while grazing intensity was related to leaf C: N ratio and canopy height. At community level, CWM- RDA gave a good overview of trait-environment relationships, as also provided by the species-based methods RLQ and double CCA. OMI- GAM revealed non-linear relationships in the field data set. Field and artificial data gave that the number and stability of functional groups produced by Cluster regression and RDA-RegTree varied more strongly than RLQ, double CCA and OMI- GAM. Conclusions Each method addresses particular ecological concepts and research questions. If a user asks for the response of average trait expressions of communities to environmental gradients, CWM- RDA may be the first choice. However, species-based methods should be applied to address questions regarding co-existence of different life histories or to assess how groups of species respond to environmental changes. The artificial data set revealed that the methods differed in sensitivity to gradient lengths and random data. [ABSTRACT FROM AUTHOR]

By focusing on sovereign defaults, this paper introduces a multidimensional distance-to-collapse point based on a two-step procedure. The first step is nonparametric and provides an early warning system that signals a potential crisis whenever preselected leading indicators exceed specific thresholds. The second is parametric and incorporates the first-step country default predictors within a probit specification. Such a two-step procedure generalizes the distance-to-default a la Merton within a multidimensional setting, wherein we care about the distance of each indicator from its threshold. Empirical evidence about debt crises of emerging markets over the period 1975-2002 proves that our methodology predicts 80% of the total defaults and non-defaults in and out of sample. Copyright © 2012 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

ABSTRACT The realized species richness of tropical forests cannot yet be reliably mapped at a regional scale due to lack of systematically collected data. An estimate of the potential species richness (PSR), however, can be produced through the use of species distribution modelling. PSR is interpretable as a climatically determined upper limit to observed species richness. We mapped current PSR and future PSR under climate change scenarios for Mesoamerica by combining the spatial distributions of 2000 tree species as predicted by generalized additive models built from herbaria records and climate layers. An explanatory regression tree was used to extract conditional rules describing the relationship between PSR and climate. The results were summarized by country, ecoregion and protected area status in order to investigate current and possible future variability in PSR in the context of regional biodiversity conservation. Length of the dry season was found to be the key determinant of PSR. Protected areas were found to have higher median PSR values than unprotected areas in most of the countries within the study area. Areas with exceptionally high PSR, however, remain unprotected throughout the region. Neither changes in realized species richness nor extinctions will necessarily follow changes in modelled PSR under climate change. However model output suggests that an increase in temperature of around 3°C, combined with a 20 percent decrease in rainfall could lead to a widespread reduction of around 15 percent of current PSR, with values of up to 40 percent in some moist lower montane tropical forests. The modelled PSR of dry forest ecoregions was found to be relatively stable. Some cooler upper montane forests in northern Mesoamerica, where few species of tropical origin are currently found, may gain PSR if species are free to migrate. [ABSTRACT FROM AUTHOR]

Using dung beetles (Coleoptera: Scarabaeidae: Scarabaeinae) in a tropical land-bridge island system, we test for the small island effect (SIE) in the species-area relationship and evaluate its effects on species richness and community composition. We also examine the determinants of species richness across island size and investigate the traits of dung beetle species in relation to their local extinction vulnerability following forest fragmentation. Lake Kenyir, a hydroelectric reservoir in north-eastern Peninsular Malaysia. We sampled dung beetles using human dung baited pitfall traps on 24 land-bridge islands and three mainland sites. We used regression tree analyses to test for the SIE, as well as species traits related to local rarity, as an indication of extinction vulnerability. We employed generalized linear models (GLMs) to examine determinants for species richness at different scales and compared the results with those from conventional linear and breakpoint regressions. Community analyses included non-metric multidimensional scaling, partial Mantel tests, nestedness analysis and abundance spectra. Regression tree analysis revealed an area threshold at 35.8 ha indicating an SIE. Tree basal area was the most important predictor of species richness on small islands (<35.8 ha). Results from GLMs supported these findings, with isolation and edge index also being important for small islands. The SIE also manifested in patterns of dung beetle community composition where communities on small islands (<35.8 ha) departed from those on the mainland and larger islands, and were highly variable with no significant nestedness, probably as a result of unexpected species occurrences on several small islands. The communities exhibited a low degree of spatial autocorrelation, suggesting that dispersal limitation plays a part in structuring dung beetle assemblages. Species with lower baseline density and an inability to forage on the forest edge were found to be rarer among sites and hence more prone to local extinction. We highlight the stochastic nature of dung beetle community composition on small islands and argue that this results in reduced ecosystem functionality. A better understanding of the minimum fragment size required for retaining functional ecological communities will be important for effective conservation management and the maintenance of tropical forest ecosystem stability. [ABSTRACT FROM AUTHOR]

