Search Results (4,788)

Computing the temporal variation in clearwater scour depth around abutments is important for bridge foundation design. To reach the equilibrium scour depth at bridge abutments takes a very long time. However, the corresponding times under prototype conditions can yield values significantly greater than the time to reach the design flood peak. Therefore, estimating the temporal variation in scour depth is necessary. This study evaluates multiple machine learning (ML) models to identify the most accurate method for predicting scour depth (Ds) over time using experimental data. The dataset of 3275 records, including flow depth (Y), abutment length (L), channel width (B), velocity (V), time (t), sediment size (d₅₀), and Ds, was used to train and test Linear Regression (LR), Random Forest Regressor (RFR), Support Vector Regression (SVR), Gradient Boosting (GBR), XGBoost, LightGBM, and KNN models. Results demonstrated the superior performance of AI-based models over conventional regression. The RFR model achieved the highest accuracy (R² = 0.9956, Accuracy = 99.73%), followed by KNN and GBR. In contrast, the conventional LR model performed poorly (R² = 0.4547, Accuracy = 57.39%). This study confirms the significant potential of ML, particularly ensemble methods, to provide highly reliable scour predictions, offering a robust tool for enhancing bridge design and safety. Full article

Chemical sensors have undergone transformative advances in recent years, driven by the convergence of nanomaterials, advanced fabrication strategies, and state-of-the-art characterization methods. This review emphasizes recent developments, with particular attention to progress achieved over the past decade, and highlights the role of the United States as a major driver of global innovation in the field. Nanomaterials such as graphene derivatives, MXenes, carbon nanotubes, metal–organic frameworks (MOFs), and hybrid composites have enabled unprecedented analytical performance. Representative studies report detection limits down to the parts-per-billion (ppb) and even parts-per-trillion (ppt) level, with linear ranges typically spanning 10–500 ppb for volatile organic compounds (VOCs) and 0.1–100 μM for biomolecules. Response and recovery times are often below 10–30 seconds, while reproducibility frequently exceeds 90% across multiple sensing cycles. Stability has been demonstrated in platforms capable of continuous operation for weeks to months without significant drift. In parallel, additive manufacturing, device miniaturization, and flexible electronics have facilitated the integration of sensors into wearable, stretchable, and implantable platforms, extending their applications in healthcare diagnostics, environmental monitoring, food safety, and industrial process control. Advanced characterization techniques, including in situ Raman spectroscopy, X-ray Photoelectron Spectroscopy (XPS, Atomic Force Microscopy (AFM) , and high-resolution electron microscopy, have elucidated interfacial charge-transfer mechanisms, guiding rational material design and improved selectivity. Despite these achievements, challenges remain in terms of scalability, reproducibility of nanomaterial synthesis, long-term stability, and regulatory validation. Data privacy and cybersecurity also emerge as critical issues for IoT-integrated sensing networks. Looking forward, promising future directions include the integration of artificial intelligence and machine learning for real-time data interpretation, the development of biodegradable and eco-friendly materials, and the convergence of multidisciplinary approaches to ensure robust, sustainable, and socially responsible sensing platforms. Overall, nanomaterial-enabled chemical sensors are poised to become indispensable tools for advancing public health, environmental sustainability, and industrial innovation, offering a pathway toward intelligent and adaptive sensing systems. Full article

