Search Results (13,050)

Quality management in mega construction projects is increasingly supported by digital technologies, yet quality information often remains fragmented across inspection systems, reality-capture platforms, Building Information Modelling (BIM) environments and enterprise systems. This fragmentation limits traceability, delays corrective actions and weakens the connection between quality performance, contractual obligations and financial accountability. This study develops a closed-loop digital QA/QC framework that integrates BIM, mobile field inspection, reality capture, artificial intelligence (AI) augmentation and enterprise resource planning (ERP) within a unified governance architecture. Following a Design Science Research approach, the study proposes a seven-layer framework linking quality events to procurement, financial control, and project-management processes while supporting role-based decision-making through data democratisation mechanisms. The framework extends conventional ERP-enabled quality management by explicitly incorporating procurement (MM) and financial-control (FI/CO) functions, including supplier-quality management, cost-of-poor-quality tracking and quality-linked payment governance. An illustrative project scenario and sensitivity analysis are used to demonstrate the application of the proposed KPI and evaluation structure. By treating integration as the primary design objective, the framework provides a foundation for enterprise-wide digital quality management, lifecycle information continuity and digital-twin readiness in mega construction projects. The contribution itself is evaluated through an illustrative Design Science Research demonstration and an assumption-bounded sensitivity analysis rather than through field data, with future empirical validation specified through a controlled before-and-after case-study protocol. Full article

The coordinated development of artificial intelligence (AI) and high-quality energy development (HED) is essential for advancing digital transformation and energy transition. However, existing research primarily explores the unidirectional impact of AI on HED, neglecting their bidirectional relationship. Drawing on provincial data from China during 2012–2022, this study examines the coupling coordination between AI and HED (AHCC) and its spatiotemporal differentiation and driving factors. Results show that although both AI and HED advanced steadily, AI started from a lower base and remained below HED, and their spatial distributions were mismatched. The national average AHCC improved from mild imbalance to marginal imbalance, but large regional disparities persisted. Only several provinces—six in the east and two in the west—entered coordination stages, with most remaining in imbalance. Intensifying spatial autocorrelation of AHCC indicates that strong or weak regions are increasingly locked into self-reinforcing trajectories, making balanced regional development difficult. Regression results indicate that technological innovation, economic development level, and industrial structure upgrading significantly promote AHCC, whereas environmental regulation, urbanization level, and government intervention inhibit it. These effects exhibit pronounced spatiotemporal heterogeneity. This study enriches the theoretical understanding of AHCC and provides empirical evidence to inform coordinated digital and energy transition policies. Full article

Rapid AI adoption has intensified public and media attention toward AI-related developments, making news sentiment an increasingly important indicator of expectations and perceptions. This study constructs a global daily AI News Sentiment Index using data from the GDELT Global Knowledge Graph and examines the forecasting properties of the index using statistical, sequential deep learning and image-based forecasting methods. The period of observation of the dataset spans from January 2016 to December 2025, and the sample consists of 3635 daily observations. A sentiment index is constructed from the positive and negative sentiments and is analyzed together with its constituent series. For the empirical framework, ARIMA, ARIMA–GARCH, ETS, LightGBM, LSTM, CNN, TCN, GAN, and convolutional models based on Gramian Angular Summation Field (GASF) and Gramian Angular Difference Field (GADF) transformations are compared using accuracy evaluation on the out-of-sample test set. In this study, we find no evidence that increasing model complexity leads to better forecasting performance for the AI news sentiment series. In most cases, sequential forecasting models perform better than their image-based counterparts, while GASF and GADF transformations do not deliver consistently better forecasting performance for sentiment series of different types and different forecasting horizons. This result indicates that transforming noisy sentiment time series into an image may hide rather than preserve useful information for forecasting purposes. The study contributes to the growing literature on AI news sentiment forecasting by providing a comprehensive comparison of statistical, sequential, and image-based forecasting paradigms and offers practical insights for researchers, policymakers, and practitioners interested in monitoring AI-related expectations and sentiment dynamics. Full article

