Search Results (283)

In service-intensive, compliance-driven settings such as banking, identifying how internal corporate social responsibility (ICSR) fosters employees’ vitality and learning is crucial for sustainable organisational performance. Amid growing interest in employee thriving, this study explores how perceived internal corporate social responsibility (PICSR) and moral meaningfulness (MM) shape thriving at work (TaW) through organisational embeddedness (OE). Rooted in self-determination theory, the findings reveal OE as a key mediator between PICSR and TaW, shedding light on how ICSR initiatives influence employee dynamics. The study also reveals that MM alone does not significantly predict TaW directly, but does so indirectly through OE, highlighting the importance of contextual mechanisms. Additionally, it identifies a surprising negative moderating effect of risk-taking, one dimension of intrapreneurial behaviour (IB), on the relationship between OE and TaW, while innovativeness, another dimension, shows no such effect. Theoretical and practical implications underscore the importance of aligning ICSR practices with employees’ psychological needs, supporting moral alignment, and tailoring support for intrapreneurs. Organisations must achieve a balance between autonomy and security to sustain engagement and innovation, advancing human and organisational sustainability, ultimately leading to thriving. Full article

Fire spotting (FS), the process by which firebrands are lofted, transported, and ignite new fires ahead of the main flame front, plays a critical role in escalating extreme wildfire events. This systematic literature review (SLR) analyzes peer-reviewed articles and book chapters published in English from 2000 to 2023 to assess the evolution of FS models, identify prevailing methodologies, and highlight existing gaps. Following a PRISMA-guided approach, 102 studies were selected from Scopus, Web of Science, and Google Scholar, with searches conducted up to December 2023. The results indicate a marked increase in scientific interest after 2010. Thematic and bibliometric analyses reveal a dominant research focus on integrating the FS model within existing and new fire spread models, as well as empirical research and individual FS phases, particularly firebrand transport and ignition. However, generation and ignition FS phases, physics-based FS models (encompassing all FS phases), and integrated operational models remain underexplored. Modeling strategies have advanced from empirical and semi-empirical approaches to machine learning and physical-mechanistic simulations. Despite advancements, most models still struggle to replicate the stochastic and nonlinear nature of spotting. Geographically, research is concentrated in the United States, Australia, and parts of Europe, with notable gaps in representation across the Global South. This review underscores the need for interdisciplinary, data-driven, and regionally inclusive approaches to improve the predictive accuracy and operational applicability of FS models under future climate scenarios. Full article

Excessive exhaust backpressure (EBP) in modern diesel engines disrupts gas exchange, increases residual gas fraction (RGF), and reduces combustion efficiency. Traditional experimental approaches, including simulations and bench testing, are often time-consuming and costly, which has driven growing interest in artificial neural networks (ANNs) for accurately modelling complex engine behavior. This research introduces an ANN model designed to predict the impact of EBP on the performance and emissions of a diesel engine across varying compression ratio (CR) of 12, 14, 16, and 18 and engine load (25%, 50%, 75%, and 100%) conditions. The ANN model was developed and optimised using genetic algorithms (GA) and particle swarm optimisation (PSO). It was then trained using data from an experimentally validated one-dimensional computational fluid dynamics (1D-CFD) model developed through GT-Power GT-ISE v2024, simulating engine responses under variation CR, load, and EBP conditions. The optimised ANN architecture, featuring an optimal (3-14-10) configuration, was trained using the Levenberg–Marquardt back propagation algorithm. The performance of the model was assessed using statistical criteria, including the coefficient of determination (R²), root mean square error (RMSE), and k-fold cross-validation, by comparing its predictions with both experimental and simulated data. Results indicate that the optimised ANN model outperformed the baseline ANN and other machine learning (ML) models, attaining an R² of 0.991 and an RMSE of 0.011. It reliably predicts engine performance and emissions under varying EBP conditions while offering insights for engine control, optimisation, diagnostics, and thermodynamic mechanisms. The overall prediction error ranged from 1.911% to 2.972%, confirming the model’s robustness in capturing performance and emission outcomes. Full article

