Search Results (3,753)

This Perspective synthesizes recent (2023–2025) progress in predicting extreme environmental values by combining empirical formulations, physics-based simulation outputs, and sensor-network data. We argue that hybrid approaches—spanning physics-informed machine learning, digital/operational twins, and edge/embedded AI—can deliver faster and more robust maxima estimates than standalone CFD or purely data-driven models, particularly for urban air quality and wind-energy applications. We distill lessons from cross-domain case studies and highlight five open challenges (uncertainty quantification, reproducibility and benchmarks, sensor layout optimization, real-time inference at the edge, and trustworthy model governance). Building on these, we propose a 2025–2030 research agenda: (i) standardized, open benchmarks with sensor–CFD pairs; (ii) physics-informed learners for extremes; (iii) adaptive source-term estimation pipelines; (iv) lightweight inference for embedded sensing; (v) interoperable digital-twin workflows; and (vi) reporting standards for uncertainty and ethics. The goal is a pragmatic path that couples scientific validity with deployability in operational environments. This Perspective is intended for researchers and practitioners in environmental sensing, urban dispersion, and renewable energy who seek actionable, cross-disciplinary directions for the next wave of extreme-value prediction. For instance, in validation studies using CFD-RANS and sensor data, the proposed hybrid models achieved prediction accuracies for peak pollutant concentrations and wind speeds within ~90–95% of high-fidelity simulations, with a computational cost reduction of over 80%. These results underscore the practical viability of the approach for operational use cases such as urban air quality alerts and wind farm micro-siting. Full article

Industrial processes governed by food safety regulations, such as high-temperature short-time (HTST) pasteurization, rely on continuous sensor monitoring to ensure compliance with standards like Hazard Analysis and Critical Control Points (HACCP). However, extracting actionable process insights from raw sensor data remains a non-trivial task, largely due to the continuous, multivariate, and often high-frequency characteristics of the signals, which can obscure clear activity boundaries and introduce significant variability in temporal patterns. This paper proposes a process mining framework to extract activity-based representations from multivariate sensor data in a pasteurization scenario. By modelling temperature, pH, conductivity, viscosity, turbidity, flow, and pressure signals, the approach segments continuous data into discrete operational phases and generates event logs aligned with domain semantics. Unsupervised learning techniques, including Hidden Markov Models (HMMs), are used to infer latent process stages, while domain knowledge guides their interpretation in accordance with critical control points (CCPs). The extracted models support conformance checking against HACCP-based procedures and enable predictive process-monitoring tasks such as next-activity prediction and remaining time estimation. Experimental results on synthetic (literature-grounded data) demonstrated the method’s ability to enhance safety, compliance, and operational efficiency. This study illustrates how integrating process mining with regulatory principles can bridge the gap between continuous sensor streams and structured process analysis in food manufacturing. Full article

Educational strategies based on technological models that integrate the dimensions of prevention, screening, and treatment of diabetic foot ulcers are emerging as promising methods to improve nurses’ knowledge, skills, and clinical competencies in primary care. In this investigation, we evaluated the effectiveness of a digital education program, mediated by a virtual learning environment, in enhancing nurses’ clinical knowledge about diabetic foot ulcers. This quasi-experimental intervention study was conducted with 114 nurses, selected for convenience, from the five health districts that make up primary care in the municipality of Teresina, Brazil. Two stages, separated by the educational intervention, allowed us to measure their knowledge levels before and after the implementation of the digital technology. A characterization form and the Nurse Knowledge Assessment Questionnaire on Diabetic Foot were used to evaluate the outcomes. The McNemar test compared the pre- and post-intervention knowledge levels, while accuracy rate-based parameters allowed for the classification of results into performance categories. The intervention effect size was estimated using Cohen’s d test. Results showed substantial improvements in knowledge, particularly in domains related to definition (p = 0.002), risk factors (p < 0.001), associated complications (p < 0.001), signs and symptoms of neuropathies (p < 0.001), application of tests to assess protective sensation (p < 0.001) and foot biomechanics (p < 0.001), risk classification (p < 0.001), and prevention strategies (p < 0.001), with performance ratings predominantly “good” or “excellent” after the intervention. The effect size for paired samples was large (Cohen’s dz = 1.82), based on the total knowledge scores. Findings support the effectiveness signal of the virtual learning environment for knowledge improvement; however, without a control group, we cannot rule out testing effects. Controlled or stepped-wedge trials should confirm causality. Full article