Traditional security methods fail to match the speed of evolving threats because Industrial Internet of Things (IIoT) technologies have become more widely adopted. A lightweight adaptive AI-based intrusion detection system (IDS) for IIoT environments is presented in this paper. The proposed system detects cyber threats in real time through an ensemble of online learning models that also adapt to changing network behavior. The system implements SHAP (SHapley Additive exPlanations) for model prediction explanations to allow human operators to verify and understand alert causes while addressing the essential need for trust and transparency. The system validation was performed using the ToN_IoT and Bot-IoT benchmark datasets. The proposed system detects threats with 96.4% accuracy while producing 2.1% false positives and requiring 35 ms on average for detection on edge devices with limited resources. Security analysts can understand model decisions through SHAP analysis because packet size and protocol type and device activity patterns strongly affect model predictions. The system underwent testing on a Raspberry Pi 5-based IIoT testbed to evaluate its deployability in real-world scenarios through emulation of practical edge environments with constrained computational resources. The research unites real-time adaptability with explainability and low-latency performance in an IDS framework specifically designed for industrial IoT security. The solution provides a scalable method to boost cyber resilience in manufacturing, together with energy and critical infrastructure sectors. By enabling fast, interpretable, and low-latency intrusion detection directly on edge devices, this solution enhances cyber resilience in critical sectors such as manufacturing, energy, and infrastructure, where timely and trustworthy threat responses are essential to maintaining operational continuity and safety. Full article

This empirical investigation explores the complex interdependencies between the concept of the Smart University Campus and the broader ecosystem of Smart City policies, with a particular focus on the New European Bauhaus initiative as a catalyst for educational transformation. The study examines how university campuses can evolve into paradigmatic models of innovation, sustainability, and inclusion through the strategic integration of emerging technologies, circular bioeconomy principles, and holistic ecological strategies. A comprehensive case study, grounded in rigorous quantitative analysis, including Principal Component Analysis (PCA), Importance-Performance Analysis (IPA), and Cluster Analysis (CA), based on questionnaires administered to a sample of 245 high school and university students—primarily from the academic community of the “King Mihai I” University of Life Sciences in Timișoara (USVT)—provides empirical insights into perceptions and expectations regarding the Smart Campus ecosystem and its core components: Smart Learning, Smart Living, Smart Safety and Security, Smart Socialization and Smart Health. The distinctive contribution of this research lies in its empirical demonstration that the strategic alignment between university campuses and Smart City initiatives, guided by the principles of the New European Bauhaus, can enhance educational efficiency by creating integrated learning ecosystems that simultaneously address academic needs, sustainability imperatives, and goals of sustainable urban development. Full article

Gas leakages pose significant safety risks in urban environments and industrial sectors like the Oil and Gas Industry (OGI), leading to accidents, fatalities, and economic losses. This paper introduces a novel generative AI framework, the Multi-Scale Dual Discriminator Generative Adversarial Network (MSDD-GAN), designed to detect and localize gas leaks by generating thermal images from RGB input images. The proposed method integrates three key innovations: (1) Attention-Guided Masking (AttMask) for precise gas leakage localization using saliency maps and a circular Region of Interest (ROI), enabling pixel-level validation; (2) Multi-scale input processing to enhance feature learning with limited data; and (3) Dual Discriminator to validate the thermal image realism and leakage localization accuracy. A comprehensive dataset from laboratory and industrial environment has been collected using a FLIR thermal camera. The MSDD-GAN demonstrated robust performance by generating thermal images with the gas leakage indications at a mean accuracy of $81.6\%$, outperforming baseline cGANs by leveraging a multi-scale generator and dual adversarial losses. By correlating ice formation in RGB images with the leakage indications in thermal images, the model addresses critical challenges of OGI applications, including data scarcity and validation reliability, offering a robust solution for continuous gas leak monitoring in pipeline. Full article

This paper presents a proof-of-concept real-time safety alerting system for safety-critical environments such as construction sites. Key components of the system include Bluetooth Low Energy (BLE) devices for indoor localization, integrated with a customized Android application using the Framework for Internal Navigation and Discovery (FIND). Administrative control and data management are handled by a server-side component, supported by an interactive website for real-time safety monitoring. The architecture supports safety zoning and employs machine learning algorithms, including k-NN, Random Forest, and SVM, for analyzing localization data. Experimental validation in a laboratory setup demonstrates a localization accuracy of 97%, a response time of 1.2 s, and a maximum spatial error of 1.2 m. These results highlight the system’s reliability and potential for enhancing safety compliance in real-world deployment scenarios. Full article