Background/Objectives: Today, Artificial intelligence (AI) and machine learning (ML) significantly enhance predictive analytics in the healthcare landscape, enabling timely and accurate predictions that lead to proactive interventions, personalized treatment plans, and ultimately improved patient care. As healthcare systems increasingly adopt data-driven approaches, the integration of AI and data analysis has garnered substantial interest, as reflected in the growing number of publications highlighting innovative applications of AI in clinical settings. This review synthesizes recent evidence on application areas, commonly used models, metrics, and challenges. Methods: We conducted a systematic literature review between using Web of Science and Google Scholar databases from 2021–2025 covering a diverse range of AI and ML techniques applied to disease prediction. Results: Twenty-two studies met criteria. The most frequently used machine learning approaches were tree-based ensemble models (e.g., Random Forest, XGBoost, LightGBM) for structured clinical data, and deep learning architectures (e.g., CNN, LSTM) for imaging and time-series tasks. Evaluation most commonly relied on AUROC, F1-score, accuracy, and sensitivity. key challenges remain regarding data privacy, integration with clinical workflows, model interpretability, and the necessity for high-quality representative datasets. Conclusions: Future research should focus on developing interpretable models that clinicians can understand and trust, implementing robust privacy-preserving techniques to safeguard patient data, and establishing standardized evaluation frameworks to effectively assess model performance. Full article

Under the accelerating demographic aging trend, the rational allocation of elderly care facilities has emerged as a critical challenge. Although existing studies have investigated elderly care facilities planning using conventional methods, they frequently overlook the nonlinear interactions between built environment factors and heterogeneous demands across different elderly care facility types. This study addresses these gaps by proposing a data-driven framework that integrates machine learning with spatial analysis to optimize elderly care facility distribution in Xi’an City central area, Shaanxi Province, China. Leveraging multi-source datasets encompassing points of interest (POIs), road networks, and demographic statistics, we classify facilities into three categories (service-oriented, activity-oriented, and care-oriented) and employ an XGBoost model with SHAP interpretability to evaluate spatial distributions and influencing factors. The results demonstrate that the XGBoost model outperforms comparative algorithms (Random Forest, CatBoost, LightGBM) with superior performance metrics (accuracy rate of 97%, precision of 95%, and F1-score of 90%), effectively capturing nonlinear thresholds effects. Key findings reveal the following: (1) Accessibility and road density exert threshold effects on care-oriented facilities, with facility attractiveness saturating when these values exceed 6; (2) Land use intensity and medical resources positively correlate with activity-oriented facilities, while excessive retail density inhibits their distribution; (3) Service-oriented facilities thrive in areas with balanced accessibility and moderate commercial diversity. Spatial analysis identifies clustered distribution patterns in urban core areas contrasted with peripheral deficiencies, indicating need for targeted interventions. This research contributes a scalable methodology for equitable facility planning, emphasizing the integration of dynamic built environment variations with model interpretability. The framework provides significant implications for formulating age-friendly urban policies applicable to global cities undergoing rapid urbanization and population aging. Full article

Driven by the latest advancements in wireless technology, location-based services have attracted the interest of computing and telecommunication industries, as well as academia, to launch fast and accurate localization systems. The aim of this work is to propose a closed-loop localization framework for large-scale deployments, facilitating both the modeling and continuous monitoring of Activities of Daily Living (ADLs). The proposed system learns from a minimal set of Received Signal Strength Indicator (RSSI) samples, enriches them to cover unmeasured distances, and keeps recalibrating itself with live data. This method delivers a 0.5–0.8 m mean error, improving the error reported in recent studies by 65%. Furthermore, once reliable position estimation is achieved, the proposed framework can detect predefined Activities of Daily Living (ADLs) based on location patterns and movement behaviors, achieving 91% accuracy. This capability opens new opportunities for context-aware services and smart environment applications. Each module of the framework was individually tested and evaluated, demonstrating strong performance both in isolation and as part of the integrated system. Full article

