Search Results (3,852)

The growing penetration of photovoltaic (PV) generation in multi-energy microgrids has amplified the challenges of maintaining real-time operational efficiency, reliability, and safety under conditions of renewable variability and forecast uncertainty. Conventional rule-based or optimization-based strategies often suffer from limited adaptability, while purely data-driven reinforcement learning approaches risk violating physical feasibility constraints, leading to unsafe or economically inefficient operation. To address this challenge, this paper develops a Physics-Informed Reinforcement Learning (PIRL) framework that embeds first-order physical models and a structured feasibility projection mechanism directly into the training process of a Soft Actor–Critic (SAC) algorithm. Unlike traditional deep reinforcement learning, which explores the state–action space without physical safeguards, PIRL restricts learning trajectories to a physically admissible manifold, thereby preventing battery over-discharge, thermal discomfort, and infeasible hydrogen operation. Furthermore, differentiable penalty functions are employed to capture equipment degradation, user comfort, and cross-domain coupling, ensuring that the learned policy remains interpretable, safe, and aligned with engineering practice. The proposed approach is validated on a modified IEEE 33-bus distribution system coupled with 14 thermal zones and hydrogen facilities, representing a realistic and complex multi-energy microgrid environment. Simulation results demonstrate that PIRL reduces constraint violations by 75–90% and lowers operating costs by 25–30% compared with rule-based and DRL baselines while also achieving faster convergence and higher sample efficiency. Importantly, the trained policy generalizes effectively to out-of-distribution weather conditions without requiring retraining, highlighting the value of incorporating physical inductive biases for resilient control. Overall, this work establishes a transparent and reproducible reinforcement learning paradigm that bridges the gap between physical feasibility and data-driven adaptability, providing a scalable solution for safe, efficient, and cost-effective operation of renewable-rich multi-energy microgrids. Full article

Background/Objectives: Sleep disturbances are recognized as a common feature of Long COVID but detailed investigation into the specific nature of these sleep symptoms remain limited. This study analyzes comprehensive sleep questionnaire data from a Long COVID clinic to better characterize the nature and prevalence of sleep complaints in this population. Methods: We conducted a cross-sectional analysis of 200 adults referred to the Stanford Long COVID Clinic. Patients completed an intake questionnaire including three sleep-related items (unrefreshing sleep, insomnia, daytime sleepiness) rated on a 0–5 Likert scale. Additionally, patients completed the Alliance Sleep Questionnaire (ASQ), incorporating the Insomnia Severity Index, Epworth Sleepiness Scale, reduced Morningness–Eveningness Questionnaire, and modules for parasomnia, restless legs, and breathing symptoms. We calculated the prevalence of six sleep symptom domains. Standardized symptom data were analyzed using principal component analysis (PCA) and K-means clustering (k = 2) to explore latent phenotypes and used logistic regression to assess associations between demographic and clinical variables and each sleep complaint. Results: Sleep-related breathing complaints affected 57.5% of participants, insomnia 42.5%, and excessive daytime sleepiness 28.5%. Parallel analysis supported a nine-factor structure explaining ~90% of variance, with varimax rotation yielding interpretable domains such as insomnia/unrefreshing sleep, fatigue/post-exertional malaise, parasomnias, and respiratory symptoms. Gaussian mixture modeling favored a two-cluster solution (n = 94 and n = 106); one cluster represented a higher-burden phenotype characterized by greater BMI, insomnia, daytime sleepiness, gastrointestinal symptoms, and parasomnias. Logistic models using factor scores predicted insomnia with high accuracy (AUC = 0.90), EDS moderately well (AUC = 0.81), but extreme chronotype poorly (AUC = 0.39). In adjusted models, hospitalization during acute COVID-19 was significantly associated with insomnia (OR 4.41; 95% CI 1.27–15.36). Participants identifying as multiracial had higher odds of insomnia (OR 3.22; 95% CI 1.00–10.34), though this narrowly missed statistical significance. No other predictors were significant. Conclusions: Sleep disturbances are frequent and diverse in Long COVID. Factor analysis showed overlapping domains, while clustering identified a higher-burden phenotype marked by more severe sleep and systemic complaints. Symptom-based screening may help target those at greatest risk. Full article

