Search Results (3,602)

Background: Exacerbations of chronic obstructive pulmonary disease (COPD) are a leading cause of morbidity, mortality, and healthcare burden worldwide. Early detection and timely intervention remain important challenges in COPD management, given the unpredictable nature of acute deterioration and limitations of traditional spirometry-based risk assessment. Methods: This narrative review synthesizes artificial intelligence (AI)-driven approaches for predicting and detecting chronic obstructive pulmonary disease (COPD) exacerbations across electronic health records, wearable sensors, imaging, environmental data, and patient-reported outcomes, emphasizing novel discoveries and emerging relationships rather than predictive performance. Results: Three major discoveries have been made. First, measurable physiological and behavioral deterioration may precede symptom recognition by approximately 7–14 days, thereby establishing a potential intervention window for anticipatory care. Second, machine learning (ML) models integrating pollutant exposure, medication adherence, and clinical characteristics have identified phenotypes with differential environmental sensitivity, including unexpected exposure–adherence interactions. Third, deep neural network analysis of full spirometry curves has revealed structural phenotypes beyond traditional Forced Expiratory Volume (FEV₁)-based measures and novel imaging biomarkers. The predictive performance ranges from the Area Under the Curve (AUC) 0.72–0.95, with a pooled meta-analytic AUC of approximately 0.77. Conclusions: AI has uncovered hidden patterns in the progression of COPD, supporting a shift from reactive to anticipatory management. Translation to routine care requires prospective validation, improved interpretability, workflow integration, and generalizability and equity. Full article

Bank telemarketing campaigns often experience low subscription rates due to customer heterogeneity and severe class imbalance, which pose challenges for reliable predictive modeling. This study investigates a data-driven approach that integrates synthetic minority oversampling and cost-sensitive learning to improve the prediction of telemarketing outcomes. Experiments are conducted using the Portuguese Bank Marketing dataset, comprising 41,188 instances with a positive response rate of 11.3%. Eight machine learning models are evaluated under a unified preprocessing pipeline and five-fold stratified cross-validation, including Logistic Regression, Decision Tree, Random Forest, and Ensemble methods. The results show that Ensemble models, particularly CatBoost, XGBoost, and LightGBM, achieve improved performance compared with traditional baselines, with notable gains in minority-class recall and overall discrimination ability. The best-performing model attains an F1-score of 0.540, a recall of 0.812 for the positive class, and a ROC–AUC of 0.908. To enhance interpretability, SHAP-based analysis is applied to quantify feature contributions, identifying campaign duration, previous contact outcomes, and selected macroeconomic indicators as key predictors. These findings indicate that combining resampling strategies with cost-sensitive optimization provides a robust and transparent approach for learning from imbalanced telemarketing data, thereby supporting reproducible and data-driven financial decision-making by explicitly addressing difficulty in minority-class identification under imbalance and class imbalance under cross-entropy training in imbalanced banking data. Full article

Olive pomace biochar, obtained through the pyrolysis of lignocellulosic biomass, has emerged as a sustainable and multifunctional additive for polymer composites. Its physicochemical properties, including porosity, surface area, and electrical conductivity, can be tailored by controlling feedstock type and pyrolysis conditions. Although mechanical reinforcement and thermal stability improvements are well documented, the influence of biochar on surface-related properties such as wettability and contact angle remains insufficiently explored for environmentally relevant composite systems. In this study, epoxy-based composites containing biochar synthesized at 750 °C were evaluated in terms of their water interaction behavior by monitoring the evaporation dynamics of ultra-pure water droplets (10 μL, 0.055 mS/cm conductivity) at eight time intervals between 20 and 580 s using high-resolution digital microscopy. Image enhancement and segmentation were performed prior to Discrete Cosine Transform (DCT) analysis to describe droplet geometry in the frequency domain. Time-dependent variations in the standard deviations of DCT coefficients were optimized using the Bat Algorithm, resulting in mathematical models capable of accurately representing droplet evolution and surface–fluid interactions. The primary novelty of this study lies in the development of a hybrid experimental–computational framework that integrates droplet-based wettability measurements with signal-domain analysis and metaheuristic optimization. Unlike conventional studies focusing solely on material characterization, this approach establishes quantitative relationships between surface behavior and numerical descriptors derived from DCT and the Bat Algorithm. The proposed methodology provides a data-driven tool for predicting wettability trends in biochar-reinforced composites and supports the development of moisture-resistant materials for coatings, packaging, and thermal insulation applications within the context of sustainable composite design. Full article