Despite increased interest in embodied learning, the role of sensorimotor activity in shaping students’ probabilistic reasoning remains underexplored. This design-based study examines how high school students develop key probabilistic concepts, including sample space, certainty, and event probability, through whole-body movement activities situated in an authentic classroom setting. Grounded in embodied cognition theory, we introduce a two-axis interpretive framework. One axis spans sensorimotor exploration and formal reasoning, drawing from established continuums in the literature. The second axis, derived inductively from our analysis, contrasts engagement with distraction, foregrounding the affective and attentional dimensions of embodied participation. Students engaged in structured yet open-ended movement sequences that elicited intuitive insights. This approach, epitomized by one student’s spontaneous question, “Can I use my leg too?”, captures the agentive and improvisational character of the embodied learning environment. Through five analyzed classroom episodes, we trace how students shifted between bodily exploration and formalization, often through nonlinear trajectories shaped by play, uncertainty, and emotionally driven reflection. While moments of insight emerged organically, they were also fragile, as they were affected by ambiguity and the difficulty in translating physical actions into mathematical language. Our findings underscore the pedagogical potential of embodied design for probabilistic learning while also highlighting the need for responsive teaching that balances structure with improvisation and supports affective integration throughout the learning process. Full article

Synthetic aperture radar (SAR), with its all-weather and all-day active imaging capability, has become indispensable for geoscientific analysis and socio-economic applications. Despite advances in deep learning–based object detection, the rapid and accurate detection of small objects in SAR imagery remains a major challenge due to their extremely limited pixel representation, blurred boundaries in dense distributions, and the imbalance of positive–negative samples during training. Recently, vision–language models such as Contrastive Language-Image Pre-Training (CLIP) have attracted widespread research interest for their powerful cross-modal semantic modeling capabilities. Nevertheless, their potential to guide precise localization and detection of small objects in SAR imagery has not yet been fully exploited. To overcome these limitations, we propose the CLIP-Driven Adaptive Tiny Object Detection Diffusion Network (CDATOD-Diff). This framework introduces a CLIP image–text encoding-guided dynamic sampling strategy that leverages cross-modal semantic priors to alleviate the scarcity of effective positive samples. Furthermore, a generative diffusion-based module reformulates the sampling process through iterative denoising, enhancing contextual awareness. To address regression instability, we design a Balanced Corner–IoU (BC-IoU) loss, which decouples corner localization from scale variation and reduces sensitivity to minor positional errors, thereby stabilizing bounding box predictions. Extensive experiments conducted on multiple SAR and optical remote sensing datasets demonstrate that CDATOD-Diff achieves state-of-the-art performance, delivering significant improvements in detection robustness and localization accuracy under challenging small-object scenarios with complex backgrounds and dense distributions. Full article

The transport sector significantly contributes to global greenhouse gas emissions, making electromobility crucial in the race toward the United Nations Sustainable Development Goals. In recent years, the increasing competition among manufacturers, the development of cheaper batteries, the ongoing policy support, and people’s greater environmental awareness have consistently increased electric vehicles (EVs) adoption. Nevertheless, EVs charging needs—highly influenced by EV drivers’ behavior uncertainty—challenge their integration into the power grid on a massive scale, leading to potential issues, such as overloading and grid instability. Smart charging strategies can mitigate these adverse effects by using information and communication technologies to optimize EV charging schedules in terms of power systems’ constraints, electricity prices, and users’ preferences, benefiting stakeholders by minimizing network losses, maximizing aggregators’ profit, and reducing users’ driving range anxiety. To this end, accurately forecasting EV charging demand is paramount. Traditionally used forecasting methods, such as model-driven and statistical ones, often rely on complex mathematical models, simulated data, or simplifying assumptions, failing to accurately represent current real-world EV charging profiles. Machine learning (ML) methods, which leverage real-life historical data to model complex, nonlinear, high-dimensional problems, have demonstrated superiority in this domain, becoming a hot research topic. In a scenario where EV technologies, charging infrastructure, data acquisition, and ML techniques constantly evolve, this paper conducts a systematized literature review (SLR) to understand the current landscape of ML-based EV charging demand forecasting, its emerging trends, and its future perspectives. The proposed SLR provides a well-structured synthesis of a large body of literature, categorizing approaches not only based on their ML-based approach, but also on the EV charging application. In addition, we focus on the most recent technological advances, exploring deep-learning architectures, spatial-temporal challenges, and cross-domain learning strategies. This offers an integrative perspective. On the one hand, it maps the state of the art, identifying a notable shift toward deep-learning approaches and an increasing interest in public EV charging stations. On the other hand, it uncovers underexplored methodological intersections that can be further exploited and research gaps that remain underaddressed, such as real-time data integration, long-term forecasting, and the development of adaptable models to different charging behaviors and locations. In this line, emerging trends combining recurrent and convolutional neural networks, and using relatively new ML techniques, especially transformers, and ML paradigms, such as transfer-, federated-, and meta-learning, have shown promising results for addressing spatial-temporality, time-scalability, and geographical-generalizability issues, paving the path for future research directions. Full article