Water quality management in large-scale institutional infrastructures faces significant challenges due to the high latency of manual sampling and the energy–connectivity trade-offs in traditional IoT deployments. This paper proposes HydroSense AI, a robust three-tier IoT framework designed for real-time multi-parameter water quality monitoring and predictive analytics. The system integrates a heterogeneous sensing layer (pH, TDS, turbidity, and temperature) with a hybrid communication architecture, utilising Long Range (LoRa) technology for low-power transmission over long ranges (manufacturer-rated for line-of-sight distances of up to 16 km, and validated up to 2 km within a dense campus environment in this study), bridged via an ESP32-based gateway to the cloud. To address the critical issue of energy autonomy in remote sensing nodes, we implement a hardware-synchronised duty-cycling mechanism using a DS3231 Real-Time Clock (RTC), enabling precise deep-sleep scheduling and significantly extending battery operational life. Beyond data acquisition, the framework incorporates AI-driven trend-forecasting and anomaly-detection models to provide early warnings of water degradation through a Telegram-integrated alert system. Experimental validation over an extended deployment period demonstrates high measurement stability, with the forecasting model achieving a one-step (10-min) normalised RMSE of 0.0063 (equivalent to 0.033 pH units) for pH and 0.0298 (17.0 ppm) for TDS on a held-out test partition; a benchmark against persistence and ARIMA baselines is also provided. A complete measured energy decomposition of the deployed node is reported: hardware-synchronised duty cycling reduces the quiescent current to 18.2 μA, and with a 12 s acquisition window at 112 mA on a 10-min cycle, the mean current is 2.26 mA, corresponding to an estimated 46 days of unattended operation on a 2500 mAh cell. Critically, the acquisition window accounts for 99.2% of the per-cycle energy budget and the sleep interval for only 0.8%, so quiescent current—the figure of merit most often reported as evidence of low-power design—is shown not to be the binding constraint for sensor-dominated nodes of this class. The results indicate that the proposed hybrid architecture offers a 99.8% packet delivery ratio for sustainable water management. Full article

Introduction: Cardiovascular risk prediction remains challenging, particularly in patients with intermediate risk, mixed dyslipidemia, elevated lipoprotein(a), or variable lipid profiles. Conventional risk calculators may not fully capture nonlinear relationships among lipid, clinical, imaging, and longitudinal data. Objectives: This narrative review summarizes evidence on artificial intelligence (AI)-based cardiovascular risk assessment, focusing on lipid profile-based and multimodal models incorporating lipid-related variables. Methods: PubMed/MEDLINE, Scopus, and Google Scholar were searched for English-language articles published up to January 2026. Original studies, reviews, and relevant clinical guidelines addressing AI-based cardiovascular risk models, lipid-related predictors, and clinically applicable approaches were considered. Results: Lipid profile-based AI models may identify lipid phenotypes and lipid-related patterns associated with increased cardiovascular risk, while multimodal models have shown improved performance in selected datasets. However, the reviewed studies address heterogeneous tasks, including phenotype classification, cardiovascular event prediction, mortality prediction, patient trajectory modeling, and absolute risk estimation. Most evidence remains retrospective, with limited external validation, calibration assessment, and clinical utility data. Conclusions: AI-based models may support cardiovascular risk assessment, but routine implementation requires prospective validation, standardized evaluation, calibration, explainability, and clinical impact studies. Full article

Objectives: This study aimed to identify latent profiles of post-stroke fatigue (PSF) and examined their associations with anxiety symptoms, depressive symptoms, and sleep quality among first-ever stroke survivors. Methods: From December 2023 to May 2024, participants were recruited via convenience sampling from the Neurology Department of a tertiary hospital in Yinchuan, Ningxia. Data were collected using the Fatigue Severity Scale (FSS), the Athens Insomnia Scale (AIS), and the Hospital Anxiety and Depression Scale (HADS). Latent profile analysis (LPA) was performed using Mplus 8.3. Intergroup differences in psychological symptoms and sleep quality were compared using the Bolck–Croon–Hagenaars (BCH) method. Results: Three distinct latent profiles were identified: low FSS profile (28.0%), subthreshold intermediate FSS profile (30.2%), and high FSS profile (41.8%). Compared with the low FSS profile, the subthreshold intermediate FSS profile reported significantly higher levels of anxiety symptoms, depressive symptoms, and sleep disturbances. Furthermore, the high FSS profile exhibited the most severe symptoms across all three variables compared to both other groups (p < 0.05). Only the high FSS profile exceeded the clinical cut-off for fatigue (FSS ≥ 4). Conclusions: Post-stroke fatigue exhibits substantial heterogeneity among first-ever stroke patients and is closely linked to psychological distress and poor sleep quality. Clinical interventions should target emotional distress and sleep disorders simultaneously through individualized rehabilitation to potentially enhance patient recovery and quality of life. Full article