As social networks continue to expand, smart advertising increasingly depends on machine learning to deliver personalized and effective advertisements. Federated Learning (FL) is a distributed learning paradigm that supports privacy-preserving advertising by training models locally while avoiding direct sharing of raw user data. However, ensuring the correctness, reliability, and operational robustness of FL-driven smart advertising systems remains a significant challenge, particularly in distributed and user-facing environments. In this study, we investigate the use of model checking as a formal verification technique for validating key properties of an FL-based smart advertising workflow in social networks. We combine a structured finite-state modeling approach with Linear Temporal Logic (LTL) specifications and model-checking tools to assess correctness, availability, and baseline privacy requirements. Using controlled simulation-based configurations, we show that, for a setup with 100 users and 20 edge servers, the system delivers advertisements to all users and the global model successfully processes 200 out of 200 requests. We further analyze verification overhead through detection-time measurements, observing an increase in average detection time from 10.05 s to 11.98 s as the number of users rises from 20 to 100. These results indicate that the proposed framework can provide practical assurance for FL-enabled smart advertising workflows, support more reliable deployment in distributed intelligent systems, and improve trustworthiness in real advertising applications. Full article

With the increasing prevalence of neurodegenerative diseases driven by population aging, imaging-based biomarkers are needed to quantify brain aging at an early stage. Brain age, which estimates structural brain aging relative to chronological age, has emerged as a useful indicator. Prior work has mainly used T1-weighted MRI with deep learning models such as convolutional neural networks (CNNs) or transformers; however, many approaches insufficiently capture three-dimensional structural continuity and localized anatomical patterns, and tissue-specific aging in gray matter (GM) and white matter (WM) is often treated as auxiliary. To address these limitations, we propose a 3D Global–Patch Transformer framework for brain age prediction that directly processes volumetric data while jointly learning global brain structure and local anatomical features. Our model runs global and patch pathways in parallel and explicitly incorporates GM and WM structural maps alongside T1-weighted MRI to encode tissue-specific aging signals. Experiments on multiple public datasets, including IXI and OASIS, show that the proposed method reduces mean absolute error (MAE) by approximately 10–15% compared with CNN-based and single-input transformer baselines, with notably improved performance in older populations, highlighting the value of tissue-level structural information for brain age estimation. Full article

The increasing complexity and uncertain system of modern discrete event system (DES) challenge traditional model-based control approaches, while artificial intelligence (AI) techniques offer powerful data-driven decision-making capabilities but lack formal guarantees. This review surveys recent research on the integration of AI with DES and supervisory control theory. Following a systematic literature mapping methodology, the literature is organized using a taxonomy based on three orthogonal perspectives: control and decision paradigm, system capability and property, and application and operational objectives. The review highlights how learning-based methods enhance adaptability and performance in DES, while also exposing persistent challenges related to safety, nonblocking behavior, data efficiency, and interpretability. By structuring existing approaches and identifying open issues, this review provides a coherent overview of the current research landscape and outlines key directions for future work on AI-enabled DES. Full article

