Search Results (35,098)

Biochar is crucial for agricultural output and plays a significant role in effectively eliminating heavy metals (HMs) from the soil, which is essential for maintaining a soil–plant environment. This work aimed to assess machine learning models to analyze the impact of soil parameters on the transformation of HMs in biochar–soil–plant environments, considering the intricate non-linear relationships involved. A total of 211 datasets from pot or field experiments were evaluated. Fourteen factors were taken into account to assess the efficiency and bioavailability of HM–biochar amendment immobilization. Four predictive models, namely linear regression (LR), partial least squares (PLS), support vector regression (SVR), and random forest (RF), were compared to predict the immobilization efficiency of biochar-HM. The findings revealed that the RF model was created using 5-fold cross-validation, which exhibited a more reliable prediction performance. The results indicated that soil features accounted for 79.7% of the absorption of HM by crops, followed by biochar properties at 17.1% and crop properties at 3.2%. The main elements that influenced the result have been determined as the characteristics of the soil (including the presence of different HM species and the amount of clay) and the quantity and attributes of the biochar (such as the temperature at which it was produced by pyrolysis). Furthermore, the RF model was further developed to predict bioaccumulation factors (BAF) and variations in crop uptake (CCU). The R² values were found to be 0.7338 and 0.6997, respectively. Thus, machine learning (ML) models could be useful in understanding the behavior of HMs in soil–plant ecosystems by employing biochar additions. Full article

Food insecurity remains a pressing issue globally, exacerbated in regions like sub-Saharan Africa, where rural communities face significant challenges in accessing nutritious food. The Eastern Cape Province of South Africa is particularly vulnerable, with high levels of poverty and limited infrastructure contributing to food insecurity among its rural households. In response to these challenges, family food gardens have emerged as a promising strategy to enhance local food production, improve dietary diversity, and foster economic resilience within these communities. Despite the potential benefits of family food gardens, empirical evidence of their effectiveness in mitigating food insecurity at the household level in the Eastern Cape Province is scarce and remains limited. Understanding the factors that influence the success of these gardens, including socio-economic, environmental, and institutional determinants, is crucial for optimizing their impact and scalability. Hence, this study sought to comprehensively explore and investigate the role of family food gardens in improving food security within rural households in the Eastern Cape Province. It seeks to identify the determinants that contribute to the success of these gardens and their potential to alleviate food insecurity. The study made use of a descriptive research design, and the study utilized purposive sampling to gather data from 130 rural households via structured questionnaires. Data analyses incorporated in the study included the Household Dietary Diversity Score and logit regression model to explore the impacts and determinants of family food gardens on food security. The study findings underscore the significant positive contributions of family food gardens to rural communities. They serve as vital sources of fresh crops and vegetables, supplementing household nutrition and providing temporary employment. Constraints identified in the study include financial limitations, theft, water scarcity, inadequate fencing, and limited market access. The study insights highlight the fact that socio-economic and institutional factors such as age, gender, household income, and access to credit are critical influencers of family food garden success. These empirical results offer practical implications for policymakers, governmental agencies, and local communities seeking to promote sustainable agricultural practices and alleviate food insecurity. The research highlights how essential family food gardens are for improving food security among rural families in the Eastern Cape Province. The findings suggest that a joint effort is needed from the government, policymakers, NGOs, and local communities to overcome challenges and make the most of social and economic resources. By working together, these groups can enhance the role of family food gardens, making them a more effective solution for local food production and a stronger defence against food insecurity in the region. Full article