Precision agriculture applies data-driven strategies to manage spatial and temporal variability within fields, aiming to increase productivity while minimizing pressure on natural resources. As interest in smart tillage systems expands, this study explores a central question: Can tillage tools be used to measure soil compaction during regular field operations? To investigate this, vibration data measurements were collected from a cultivator shank in the northeast of Kansas using the AVDAQ system. The test field soils were Reading silt loam and Eudora–Bismarck Grove silt loams. The relationship between shank vibrations, soil moisture (measured by a Hydrosense II soil–water sensor), and soil compaction (measured by a cone penetrometer) was evaluated using machine learning models. Both XGBoost and Random Forest demonstrated strong predictive performance, with Random Forest achieving a slightly higher correlation of 93.8% compared to 93.7% for XGBoost. Statistical analysis confirmed no significant difference between predicted and measured values, validating the accuracy and reliability of both models. Overall, the results demonstrate that combining vibration data with soil moisture data as model inputs enables accurate estimation of soil compaction, providing a foundation for future in situ soil sensing, reduced tillage intensity, and more sustainable cultivation practices. Full article

Background/Objectives: Sepsis is a severe medical condition characterized by a dysregulated host response to infection, with potentially fatal outcomes, requiring early diagnosis and rapid intervention. The limitations of traditional sepsis identification methods, as well as the complexity of clinical data generated in intensive care, have driven increased interest in applying artificial intelligence in this field. The aim of this narrative review article is to analyze how artificial intelligence is being used in the diagnosis and prognosis of sepsis, to present the most relevant current models and algorithms, and to discuss the challenges and opportunities related to integrating these technologies into clinical practice. Methods: We conducted a structured literature search for this narrative review, covering studies published between 2016 and 2024 in databases such as PubMed/Medline, Scopus, Web of Science, IEEE Xplore, and Google Scholar. The review covered models based on machine learning (ML), deep neural networks (DNNs), Recurrent Neural Networks (RNNs), and clinical alert systems implemented in hospitals. The clinical data sources used, algorithms applied, system architectures, and performance outcomes are presented. Results: Numerous artificial intelligence models demonstrated superior performance compared to conventional clinical scores (qSOFA, SIRS), achieving AUC values above 0.90 in predicting sepsis and mortality. Systems such as Targeted Real-Time Early Warning System (TREWS) and InSight have been clinically validated and have significantly reduced the time to treatment initiation. However, challenges remain, such as a lack of model transparency, algorithmic bias, difficulties integrating into clinical workflows, and the absence of external validation in multicenter settings. Conclusions: Artificial intelligence has the potential to transform sepsis management through early diagnosis, risk stratification, and personalized treatment. A responsible, multidisciplinary approach is necessary, including rigorous clinical validation, enhanced interpretability, and training of healthcare personnel to effectively integrate these technologies into everyday practice. Full article