In this paper, we introduce two novel subclasses of analytic functions, namely, starlike and convex functions of Ma–Minda-type, associated with a newly proposed domain. We set sharp bounds on the basic coefficients of these classes and provide sharp estimates of the second- and third-order Hankel determinants, demonstrating the power of our analytic approach, the clarity of its results, and its applicability even in unconventional domains. Full article

The difficulty in precisely extracting single-fault signatures from hydraulic pump composite faults, which stems from structural complexity and coupled multi-source vibrations, is tackled herein via a new diagnostic technique based on underdetermined blind source separation (UBSS). Utilizing sparse component analysis (SCA), the proposed method achieves blind source separation without relying on prior knowledge or multiple sensors. However, conventional SCA-based approaches are limited by their reliance on a predefined number of sources and their high sensitivity to noise. To overcome these limitations, an adaptive source number estimation strategy is proposed by integrating information–theoretic criteria into density peak clustering (DPC), enabling automatic source number determination with negligible additional computation. To facilitate this process, the short-time Fourier transform (STFT) is first employed to convert the vibration signals into the frequency domain. The resulting time–frequency points are then clustered using the integrated DPC–Bayesian Information Criterion (BIC) scheme, which jointly estimates both the number of sources and the mixing matrix. Finally, the original source signals are reconstructed through the minimum L1-norm optimization method. Simulation and experimental studies, including hydraulic pump composite fault experiments, verify that the proposed method can accurately separate mixed vibration signals and identify distinct fault components even under low signal-to-noise ratio (SNR) conditions. The results demonstrate the method’s superior separation accuracy, noise robustness, and adaptability compared with existing algorithms. Full article

Background/Objectives: Self-perceptions in childhood shape motivation, behavior, and well-being; however, their relationship to motor competence and physical fitness remains unclear. We tested whether physical fitness mediates the association between motor competence and domain-specific self-perceptions in middle childhood. Methods: In a school-based sample of 100 ten-year-olds (59 girls, 41 boys; 3 exclusions ≤ 5th MABC-2 percentile), children completed MABC-2 (motor competence), EUROFIT (physical fitness), and SPPC (self-perceptions). Principal component analysis of the nine EUROFIT tests yielded two factors: Motor Fitness (agility/endurance/flexibility/muscular endurance) and Strength/Size (handgrip and BMI). Parallel mediation models (MABC-2 → [Motor Fitness, Strength/Size] → SPPC) were estimated with maximum likelihood and 5000 bias-corrected bootstrap resamples. Benjamini–Hochberg FDR (q = 0.05) was applied within each path family across the six SPPC domains. Results: In baseline models (no covariates), Motor Fitness → Athletic Competence was significant after FDR (β = 0.263, p = 0.003, FDR p = 0.018). Associations with Scholastic (β = 0.217, p = 0.039, FDR p = 0.090) and Social (β = 0.212, p = 0.046, FDR p = 0.090) were positive but did not meet the FDR threshold. Strength/Size showed no associations with any SPPC domain. Direct effects from MABC-2 to SPPC were non-significant. Indirect effects via Motor Fitness were minor and not supported after FDR (e.g., Athletic: β = 0.067, p = 0.106, 95% CI [0.007, 0.174], FDR p = 0.251). In BMIz-adjusted sensitivity models, Motor Fitness remained significantly related to Athletic (β = 0.285, p = 0.008, FDR p = 0.035), Scholastic (β = 0.252, p = 0.018, FDR p = 0.035), and Social (β = 0.257, p = 0.015, FDR p = 0.035); MABC-2 → Motor Fitness was β = 0.235, p = 0.020. Some paths reached unadjusted significance but were not significant after FDR correction (all FDR p-values = 0.120 for indirect effects). Conclusions: Functional Motor Fitness, but not Strength/Size, showed small-to-moderate, domain-specific links with children’s Athletic (and, when adjusting for adiposity, Scholastic/Social) self-perceptions; mediated effects were small and not FDR-supported. Findings highlight the salience of visible, functional performances (e.g., agility/endurance tasks) for children’s self-views and support PE approaches that foster diverse motor skills and motor fitness. Because the study is cross-sectional and BMI-adjusted analyses are presented as robustness checks, caution should be exercised when interpreting the results causally. Full article