This article proposes new values and geospatial models of winter and summer external design temperatures for designing buildings’ heating, ventilation, and air-conditioning (HVAC) systems. The climatic design parameters applicable in Poland for the sizing of these installations are approximately 50 years old and do not correspond to Poland’s current climate. New values of climatic design parameters were determined following the methods described in European standards and the American Society of Heating, Refrigerating and Air-Conditioning Engineers (ASHRAE) Handbook of Fundamentals. The determined climatic design parameters, particularly the winter and summer external design temperatures, were compared with those currently in force by law in Poland. The external air design dry-bulb temperatures presented in the article were developed based on meteorological and climatic data from the years 1991–2020 from two data sources: synoptic data from the Institute of Meteorology and Water Management (IMWM) in Poland and reanalysis models of the ERA5 database of the European Centre for Medium-Range Weather Forecasts (ECMWF). According to ASHRAE, with 99.6% and 0.4% frequency of occurrence, external air design dry-bulb temperatures for winter and summer were used to develop mathematical geospatial models of external design temperatures for the Central Europe area with Poland’s territory in the centre part. Scattered data from 667 meteorological stations were interpolated to 40,000 uniform mesh points using a biharmonic spline interpolation method to develop these models. Linear regression and ANOVA analysis for the ERA5-generated data from 900 checkpoint data items were used to estimate the correctness of these models. Verified models were used to calculate winter and summer external design temperature isolines presented together with colour space representation on Mercator projected maps of Central Europe. Full article

Wood surface defect detection is a challenging task due to the complexity and variability of defect types. To address these challenges, this paper introduces a novel deep learning approach named SiM-YOLO, which is built upon the YOLOv8 object detection framework. A fine-grained convolutional structure, SPD-Conv, is introduced with the aim of preserving detailed defect information during the feature extraction process, thus enabling the model to capture the subtle variations and complex details of wood surface defects. In the feature fusion stage, a SiAFF-PANet-based wood defect feature fusion module is designed to improve the model’s ability to focus on local contextual information and enhance defect localization. For classification and regression tasks, the multi-attention detection head (MADH) is employed to capture cross-channel information and the accurate spatial localization of defects. In addition, MPDIoU is employed to optimize the loss function of the model to reduce the leakage of detection due to defect overlap. The experimental results show that SiM-YOLO achieves superior performance compared to the state-of-the-art YOLO algorithm, with a 9.3% improvement in mAP over YOLOX and a 4.3% improvement in mAP over YOLOv8. The Grad-CAM visualization further illustrates that SiM-YOLO provides more accurate defect localization and effectively reduces misdetection and omission issues. This study highlights the effectiveness of SiM-YOLO for wood surface defect detection and offers valuable insights for future research and practical applications in quality control. Full article

The development and understanding of the behavior of construction materials is extremely complex due to the great variability of raw materials that can be used, which becomes even more challenging when functional materials, such as phase-change materials (PCM), are incorporated. Currently, we are witnessing an evolution of advanced construction materials as well as an evolution of powerful tools for modeling engineering problems using artificial intelligence, which makes it possible to predict the behavior of composite materials. Thus, the main objective of this study was exploring the potential of machine learning to predict the mechanical and physical behavior of mortars with direct incorporation of PCM, based on own experimental databases. For data preparation and modelling process, the cross-industry standard process for data mining, was adopted. Seven different models, namely multiple regression, decision trees, principal component regression, extreme gradient boosting, random forests, artificial neural networks, and support vector machines, were implemented. The results show potential, as machine learning models such as random forests and artificial neural networks were demonstrated to achieve a very good fit for the prediction of the compressive strength, flexural strength, water absorption by immersion, and water absorption by capillarity of the mortars with direct incorporation of PCM. Full article

Located in the south of the Iberian Peninsula, the Doñana salt marshes occupy around half of Doñana National Park and are currently considered among the most important wetlands worldwide due to the importance of their ecosystem. In this research work, using a novel patented procedure, the effects of climate change on the study area between 2009 and 2020 were evaluated. For this reason, DEMs were downloaded from the 30-meter Shuttle Radar Topography Mission (SRTM). Furthermore, to check the depth of the flooded area, 792 satellite images (L5 TM, L7 ETM+, and L8 OLI) with a resolution of 30 m were analyzed. The results show how the combined use of geomatic techniques, such as radar, optical, and geographic information system (GIS) data, along with regression models and iterative processes, plays a key role in the prediction and analysis of the flooded area volume in the Doñana salt marshes. Another significant contribution of this work is the development of a new remote sensing index. In conclusion, given that the study area depends on its aquifers’ status, it would be advisable to implement policies aimed at eradicating illegal aquifer extraction, as well as recovery plans to avoid the complete clogging of this salt marsh. Full article

