Search Results (22,474)

To capture bus passenger flow fluctuations and address the problems of slow convergence and high error in machine learning parameter optimization, this paper develops an improved Whale Optimization Algorithm (IWOA) integrated with a Bidirectional Gated Recurrent Unit (BiGRU). First, a Logistic–Tent chaotic mapping is introduced to generate a diverse and high-quality initial population. Second, a hybrid mechanism combining elite opposition-based learning and Cauchy mutation enhances population diversity and reduces premature convergence. Third, a cosine-based adaptive convergence factor and inertia weight strategy improve the balance between global exploration and local exploitation. Based on the correlation analysis between bus passenger flow and weather condition data in Harbin, and combined with the fluctuation characteristics of bus passenger flow, the data were divided into windows with a 7-day weekly cycle and processed by fuzzy information granulation to obtain three groups of fuzzy granulated window data, namely LOW, R, and UP, representing the fluctuation trend and spatial characteristics of bus passenger flow. The IWOA was employed to optimize and solve parameters such as the hidden layer weights and bias vectors of the BiGRU, thereby constructing a bus passenger flow fluctuation trend and spatial prediction model based on FIG-IWOA-BiGRU. Simulation experiments with 21 benchmark functions and real bus data verified its effectiveness. Results show that IWOA significantly improves optimization accuracy and convergence speed. For bus passenger flow forecasting, the average MAE, RMSE, and MAPE of LOW, R, and UP data are 2915, 3075, and 8.1%, representing improvements over existing classical models. The findings provide reliable decision support for bus scheduling and passenger travel planning. Full article

Background: Pediatric asthma is a multifactorial condition influenced by environmental, biological, and social determinants. The COVID-19 pandemic introduced new variables that may have affected the severity and management of asthma in children and adolescents, particularly through changes in healthcare access, treatment adherence, and exposure to environmental risk factors. Objective: To evaluate the association between asthma severity and various factors including nutritional status, corticosteroid use, COVID-19 vaccination, and pollutant exposure before and during the COVID-19 pandemic in a pediatric population. Methods: A retrospective analysis was conducted using 307 medical records of patients aged 3 to 17 years. Data collected included sociodemographic characteristics, nutritional indicators, history of corticosteroid use, vaccination status against COVID-19, and exposure to environmental pollutants. Asthma severity was assessed using the pulmonary score, and multiple statistical analyses, including logistic regression using the Bayesian Logistic Regression Model (BLRM), were employed to identify significant associations. Results: The analysis revealed a statistically significant impact of the pandemic on hospitalization rates (p = 0.0187) and the use of corticosteroids (p = 0.009), indicating changes in asthma management during this period. Notable differences were observed in the geographic distribution of mild versus severe asthma cases prior to the pandemic, associated with nutritional status and gender (p = 0.018). During the pandemic, breastfeeding history, body weight, and hospitalization emerged as significant predictors of asthma severity (p < 0.05). In addition, breastfeeding in young children (aged 3 to 6 years) and hospitalization were strongly associated with pulmonary scores, with significance values of 0.022 and 0.012, respectively, as identified by the BLRM. Conclusions: These findings suggest that the pandemic context influenced both the clinical course and management of pediatric asthma. Preventive strategies should consider individual and environmental factors such as nutrition, early-life health practices (e.g., breastfeeding), and equitable access to appropriate asthma care and vaccination. Tailoring pediatric asthma management to these variables may improve outcomes and reduce disparities in disease severity. Full article

Efficient irrigation management is crucial for optimizing crop development while minimizing resource use. This study aimed to assess the spatial variability of water distribution under conventional sprinkler irrigation, alongside soil moisture and infiltration dynamics, using multispectral sensors onboard Remotely Piloted Aircraft (RPAs). The experiment was conducted over a 466.2 m² area equipped with 65 georeferenced collectors spaced at 3 m intervals. Soil data were collected through volumetric rings (0–5 cm), auger sampling (30–40 cm), and 65 measurements of penetration resistance down to 60 cm. Four RPA flights were performed at 20 min intervals post-irrigation to generate NDVI and NDWI indices. NDWI values decreased from 0.03 to −0.02, indicating surface moisture reduction due to infiltration and evaporation, corroborated by gravimetric moisture decline from 0.194 g/g to 0.191 g/g. Penetration resistance exceeded 2400 kPa at 30 cm depth, while bulk density ranged from 1.30 to 1.50 g/cm³. Geostatistical methods, including Inverse Distance Weighting and Ordinary Kriging, revealed non-uniform water distribution and subsurface compaction zones. The integration of spectral indices within situ measurements proved effective in characterizing irrigation system performance, offering a robust approach for calibration and precision water management. Full article