Background: Skin cancer represents one of the most prevalent malignancies worldwide, with melanoma accounting for approximately 75% of skin cancer-related deaths despite comprising fewer than 5% of cases. Early detection dramatically improves survival rates from 14% to over 99%, highlighting the urgent need for accurate and accessible diagnostic tools. While deep learning has shown promise in dermatological diagnosis, existing approaches lack clinical explainability and deployable interfaces that bridge the gap between research innovation and practical healthcare applications. Methods: This study implemented a comprehensive multimodal deep learning framework using the HAM10000 dataset (10,015 dermatoscopic images across seven diagnostic categories). Three CNN architectures (DenseNet-121, EfficientNet-B3, ResNet-50) were systematically compared, integrating patient metadata, including age, sex, and anatomical location, with dermatoscopic image analysis. The first implementation of XRAI (eXplanation with Region-based Attribution for Images) explainability for skin lesion classification was developed, providing spatially coherent explanations aligned with clinical reasoning patterns. A deployable web-based clinical interface was created, featuring real-time inference, comprehensive safety protocols, risk stratification, and evidence-based cosmetic recommendations for benign conditions. Results: EfficientNet-B3 achieved superior performance with 89.09% test accuracy and 90.08% validation accuracy, significantly outperforming DenseNet-121 (82.83%) and ResNet-50 (78.78%). Test-time augmentation improved performance by 1.00 percentage point to 90.09%. The model demonstrated excellent performance for critical malignant conditions: melanoma (81.6% confidence), basal cell carcinoma (82.1% confidence), and actinic keratoses (88% confidence). XRAI analysis revealed clinically meaningful attention patterns focusing on irregular pigmentation for melanoma, ulcerated borders for basal cell carcinoma, and surface irregularities for precancerous lesions. Error analysis showed that misclassifications occurred primarily in visually ambiguous cases with high correlation (0.855–0.968) between model attention and ideal features. The web application successfully validated real-time diagnostic capabilities with appropriate emergency protocols for malignant conditions and comprehensive cosmetic guidance for benign lesions. Conclusions: This research successfully developed the first clinically deployable skin lesion classification system combining diagnostic accuracy with explainable AI and practical patient guidance. The integration of XRAI explainability provides essential transparency for clinical acceptance, while the web-based deployment democratizes access to advanced dermatological AI capabilities. Comprehensive validation establishes readiness for controlled clinical trials and potential integration into healthcare workflows, particularly benefiting underserved regions with limited specialist availability. This work bridges the critical gap between research-grade AI models and practical clinical utility, establishing a foundation for responsible AI integration in dermatological practice. Full article

Identifying strategies to enhance patient engagement and to control healthcare costs promotes a responsive and efficient healthcare system. The aim of this study is to predict healthcare cost savings associated with delivering telehealth advance care planning (ACP) to patients living with dementia. Two Geriatrics Workforce Enhancement Programs delivered training to primary care providers on using telehealth to provide ACP. Using electronic health records data from 6344 dual-eligible Medicare/Medicaid patients receiving telehealth primary care from trained providers in an urban safety net system, persons living with dementia (n = 401) were identified by extracting ICD-10 codes. The primary outcome was the estimated hospitalization-associated cost, with a key independent variable of ACP billing status. Multiple linear regressions and machine learning techniques estimated the impact of telehealth ACP on hospitalization-associated costs with a differential analysis by race. Compared to non-Hispanic Whites, hospitalization costs among Hispanic elders were higher by USD 14,232.40. Costs for non-English speakers or those having increased comorbidities were higher by USD 27,346.60 and USD 26,072.70, respectively. Overall, receiving ACP was associated with lower costs of USD 23,928.84. Dementia patients seen by primary care providers in a system receiving training to offer ACP via telehealth realized significant cost savings, with marked differences among those of non-White racial backgrounds. Full article