Pneumococcal vaccination (PV) is effective in preventing vaccine-type pneumococcal diseases. This study investigated the changes in PV uptake and its determinants before, during, and after the Coronavirus Disease 2019 (COVID-19) pandemic among community-living older adults aged ≥65 years in Hong Kong, China. Three rounds of random telephone surveys were conducted every two years from May 2019 to October 2023. Multivariate logistic regression models were fitted to examine the between-round differences in PV uptake rate and factors associated with PV uptake in each round. This study included 1563 participants. The standardized PV uptake rate in Round 1, 2, and 3 was 17.3%, 28.3%, and 35.5%, respectively. A significant difference in the PV uptake rate was found between Rounds 2 and 1 (p = 0.02), but not between Rounds 3 and 2 (p = 0.98). Perceived barriers, cue to action and self-efficacy, were significant determinants of PV uptake in all rounds. Perceived benefits were significant determinants of PV uptake in the first and second rounds, but not in the third round. Continuous monitoring of PV uptake and its determinants, and evaluating and adjusting the PV program, might contribute to the success of such a vaccination program in the post-pandemic era. Full article

Wildfires generate substantial smoke containing fine particulate matter (PM_2.5) that adversely impacts health. This study develops machine learning models integrating pre-wildfire factors like weather and fuel conditions with post-wildfire health impacts to provide a holistic understanding of smoke exposure risks. Various data-driven models including Support Vector Regression, Multi-layer Perceptron, and three tree-based ensemble algorithms (Random Forest, Extreme Gradient Boosting (XGBoost), and Natural Gradient Boosting (NGBoost)) are evaluated in this study. Ensemble models effectively predict PM_2.5 levels based on temperature, humidity, wind, and fuel moisture, revealing the significant roles of radiation, temperature, and moisture. Further modelling links smoke exposure to deaths from chronic obstructive pulmonary disease (COPD) and lung cancer using age, sex, and pollution type as inputs. Ambient pollution is the primary driver of COPD mortality, while age has a greater influence on lung cancer deaths. This research advances atmospheric and health impact understanding, aiding forest fire prevention and management. Full article

Computer vision in marine ranching enables real-time monitoring of underwater resources. Detecting fish presents challenges due to varying water turbidity and lighting, affecting color consistency. We propose a Foreground Region Convolutional Neural Network (FR-CNN) that combines unsupervised and supervised methods. It introduces an adaptive multiscale regression Gaussian background model to distinguish fish from noise at different scales. Probability density functions integrate spatiotemporal information for object detection, addressing illumination and water quality shifts. FR-CNN achieves 95% mAP with IoU of 0.5, reducing errors from open-source datasets. It updates anchor boxes automatically on local datasets, enhancing object detection accuracy in long-term monitoring. The results analyze fish species behaviors in relation to environmental conditions, validating the method’s practicality. Full article