Wireless Sensor Networks (WSNs) consist of numerous battery-powered sensor nodes that operate with limited energy, computation, and communication capabilities. Designing routing strategies that are both energy-efficient and attack-resilient is essential for extending network lifetime and ensuring secure data delivery. This paper proposes Adaptive Federated Reinforcement Learning-Hunger Games Search (AFRL-HGS), a Hybrid Routing framework that integrates multiple advanced techniques. At the node level, tabular Q-learning enables each sensor node to act as a reinforcement learning agent, making next-hop decisions based on discretized state features such as residual energy, distance to sink, congestion, path quality, and security. At the network level, Federated Reinforcement Learning (FRL) allows the sink node to aggregate local Q-tables using adaptive, energy- and performance-weighted contributions, with Polyak-based blending to preserve stability. The binary Hunger Games Search (HGS) metaheuristic initializes Cluster Head (CH) selection and routing, providing a well-structured topology that accelerates convergence. Security is enforced as a constraint through a lightweight trust and anomaly detection module, which fuses reliability estimates with residual-based anomaly detection using Exponentially Weighted Moving Average (EWMA) on Round-Trip Time (RTT) and loss metrics. The framework further incorporates energy-accounted control plane operations with dual-format HELLO and hierarchical ADVERTISE/Service-ADVERTISE (SrvADVERTISE) messages to maintain the routing tables. Evaluation is performed in a hybrid testbed using the Graphical Network Simulator-3 (GNS3) for large-scale simulation and Kali Linux for live adversarial traffic injection, ensuring both reproducibility and realism. The proposed AFRL-HGS framework offers a scalable, secure, and energy-efficient routing solution for next-generation WSN deployments. Full article

Iodine deficiency remains a significant nutritional problem, which stimulates the search for sustainable approaches to biofortification of vegetable crops. The aim of the work was to develop a “smart” bio-iodine fertilizer based on the organoiodide complex 1-carboxy-2-phenylethan-1-aminium iodide 2-azaniumyl-3-phenylpropanoate (PPI) and highly porous biochar from agro-waste, assessing its efficiency on the parsley model. PPI was synthesized and characterized (IR/UV spectroscopy, thermal analysis), and biochar was obtained by KOH activation and studied by low-temperature nitrogen adsorption (S_BET) methods, as well as standard physico-chemical characterization. The granulated composition PPI + biochar (BIOF) was tested in pot experiments in comparison with KI and control. The biomass of leaves and roots, iodine and organic nitrogen content, and antioxidant indices (ascorbic acid, total polyphenols, antioxidant activity) were assessed. BIOF provided a significant increase in yield and nutrition: leaf mass reached 86.55 g/plant versus 77.72 g/plant with KI and 65.04 g/plant in the control; root mass—up to 8.25 g/plant (p < 0.05). Iodine content in leaves and roots increased to 11.86 and 13.23 mg/kg (d.w.), respectively, while organic nitrogen levels increased simultaneously (57.37 and 36.63 mg/kg). A significant increase in the antioxidant status was noted (ascorbic acid 36.46 mg/100 g dry weight; antioxidant activity 44.48 mg GA/g; polyphenols 23.79 mg GA/g). The presented data show that the combination of PPI with activated biochar forms an effective platform for controlled supply of iodine to plants, increasing the yield and functional qualities of products; the prospects for implementation are associated with field trials and dosage optimization. Full article

Introduction: Occupational allergic rhinitis (OAR) is a common respiratory condition that can lead to varying degrees of symptom severity, significantly impacting workers’ quality of life and productivity. While occupational risk factors are well established, the influence of nonoccupational factors, such as obesity, that contribute to OAR severity remains largely unexplored. Aims: This study aims to study the association between obesity and the severity of OAR. Methods: A cross-sectional analytical study was conducted among patients diagnosed with OAR at the Occupational Medicine Department of Farhat Hached University Hospital of Sousse. It combines a retrospective review of medical records (2013–2021) with prospective structured telephone interviews (January–March 2023). Data were collected from medical records and supplemented with telephone interviews. The severity of OAR was assessed via the PAREO score and rhinomanometry results. Results: A total of 196 patients were included. The mean age was 39.69 ± 7.92 years, with a sex ratio of 0.53. The most frequently reported symptoms were nasal obstruction (78.6%) and sneezing (88.8%). The mean PAREO score was 5.78 ± 1.61, with severe OAR reported in 59.2% of the patients. Obesity was significantly associated with increased severity of OAR symptoms (p < 0.001; OR = 5.4; 95% CI [2.6–11.1]), a finding confirmed after adjustment for variables such as age, sex, and occupational seniority. Conclusion: Obesity appears to be a modifiable risk factor influencing OAR severity. Integrating weight management strategies into the treatment of OAR patients may contribute to significant symptom relief and improved quality of life. Further longitudinal studies are needed to confirm these findings and explore the underlying mechanisms involved. Full article

