Search Results (8,780)

Elderly individuals in rural China are highly vulnerable to extreme weather events and temperature fluctuations due to inadequate infrastructure in the built environment and constrained economic conditions, thereby increasing their health risks. Outdoor spaces represent one of the primary daily activity settings for rural older adults. However, existing research rarely links spatiotemporal patterns of outdoor activities to evidence-based thermal environment optimization, leaving a critical knowledge gap for age-friendly and sustainable rural design. This study focuses on the spatiotemporal differentiation patterns of daily outdoor activities among elderly people aged 60 years and above in rural Xi’an, as well as the optimization of spatial variations in thermal environments. Using on-site interviews, thermal environment measurements, thermal comfort questionnaires, continuous thermal environment monitoring, and machine learning based on random forest, this study drew the following conclusions: (1) outdoor activities in winter were concentrated between 9:00–11:00 and 13:00–17:00, while in summer, they shifted to the morning and evening periods, namely 6:00–9:00 and 17:00–21:00. (2) Models for outdoor clothing adjustment, thermal sensation, and thermal acceptability among elderly residents were established. The calculated neutral temperature was 10.19 °C, with a 90% outdoor thermal acceptability range of 9.6–27.2 °C and an 80% outdoor thermal acceptability range of 6.2–30.6 °C. These findings differ from those documented in regions with distinct climate zones and geographical settings. This discrepancy stems from regional climatic features, lifestyle variations between urban and rural older adults, and differences in the thermal environment quality of elderly-oriented outdoor activity spaces. (3) In winter, the acceptable period of the Universal Thermal Climate Index (UTCI) at south-facing entrances (10:30–16:30) was significantly longer than that in the courtyard (13:30–14:00). In summer, the comfortable period in the courtyard (before 10:00 and after 20:00) was longer than that at north-facing entrances (before 09:00). A random forest model for thermal sensation was established, and the relative importance of each parameter influencing thermal sensation was analyzed. On this basis, priority improvement pathways and strategies for the thermal environment, as well as suggestions for the subjective adaptive behaviors of elderly residents, were proposed. The research results of this study can provide technical solutions for age-friendly thermal environment design in rural areas, thereby safeguarding the comfort, health, and social well-being of the elderly population in rural areas. Full article

Background: Intracranial hypertension is a critical complication of acute intracerebral hemorrhage (ICH), contributing to high early mortality and poor functional outcomes. Invasive intracranial pressure (ICP) monitoring remains the gold standard but carries procedural risks and is resource-intensive. This study evaluated the diagnostic and prognostic utility of optic nerve sheath diameter (ONSD) ultrasonography and transcranial Doppler (TCD)-derived pulsatility index (PI) as non-invasive ICP surrogates in patients with severe ICH. Methods: A prospective observational study was conducted in 42 patients with acute ICH who underwent concurrent invasive ICP monitoring and serial ONSD/PI measurements at 10 time points (T0–T9) between October 2021 and August 2024. Diagnostic performance was assessed using measurement-level receiver operating characteristic (ROC) curve analysis. Exploratory early mortality prediction was evaluated using random forest machine learning models incorporating ONSD, PI, age, and sex. Results: A total of 274 paired ONSD–PI–ICP measurements were obtained. Both ONSD and PI showed moderate positive correlations with invasive ICP (rho = 0.49 and 0.43, respectively; p < 0.001). ONSD demonstrated superior diagnostic accuracy for detecting ICP ≥ 20 mmHg (AUC = 0.83; optimal threshold: 5.88 mm; sensitivity: 81%; specificity: 82%) compared to PI (AUC = 0.75). In exploratory random forest analyses, the combined ONSD–PI model showed high apparent discrimination for elevated ICP detection (AUC = 0.98), while the model incorporating ONSD, PI, age, and sex showed promising but potentially optimistic discrimination for early mortality prediction (AUC = 0.95). These machine learning results should be interpreted cautiously because of the small sample size, repeated-measurement structure, measurement-level data partitioning, and limited number of early deaths. Conclusions: ONSD ultrasonography and TCD-derived PI showed promising performance as non-invasive ICP markers in severe acute ICH. However, because of the small sample size, repeated-measurement design, measurement-level analyses, and exploratory nature of the machine learning models, these findings require validation in larger external cohorts before routine clinical implementation. Full article