AI-generated instructional videos are increasingly used in higher education, yet their effectiveness relative to carefully designed conventional instructional materials remains unclear, particularly for introductory procedural learning. This randomized two-group study compared two complete instructional formats, static text-and-image instruction and AI-avatar video instruction. Both covered the same learning objectives and worked procedure, but differed in verbal presentation, temporal pacing, navigation, visual signaling and avatar presence. Eighty-one first-year university students with no prior formal university instruction in Adobe Illustrator provided pre-test, post-test, practical-task, questionnaire and seven-day retention data. The text-and-image group achieved higher immediate post-test scores than the video group. No statistically significant group differences were detected in practical task or delayed-test scores, and the exploratory comparison of post-to-retention change was also not significant. Holm correction for three perception comparisons indicated that only perceived clarity remained significantly higher in the text-and-image group. For the materials tested, the text-and-image material provided a stronger basis for immediate learning, although this advantage was not detected in practical performance or delayed outcomes. Because the formats differed in several instructional features, the observed pattern cannot be attributed specifically to avatar presence. The results highlight the importance of pacing, segmentation, visual signaling and learner control when designing AI-supported instructional videos for novice procedural learning. Full article

Ideathons and pitch competitions have expanded rapidly as experiential learning devices, but the textual artefacts they produce—presentation slides—remain under-examined. This study applies interpretable computational text analysis to 104 ideathon decks (1289 content slides) from four cohorts: Cambodia 2023, 2024, 2025 and Thailand 2025. Measures include lexical frequency, TF-IDF, lexicon-based sentiment, a ten-component pitch-completeness proxy, numerical density, and Jaccard similarity. Because sector designation was absent in Cambodia 2023 and present from 2024 onward, the longitudinal Cambodian data support an observational cohort comparison with an institutional change between cohorts; year effects, programme evolution, and sector designation cannot be separated. The Cambodia 2025 vs. Thailand 2025 contrast is a single-year cross-country comparison, not a longitudinal one. Between Cambodia 2023 and 2024, presentations show large Cohen’s d differences with 95% bootstrap confidence intervals (CIs) in total words, unique words, slide count, pitch completeness, and market-related vocabulary, alongside a small decline in type–token ratio. At fixed sector composition, Cambodia 2025 and Thailand 2025 differ sharply in surface vocabulary (top-50 Jaccard = 0.176): Cambodia leans toward agriculture, rural markets, and community development, while Thailand leans toward AI, learning, and cassava-centric agronomy. AI use was not directly measured, so all claims about generative AI are hypothesis-generating; the drop in within-cohort pairwise Jaccard from 2024 to 2025 (0.061 → 0.041) is consistent with—but does not establish—an augmentative rather than homogenising effect of AI assistance. Findings are reported as descriptive associations and interpreted through the lens of constraint-based creativity and institutional theory. We discuss implications for curriculum designers who wish to balance structural templates with exercises that promote diverse problem framings. Full article