1. Eutrophication has a profound effect on the biological structure and function of shallow lakes, altering the composition and abundance of submerged macrophyte and fish assemblages. Relatively little is known, however, about decadal to centennial-scale change in these important aspects of shallow lake ecology. 2. Established palaeolimnological inference models are limited to reconstructing a single variable. As macrophyte and zooplanktivorous fish abundance exert dual and interacting controls on cladoceran assemblages a single variable inference model may contain significant error. To obviate this problem, we applied a new cladoceran-based multivariate regression tree (MRT) model to cladoceran subfossil assemblages from dated cores from a small shallow lake (Felbrigg Lake, U.K.) to assess long-term change in fish and submerged macrophyte abundance. Plant macrofossil, chironomid and mollusc subfossil assemblages were also analysed to track changes in biological structure and function and to evaluate the inferences of the MRT model. 3. Over the 200+ year period covered by the sediment cores, there was good agreement in the timing and nature of ecological change reflected by the plant macrofossil, mollusc, chironomid and cladoceran data. The sediment sequence was divided into three dated zones: c. 1797–1890, c. 1890–1954 and c. 1954–present. Prior to 1890 plant-associated mollusc, cladoceran and chironomid assemblages indicated a species-rich macrophyte community; a scenario confirmed by the plant macrofossil data. From c. 1890 to 1954 macrophyte-associated species of all three invertebrate groups remained abundant but the proportion of pelagic cladocerans rose. Post-1954 mollusc and chironomid assemblages changed to sediment associated detrital feeders and the proportion of pelagic cladoceran taxa increased further. 4. The cladoceran-based MRT model indicated a long period of stability, c. 1790–1927, characterised by abundant submerged macrophytes and zooplanktivorous fish. From c. 1927 to 1980, the MRT model inferred a decline in zooplanktivorous fish density (ZF) but relative stability in August macrophyte abundance. From 1980 to 2000, an increase in zooplanktivorous fish was inferred tallying well with available data on the fish population (since the 1970s), which indicated extirpation of perch in the 1970s and a subsequent increase in the rudd population. The model inferred little change in August macrophyte abundance until post- c. 1980 at which point it indicated a decline. The surface sediment assemblage was placed in MRT group A, where submerged plants are absent or very rare in late summer in good agreement with current conditions at the site. 5. The MRT model, applied here for the first time, appears to have successfully tracked changes in macrophyte abundance and ZF over the last 200 years at Felbrigg Lake. The inferences agreed with historical observations on the fish community and the supporting palaeolimnological data. Given that multiple structuring forces shape most biological communities, the application of a model capable of allowing for this represents a significant advance in palaeolimnology. [ABSTRACT FROM AUTHOR]

I evaluated the predictive ability of statistical models obtained by applying seven methods of variable selection to 12 ecological and environmental data sets. Cross-validation, involving repeated splits of each data set into training and validation subsets, was used to obtain honest estimates of predictive ability that could be fairly compared among methods. There was surprisingly little difference in predictive ability among five methods based on multiple linear regression. Stepwise methods performed similarly to exhaustive algorithms for subset selection, and the choice of criterion for comparing models (Akaike’s information criterion, Schwarz’s Bayesian information criterion or F statistics) had little effect on predictive ability. For most of the data sets, two methods based on regression trees yielded models with substantially lower predictive ability. I argue that there is no ‘best’ method of variable selection and that any of the regression-based approaches discussed here is capable of yielding useful predictive models. [ABSTRACT FROM AUTHOR]

There is a long history of studying the relationship between weather and maritime activities. This article analyzes the link between relative incident rate (RIR) and general weather factors within certain gridded areas and time periods. The study area, which encompasses a broad extent of Atlantic Canadian waters, includes fishing incidents recorded by the Canadian Coast Guard from 1997 to 1999. Methodologies used for traffic track generation in a geographical information system and aggregation of all relevant weather data needed for the statistical analyses are presented. Ultimately, a regression tree was built to illustrate the relationship between incident rate and the following six weather factors: wave height; sea surface temperature; air temperature; ice concentration; fog presence; and precipitation. Results from the regression tree reveal that the RIR defined as (incident number per area-day)/(traffic amount per area-day) across grid cells with incidents, increases as the weather conditions deteriorate in a general way, and the concentration of ice has the biggest influence on the magnitude of incident rates for a given level of traffic exposure. The results from this analysis may assist administrators of maritime traffic, especially those associated with fishing activities, through a better understanding of the influence on RIR of certain weather conditions within given areas in specific time periods. [ABSTRACT FROM AUTHOR]