Background: Neuroimaging-based diagnostic approaches are of critical importance for the accurate diagnosis and treatment of major depressive disorder (MDD). However, multisite neuroimaging data often exhibit substantial heterogeneity in terms of scanner protocols and population characteristics. Moreover, concerns over data ownership, security, and privacy make raw MRI datasets from multiple sites inaccessible, posing significant challenges to the development of robust diagnostic models. Federated learning (FL) offers a privacy-preserving solution to facilitate collaborative model training across sites without sharing raw data. Methods: In this study, we propose the personalized Federated Gradient Matching and Contrastive Optimization (pF-GMCO) algorithm to address domain shift and support scalable MDD classification using multimodal MRI. Our method incorporates gradient matching based on cosine similarity to weight contributions from different sites adaptively, contrastive learning to promote client-specific model optimization, and multimodal compact bilinear (MCB) pooling to effectively integrate structural MRI (sMRI) and functional MRI (fMRI) features. Results and Conclusions: Evaluated on the Rest-Meta-MDD dataset with 2293 subjects from 23 sites, pF-GMCO achieved accuracy of 79.07%, demonstrating superior performance and interpretability. This work provides an effective and privacy-aware framework for multisite MDD diagnosis using federated learning. Full article

The large-eye dentex (Dentex macrophthalmus) is a relatively small sparid fish with increasing potential as a supplementary fishery resource in the Mediterranean Sea, particularly as traditional stocks face overexploitation. Despite its widespread distribution, biological data on this species, especially from Greek waters, remain scarce. This study presents the first comprehensive biological assessment of D. macrophthalmus in the Pagasitikos Gulf, focusing on population structure, growth, mortality, and the application of machine learning (ML) for age prediction. A total of 305 individuals were collected, revealing a female-biased sex ratio and negative allometric growth in both somatic and otolith dimensions. The von Bertalanffy growth parameters indicated a slow growth rate (k = 0.16 year⁻¹), with an estimated asymptotic length (L∞) of 25.97 cm. The population was found to be underexploited (E = 0.41), suggesting resilience to current fishing pressure. Stepwise regression and ML models were employed to predict age from otolith morphometrics. A linear model identified otolith weight and aspect ratio as the most significant predictors of age (R² = 0.8). Among the ML algorithms tested, the Neural Network model achieved the highest performance (R² = 0.764, MAPE = 14.10%), demonstrating its potential for accurate and efficient age estimation. These findings provide crucial baseline data for the sustainable management of D. macrophthalmus and highlight the value of integrating advanced ML techniques into fisheries biology. Full article

Polycystic ovary syndrome (PCOS) is a prevalent endocrine disorder connected with insulin resistance (IR), low-grade inflammation, dyslipidemia, and altered adipokine secretion. We evaluated serum levels of leptin, adiponectin, visfatin, resistin, IL-6, and TNF-α in 150 women with PCOS, stratified by IR status (IR, n = 76; non-IR, n = 74), and examined their associations with anthropometric, metabolic, hormonal, inflammatory, and atherogenic parameters. Anthropometric data included body weight, height, BMI, waist circumference, and waist-to-height ratio (WHtR), while IR was assessed using HOMA-IR and the Matsuda index. Serum adipokines were measured using ELISA, and lipid parameters and atherogenic indices—including non-HDL cholesterol, AIP, leptin/adiponectin, and adiponectin/resistin ratios—were calculated. Women with IR had higher levels of leptin, visfatin, resistin, and TNF-α, and lower levels of adiponectin. Leptin correlated positively with weight, WHtR, HOMA-IR, and atherogenic indices. Adiponectin showed the strongest and most consistent associations with anthropometric indices, HOMA-IR, and the Matsuda index. Resistin was linked to IR indices and IL-6, and visfatin correlated negatively with HDL-C and insulin sensitivity. In a multivariate general linear model, WHtR, but not HOMA-IR, remained independently associated with higher leptin levels and with atherogenic indices. These findings suggest that in PCOS, central adiposity rather than IR explains a substantial part of the adverse adipokine and inflammatory profile, thereby contributing to elevated cardiometabolic risk and highlighting the need for targeted treatment strategies. Full article

