This paper presents a methodology that permits to automate binary classification using the minimum possible number of attributes. In this methodology, the success of the binary prediction does not lie in the accuracy of an algorithm but in the evaluation metrics, which give information about the goodness of fit; which is an important factor when the data batch is unbalanced. The proposed methodology assesses the possible biases in identifying one algorithm as the best performer when considering the goodness of fit of an algorithm through evaluation metrics. The dimension of data has been reduced through the cumulative explained variance. Then, the performance of six machine learning classification models has been compared through Matthew correlation coefficient (MCC), area under curve – receiver operating characteristic (ROC-AUC), and area under curve – precision-recall (AUC-PR). The results show graphically and numerically how the evaluation metrics interfere with the most optimal outcome of an algorithm. The algorithms with the best performance in terms of evaluation metrics have been random forest and gradient boosting. In the imbalanced datasets, MCC has provided better prediction results than ROC-AUC or AUC-PR. The proposed methodology is adapted to the case of bankruptcy prediction.

Four key policy challenges, framed here as dichotomies, are commonly associated with attempts to improve the use of natural resources in the socioecological commons. These dichotomies present tradeoffs when addressing market failures and in general seem to suggest the need to settle for second-best outcomes rather than first-best outcomes identified in stylized models. Citing examples, we argue that these models, while illustrating these dichotomies, also suggest means for circumventing them, and perhaps provide a degree of optimism about prospective outcomes in socioecological systems.

High blood pressure (BP) has been ranked as the most important risk factor worldwide regarding attributable deaths. Dietary habits are major determinants of BP. Among them, frequent intake of low-fat dairy products may protect against hypertension. Our aim was to assess the relationship between low-fat dairy product intake and BP levels and their changes after 12-month follow-up in a cohort of asymptomatic older persons at high cardiovascular risk recruited into a large-scale trial assessing the effects of Mediterranean diets on cardiovascular outcomes. Data from 2290 participants, including 1845 with hypertension, were available for analyses. Dairy products were not a specific part of the intervention; thus, data were analysed as an observational cohort. Dietary information was collected with validated semi-quantitative FFQ and trained personnel measured BP. To assess BP changes, we undertook cross-sectional analyses at baseline and at the end of follow-up and longitudinal analyses. A statistically significant inverse association between low-fat dairy product intake and systolic BP was observed for the 12-month longitudinal analysis. In the longitudinal analysis, the adjusted systolic and diastolic BP were significantly lower in the highest quintile of low-fat dairy product intake ( − 4·2 (95% CI − 6·9, − 1·4) and − 1·8 (95% CI − 3·2, − 0·4) mmHg respectively), whereas the point estimates for the difference in diastolic BP indicated a modest non-significant inverse association. Intake of low-fat dairy products was inversely associated with BP in an older population at high cardiovascular risk, suggesting a possible protective effect against hypertension.

Through a series of ichthyoplankton surveys carried out off central Chile, we characterize the offshore spawning and coastal nursery ground of the bigeye flounder Hippoglossina macrops. Eggs were collected in higher abundances over the continental shelf during late winter, over the shelf-break in mid spring, and at the continental slope in late summer, showing a seasonal depth gradient in spawning. No significant spawning was detected nearshore (less than 8 km offshore). Field data suggest a longitudinal progression from offshore to onshore of larval stages from preflexion to transformation stage. Finally, vertically stratified samples showed that eggs and larvae were present mainly in the upper 100 m. We discuss the potential onshore transport of early life stages of H. macrops through the compensatory flow of Equatorial Subsurface Waters that balances the surface offshore transport in the Ekman layer during upwelling events. Additionally, larval development from yolk-sac to transformation stage is briefly described.

Neonatal cerebral white matter echolucencies predict visual resolution acuity deficits in very-low-birthweight (VLBW) infants. We examined maternal sociodemographic, lifestyle, intrapartum, infant birth/perinatal, and ocular motor/refractive characteristics to determine whether they accounted for this association in infants who were tested once between postnatal age 25 and 56 weeks (corrected for gestational age at birth). Cranial ultrasound scans were read by consensus to identify echolucency in a population of VLBW infants with no known ocular abnormalities. Visual resolution acuity was measured with the Acuity Card Procedure (ACP) in 14 infants with echolucency and compared with that of 81 VLBW infants born in the same hospitals with normal ultrasound scans. In time-oriented logistic regression models, echolucency remained a consistent predictor of abnormal visual resolution acuity after adjustment for covariates in three developmental periods (pre-, peri-, and postnatal). Odds ratios ranged from 19.3 (95% confidence interval, 4.5 to 82.2; p=0.001) to 10.4 (95% confidence interval, 1.3 to 81.9; p=0.03). Reduced visual resolution acuity in VLBW infants appears to be due to cerebral white matter damage.

The foraging behaviour of capybaras (Hydrochaeris hydrochaeris) was assessed in relation to habitat and season in a flooded savanna of Venezuela from February (dry season) 1993 to June (rainy season) 1994. Direct observations were carried out to record group movements and foraging activities of individual capybaras when feeding on specific plant species. The time devoted to feeding upon some species was recorded in relation to total foraging time (feeding + searching). Capybaras spent similar times feeding on reed (Eleocharis interstincta; Cyperaceae) and Paratheria prostrata (Poaceae) patches during the dry season though plant quality was different. During the rainy season, reeds were almost ignored by the animals which fed mainly on Hymenachne amplexicaulis, a grass with a significantly higher content of energy and protein. Capybaras fed for longer time during the dry season but more selectively during the rainy season. Capybaras were the dominant grazers in this flood savanna as inferred from the comparative effects they produced in the height, biomass and quality of the pasture in relation to those effects produced by other vertebrate herbivores, namely, cattle, feral horses and asses.