Electromagnetic field-based stimulation has emerged as a promising noninvasive approach for enhancing bone fracture healing. Beyond conventional pulsed electromagnetic field (PEMF) therapies employing spatially uniform fields, dielectrophoretic-force-based (DEPF) stimulation exploits electromagnetic field non-uniformities to induce localized interactions to enhance fracture healing. However, the thermal behavior associated with DEPF-driven PEMF exposure in the presence of metallic orthopedic implants remains largely unexplored. In this study, the thermal response of tissue-like tibia phantoms with and without metallic implants is investigated using an integrated experimental and numerical framework. A custom-designed conical coil is employed to generate non-uniform DEPF excitation capable of affecting the fracture site. Surface temperature evolution is measured using infrared thermal imaging, while electromagnetic power absorption is quantified through specific absorption rate (SAR)-based thermal measurement coupled with a bio-heat formulation. Anatomically realistic tibia phantoms reconstructed from computed tomography data are fabricated via a 3D printer to represent clinically relevant fracture configurations. Experimental results show that the metallic implant exhibits a rapid temperature increase of approximately $0.4 °\mathrm{C}$ within the first few minutes of exposure, followed by thermal stabilization, corresponding to an effective absorbed power of ${\mathrm{SAR}}_{\mathrm{eff},\mathrm{implant}}\approx 2.2 \mathrm{W}/\mathrm{kg}$ inferred from the initial temperature slope. In contrast, the non-conductive resin phantom displays a temperature rise of only $0.05 °\mathrm{C}$ over the same interval, yielding ${\mathrm{SAR}}_{\mathrm{eff},\mathrm{resin}}\approx 0.8 \mathrm{W}/\mathrm{kg}$. These findings demonstrate that implant-related eddy-current losses dominate localized heating under DEPF excitation, while tissue-like media remain weakly affected. This work provides SAR-based experimental evaluation of DEPF stimulation in implanted tibia fracture models, offering new insight into implant-induced electromagnetic heating and its implications for the safety and optimization of DEPF-based bone-healing therapies. Full article

Background: Chronic kidney disease (CKD) and end-stage renal disease (ESRD) represent a growing global health burden, affecting nearly one in ten adults worldwide. CKD is associated with high morbidity, premature mortality, reduced quality of life and enormous healthcare costs, and is primarily driven by dialysis and kidney transplantation. The silent and progressive nature of CKD means that most patients are diagnosed late, when irreversible damage has already occurred and costly kidney replacement therapies (KRT) become necessary. Dialysis services are resource-intensive, requiring significant infrastructure, specialized staff, and consumables, which makes them especially challenging to sustain in low- and middle-income countries. Traditional models of nephrology, care center-based dialysis and fragmented follow-up are increasingly inadequate in meeting the demands of a rising CKD population. These challenges highlight the urgent need for innovative approaches that enhance efficiency, improve patient outcomes, and expand access. Objective: This review aims to analyze the current landscape of information and communication technology (ICT) applications in nephrology and to evaluate how digital innovations are reconfiguring kidney therapy. Specifically, it seeks to identify the major ICT tools that are currently in use, assess their clinical and operational impact, and discuss their role in creating more sustainable, patient-centered kidney care models. This study reviews and analyzes ICT tools that are reconfiguring nephrology, including remote monitoring, AI, wearables, patient engagement apps and data dashboards. Methods: Narrative and scoping review of recent innovations in nephrology, including remote patient monitoring (RPM), telehealth, artificial intelligence (AI) analytics, wearable sensors, and clinical decision support platforms. Results: ICT tools such as Sharesource, Versia, telenephrology platforms, medical assistant for Chronic Care Service (MACCS), AI-based predictive analytics, wearable devices and patient engagement apps have improved patient outcomes, adherence, and early detection of complications. Key metrics include technique survival, hospitalization rate, patient-reported outcomes, workflow efficiency, and prediction accuracy. The relevant literature describing the potential of digital health technologies, including ICT platforms, artificial intelligence tools, and remote monitoring systems, to transform nephrology care was retrieved and screened for inclusion in this narrative review. Conclusions: ICT has shifted nephrology from reactive to proactive care, enhancing accessibility, patient empowerment and clinical efficiency. Future directions include precision nephrology, fully wearable kidneys, AI integration and large language models for education and triage. Challenges include digital divide, regulatory heterogeneity, cost and the need for long-term evidence. Full article