Background: Pre-existing diabetes mellitus is prevalent among critically ill adults and can influence initial glycemic targets, therapeutic decisions, and early risk stratification in the intensive care unit (ICU). However, diabetes status may be distributed across heterogeneous electronic health record (EHR) sources and may be incomplete at the time of ICU admission, particularly for inter-facility transfers. Methods: Using the public WiDS Datathon 2021 tabular release derived from the Global Open-Source Severity of Illness Score (GOSSIS) initiative, we conducted a retrospective machine-learning benchmarking study for admission-time identification of documented diabetes status in ICU patients. Candidate predictors included demographics, admission characteristics, anthropometrics, day-1 physiologic and laboratory summaries, APACHE-related variables, comorbidity indicators, and site descriptors. We compared CatBoost, random forest, tuned XGBoost, tuned LightGBM, histogram-based gradient boosting, and a soft-voting ensemble combining XGBoost, LightGBM, and histogram-based gradient boosting. Because class imbalance was a central concern, the final workflow emphasized model-intrinsic class weighting and threshold-aware evaluation rather than synthetic oversampling. Results: In the primary leakage-mitigated random validation split, the voting ensemble achieved the highest overall balance, with AUROC 0.8539, precision 0.5671, recall 0.6690, and F1-score 0.6138. Tuned LightGBM was the most sensitivity-oriented individual model, achieving recall 0.7677 and AUROC 0.8537, although with lower precision and a less favorable Brier score. Ablation analyses clarified the source of this performance: removing leakage-prone and APACHE-related variables caused only modest decreases in discrimination, whereas the strict reduced model that also excluded glucose-like predictors produced a marked decline, with LightGBM AUROC falling to 0.7432 and the voting ensemble AUROC falling to 0.7448. These findings, together with SHAP analyses identifying day-1 glucose maximum, day-1 glucose minimum, BMI, age, hemoglobin, and related clinical variables as major contributors, indicate that glucose-related admission variables remained the dominant predictive signal. In grouped hospital validation, tuned LightGBM maintained recall of 0.7684 while AUROC decreased modestly to 0.8443, indicating preserved case detection under stricter site separation but reduced precision. Precision–recall analysis further showed that average precision decreased from 0.622 under random validation to 0.551 under grouped validation; at a high-sensitivity grouped-site operating point, a probability threshold of 0.4537 achieved recall of 0.8001 with precision of 0.4314. Calibration curves and Brier scores showed that predicted probabilities were imperfectly calibrated. Conclusions: Although the dominance of glucose-related predictors is clinically plausible for identifying documented diabetes status, early glycemic measurements in critically ill patients may also partly capture acute stress physiology, treatment-related effects, monitoring intensity, or other forms of acute dysglycemia rather than chronic diabetes status alone. Therefore, these findings support gradient-boosted and ensemble models as reproducible tools for ICU admission-time phenotyping of documented diabetes status, but the proposed system should be interpreted primarily as a screening-oriented phenotyping aid for chart review, cohort enrichment, or workflow support, not as a stand-alone diagnostic tool. Further external validation, recalibration, threshold selection matched to intended use, and clinical review are needed before deployment. Full article