This study presents a field-informed simulation-based decision-support framework for improving transportation operations within the Port Said–Port Fouad bridge–ferry crossing corridor in Egypt. The investigated corridor represents an interruption-sensitive multimodal transportation system where traffic performance is strongly influenced by maritime navigation activity, bridge-closure events, ferry batch-service operations, fluctuating travel demand, and adaptive traveler behavior. The proposed framework integrates AIS-assisted operational characterization, SUMO-based microscopic traffic simulation, adaptive traveler redistribution, congestion-spillback analysis, XGBoost surrogate modeling, and multi-objective optimization within a unified analytical environment. AIS data were used to identify representative vessel-passage events and bridge-closure periods that supported field calibration of the simulation framework. The methodology explicitly represents bridge-capacity interruptions, ferry operational constraints, multimodal demand redistribution, and corridor-wide congestion dynamics. To reduce the computational burden associated with repeated simulation evaluations, an XGBoost surrogate model was developed to estimate key performance indicators, including transportation delay, vehicle accumulation, ferry waiting time, emissions, and spillback severity. The surrogate model achieved strong predictive performance with a coefficient of determination of R² = 0.965. Model calibration and within-sample validation were conducted using operational observations collected during a six-day field campaign. The within-sample validation results demonstrated satisfactory agreement between observed and simulated conditions, with an average relative error of approximately 4.8% across major performance indicators. Comparative analyses were performed under existing-operation, rule-based, optimization-based, and adaptive-control scenarios. The results indicate that the proposed framework reduced total transportation delay by 43.8%, peak corridor-wide vehicle accumulation by 65.9%, and estimated CO₂ emissions by 17.4% relative to existing operating conditions. In addition, the framework maintained stable performance under increased demand levels and prolonged bridge-interruption scenarios. Overall, the findings demonstrate the potential of simulation-informed decision support and surrogate-assisted optimization for improving operational efficiency, congestion resilience, and environmental sustainability within interruption-sensitive bridge–ferry transportation systems. Full article

Power transformers are an integral part of electrical power system infrastructure and play a vital role in the efficient and reliable transmission of bulk electrical power to distribution networks. The careful use of these assets enables the optimization of transmission voltages in power networks, a crucial step for reducing electrical energy losses, enhancing grid reliability, and ensuring uninterrupted electricity supply to end-users in interconnected power networks. Operational reliability of power transformers is a critical aspect in ensuring a continuous power supply. The health index (HI) is a crucial diagnostic tool to determine their real condition. Historically, HI assessments were based on scoring and weighting. Lately, however, there has been a significant change in the attitude towards the use of artificial intelligence (AI) and machine learning (ML) to predict the health of high-voltage power transformers. Although developments are taking place, the existing studies on ML-based HI prediction models for power transformers largely rely on an incomplete dataset containing improper parameters. Moreover, dependency on traditional ML models is a significant limitation when it comes to achieving a higher degree of predictive accuracy. This article presents a sophisticated method for determining the overall health condition of power transformers. A total of twenty of the most appropriate and highly relevant input parameters were selected to effectively evaluate the transformer condition. The dataset for these parameters was collected from real-time testing in accordance with international industry standards (i.e., IEC, IEEE, and ASTM), conducted at 220 kV and 500 kV grid stations in the Multan and Lahore regions, operated by the National Grid Company (NGC) in Pakistan. This comprehensive dataset was fed to five state-of-the-art ML models. The Categorical Boosting Regression (CatBoost Regressor) model demonstrated superior performance, achieving the highest accuracy (R² Score) of 97.2% and the lowest mean absolute error (MAE) of 1.73. The best-performing model was then employed to predict the health index of the power transformers at the 500 kV grid station, Rahim Yar Khan, and the 500 kV grid station, Multan, as a practical case study. To demonstrate the economic importance of the proposed framework, an economic analysis was conducted via an iterative, parameter-skipping imputation strategy for maintenance cost optimization of the electrical power grid. The results verify that the omission of four diagnostic tests (i.e., Dissipation Factor, Capacitance, Insulation Resistance, and Transformer Turn Ratio) can reduce the economic burden by 46.99%, yielding a cost saving of 259,000 PKR per transformer unit. The implementation of this data-driven framework in the national grid can significantly reduce maintenance costs and facilitate an operational shift from traditional preventive maintenance to advanced predictive maintenance. Full article

The excessive cost and complexity of Industry 4.0 laboratory infrastructure limit the adoption of Digital Twin concepts in engineering education. This paper proposes a low-cost Digital Twin framework for sustainable manufacturing education integrating SAP NetWeaver, Node-RED, and AI-based decision support. The framework adopts a layered architecture that connects PLC-based simulation, IoT middleware, enterprise resource planning systems, and intelligent decision-making components. Node-RED enables real-time data exchange, while SAP NetWeaver provides enterprise-level integration through OData services. An AI module supports decision-making for production and inventory management. The framework has been validated through the implementation of a functional prototype and a series of end-to-end integration tests that evaluated communication reliability, system interoperability, API response performance, and AI-assisted decision-support capabilities. Competency-based mapping aligns the framework with Industry 4.0 engineering skills, supporting its use in academic environments. A sustainability assessment highlights reductions in infrastructure cost, energy consumption, and resource usage compared to traditional laboratory approaches. The results indicate that the framework has the potential to provide a scalable and accessible solution for teaching Digital Twin concepts, pending further classroom-based validation. Full article