Aim: The research examined the relationship between SLC6A3 3′-UTR and intron 8 VNTR polymorphisms and their influence on supra-second time estimation performance and EEG alpha band activity. Material and methods: A total of 178 male participants (aged 18 to 32 years) underwent genotyping for the SLC6A3 3′-UTR and intron 8 VNTR polymorphisms. An electroencephalographic assessment was conducted targeting the dorsolateral prefrontal cortex (DLPFC), simultaneously with the time estimation task. The 3′-UTR and intron 8 VNTRs polymorphisms were linked to absolute error and ratio in a time estimation task (target duration: 1 s, 4 s, 7 s, and 9 s) neurophysiological variable. Results: Regarding the absolute error and ratio, the combinatory effect of SLC6A3 3′-UTR and intron 8 VNTRs showed a difference in the interpretation of time only for 1 s (p = 0.0002). In the EEG alpha power, the analysis revealed a difference only for the left DLPFC (p = 0.0002). Conclusions: Electrophysiological and behavioral investigation in the time perception associated with the SLC6A3 gene suggests an alternative evaluation of neurobiological aspects inbuilt in timing. The 3′-UTR and intron 8 VNTR polymorphisms modulate dopaminergic neurotransmission during short-temporal scale judgment in the domain of supra seconds and indicate a role in its inputs to the left dorsolateral prefrontal cortex during the voluntary attention processes for visual stimulus. Our findings demonstrate that cognitive resources to capture and store time intervals can be measured based on the EEG power activity pattern. Full article

Supervised learning models in healthcare and other domains heavily depend on high-quality, labeled data. However, acquiring expert-verified labels (i.e., the gold standard) is often impractical due to cost, time, and subjectivity. Crowdsourcing offers a scalable alternative by collecting labels from multiple non-expert annotators; however, it introduces label noise due to the heterogeneity of annotators. In this work, we propose CrowdAttention, a novel end-to-end deep learning framework that jointly models classification and annotator reliability using a cross-attention mechanism. The architecture consists of two coupled networks: a classification network that estimates the latent true label, and a crowd network that assigns instance-dependent reliability scores to each annotator’s label based on its alignment with the model’s current prediction. We demonstrate the effectiveness of our approach on both synthetic and real-world datasets, showing improved accuracy and robustness compared to state-of-the-art multi-annotator learning methods. Full article

Background: Adolescent depression is highly prevalent in low- and middle-income countries (LMICs). Identifying top key risk factors is necessary to inform effective prevention program design. Machine learning (ML) offers a powerful approach to analyze complex multidomain of data to identify the most relevant predictors and estimate risks for mental health problems. This paper applies ML to study risks for adolescent depression to enhance adolescent depression prevention efforts in LMICs. Methods: Six ML approaches (e.g., Explainable Boosting Machine, random forests, and XGBoost) were applied to study the risks of depression. Data were drawn from a digital health intervention study conducted in Kenya (year 2024–2025, n = 269). Multiple domains of childhood and adolescent adversity and stress experiences were used to predict adolescent depression (using PHQ9-A). Findings: We found that ML was a valuable approach in the early identification of adolescents at risk for depression. Among the six ML approaches applied, the random forest approach outperformed other ML approaches, especially when multiple domains of risks were included. We also found that childhood adversity or home adversity alone were not strong predictors for depression. Adding adolescent stress experiences and community school adversity experiences significantly improves the accuracy and predictability of depression. Using the top-15 and top-20 ranking factors, we achieved 74.8% and 75.1% accuracy in depression prediction, which was similar to the accuracy when all 49 adverse/stress factors were included in the predictive model (78.3%). Conclusions: Innovative ML and modern predictive modeling approaches have the potential to transform modern preventive mental health care by better utilizing multidomain data to identify individuals at risk for developing depression early and identify top risk factors (for targeted individuals and/or populations). Findings from ML can inform tailored intervention design to better mitigate risks in order to prevent depression problem development. They can also inform the better utilization of resources to target high-need cases and key determinants, which is particularly useful for LMICs and low-resource settings. This paper illustrates an example of how to move toward this direction. Future research is needed to validate the approach. Full article