Water conveyance channels, as critical components of water diversion projects, feature numerous structures, complex configurations, and intensive operational management requirements, making them vulnerable to multiple risks, such as extreme flooding, channel blockage, structural failures, and management deficiencies. To ensure an accurate assessment of the operational safety risk, this study proposes a comprehensive risk assessment framework that integrates risk probability and risk loss. The former is quantified using the Consequence Reverse Diffusion Method (CRDM), which systematically identifies and categorizes key factors of primary dike failure modes into four domains: hydrological characteristics, channel morphology, engineering structures, and operational management. The latter is assessed by integrating socioeconomic impacts, including population exposure, infrastructure investment, and industrial and agricultural production. A structured assessment framework is established through systematic indicator selection, justified weight assignment, and standardized scoring criteria. Application of the framework to Yangtze-to-Huaihe Water Diversion Project (Henan Reach) reveals that the risk probability across four segments falls within the (1, 3) range, indicating a generally low to moderate risk profile, while channel morphology shows greater spatial variability than hydrological, structural, and management indicators, driven by local differences in crossing structure density, sinuosity, and regime coefficients. Meanwhile, the segments along the Qingshui River face higher risk losses owing to their upstream location and large-scale water supply capacity, resulting in a relatively higher comprehensive risk level. Full article

Background: Older adults are highly vulnerable to infectious diseases due to immunosenescence, multimorbidity, and atypical presentations. Artificial intelligence (AI) offers promising opportunities to improve diagnosis, prognosis, treatment, and continuity of care in this population. This review summarizes current applications of AI in the management of infections in older adults across diagnostic, prognostic, therapeutic, and preventive domains. Methods: We conducted a narrative review of peer-reviewed studies retrieved from PubMed, Scopus, and Web of Science, focusing on AI-based tools for infection diagnosis, risk prediction, antimicrobial stewardship, prevention of healthcare-associated infections, and post-discharge care in individuals aged ≥65 years. Results: AI models, including machine learning, deep learning, and natural language processing techniques, have demonstrated high performance in detecting infections such as sepsis, pneumonia, and healthcare-associated infections (Area Under the Curve AUC up to 0.98). Prognostic algorithms integrating frailty and functional status enhance the prediction of mortality, complications, and readmission. AI-driven clinical decision support systems contribute to optimized antimicrobial therapy and timely interventions, while remote monitoring and telemedicine applications support safer hospital-to-home transitions and reduced 30-day readmissions. However, the implementation of these technologies is limited by the underrepresentation of frail older adults in training datasets, lack of real-world validation in geriatric settings, and the insufficient explainability of many models. Additional barriers include system interoperability issues and variable digital infrastructure, particularly in long-term care and community settings. Conclusions: AI has strong potential to support predictive and personalized infection management in older adults. Future research should focus on developing geriatric-specific, interpretable models, improving system integration, and fostering interdisciplinary collaboration to ensure safe and equitable implementation. Full article

Background/Objectives: The neonatal and infant periods represent a critical window for brain development, characterized by rapid and heterogeneous processes such as myelination and cortical maturation. Accurate assessment of these changes is essential for understanding normative trajectories and detecting early abnormalities. While conventional MRI provides valuable insights, automated classification remains challenging due to overlapping developmental stages and sex-specific variability. Methods: We propose SEPoolConvNeXt, a novel deep learning framework designed for fine-grained classification of neonatal brain development using T1- and T2-weighted MRI sequences. The dataset comprised 29,516 images organized into four subgroups (T1 Male, T1 Female, T2 Male, T2 Female), each stratified into 14 age-based classes (0–10 days to 12 months). The architecture integrates residual connections, grouped convolutions, and channel attention mechanisms, balancing computational efficiency with discriminative power. Model performance was compared with 19 widely used pre-trained CNNs under identical experimental settings. Results: SEPoolConvNeXt consistently achieved test accuracies above 95%, substantially outperforming pre-trained CNN baselines (average ~70.7%). On the T1 Female dataset, early stages achieved near-perfect recognition, with slight declines at 11–12 months due to intra-class variability. The T1 Male dataset reached >98% overall accuracy, with challenges in intermediate months (2–3 and 8–9). The T2 Female dataset yielded accuracies between 99.47% and 100%, including categories with perfect F1-scores, whereas the T2 Male dataset maintained strong but slightly lower performance (>93%), especially in later infancy. Combined evaluations across T1 + T2 Female and T1 Male + Female datasets confirmed robust generalization, with most subgroups exceeding 98–99% accuracy. The results demonstrate that domain-specific architectural design enables superior sensitivity to subtle developmental transitions compared with generic transfer learning approaches. The lightweight nature of SEPoolConvNeXt (~9.4 M parameters) further supports reproducibility and clinical applicability. Conclusions: SEPoolConvNeXt provides a robust, efficient, and biologically aligned framework for neonatal brain maturation assessment. By integrating sex- and age-specific developmental trajectories, the model establishes a strong foundation for AI-assisted neurodevelopmental evaluation and holds promise for clinical translation, particularly in monitoring high-risk groups such as preterm infants. 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