VERO cells, derived from the kidney epithelium of the African green monkey, are widely used in virology, but their ability to metabolize xenobiotics is not fully understood. Since cytochrome P450 (CYP) enzymes participate in xenobiotic metabolism, we investigated which CYP genes are expressed in VERO-E6 cells. Reverse transcription–quantitative polymerase chain reaction (RT-qPCR) showed that VERO-E6 cells express CYP3A4, CYP3A5, and CYP3A7. In contrast, CYP1A1, CYP1A2, CYP1B1, CYP2E1, CYP2D6, and CYP2C9 transcripts were either not detected or at a low detection level. To determine whether the encoded enzymes have the potential to activate aflatoxin B1 (AFB1), we used artificial intelligence (AI)-based structural modeling along with molecular docking. AI modeling suggested that CYP3A enzymes can position AFB1 in an orientation compatible with the formation of the reactive intermediate, and CYP3A4 showed the most favorable predicted interaction (docking score: −16.3 kcal/mol). To demonstrate AFB1 bioactivation, we exposed VERO-E6 cells to 200 nmol/L AFB1. After 10 days, we observed about 40% cell death. Liquid chromatography–tandem mass spectroscopy (LC–MS/MS) analysis confirmed the presence of AFB1-derived DNA adducts, indicating that metabolic activation occurred in these cells. These findings support the presence of CYP-dependent AFB1 bioactivation in VERO-E6 cells. Thus, combining computational and experimental approaches elucidates xenobiotic metabolism in cells where biochemical data are limited. Full article

Federated learning enables collaborative data mining without centralizing raw data, but communication budgets remain a practical bottleneck in distributed deployment. Existing federated optimization methods mainly address statistical heterogeneity or aggregation stability, while client participation is often treated as full participation or random sampling. This paper proposes FedBudget, a budget-aware client selection method for communication-constrained federated data mining. In each round, FedBudget constructs a scheduling score from historical utility, stability, freshness, communication cost, and a coverage-aware penalty, and then greedily selects clients under a given communication budget. The aggregation stage follows the standard sample-size-weighted selected-client FedAvg rule, which makes the scheduling contribution directly attributable. Experiments on AI4I, Mammography, Shuttle, SMD, and SWaT compare FedBudget with representative federated optimization and scheduling baselines. Statistical analysis shows that FedBudget significantly reduces communication cost and improves communication-normalized performance relative to budgeted optimization baselines, while maintaining competitive AUC and PR-AUC. Larger-scale experiments with 20 and 50 simulated clients show mean performance-per-MB improvements of 4.019 and 1.945, respectively, together with lower mean communication cost. Sensitivity and convergence analyses confirm the robustness of the proposed scheduling mechanism and its stable communication–performance trade-off. These results indicate that explicit budget-aware participation modeling improves communication efficiency in federated data mining while preserving a simple and compatible training pipeline. Full article

Continual learning (CL) aims to develop intelligent systems capable of learning continuously from sequential data while retaining previously acquired knowledge. As AI systems are increasingly deployed in dynamic real-world environments, CL has become essential for enabling long-term adaptation without catastrophic forgetting. This review provides a structured overview of major CL paradigms, including task-incremental, domain-incremental, class-incremental, online, multimodal, and federated CL. We examine the theoretical foundations of CL, particularly the stability–plasticity dilemma, catastrophic forgetting, transfer dynamics, and representation learning. In addition, we analyze major methodological categories, including regularization-based, replay-based, architecture-based, optimization-based, representation-learning, and parameter-efficient approaches. Recent developments involving transformers, prompt learning, foundation models, and multimodal adaptation are also discussed as emerging directions in modern CL research. Furthermore, this review highlights important issues related to benchmark fragmentation, evaluation inconsistency, memory constraints, computational efficiency, scalability, and privacy-aware learning. We also summarize key application domains, including computer vision, natural language processing, robotics, healthcare, and medical imaging. Finally, we identify open research challenges and future directions toward scalable, reliable, and deployment-oriented lifelong learning systems capable of operating effectively in continuously evolving environments. Full article