Fatigue and distracted driving are among the leading causes of traffic accidents, highlighting the importance of developing efficient and non-intrusive driver monitoring systems. Traditional camera-based methods are often limited by lighting variations, occlusions, and privacy concerns. In contrast, millimeter-wave (mmWave) radar offers a non-contact, privacy-preserving, and environment-robust solution, providing a forward-looking alternative. This study introduces a novel deep learning model, RTSFN (radar-based temporal-spatial fusion network), which simultaneously analyzes the temporal motion changes and spatial posture features of the driver. RTSFN incorporates a cross-gated fusion mechanism that dynamically integrates multi-modal information, enhancing feature complementarity and stabilizing behavior recognition. Experimental results show that RTSFN effectively detects dangerous driving states with an average F1 score of 94% and recognizes specific high-risk behaviors with an average F1 score of 97% and can run in real-time on edge devices such as the NVIDIA Jetson Orin Nano, demonstrating its strong potential for deployment in intelligent transportation and in-vehicle safety systems. Full article

Meaningful Physical Education (MPE) emphasizes six pedagogical dimensions, social interaction, enjoyment, fair challenge, motor competence, personally relevant learning, and enduring satisfaction, that contribute to students’ motor and emotional development. This study explores how experienced in-service Physical Education (PE) teachers perceive their capacity to foster these dimensions in their daily teaching practice. A qualitative, interpretative study was conducted through semi-structured interviews with 14 PE teachers (≥10 years of experience) from primary and secondary schools in Spain. A validated interview protocol, structured around the six MPE dimensions, guided data collection. Transcriptions were thematically analyzed using an inductive–deductive coding approach. Teachers described strategies to promote social cohesion, engagement through playful experiences, and differentiation to achieve fair challenges. They emphasized the importance of visible motor progress and emotional safety, and highlighted that when students perceive lessons as relevant, their motivation and long-term adherence to physical activity increases. Although teachers recognized challenges in implementing all dimensions simultaneously, they valued MPE as a guiding framework. The findings support MPE as a feasible and pedagogically rich model in real school contexts. Promoting these dimensions appears to be critical in fostering students’ sustained participation in physical activity and supporting their holistic motor development. Full article

Trajectory prediction is a critical component of autonomous driving decision-making systems, directly impacting driving safety and traffic efficiency. Despite advancements, existing reviews exhibit limitations in timeliness, classification frameworks, and challenge analysis. This paper systematically reviews multi-agent trajectory prediction technologies, focusing on generating future position sequences from historical trajectories, high-precision maps, and scene context. We propose a multi-dimensional classification framework integrating input representation, output forms, method paradigms, and interaction modeling. The review comprehensively compares conventional methods and deep learning architectures, including diffusion models and large language models. We further analyze five core challenges: complex interactions, rule and map dependence, long-term prediction errors, extreme-scene generalization, and real-time constraints. Finally, interdisciplinary solutions are prospectively explored. Full article

Acute kidney injury is a common complication in the perioperative setting, especially among patients undergoing high-risk surgeries such as cardiac, abdominal, or orthopedic procedures. Characterized by a sudden decline in renal function, perioperative acute kidney injury is typically diagnosed based on rising serum creatinine or reduced urine output. Its incidence varies depending on the surgical type and patient risk factors, but even mild cases are linked to significant consequences, including prolonged hospital stays, enhanced healthcare costs, and higher mortality rates. Despite advances in surgical and anesthetic care, acute kidney injury remains a major cause of morbidity. The development of acute kidney injury in the perioperative period often results from a complex interplay of hypoperfusion, ischemia–reperfusion injury, inflammation, and exposure to nephrotoxic agents. While some predictive models and biomarkers, such as neutrophil gelatinase-associated lipocalin (NGAL), have shown promise in identifying patients at risk, widespread adoption remains inconsistent, and standardized prevention protocols are lacking. This narrative review synthesizes current evidence on the pathophysiology, risk factors, and prevention strategies for perioperative acute kidney injury. It explores emerging tools for risk stratification and early diagnosis, including novel biomarkers and learning-based models. Additionally, it highlights pharmacologic and non-pharmacologic measures to reduce acute kidney injury incidence, such as balanced fluid management, renal-protective anesthetic strategies, and bundle-based care approaches. Emphasizing a multidisciplinary and personalized model of care, this review highlights the need for coordinated efforts between anesthesiologists, surgeons, and nephrologists to identify modifiable risks and improve outcomes. Reducing the incidence of perioperative acute kidney injury has the potential to enhance recovery, preserve long-term kidney function, and ultimately improve surgical safety. Full article