Background: Functional lumbar segmental instability (FLSI) is a clinically significant subtype of nonspecific low back pain, characterized by impaired motor control during mid-range spinal motion. Despite its prevalence, diagnostic approaches remain fragmented, and no single clinical test reliably captures its complexity. This scoping review aims to synthesize current evidence on the reliability, validity, subclassification, and predictive value of manual tests used in the evaluation of FLSI, and to identify conceptual and methodological gaps in the literature. Methods: A structured search was conducted across five databases (PubMed, Scopus, Web of Science, CINAHL, Embase) between May and August 2025. Twenty-four empirical studies and eleven foundational conceptual sources were included. Data were charted into five thematic domains: conceptual frameworks, diagnostic accuracy, reliability, subclassification models, and predictive value. Methodological appraisal was performed using QUADAS and QAREL tools. Results: The Passive Lumbar Extension Test (PLET) demonstrated the most consistent reliability and clinical utility. The Prone Instability Test (PIT) and Posterior Shear Test (PST) showed variable performance depending on protocol standardization. Subclassification models distinguishing functional, structural, and combined instability achieved high inter-rater agreement. Screening tools for sub-threshold lumbar instability (STLI) showed preliminary feasibility. Predictive validity of manual tests for rehabilitation outcomes was inconsistent, suggesting the need for multivariate models. Conclusions: Manual tests can support the clinical evaluation of FLSI when interpreted within structured diagnostic frameworks. Subclassification models and composite test batteries enhance diagnostic precision, but standardization and longitudinal validation remain necessary. Future research should prioritize protocol harmonization, integration of sensor-based technologies, and stratified outcome studies to guide individualized rehabilitation planning. Full article

To address the challenge of high wind speed variability in wind farm planning, a small-sample-based spatio-temporal fusion and compression deep residual point prediction model, STiCDRS (Spatio-Temporal integration and Compression Deep Residual), is proposed. This model is designed to deeply explore the spatial and temporal characteristics within wind speed sequences to enhance the accuracy of point predictions. Initially, the spatio-temporal integration and compression deep residual network is employed to obtain point prediction results. Subsequently, an innovative hybrid model, STiCDRS-NKDE (STiCDRS-Nonparametric Kernel Density Estimation), is introduced to achieve interval predictions, thereby providing more reliable probabilistic forecasts of wind speed. The hyper-parameters of the model are optimized using Bayesian optimization, ensuring efficient and automated tuning. Finally, a case study involving wind speed forecasting at a wind farm in Inner Mongolia, China, is conducted, comparing the performance of the STiCDRS model with traditional models. Experimental results demonstrate that in comparison to other models, the proposed STiCDRS-NKDE model delivers superior point prediction accuracy, appropriate interval predictions, and reliable probabilistic forecasting outcomes, fully showcasing its significant potential in the domain of wind speed forecasting. Full article