This study investigates how different rural landscape types shape visual attention and physiological responses, with the aim of informing more targeted rural landscape renewal. Four typical rural landscape types in the suburbs of Hefei, China, were examined: Flat Farmland (FF), Hilly Forest (HF), Developed Plain (DP), and Water-network Lowland (WNL). All four study villages are project villages in the suburban area of Hefei where rural revitalization is currently being advanced. This study therefore treats them as empirical cases within the context of rural revitalization in China, using them to examine perceptual differences among rural landscape types and their implications for rural landscape renewal. A two-stage research design was adopted to balance field realism and laboratory control. In the first stage, 40 representative scene images were selected by combining field video records with fluctuations in on-site skin conductance response (SCR). In the second stage, laboratory experiments were conducted while participants viewed the selected images, during which eye-tracking, skin conductance, and heart rate data were recorded simultaneously. These measures were used to characterize visual attention allocation and autonomic physiological responses across different rural landscape types, rather than to directly measure landscape preference. For Area of Interest (AOI) analysis, each image was coded into six landscape element categories: vegetation, buildings, roads, sky, vernacular buildings, and water bodies. The results revealed significant typological differences in overall visual search patterns and autonomic responses. Gaze hotspots were concentrated on identifiable targets and boundary regions in the foreground and midground, whereas the sky attracted relatively limited attention. FF primarily emphasized vernacular buildings and farmland boundaries, HF emphasized settlement interfaces and spatial transition nodes, DP emphasized road junctions and facilities along routes, and WNL emphasized water bodies and water–land interface zones. These findings suggest that a two-stage multimodal design can provide supporting evidence for understanding type-specific perceptual responses and can support more targeted strategies for rural landscape renewal. Full article

This study proposes a transparent, data-driven framework for behavior recognition based exclusively on IMU measurements, hypothesizing that vehicular jerk-based features can help in differentiating driving behavior. Unlike studies relying on direct jerk values, our approach derives novel findings from jerk-based features. For rolling windows of 300 samples, a comprehensive set of statistical and dynamic descriptors is extracted, including amplitude, variance, standard deviation, coefficient of variation, standard error, skewness, and kurtosis, as well as jerk-based features such as jerk_std, jerk_variance, jerk_amplitude, and jerk_spikes. Statistical analysis is used to identify features with strong discriminative power. The selected features are used to compute the Driving Score (DS) and, along with the Kernel Density Estimation (KDE) and associated statistics, provide a driver’s profile. Low DS values are consistently associated with increased jerk variability, whereas high DS values correspond to smoother and more controlled motion profiles. The robustness of the proposed framework is evaluated using several machine learning classifiers as baselines, with the jerk-based features as inputs. For the aggressive driver class, the Driving Behavior Score (DBS) model reports a Recall of 0.952 and an F1 of 0.925. For the normal driver class, the DBS model reports a Recall of 0.839 and an F1 of 0.879. The model has a total accuracy of 0.907. Also, Logistic Regression and ensemble models like Extreme Gradient Boosting (XGB) and Random Forest (RF) perform well. The proposed framework offers an explainable, computationally efficient alternative to conventional machine-learning classifiers for identifying aggressive drivers. It relies on lightweight statistical computations being suitable for real-time implementation. Full article

Non-timber forest products (NTFPs) constitute an important component of forest-based production systems and biomass supply chains in Türkiye. Despite their growing economic and ecological significance, the long-term structural dynamics of NTFP production remain insufficiently understood. This study examines temporal and structural changes in NTFP production in Türkiye during the period 1988–2024 using official production statistics and production support data. The analysis applies a quantitative framework that combines linear trend analysis, Shannon diversity and Herfindahl–Hirschman concentration indices, volatility measures based on the coefficient of variation, and regression models to evaluate production trends, structural transformations, stabilization patterns, and the effectiveness of production support mechanisms. The findings reveal a non-linear and multi-phase development pattern characterized by diversification and production growth after 2000, followed by increasing concentration and greater production volatility after 2018. Although total production volume increased substantially, portfolio diversity declined over time, and dependence on a limited number of high-volume products intensified, indicating growing structural vulnerability within the system. In addition, production support mechanisms showed a weak and heterogeneous relationship with production outcomes. A limited contextual comparison with Lithuania’s multifunctional NTFP system is also included to position the findings within a broader European context. Overall, the results suggest that increasing production alone is insufficient to ensure long-term system stability. Instead, diversification-oriented and risk-sensitive resource management strategies that account for production risks, regional disparities, and product heterogeneity are essential for developing sustainable and resilient NTFP production systems. Full article