With the rapid development of technology and increasing material consumption, the efficient management of waste streams has become a critical challenge within the circular economy, particularly in resource-intensive sectors such as electronic waste recycling. This study examines how artificial intelligence can improve the assessment and forecasting of circular economy investment efficiency, with particular attention paid to resource-intensive sectors such as electronic waste recycling. The study reviews data from European Union countries for the period 2010–2024, including economic, technological, and environmental indicators. A machine learning model system based on ensemble predictive methods was developed to assess the effectiveness of circular economy investments. The results show that artificial intelligence-based models have higher forecasting accuracy than traditional econometric methods, and the most important factors determining investment efficiency are the level of automation, recycling efficiency, and the stringency of environmental policies. The study provides a new, data-driven methodological approach to assessing circular economy investments and discusses their implications for sustainable real estate development and resource management. Full article

The discharge of untreated paper mill effluent poses significant ecological risks due to its high organic and nutrient loads. This study aimed to assess the phytoremediation potential of Azolla pinnata for treating paper mill effluent. Response Surface Methodology (RSM) and Artificial Neural Network (ANN) modeling approaches were applied and optimization was used for pollutant removal and plant biomass production. Experiments were designed using a Central Composite Design with two independent variables: effluent concentration (0, 50, and 100%) and plant density (10, 20, and 30 g per container). The responses measured were biochemical oxygen demand (BOD), chemical oxygen demand (COD) removal efficiencies, and final biomass yield after 16 days of exposure. RSM produced statistically significant (p < 0.05) second-order regression models for all three responses (coefficient of determination; R² > 0.98), while ANN showed slightly lower prediction errors within the experimental range studied. Maximum observed removal efficiencies were 91.74% for BOD, 80.91% for COD, and 92.66 g biomass yield under 50% effluent concentration and 30 g plant density. Optimization via both models suggested closely comparable operating conditions (79% effluent concentration and 29 g biomass) for optimal performance. The results indicate that A. pinnata demonstrates potential as a low-cost, nature-based treatment system for industrial effluent remediation under controlled conditions. The integration of data-driven optimization with biological treatment contributes to sustainable effluent management strategies by reducing chemical inputs, minimizing energy demand, and enabling biomass generation with potential downstream valorization. Full article

Unsaturated polyester resin (UPR)–quartz composites have become increasingly important in structural, sanitary, and architectural applications. However, their manufacturing processes still rely heavily on empirical knowledge. This review compiles recent developments in materials science, curing kinetics, and digital manufacturing, outlining a pathway toward data-driven, adaptive production of quartz-filled thermosets. The chemical and physical fundamentals of UPR polymerization are summarized, including the influence of initiator systems, filler characteristics, and thermal management on network formation. Challenges associated with highly filled formulations—such as viscosity control, dispersion, shrinkage, and exothermic peak prediction—are discussed in detail. Recent advances in digital twins (DTs) and artificial intelligence (AI) are reviewed, demonstrating how physics-based simulations, machine learning models, and hybrid mechanistic–data-driven approaches improve the prediction of rheology, curing behavior, and quality outcomes in thermoset polymer processes. A practical application example demonstrates the prediction of peak time in quartz–UPR composites using Random Forest and Gradient Boosting ensemble models. Two prediction scenarios are evaluated: Scenario A with gel time by Leave-One-Out cross-validation, and Scenario B without gel time, representing post-mixing and pre-process prediction contexts, respectively. Stratified bootstrap augmentation improves Gradient Boosting in both scenarios. Principal component analysis confirms that the curing process is governed by three independent physical dimensions: curing reactivity, thermal environment and resin thermal state. Full article

As a key metering device in the smart grid, the clock battery status of smart meters directly affects the operational efficiency and economy of the grid. In response to the limitations of current evaluation methods in feature correlation analysis and model interpretability, this study proposes a knowledge-and-data-driven low battery voltage status prediction method. We systematically dissected the physical mechanisms underlying battery undervoltage faults and constructed a status features knowledge graph comprising 17 state features across four dimensions. By employing Pearson correlation analysis and association rule mining techniques, we achieved a quantitative correlation analysis between multi-source heterogeneous features and battery status. Building on this foundation, we developed an interpretable model framework based on XGBoost-SHAP. Empirical studies utilized a dataset of 939,000 faulty meters recalled by a provincial power company in 2023, with 9.87% of outlier samples eliminated using the Isolation Forest algorithm during preprocessing. Results demonstrate that the proposed model achieved an R² of 0.851 and a Mean Squared Error (MSE) of 0.0088 on the test set. The prediction performance significantly surpassed that of Random Forest (R² = 0.692) and MLP+BP neural networks (R² = 0.583), thereby validating the effectiveness of the approach in combining predictive accuracy with decision transparency. Full article