The complexity of global food supply chains challenges public health, requiring advanced detection technologies beyond traditional lab methods. Fluorescent sensing, known for its sensitivity and quick response, is promising for food safety but hindered by inefficient probe design and difficulties in analyzing complex signals in food. Deep Learning (DL) offers solutions with its nonlinear modeling and pattern recognition capabilities. This review explores recent advancements in DL applications for fluorescent sensing. We explore deep learning methods for predicting fluorescent probe properties and generating fluorescent molecule structures, highlighting their role in accelerating high-performance probe development. We then offer a detailed discussion on the pivotal technologies of deep learning in the intelligent analysis of complex fluorescent signals. On this basis, we engage in a thorough reflection on the core challenges presently confronting the field and propose a forward-looking perspective on the future developmental trajectories of fluorescent sensing technology, offering a comprehensive and insightful roadmap for future research in this interdisciplinary domain. Full article

Background: Individuals who are victimized and exploited by the heinous crimes of human trafficking (HT) access healthcare during their exploitation, yet gaps in education on HT content exist in prelicensure nursing programs. This study explored the impact of an HT simulation on nursing students’ preparedness in the identification of victims as well as their perceptions of the impact of this educational intervention on future practices. Methods: A quasi-experimental design with a qualitative component was used. A convenience sample of 120 nursing students were recruited. The participants completed a pretest survey, viewed a preparatory education video, and participated in the simulation followed by a debriefing, a 20-min video, and posttest survey. Results: More than 3/4 of the participants reported no previous exposure to this content. A paired sample t-test showed efficacy (p < 0.001) with a Cohen’s d > 0.8, illustrating an increase in knowledge gained. The qualitative data yielded four themes: eye-opening, educational and informative, increased awareness, and preparedness. Conclusions: Nurses are well-positioned to identify, treat, and respond to victims of HT. The findings underscore the critical need to incorporate comprehensive HT content into prelicensure nursing curricula. Through integration of an HT simulation, future nurses can be better prepared to address this pervasive issue, ultimately improving victim outcomes and ensuring progress towards UN Sustainable Development Goal 5 of Gender Equality and Goal 16 of Peace, Justice, and Strong Institutions. In addition, addressing this topic in prelicensure nursing education ensures that future nurses are not only clinically competent but also morally and emotionally prepared to handle the complexities of HT in their professional roles. Full article

This study investigates the severity of injuries sustained by over seven million participants involved in road traffic incidents in Poland between 2015 and 2024, with a view to supporting sustainable mobility and the United Nations Sustainable Development Goals. Road safety is a crucial dimension of sustainable development, directly linked to public health, urban liveability, and the socio-economic costs of transportation systems. Using a harmonised participant-level dataset, this research identifies key demographic, behavioural, and environmental factors associated with injury outcomes. A novel five-level injury severity variable was developed by integrating inconsistent records on fatalities and injuries. Descriptive analyses revealed clear seasonal and weekly patterns, as well as substantial differences by participant type and driving licence status. Pedestrians and passengers faced the highest risk, with fatality rates more than five times higher than those of drivers. An XGBoost classifier was trained to predict injury severity, and SHAP analysis was applied to interpret the model’s outputs at the feature level. Participant role emerged as the most important predictor, followed by driving licence status, vehicle type, lighting conditions, and road geometry. These findings provide actionable insights for sustainable road safety interventions, including stronger protection for pedestrians and passengers, stricter enforcement against unlicensed driving, and infrastructural improvements such as better lighting and safer road design. By combining machine learning with interpretability tools, this study offers an analytical framework that can inform evidence-based policies aimed at reducing crash-related harm and advancing sustainable transport development. Full article