Kiwifruit (Actinidia deliciosa cv. Hayward) is a high-demand crop due to its nutritional value. Climate change increasingly challenges its cultivation, particularly under Mediterranean conditions, due to limited water resources. Therefore, the early detection of water stress onset is crucial for optimizing irrigation water use and enhancing kiwi productivity. In this context, advanced sensors capable of continuously monitoring critical hydrodynamic parameters, combined with machine learning approaches, offer a promising solution for reliable prediction of plant water status, supporting irrigation decision-making systems. This study develops and evaluates machine learning (ML) models to predict trunk water potential (Ψtrunk), integrating soil moisture, climatic variables, and plant-based measurements, including sap flow. Various machine learning models were evaluated including Ridge Regression, Lasso Regression, Random Forest, Support Vector Machine (SVM), Extreme Gradient Boosting (XGBoost), and Light Gradient Boosting Machine (LightGBM), using soil moisture, trunk water potential (Ψtrunk), sap flow, and microclimatic variables (relative humidity, wind speed, temperature, solar radiation, vapor pressure deficit, and reference evapotranspiration). Among the tested models, XGBoost demonstrated the best performance, achieving an accuracy of approximately 0.80, followed by Ridge, Lasso and SVM, which showed similar accuracy. Full article

Climate change poses an increasing threat to the functionality of forest transportation infrastructure, particularly in northern regions where seasonal access and ground conditions are critical for wood mobilization. The objective of this study was to assess how projected changes in temperature and precipitation may compromise accessibility to forest resources. In addition, it aimed to develop targeted adaptation recommendations to support resilient transportation systems. These actions are essential to ensure the continuity of wood supply under future climatic conditions. Climate projections were extracted from the climatedata.ca platform based on the CMIP6 (CanDCS-M6) model under three Shared Socioeconomic Pathways (SSP1-2.6, SSP2-4.5, and SSP5-8.5). Using a GIS-based workflow, projected temperature and precipitation data were spatially matched to the selected Forest Management Units (FMUs) in Quebec, Canada, and the study area was divided into three latitudinal subregions to capture spatial temperature variation. Classified road network maps were then overlaid with projected climate data for 2020, 2040, 2060, and 2080 to evaluate winter road usability, precipitation-related exposure of road classes, and changes in effective winter road density. Results showed a consistent shortening of the winter road operational period under all scenarios, with the most severe reductions under SSP5-8.5. In highly affected areas, the winter road usability window may decrease from 90 days in 2020 to only 21 days by 2080. Increased precipitation is also expected to affect numerous road segments, raising risks of erosion, sedimentation, and loss of accessibility. A reduction of approximately 7% in effective winter road density is projected across the study area under the high-emission scenario (SSP5-8.5), reflecting the most severe impact of future temperature increases. Based on these findings, targeted road upgrades, climate-informed infrastructure design, and alternative access planning are proposed to help sustain wood flow and support year-round forest operations under future climatic conditions. Full article

Soil algae are important photoautotrophs, yet drivers of their diversity in peri-urban landscapes and across soil horizons remain poorly resolved. We used ITS2 metabarcoding to profile eukaryotic algal and fungal communities in 34 samples from Mexico City’s peri-urban conservation soils. Samples represented three Soil Systems: agricultural mineral soil, forest mineral soil, and forest litter, collected in two boroughs (Xochimilco and Tlalpan). We inferred amplicon sequence variants (ASVs), then alpha diversity and Bray–Curtis turnover were analyzed against edaphic and stoichiometric variables using random forests and PERMANOVA, and compared algal with fungal turnover. We recovered 662 algal ASVs spanning eight classes dominated by Trebouxiophyceae and Chlorophyceae. Litter was the richest and most distinct compartment with a high prevalence and abundance of lichen-associated taxa, whereas mineral soils were dominated by Chlorophyceae. Random forests ranked N/P ratio as the top predictor of both diversity indices. PERMANOVA indicated that the Soil System explained the largest single fraction of turnover. Algal and fungal turnover were positively correlated in mineral soils. Together, soil management practices, vertical compartmentalization and measured edaphic gradients were associated with community differences. These results point to potential algal management practices that could enhance peri-urban soil conservation and agroecological productivity. Full article