Recent advances in hyperspectral imaging (HSI) and multimodal deep learning have opened new opportunities for crop health analysis; however, most existing models remain limited by dataset scope, lack of interpretability, and weak cross-domain generalization. To overcome these limitations, this study introduces Agri-DSSA, a novel Dual Self-Supervised Attention (DSSA) framework that simultaneously models spectral and spatial dependencies through two complementary self-attention branches. The proposed architecture enables robust and interpretable feature learning across heterogeneous data sources, facilitating the estimation of spectral proxies of chlorophyll content, plant vigor, and disease stress indicators rather than direct physiological measurements. Experiments were performed on seven publicly available benchmark datasets encompassing diverse spectral and visual domains: three hyperspectral datasets (Indian Pines with 16 classes and 10,366 labeled samples; Pavia University with 9 classes and 42,776 samples; and Kennedy Space Center with 13 classes and 5211 samples), two plant disease datasets (PlantVillage with 54,000 labeled leaf images covering 38 diseases across 14 crop species, and the New Plant Diseases dataset with over 30,000 field images captured under natural conditions), and two chlorophyll content datasets (the Global Leaf Chlorophyll Content Dataset (GLCC), derived from MERIS and OLCI satellite data between 2003–2020, and the Leaf Chlorophyll Content Dataset for Crops, which includes paired spectrophotometric and multispectral measurements collected from multiple crop species). To ensure statistical rigor and spatial independence, a block-based spatial cross-validation scheme was employed across five independent runs with fixed random seeds. Model performance was evaluated using $R^2$, RMSE, F1-score, AUC-ROC, and AUC-PR, each reported as mean ± standard deviation with 95% confidence intervals. Results show that Agri-DSSA consistently outperforms baseline models (PLSR, RF, 3D-CNN, and HybridSN), achieving up to $R^2=0.86$ for chlorophyll content estimation and F1-scores above 0.95 for plant disease detection. The attention distributions highlight physiologically meaningful spectral regions (550–710 nm) associated with chlorophyll absorption, confirming the interpretability of the model’s learned representations. This study serves as a methodological foundation for UAV-based and field-deployable crop monitoring systems. By unifying hyperspectral, chlorophyll, and visual disease datasets, Agri-DSSA provides an interpretable and generalizable framework for proxy-based vegetation stress estimation. Future work will extend the model to real UAV campaigns and in-field spectrophotometric validation to achieve full agronomic reliability. Full article

Unmanned aerial vehicle (UAV)-assisted wireless communication systems often employ the carrier aggregation (CA) technique to alleviate the issue of insufficient bandwidth. However, in high-mobility UAV communication scenarios, the dynamic channel characteristics pose significant challenges to channel estimation (CE). Given these challenges, this paper proposes a line-of-sight (LoS) and echo sensing-based CE scheme for CA-enabled UAV-assisted communication systems. Firstly, LoS sensing and echo sensing are employed to obtain sensing-assisted prior information, which refines the CE for the primary component carrier (PCC). Subsequently, the path-sharing property between the PCC and secondary component carriers (SCCs) is exploited to reconstruct SCC channels in the delay-Doppler (DD) domain through a three-stage process. The simulation results demonstrate that the proposed method effectively enhances the CE accuracy for both the PCC and SCCs. Furthermore, the proposed scheme exhibits robustness against parameter variations. Full article

Short sleep duration (≤6 h) is a public health concern linked to cardiometabolic disease and premature mortality. However, persistent disparities across sociodemographic, psychosocial, and structural domains remain underexplored in recent nationally representative samples. We analyzed 2022 Behavioral Risk Factor Surveillance System (BRFSS) data, including 228,463 adults (weighted N ≈ 122 million). Sleep duration was dichotomized as short (≤6 h) versus adequate (≥7 h). Complex samples logistic regression estimated associations between sociodemographic, psychosocial, behavioral, and structural determinants and short sleep, accounting for survey design. The weighted prevalence of short sleep was 33.2%. Non-Hispanic Black (AOR = 1.56, 95% CI: 1.46–1.65) and American Indian/Alaska Native adults (AOR = 1.46, 95% CI: 1.29–1.65) were disproportionately affected compared with non-Hispanic White adults. Psychosocial factors contributed strongly: life dissatisfaction, limited emotional support, and low social connectedness increased odds, whereas high connectedness was protective. Food insecurity and smoking were significant structural and behavioral risks, while binge drinking and urbanicity were not. One-third of U.S. adults report short sleep, with marked disparities across demographic, socioeconomic status, psychosocial stressors, and structural barriers. Findings highlight the multifactorial nature of sleep health inequities and the need for multilevel interventions addressing both individual behaviors and upstream determinants. Full article