Currently, spatial modeling is of particular relevance as it enables the understanding of the patterns and spatial variability of an event, the monitoring and prediction of the spatial behavior of a variable, the optimization of resources, and the evaluation of the impacts of a phenomenon of interest. Research carried out recently on variables related to solar energy budgets has been of special relevance due to its applications and developments in machine learning (ML) and deep learning (DL). These algorithms are crucial to improve the efficiency, precision, and applicability of remote sensing, allowing greater decision making with more reliable and timely data. Thus, this work proposes a systematic and rigorous methodology for searching research articles about the latest advances and contributions related to the modeling of radiative energy budgets using novel techniques and algorithms in some of the most relevant international scientific databases (Scopus, ScienceDirect, ResearchGate). Search parameters were applied using tracking methods through various filters, specific classifiers, and Boolean operators. The results allowed for an analysis of search trends and citations in the last 5 years related to the topic of interest and the number of most relevant articles for this research, analyzed through specialized metrics and graphs. Additionally, this methodology was classified into four categories of importance for refined and articulated searches in this evaluation: (i) according to the applied interpolation methods, (ii) according to the remote sensors used, (iii) according to the applications in different fields of knowledge. As a relevant fact and with an essentially prospective purpose, a subchapter of this review was dedicated to the latest advances and developments applied to (iv) spatial modeling of terrestrial radiation through ML, this method being a tool that opens multiple alternatives for data processing and analysis in the development and achievement of objectives in the field of geotechnologies. A quantitative comparison was conducted on the predictive performance results between the classification/regression algorithms found in the studies explored in this review. The evaluation confirmed the existence of a persistent shortage of studies in recent years within the geotechnologies field, particularly concerning the comparison of spatial distribution modeling techniques developed and implemented through ML for incident solar and terrestrial radiation. Therefore, this work provides a synthesis and analysis of the most used and novel techniques in the modeling of solar energy budgets, their limitations, and biggest challenges. Full article

Hybrid methods are a suitable option for extracting dietary patterns associated with health outcomes. This study aimed to identify the dietary patterns of Brazilian adults (20–59 years old; n = 28,153) related to dietary components associated with the risk of obesity. Data from the 2017–2018 Brazilian National Dietary Survey were analyzed. Food consumption was obtained through 24 h recall. Dietary patterns were extracted using partial least squares regression, using energy density (ED), percentage of total fat (%TF), and fiber density (FD) as response variables. In addition, 32 food groups were established as predictor variables in the model. The first dietary pattern, named as energy-dense and low-fiber (ED-LF), included with the positive factor loadings solid fats, breads, added-sugar beverages, fast foods, sauces, pasta, and cheeses, and negative factor loadings rice, beans, vegetables, water, and fruits (≥|0.15|). Higher adherence to the ED-LF dietary pattern was observed for individuals >40 years old from urban areas, in the highest income level, who were not on a diet, reported away-from-home food consumption, and having ≥1 snack/day. The dietary pattern characterized by a low intake of fruits, vegetables, and staple foods and a high intake of fast foods and sugar-sweetened beverages may contribute to the obesity scenario in Brazil. Full article

(1) Background: A low socioeconomic status significantly increases the risk of hypertension and its associated cardiovascular diseases due to limited access to healthcare and may be even more accentuated by the presence of unhealthy lifestyle habits. The aim of the present research was to study if associations exist between having a family income under the poverty threshold and having an unhealthy diet, being physically inactive, being an alcohol drinker, perceiving one’s own health as bad, and suffering from congestive heart failure, coronary heart disease, angina pectoris, heart attack, or stroke. Additionally, the odds ratios of having these unhealthy habits and of suffering from the abovementioned cardiac complications of participants under the poverty threshold were calculated. (2) Methods: This cross-sectional study was based on the National Health and Nutrition Examination Survey (NHANES) 2011–2020. The sample comprised 6120 adults with hypertension (3188 males and 2932 females). A descriptive analysis and non-parametric chi-squared tests were used to study the associations. A binary logistic regression model and backward LR method were used to calculate the odds ratios, normalized by age and sex. (3) Results: The chi-squared test showed associations between having a family income under the poverty threshold and being physically inactive (p < 0.001), having an unhealthy diet (p < 0.001), being an alcohol drinker (p < 0.001), perceiving one’s own health as bad (p < 0.001), and suffering from congestive heart failure (p = 0.002), heart attack (p = 0.001), or stroke (p = 0.02). A significantly increased odds ratio for these unhealthy habits and cardiac complications, and also for having coronary heart disease and angina pectoris, were found for hypertension sufferers under the poverty threshold. (4) Conclusions: It was confirmed that having a family income under the poverty threshold is associated with perceiving one’s own health as bad, having a series of negative habits in terms of physical activity, diet, and alcohol consumption, and with suffering from congestive heart failure, heart attack, or stroke. Increased odds ratios for these unhealthy habits and these conditions, plus coronary heart disease and angina pectoris, were found for hypertension sufferers under the poverty threshold. Full article