In this paper, the evaluation of the mechanical performance of novel, designed topologically optimized shin pads with advanced materials will be conducted with the aid of Finite Element Analysis (FEA) to assess the endurance of the final structure on impact phenomena extracted from actual real-life data acquired from contact sports. The main focus of the developed prototype is to have high-enough energy absorption capabilities and vibration isolation properties, crucial for the development of trustworthy protective equipment. The insertion of advanced materials with controlled weight fractions and lattice geometries aims to strategically improve those properties and provide tailored characteristics similar to the actual human skeleton. The final design is expected to be used as standalone protective equipment for athletes or as a protective shield for the development of human lower limb prosthetics. In this context, computational investigation of the dynamic mechanical response was conducted by replicating a real-life phenomenon of the impact during a contact sport in a median condition of a stud kick impact and an extreme case scenario to assess the dynamic response under shock-absorption conditions and the final design’s structural integrity by taking into consideration the injury prevention capabilities. The results demonstrate that the proposed lattice geometries positively influence the injury prevention capabilities by converting a severe injury to light one, especially in the gyroid structure where the prototype presented a unified pattern of stress distribution and a higher reduction in the transmitted force. The incorporation of the PA-12 matrix reinforced with the reused ground tire rubber results in a structure with high enough overall strength and crucial modifications on the absorption and damping capabilities vital for the integrity under dynamic conditions. Full article

Background: Recurrent urinary tract infections (rUTIs) significantly impair women’s quality of life, making antimicrobial prophylaxis a critical preventative strategy. This retrospective observational study aimed to characterize antibiotic prophylaxis patterns, relapse rates, comparative efficacy of different agents, and tolerability in 908 women (663 postmenopausal, 245 premenopausal) with rUTIs managed at a tertiary university hospital. Methods: Data from medical records (January 2022–December 2024) were analyzed. Patients were stratified by menopausal status. We assessed antibiotic usage, relapse rates (per 100 patient-months), and adverse events. Comparative efficacy of nitrofurantoin-based versus fosfomycin/other prophylaxis was evaluated for rUTIs caused by E. coli, E. faecalis, or E. coli ESBL using weighted and matched analyses to control for covariates. Results: Continuous antimicrobial prophylaxis was the primary strategy, with nitrofurantoin being most frequently used. Premenopausal women showed a greater tendency for intermittent or combined prophylactic approaches. Postmenopausal women exhibited a higher overall crude relapse rate (5.54/100 p-m) compared to premenopausal women (3.14/100 p-m), with E. coli being the most common causative agent in relapses. For rUTIs caused by E. coli, E. faecalis, or E. coli ESBL, nitrofurantoin-based prophylaxis demonstrated significantly lower adjusted relapse rates than fosfomycin/other regimens (rate ratio: 0.47 for postmenopausal, 0.35 for premenopausal women). This observed efficacy for nitrofurantoin was robust against potential unmeasured confounding. Prophylaxis was generally well-tolerated (3.0% gastrointestinal adverse events overall); however, premenopausal women reported a higher adverse event incidence. Conclusions: Our findings strongly suggest that nitrofurantoin is an effective prophylactic choice for rUTIs caused by common uropathogens (E. coli, E. faecalis, E. coli ESBL), particularly in postmenopausal women. The diverse prophylactic strategies highlight the need for individualized care. While generally well-tolerated, adverse event profiles vary between menopausal groups, necessitating careful monitoring. Full article

Background: Musculoskeletal (MSK) pain is a frequent but under-addressed concern during pregnancy. In Bangladesh, challenges such as limited antenatal care (ANC) access and heavy maternal workloads make this issue particularly urgent for maternal health. This study aimed to determine the prevalence and predictors of MSK pain among pregnant women attending government ANC clinics in Bangladesh. Methods: A facility-based cross-sectional study was conducted among 300 pregnant women recruited from two government hospitals in Dhaka Division. Data were collected using structured interviewer-administered questionnaires covering patient characteristics, pain-related characteristics, and pregnancy-related characteristics. Pain was measured using the Numeric Pain Rating Scale (NPRS; mild <4, moderate 4–7, severe >7), and body mass index (BMI) was calculated based on self-reported height and weight. Descriptive statistics, chi-square tests, and multivariable logistic regression were employed to identify factors independently associated with MSK pain. Results: Overall, 67% of women reported MSK pain, most frequently in the lower back and lower abdomen. Women in later trimesters had about twice the odds of experiencing pain, while those with obesity had nearly six times higher odds compared to women with normal body mass index (BMI). Conclusions: MSK pain is common among pregnant women in Bangladesh and shows associations with later gestational stages and obesity. These findings suggest that integrating routine screening and non-pharmacological management into ANC may help support maternal health and reduce preventable complications in resource-limited settings. Full article