Port seaside scheduling, involving berth allocation, quay crane, and tugboat scheduling, is central to intelligent port operations. This survey reviews and statistically analyzes 152 academic publications from 2000 to 2025 that focus on optimization techniques for port seaside scheduling. The reviewed methods span mathematical modeling and exact algorithms, heuristic and simulation-based approaches, and agent-based and learning-driven techniques. Findings show deterministic models remain mainstream (77% of studies), with uncertainty-aware models accounting for 23%. Heuristic and simulation approaches are most commonly used (60.5%), followed by exact algorithms (21.7%) and agent-based methods (12.5%). While berth and quay crane scheduling have historically been the primary focus, there is growing research interest in tugboat operations, pilot assignment, and vessel routing under navigational constraints. The review traces a clear evolution from static, single-resource optimization to dynamic, multi-resource coordination enabled by intelligent modeling. Finally, emerging trends such as the integration of large language models, green scheduling strategies, and human–machine collaboration are discussed, providing insights and directions for future research and practical implementations. Full article

Personalized, scalable, and data-driven learning is now possible in cyber science education because of artificial intelligence (AI). This article examines how AI technologies, such as intelligent tutoring, adaptive learning, virtual labs, and AI assessments, are being included in cyber science curricula. Using examples and research studies published between 2020 and 2025 that have undergone peer review, this paper combines qualitative analysis and framework analysis to discover any similarities in how these policies were put into place and their effects. According to the findings, using AI in instruction boosts student interest, increases the number of courses finished, improves skills, and ensures clear instruction in areas such as cybersecurity, digital forensics, and incident response. Ethical issues related to privacy, bias in algorithms, and access issues are also covered in this paper. This study gives a useful approach that helps teachers, curriculum designers, and institution heads use AI in cyber education properly. Full article

Summer Youth Employment Programs (SYEPs) operate in most major U.S. cities and are known to build social–emotional and job skills in youth while reducing crime. Integrating STEM learning and summer employment offers a promising way to increase youth engagement in STEM—and allow leaders to access funding not typically used for education. Using a connected learning framework, we examined how STEM-focused SYEPs support STEM pathways, the practices they implement, and their connections with schools. Our study explored 10 diverse STEM programs (e.g., robotics, renewable energy, coding) within a citywide employment initiative in summer 2015. Through 22 staff interviews and focus groups with 59 youth, we found that these programs provided meaningful and engaging STEM experiences. They combined interest-driven exploration with hands-on, real-world learning in supportive environments. Many included mentors from groups underrepresented in STEM fields. While collaboration with schools was generally limited to recruitment and shared facilities, opportunities for deeper partnerships were evident. Our findings led to a list of ten promising practices for STEM-focused SYEPs. This study underscores the importance of lifelong, lifewide, and connected approaches to STEM learning through summer employment initiatives. Full article

Although SAR systems can provide high-resolution aerial view images all-day, all-weather, the aspect and pose-sensitivity of the SAR target signatures, which defies the Gestalt perceptual principles, sets a frustrating performance upper bound for SAR Automatic Target Recognition (ATR). Therefore, we propose a network to support context-guided ATR by using aligned Electro-Optical (EO)-SAR image pairs. To realize EO-SAR image scene grammar alignment, the stable context features highly correlated to the parking patterns of the vehicle and aircraft targets are extracted from the EO images as prior knowledge, which is used to assist SAR-ATR. The proposed network consists of a Scene Recognition Module (SRM) and an instance-level Cross-modality ATR Module (CATRM). The SRM is based on a novel light-condition-driven adaptive EO-SAR decision weighting scheme, and the Outlier Exposure (OE) approach is employed for SRM training to realize Out-of-Distribution (OOD) scene detection. Once the scene depicted in the cut of interest is identified with the SRM, the image cut is sent to the CATRM for ATR. Considering that the EO-SAR images acquired from diverse observation angles often feature unbalanced quality, a novel class-incremental learning method based on the Context-Guided Re-Identification (ReID)-based Key-view (CGRID-Key) exemplar selection strategy is devised so that the network is capable of continuous learning in the open-world deployment environment. Vehicle ATR experimental results based on the UNICORN dataset, which consists of 360-degree EO-SAR images of an army base, show that the CGRID-Key exemplar strategy offers a classification accuracy 29.3% higher than the baseline model for the incremental vehicle category, SUV. Moreover, aircraft ATR experimental results based on the aligned EO-SAR images collected over several representative airports and the Arizona aircraft boneyard show that the proposed network achieves an F1 score of 0.987, which is 9% higher than YOLOv8. Full article