Tall-pier, long-span continuous rigid-frame bridges are prone to wind-induced vibration due to their large spans and pier heights; during cantilever erection, the maximum double-cantilever stage has reduced stiffness and buffeting becomes more evident. Accordingly, a time-domain framework driven by three-component aerodynamic coefficients and their angle-of-attack derivatives is adopted. Code-based target spectra are used to synthesize multi-point fluctuating wind time histories via harmonic superposition, followed by statistical and spectral consistency checks. Buffeting forces are then computed under the quasi-steady assumption, mapped to finite-element nodes, and integrated in time to obtain global responses (displacement and acceleration). In parallel, static six-component wind tunnel tests provide mean force and moment coefficients and their derivatives for comparison. The results indicate that the three-component time-domain approach captures the buffeting features dominated by vertical and torsional responses. When pronounced along-span sectional variation and high angle-of-attack sensitivity are present, errors associated with the strip assumption increase, whereas the force–moment coupling revealed by the six-component data helps explain discrepancies between simulation and tests. These response patterns and error characteristics delineate the applicability and limits of the three-component time-domain evaluation for variable-depth continuous rigid-frame bridges, offering a reference for wind resistance assessment and construction-stage checking of similar bridges. Full article

This study investigates the dynamic relationship between interest and noninterest income at Azer Turk Bank using quarterly data from 2016Q1–2024Q3. Unit root tests including Augmented Dickey–Fuller (ADF), Kwiatkowski–Phillips–Schmidt–Shin (KPSS), and Fourier–KPSS indicate that both variables are non-stationary in levels but become stationary after first differencing. The Hylleberg–Engle–Granger–Yoo (HEGY) test further shows that both series contain a unit root at the non-seasonal (0) frequency, while no unit roots are detected at the seasonal frequencies (π/2 and 3π/2). Johansen cointegration and the Fourier Autoregressive Distributed Lag (Fourier–ADL) framework confirm the existence of a stable long-run equilibrium. As a key methodological contribution, the study derives explicit Fourier-based Vector Error Correction Model (VECM) equations, enabling the modeling of cyclical deviations around nonlinear trends. Fourier Toda–Yamamoto and Breitung–Candelon frequency-domain causality tests reveal asymmetry: interest income consistently drives noninterest income in the short and medium run, whereas the reverse effect is weak. The results also confirm mean reversion, with deviations from equilibrium corrected within 5.9; 2.5 quarters. Overall, the findings highlight the limited diversification potential of noninterest income and the decisive role of lending in bank revenues, offering both methodological advances and practical guidance for macroprudential policy. Full article

This paper presents the development and evaluation of a method for rendering realistic haptic textures in virtual environments, with the goal of enhancing immersion and surface recognizability. By using Blender for the creation of geometric models, Unity for real-time interaction, and integration with the Touch haptic device from 3D Systems, virtual surfaces were developed with parameterizable characteristics of friction, stiffness, and relief, simulating different physical textures. The methodology was assessed through two experimental phases involving a total of 47 participants, examining both tactile recognition accuracy and the perceived realism of the textures. Results demonstrated improved overall performance and reduced variability between textures, suggesting that the approach can provide convincing haptic experiences. The proposed method has potential applications across a wide range of domains, including education, medical simulation, cartography, e-commerce, entertainment, and artistic creation. The main contribution of this research lies in the introduction of a simple yet effective methodology for haptic texture rendering, which is based on the flexible adjustment of key parameters and iterative optimization through human feedback. Full article

As artificial intelligence (AI) technology becomes increasingly prevalent in the tourism sector, an in-depth exploration of its opportunities and potential risks for the United Nations Sustainable Development Goals (SDGs) is urgently needed. However, existing research falls short in constructing an integrated knowledge framework that systematically clarifies how AI can effectively advance sustainable tourism, leaving theoretical understanding and practical pathways relatively fragmented. To address this gap, this study employs a systematic literature review following the strict SPAR-4-SLR protocol and integrates a domain-based TCCM (i.e., theories, contexts, characteristics, and methods) analysis framework. A total of 177 core articles from the Scopus and Web of Science databases were rigorously analyzed. This study first examines publication trends, key journals, and the citation impact of AI in tourism. It then systematically synthesizes the theoretical foundations, research contexts, characteristics, and methodologies. Most importantly, this review delves into the antecedents, decision-making processes (including mediating and moderating variables), and outcomes of AI applications in the tourism industry. This study not only delineates a clear direction and agenda for future academic inquiry but also provides theoretical support and practical guidance for policymakers and tourism managers to design and implement AI-driven sustainable tourism strategies. Full article