Tropical forest restoration has increased in the past decades, with possible advancements given the UN declaration of the “Decade of Ecosystem Restoration”. However, robust assessments to compare ecosystem functions among restored forest stages are essential. We evaluated 13 actively restored forest stands ranging from 3 to 21 years of age and compared measures of forest biodiversity, structure, and ecosystem function to four 70+ year old “reference” stands that serve as restoration “targets” in the study region of the Premontane wet forest of Costa Rica. The restored stands were planted with an average of 13 tree species on abandoned pastures that were fallow for at least two years. Sixteen tree-stand attributes and six ecosystem function estimates were assessed, including: annual biomass (C) accumulation, N-fixation potential, threatened species conservation, and the provision of avian frugivore forage, insect habitat, and insect pollination. Using Principal Component Analysis, linear modeling, and Mahalanobis distance analyses, we learned that planting a diversity of tree species sets the stage for forest recovery at early restoration ages, with an inflection point at 15 years towards older reference forest characteristics and functions. Given that all restoration ages provided tree diversity and some level of ecosystem functions, the value of all restored stands in the landscape is notable. The assessment methods are easily employed, thereby providing an accessible tool to restoration practitioners. Full article

The Seven-coloured Tanager Tangara fastuosa is a threatened species, with little data available on its reproduction. Between 1987 and 2025, 29 nests were found around the Pedra Talhada Biological Reserve in Quebrangulo, Alagoas, north-eastern Brazil. Nests were cup-shaped, with average external dimensions of 11.0 × 7.3 cm and average internal dimensions of 6.2 × 3.7 cm. They were built at an average height of 5.4 m above ground. Mean clutch size was 2.7 eggs, which measured 20.9 × 15.6 mm, and weighed 2.6 g. Eggs were beige in colour with greenish undertones and were heavily spotted with purple or rusty brown. Average incubation period was 13.8 days, and average nestling period was 15.4 days. Apparent nest success was 51.7%, with predation being the main cause of nest failure. Parents, sometimes assisted by helpers, fed the nestlings with small fruits, fruit pulp, seeds, and various arthropods. Our records provide new information on the reproduction of this species in interior and edge forests. However, forest destruction and capture for the illegal wildlife trade pose a threat to the survival of its populations, both remaining an issue in the study area. Full article

Cognitive impairment is common in Post-COVID-19 Condition (PCC), yet full neuropsychological testing remains resource-intensive. Because eye movements are known to be altered in certain cognitive disorders, Eye-Tracking (ET) offers a fast, non-invasive complementary approach for large-scale screening. This study aimed to predict neuropsychological test scores of participants with PCC from ET metrics using machine and deep learning models. ET data was collected from 172 participants performing a battery of visual tasks designed to elicit smooth pursuit and fixational eye movements, as well as pupil responses to light. Cognitive performance was assessed through established neuropsychological tests. We applied regression and classification models (e.g., Random Forest, XGBoost, and deep neural networks) to predict neuropsychological performance. Models were trained using ET data alone and in combination with the Montreal Cognitive Assessment (MoCA) scores, a widely used neuropsychological test for global cognitive screening. Although predicting individual test scores was challenging, combining them into a global composite measure improved performance. Model sensitivity and specificity reached 88% and 34% using ET data alone, and 87% and 60% when integrating ET with MoCA. This last trained model outperformed the conventional MoCA, highlighting the potential of ET as a rapid screening support tool for cognitive assessment. Full article