The factors controlling the extent of fire in Africa south of the equator were investigated using moderate resolution (500 m) satellite-derived burned area maps and spatial data on the environmental factors thought to affect burnt area. A random forest regression tree procedure was used to determine the relative importance of each factor in explaining the burned area fraction and to address hypotheses concerned with human and climatic influences on the drivers of burnt area. The model explained 68% of the variance in burnt area. Tree cover, rainfall in the previous 2 years, and rainfall seasonality were the most important predictors. Human activities – represented by grazing, roads per unit area, population density, and cultivation fraction – were also shown to affect burnt area, but only in parts of the continent with specific climatic conditions, and often in ways counter to the prevailing wisdom that more human activity leads to more fire. The analysis found no indication that ignitions were limiting total burnt area on the continent, and most of the spatial variation was due to variation in fuel load and moisture. Split conditions from the regression tree identified (i) low rainfall regions, where fire is rare; (ii) regions where fire is under human control; and (iii) higher rainfall regions where burnt area is determined by rainfall seasonality. This study provides insights into the physical, climatic, and human drivers of fire and their relative importance across southern Africa, and represents the beginnings of a predictive framework for burnt area. [ABSTRACT FROM AUTHOR]

In this paper, a new efficient feature extraction method is proposed to handle the one-step-ahead daily maximum load forecasting. In recent years, power systems become more complicated under the deregulated and competitive environment. As a result, it is not easy to understand the cause and effect of short-term load forecasting with a bunch of data. This paper analyzes load data from the standpoint of data mining. By it we mean a technique that finds out rules or knowledge through large database. As a data mining method for load forecasting, this paper focuses on the regression tree that handles continuous variables and expresses a knowledge rule as if-then rules. Investigating the variable importance of the regression tree gives information on the transition of the load forecasting models. This paper proposes a feature extraction method for examining the variable importance. The proposed method allows to classify the transition of the variable importance through actual data. © 2006 Wiley Periodicals, Inc. Electr Eng Jpn, 156(2): 43–51, 2006; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/eej.20104 [ABSTRACT FROM AUTHOR]

Widespread extinction is a predicted ecological consequence of global warming. Extinction risk under climate change scenarios is a function of distribution breadth. Focusing on trees and birds of the eastern United States, we used joint climate and environment models to examine fit and climate change vulnerability as a function of distribution breadth. We found that extinction vulnerability increases with decreasing distribution size. We also found that model fit decreases with decreasing distribution size, resulting in high prediction uncertainty among narrowly distributed species. High prediction uncertainty creates a conservation dilemma in that excluding these species under-predicts extinction risk and favors mistaken inaction on global warming. By contrast, including narrow endemics results in over-predicting extinction risk and promotes mistaken inaction on behalf of individual species prematurely considered doomed to extinction. [ABSTRACT FROM AUTHOR]

1. In the face of large-scale environmental changes, predicting the consequences for species composition from species’ traits can be a major step towards generalizing ecological patterns and management. Few studies, however, have explored the applicability of this tool in relation to different climatic conditions. Here, the changes in species composition along a gradient of sheep-grazing pressure (high, low, abandonment) were used to test whether a common set of plant functional traits (PFT) would provide consistent predictions of species’ responses to grazing in different biogeographical regions. 2. Data were collected across an altitudinal and climatic gradient from Mediterranean rangelands to subalpine grasslands in north-eastern Spain. Species’ responses were calculated using partial constrained ordination to account only for the effect of grazing intensity. Regression trees and general linear models were applied to identify traits that could predict species’ responses. 3. Results were mostly consistent with the ruderal vs. competitive strategy ( sensu Grime ), in terms of life cycle, life form and plant height, and their expected responses to repeated disturbance. 4. However, the predictive capacity of the investigated traits changed with climatic conditions. Traits generally related to grazing did not show a strong repeatability across the climatic gradient. Convergent selection of climatic conditions and grazing indicated that plant features might reflect an adaptation to multiple selective forces. The climatic conditions acted as filters on the pool of PFT available and shifted the relevance of plant traits as potential predictors. Results were not substantially different after applying phylogenetically independent contrasts (PIC). 5. Synthesis and applications. At a local scale, plant functional traits are useful tools in predicting species’ responses to grazing and, for conservation purposes, identifying species vulnerable to land-use changes. However, predictions cannot be extrapolated from one climatic region to another. The methodology proposed in this study to detect predicting traits can be applied more generally. Regression trees, in particular, appear to be a useful tool because they account for non-additive effects and allow visualizations of trait combinations. [ABSTRACT FROM AUTHOR]

The article presents a research study which focuses on the habitat requirements of threatened desert tortoises, also known as Gopherus agassizii. It states that in the research study, data derived from various spatial databases, including satellite imagery, was also used. It disusses the field surveys, which collected vegetation and tortoise relative density data.