Assessing environmental impacts across the full life cycle of buildings is essential for advancing toward a net-zero and regenerative built environment. However, life cycle inventory generation and impact assessment remain methodologically complex and time-intensive, limiting their integration into early design decision-making. This study aims to quantify and reduce the embodied carbon of a regenerated building while optimizing material selection based on environmental performance and circularity potential. An integrated Building Information Modeling–Life Cycle Assessment (BIM–LCA) framework combined with Sensitivity Analysis (SA) was applied within a circular economy perspective. A regenerative building was modeled using BIM, and Industry Foundation Classes (IFC) data were employed to conduct a detailed life cycle assessment to quantify embodied carbon and identify emission hotspots across life cycle stages. The results indicate that material extraction, processing, and manufacturing dominate environmental impacts, contributing more than 85% of total CO₂ emissions. Sensitivity analysis further demonstrates the influence of material choices on overall carbon performance. The findings underscore the importance of evaluating embodied carbon at early design stages to support informed decisions regarding material efficiency, renewability, and recyclability. The proposed BIM–LCA framework provides a scalable, data-driven approach to support early-stage decarbonization strategies and contributes to reducing the carbon footprint of buildings in alignment with net-zero and regenerative design objectives. Full article

Accurate estimation of lithium-ion battery state of health and capacity is critical for intelligent battery management. This study develops a multi-variable cross-condition capacity estimation model based on incremental capacity (IC) curve features. First, the IC curve area is extracted to construct a health indicator. To capture the coupled, non-linear effects of temperature and discharge current on capacity fade, a temperature-zoned modeling framework is implemented. Specifically, first-order linear polynomials are applied for room temperature conditions to prevent overfitting, while second-order polynomials with interaction terms are utilized for high and low temperature conditions to model complex degradation behaviors. Furthermore, to mitigate estimation errors caused by individual battery inconsistency and varying initial states across different operating conditions, the capacity retention rate (CRR) and health indicator retention rate metrics are defined and integrated into the estimation framework. Validation across multiple dynamic operating conditions demonstrates that the optimized CRR-based model achieves an average root mean square error of 0.0261 Ah and a mean absolute percentage error of 2.83%. The proposed temperature-zoned approach provides a robust, data-driven methodology for cross-condition battery health monitoring. Full article

Accurate and interpretable air quality prediction remains a critical challenge for environmental health management due to complex, nonlinear interactions among emissions, meteorology, and atmospheric chemistry. This study presents a hybrid physics informed and multimodal deep learning framework for city-scale air quality and health risk prediction. The framework combines a Gaussian plume dispersion model with a residual CNN-LSTM network that learns data driven corrections while preserving physical consistency. Multimodal open datasets, including ground based pollutant sensors, meteorological records, and satellite derived aerosol and temperature features, are jointly fused to improve spatiotemporal fidelity. An Exposure Health Index module further links predicted pollutant fields with respiratory morbidity indicators, providing a quantitative bridge between atmospheric variability and health outcomes. Using open source datasets from Riyadh, Jeddah, and Dammam, the proposed approach achieves up to 25% lower mean absolute error and $R^2$ values above 0.85 compared with physics only and purely data driven baselines. Explainability analyses using SHAP and spatial attention highlight physically plausible drivers and confirm feature relevance. The results demonstrate that physics guided residual learning can unify deterministic dispersion modeling and multimodal inference, providing a transparent, scalable, and reproducible foundation for air quality forecasting and health risk assessment. Full article