Reliable short-term agroclimatic forecasting is essential for precision agriculture, irrigation planning, disease-risk assessment, and microclimatic decision support. However, field-deployed sensor systems often operate under degraded data conditions, including missing measurements, noise, temporal interruptions, and limited local computational resources. These constraints make it necessary to evaluate not only forecasting accuracy under clean data, but also model robustness under realistic sensor-data degradation. The objective of this study is to compare machine-learning models for one-step-ahead agroclimatic time-series forecasting under degraded sensor-data conditions. Using a real meteorological dataset collected by a field weather station in the Dnipro region of Ukraine, twelve regression models were evaluated: Ridge Regression, Random Forest, Extra Trees, Gradient Boosting, HistGradientBoosting, Support Vector Regression, Linear SVR, KNN, PLSRegression, ElasticNet, Lasso, and MultiTaskElasticNet. The models were tested under five controlled scenarios: baseline data, missing values, additive noise, reduced training history, and combined noise–missingness degradation. Quantitatively, Ridge Regression achieved the strongest baseline temperature-forecasting performance, with MAE = 0.318 and R² ≈ 0.98 under clean data. It also maintained R² > 0.90 when trained on only 50% of the available history. Under Gaussian noise with σ = 0.05–0.10, Ridge Regression and HistGradientBoosting maintained R² values in the range of 0.95–0.97, whereas under combined degradation with σ = 0.10 and 20% missing data, HistGradientBoosting retained R² > 0.85. These findings indicate that machine-learning models differ substantially in their sensitivity to sensor-data degradation and that robustness-oriented benchmarking is necessary before selecting models for agroclimatic forecasting systems. Full article

The integration of quadruped robotics with advanced sensing technologies offers a transformative approach to forest management, particularly for real-time measurement of tree Diameter at Breast Height (DBH). This paper introduces a novel methodology by deploying a quadruped robot equipped with GPS, LiDAR, and an aligned high-definition camera to patrol forest paths via a developed dynamic autonomous mission. Utilizing a YOLO-based model for trunk detection, the methodology retrieves precise DBH measurements and corresponding geotags, constructing a spatial database of DBH ground-truth data. This database serves as a real-time ground-truth lookup table to calibrate allometric equations used in drone-based crown detection missions, enhancing the accuracy of forest biophysical attribute estimations such as tree height, volume, and biomass. Experimental validation demonstrates high precision in DBH estimation (error < 5% in controlled tests), supporting automated, around-the-clock data collection for sustainable forest management in Mediterranean ecosystems. Full article

The reliable identification of productive and nutritionally valuable Bromus inermis Leyss. germplasm requires multi–year evaluation because forage performance is strongly influenced by genotype, stand age, and annual environmental variation. We evaluated four experimental genotypes and the cultivar WUSU as a control over three production years at a fixed alpine site on the Qinghai–Tibet Plateau. Agronomic traits, forage yield, dry matter accumulation, and nutritional quality were measured annually. A multi–criteria TOPSIS model was used to integrate yield and quality traits for genotype ranking, while random forest analysis and piecewise structural equation modeling were applied to identify key traits and potential pathways influencing forage performance. Genotype, year, and their interaction significantly affected most agronomic, yield, and nutritional traits. Most traits reached their highest values in the third production year, indicating that this stage was critical for evaluating full productive potential. Among the tested materials, genotype 4–4 showed consistently high biomass production and favorable nutritional performance, whereas WUSU and genotype 1–10 generally ranked lower. Plant height and grass height were positively associated with fresh and hay yield, while fresh forage yield, crude protein content, and stem diameter contributed strongly to model prediction. The SEM results suggested that genotype–year interaction influenced hay yield mainly through changes in stem diameter and acid detergent fiber content. These findings indicate that combining multi–year field evaluation with multi–criteria ranking and pathway analysis can improve the identification of promising B. inermis germplasm. Genotype 4–4 represents a useful candidate for further multi–site validation and breeding for high–yield, high–quality forage production in alpine regions. These findings provide a theoretical basis and candidate germplasm for the genetic improvement of Bromus inermis Leyss. adapted to the Qinghai–Tibet Plateau. Full article