YKL-40, an obesity-related inflammatory biomarker, has inconsistently been associated with insulin resistance, and its relationship with metabolic syndrome is not well established. This study investigated the associations of YKL-40 levels with insulin resistance and metabolic syndrome independently of obesity. We analyzed data from 4303 participants without diabetes in the Taiwan Biobank. Insulin resistance was defined by the highest quartile of triglyceride-glucose body mass index (TyG-BMI). Metabolic syndrome was defined per AHA/NLHBI criteria. Both univariate and multivariate analyses demonstrated significant correlations between YKL-40 levels and TyG-BMI. Participants with higher YKL-40 quartiles exhibited increased odds of TyG-BMI-estimated insulin resistance even after adjusting for established predictors of TyG-BMI, including waist circumference. Similarly, higher YKL-40 quartiles significantly correlated with increased metabolic syndrome prevalence, and this relationship persisted after stratifying participants by weight status (normal weight vs. overweight/obese). Interaction analysis indicated that overweight/obesity individuals consistently had higher metabolic syndrome prevalence than normal-weight counterparts within identical YKL-40 quartiles, though the impact of overweight/obese diminished across rising YKL-40 quartiles (p for interaction = 0.008). Increased YKL-40 levels are significantly associated with TyG-BMI-estimated insulin resistance and metabolic syndrome, independent of obesity. There is a significant interaction between overweight/obese and YKL-40 levels in determining metabolic syndrome prevalence. Full article

Background: Bone health in youth is influenced by both modifiable factors, such as nutrition and physical activity, and non-modifiable factors, such as biological maturation and heredity. Understanding how these elements interact to predict body composition may enhance the effectiveness of early interventions. Importantly, the integration of both supervised and unsupervised machine learning models enables a data-driven exploration of complex relationships, allowing for accurate prediction and subgroup discovery. Methods: This cross-sectional study examined 94 male athletes during the developmental period. Anthropometric, performance, and nutritional data were collected, and bone parameters were assessed using dual-energy X-ray absorptiometry (DXA). Three supervised machine learning models (Random Forest, Gradient Boosting, and Support Vector Regression) were trained to predict Total Body-Less Head (TBLH) values. Nested cross-validation assessed model performance. Unsupervised clustering (K-Means) was also applied to identify dietary intake profiles (calcium, protein, vitamin D). SHAP analysis was used for model interpretability. Results: The Random Forest model yielded the best predictive performance (R² = 0.71, RMSE = 0.057). Weight, height, and handgrip strength were the most influential predictors. Clustering analysis revealed two distinct nutritional profiles; however, t-tests showed no significant differences in TBLH or regional BMD between the clusters. Conclusions: Machine learning, both supervised for accurate prediction and unsupervised for nutritional subgroup discovery, provides a robust, interpretable framework for assessing adolescent bone health. While dietary intake clusters did not align with significant differences in bone parameters, this finding underscores the multifactorial nature of skeletal development and highlights areas for further exploration. Full article

Accurate prediction of the RUL of electric drive bearings over the entire service life cycle for new energy vehicles optimizes maintenance strategies and reduces costs, addressing clear application needs. Full life data of electric drive bearings exhibit long time spans and abrupt degradation, complicating the modeling of time dependent relationships and degradation states; therefore, a piecewise linear degradation model is appropriate. An RUL prediction method is proposed based on degradation assessment and spatiotemporal feature fusion, which extracts strongly time correlated features from bearing vibration data, evaluates sensitive indicators, constructs weighted fused degradation features, and identifies abrupt degradation points. On this basis, a piecewise linear degradation model is constructed that uses a path graph structure to represent temporal dependencies and a temporal observation window to embed temporal features. By incorporating GAT-LSTM, RUL prediction for bearings is performed. The method is validated on the XJTU-SY dataset and on a loaded ball bearing test rig for electric vehicle drive motors, yielding comprehensive vibration measurements for life prediction. The results show that the method captures deep degradation information across the full bearing life cycle and delivers accurate, robust predictions, providing guidance for the health assessment of electric drive bearings in new energy vehicles. Full article