The adoption of artificial intelligence (AI) in healthcare requires not only accurate predictions but also a clear understanding of its reliability. In safety-critical domains such as medical imaging and diagnosis, clinicians must assess the confidence in model outputs to ensure safe decision making. Uncertainty quantification (UQ) addresses this need by providing confidence estimates and identifying situations in which models may fail. Such uncertainty estimates enable risk-aware deployment, improve model robustness, and ultimately strengthen clinical trust. Although prior studies have surveyed UQ in centralized learning, a systematic review in the federated learning (FL) context is still lacking. As a privacy-preserving collaborative paradigm, FL enables institutions to jointly train models without sharing raw patient data. However, compared with centralized learning, FL introduces more complex sources of uncertainty. In addition to data uncertainty caused by noisy inputs and model uncertainty from distributed optimization, there also exists distributional uncertainty arising from client heterogeneity and personalized uncertainty associated with site-specific biases. These intertwined uncertainties complicate model reliability and highlight the urgent need for UQ strategies tailored to federated settings. This survey reviews UQ in medical FL. We categorize uncertainties unique to FL and compare them with those in centralized learning. We examine the sources of uncertainty, existing FL architectures, UQ methods, and their integration with privacy-preserving techniques, and we analyze their advantages, limitations, and trade-offs. Finally, we highlight key challenges—scalable UQ under non-IID conditions, federated OOD detection, and clinical validation—and outline future opportunities such as hybrid UQ strategies and personalization. By combining methodological advances in UQ with application perspectives, this survey provides a structured overview to inform the development of more reliable and privacy-preserving FL systems in healthcare. Full article

In tightly coupled Industrial Control Systems (ICS), abnormal disturbances often propagate throughout the process, triggering a large number of time-correlated alarms that exceed the handling capacity of the operator. Consequently, a key challenge is how to leverage the directional and temporal characteristics of disturbance propagation to alleviate alarm overload. This paper proposes a delay-sensitive causal inference approach for industrial alarm analysis to address this problem. On the one hand, time delay estimation is introduced to precisely align the responses of two sensor sequences to disturbances, thereby improving the accuracy of causal relationship identification in the temporal domain. On the other hand, a multi-scale subgraph fusion strategy is designed to address the inconsistency in causal strength caused by disturbances of varying intensities. By integrating significant causal subgraphs from multiple scenarios into a unified graph, the method reveals the overall causal structure among alarm variables and provides guidance for alarm mitigation. To validate the proposed method, a case study is conducted on the Tennessee Eastman Process. The results demonstrate that the approach identifies causal relationships more accurately and reasonably and can effectively reduce the number of alarms by up to 51.6%. Full article

When the spaceborne satellite target rotates non-uniformly relative to the ladar, the high-order space-variant phase will be introduced into the echo phase along both the range and azimuth direction, which will cause the degree of defocusing of the scatterers on the target to rely on their locations. Traditional imaging algorithms usually assume that the target is in uniform motion and only compensate for second-order phase errors, ignoring spatial phase variations caused by higher-order non-uniform rotation. Consequently, these algorithms are ineffective in accurately focusing on edge scatterers, leading to image blurring at the target boundaries. To solve this problem, an ISAL imaging algorithm for spaceborne non-uniformly rotating targets based on matched Fourier transform (MFT) and a genetic algorithm is proposed in this paper. First, the echo signal model of the non-uniform rotation target is established. Second, the corresponding higher-order space-variant phase compensation method based on the estimated parameters is proposed, with time-domain higher-order phase compensation along the range direction and MFT algorithm along the azimuth direction. Then, the genetic algorithm is employed for parameter estimation. Finally, the results obtained from both simulation experiments and real data experiments verify that the proposed algorithm has good compensation accuracy and robustness. Full article