With the increasing use of data-driven modeling methods, new approaches to complex problems in the field of wind energy can be addressed. Topics reviewed through the literature include wake modeling, performance monitoring and controls applications, condition monitoring and fault detection, and other data-driven research. The literature shows the advantages of data-driven methods: a reduction in computational expense or complexity, particularly in the cases of wake modeling and controls, as well as various data-driven methodologies’ aptitudes for predictive modeling and classification, as in the cases of fault detection and diagnosis. Significant work exists for fault detection, while less work is found for controls applications. A methodology for creating data-driven wind turbine models for arbitrary performance parameters is proposed. Results are presented utilizing the methodology to create wind turbine models relating active adaptive twist to steady-state rotor thrust as a performance parameter of interest. Resulting models are evaluated by comparing root-mean-square-error (RMSE) on both the training and validation datasets, with Gaussian process regression (GPR), deemed an accurate model for this application. The resulting model undergoes particle swarm optimization to determine the optimal aerostructure twist shape at a given wind speed with respect to the modeled performance parameter, aerodynamic thrust load. The optimization process shows an improvement of 3.15% in thrust loading for the 10 MW reference turbine, and 2.66% for the 15 MW reference turbine. Full article

This study employed a cross-sectional design to explore the impact of social support and self-efficacy on activity of daily living (ADL) among post-stroke patients in Saudi Arabia and investigate the mediating role of self-efficacy. Data were collected from 158 post-stroke patients across six healthcare facilities in three regions of Saudi Arabia using convenience sampling, between February 2023 and July 2023. The analysis included descriptive statistics, variance analysis, and linear regression using bootstrap methods. PROCESS Macro was used for the mediation model. This study revealed that most participants had high ADL, social support, and self-efficacy levels. Significant negative associations were found between ADL and age (p < 0.001), time since stroke (p = 0.009), and stroke history (p < 0.001), while significant positive associations were observed with educational background (p = 0.049), employment status (p < 0.001), and self-efficacy (p < 0.001). ADL in post-stroke patients was significantly influenced negatively by age (p = 0.025), time since stroke (p = 0.027), and stroke history (p < 0.001), while self-efficacy (p < 0.001) had a positive impact and moderated the relationship between social support and ADL. This study highlights the physical and psychosocial aspects affecting post-stroke patients, identifies key areas for enhancing their experiences, and informs the development of targeted interventions to address their comprehensive needs. Full article

Background and Objectives: This study aimed to evaluate the potential chemopreventive effect of antidiabetic medications, specifically metformin and pioglitazone, on lung cancer in patients with type 2 diabetes mellitus (T2DM). Additionally, the potential dose–response relationship for metformin use was analyzed. Methods: We conducted a retrospective cohort study utilizing comprehensive national health insurance and cancer registry databases to gather a large cohort of T2DM patients. Cox proportional hazards regression models were used to assess the risk of lung cancer across different antidiabetic medication groups, adjusting for potential confounders such as age and gender. A dose–response analysis was conducted for metformin users. Results: Our results indicated that metformin users had a significantly lower lung cancer risk than the reference group (HR = 0.69, 95% CI [0.55–0.86], p = 0.001). The risk reduction increased with higher cumulative metformin doses: a metformin cumulative dose between 1,370,000 and 2,976,000 had an HR of 0.61 (95% CI [0.49–0.75], p < 0.001) vs. cumulative metformin dose >2,976,000 which had an HR of 0.35 (95% CI [0.21–0.59], p < 0.001). No significant association between pioglitazone use and the risk of lung cancer was found (HR = 1.00, 95% CI [0.25–4.02]). Conclusions: This study shows that metformin may have a dose-dependent chemopreventive effect against lung cancer in T2DM, while the impact of pioglitazone remains unclear and requires further investigation. Full article