Coastal upwelling off La Guajira, Colombia, is an atypical system where persistent easterly winds drive upwelling along a zonally oriented coastline. To characterize its seasonal cycle and variability, the ROMS AGRIF hydrodynamic model was implemented under climatological forcing. Three indicators were analyzed: the 25 °C isotherm, the 36.5 isohaline, and sea-level anomalies. The simulations showed that upwelling initiates in December, reaches maximum intensity during February–April, and weakens from September to November. At maturity, vertical velocities up to 8.5 m·day⁻¹ and the shoaling of Subtropical Underwater (T = 22–25 °C; S = 36.5–37.0) dominate the coastal domain, producing widespread surface cooling (23–24 °C) and salinity enhancement. During relaxation, weaker winds and the influence of the Caribbean Coastal Undercurrent displace the upwelled waters to below 80–100 m in depth, with surface temperatures above 27 °C. Model performance against MODIS Aqua SST was high (d > 0.99; RMSE < 1.7 °C), confirming its reliability to reproduce the observed thermal cycle. The multiparametric approach reveals that upwelling persistence depends on both seasonal trade wind forcing and regional circulation. This framework provides a more integrated description of the Guajira upwelling system than previous studies and supports applications in fisheries management, ecosystem monitoring, and maritime operations. Full article

Generative Artificial Intelligence (GAI) is gaining increasing attention as a catalyst for advancing sustainability within project management for buildings and infrastructure. This paper systematically reviews 173 peer-reviewed publications, including 142 journal and conference papers, to examine the current research landscape. Bibliometric mapping and thematic synthesis reveal expanding applications of GAI in project planning, design optimization, risk management, and sustainability assessment, but adoption remains fragmented across regions and domains. This review identifies persistent challenges that constrain large-scale implementation, including data variability and interoperability gaps, high computational demand, limited regulatory alignment, and ethical and governance concerns, coupled with the absence of standardized evaluation metrics. In response, this paper outlines future research prospects through a structured agenda that emphasizes scalable and generalizable AI models, real-time integration with IoT and digital twins, explainable and secure AI systems, and policy-aligned governance frameworks. These priorities aim to strengthen environmental, social, and economic sustainability outcomes in the built environment. By clarifying current progress and knowledge gaps, this review supports both scholars and practitioners in strengthening the role of GAI in the built environment. Full article

Neuromorphic circuits emulate the brain’s massively parallel, energy-efficient, and robust information processing by reproducing the behavior of neurons and synapses in dense networks. Memristive technologies have emerged as key enablers of such systems, offering compact and low-power implementations. In particular, locally active memristors (LAMs), with their ability to amplify small perturbations within a locally active domain to generate action potential-like responses, provide powerful building blocks for neuromorphic circuits and offer new perspectives on the mechanisms underlying neuronal firing dynamics. This paper introduces a novel second-order locally active memristor (LAM) governed by two coupled state variables, enabling richer nonlinear dynamics compared to conventional first-order devices. Even when the capacitances controlling the states are equal, the device retains two independent memory states, which broaden the design space for hysteresis tuning and allow flexible modulation of the current–voltage response. The second-order LAM is then integrated into a FitzHugh–Nagumo neuron circuit. The proposed circuit exhibits oscillatory firing behavior under specific parameter regimes and is further investigated under both DC and AC external stimulation. A comprehensive analysis of its equilibrium points is provided, followed by bifurcation diagrams and Lyapunov exponent spectra for key system parameters, revealing distinct regions of periodic, chaotic, and quasi-periodic dynamics. Representative time-domain patterns corresponding to these regimes are also presented, highlighting the circuit’s ability to reproduce a rich variety of neuronal firing behaviors. Finally, two unknown system parameters are estimated using the Aquila Optimization algorithm, with a cost function based on the system’s return map. Simulation results confirm the algorithm’s efficiency in parameter estimation. Full article