Search Results (282)

Early warning of structural damage from induced seismic events requires rapid and reliable ground motion forecasting. This study presents a novel real-time framework that couples a deep learning approach with structural fragility assessment to generate immediate damage alerts following the onset of seismic shaking. Long Short-Term Memory (LSTM) neural networks are employed to predict full S-wave accelerograms from initial P-wave inputs, trained and tested on accelerometric records from induced seismicity scenarios. The predicted S-wave motion is then used as input for a suite of fragility curves in real time to estimate the probability of structural damage for masonry buildings typical in rural areas of geothermal platforms. The proposed method captures both the temporal evolution of shaking and the structural response potential, offering critical seconds of lead time for automated decision-making systems. Results demonstrate high predictive accuracy of the LSTM model and effective early classification of structural risk. This integrated system provides a practical tool for early warning or rapid response in regions experiencing anthropogenic seismicity, such as those affected by geothermal operations. Full article

To gain a comprehensive understanding of the current research landscape in the field of new energy vehicle (NEV) fires and to explore its knowledge base and emerging trends, bibliometric methods—such as co-occurrence, clustering, and co-citation analyses—were employed to examine the relevant literature. A research knowledge framework was established, encompassing four primary themes: thermal management and performance optimization of power batteries, battery materials and their safety characteristics, thermal runaway (TR) and fire risk assessment, and fire prevention and control strategies. The key research frontiers in this domain could be classified into five categories: mechanisms and propagation of TR, development of high-safety battery materials and flame-retardant technologies, thermal management and thermal safety control, intelligent early warning and fault diagnosis, and fire suppression and firefighting techniques. The focus of research has gradually shifted from passive identification of causes and failure mechanisms to proactive approaches involving thermal control, predictive alerts, and integrated system-level fire safety solutions. As the field advances, increasing complexity and interdisciplinary integration have emerged as defining trends. Future research is expected to benefit from broader cross-disciplinary collaboration. These findings provide a valuable reference for researchers seeking a rapid overview of the evolving landscape of NEV fire-related studies. Full article

Early train detection is vital for ensuring the safety of railway personnel, particularly in remote locations where fixed signaling infrastructure is unavailable. Unlike many existing solutions that rely on high-power, high-cost sensors and compute platforms, this work presents a lightweight, low-cost, and portable framework designed to run entirely on resource-constrained microcontrollers with just kilobytes of Random Access Memory (RAM). The proposed system uses vibration data from low-cost accelerometers and employs a simple yet effective Linear Regression (LR) model for almost real-time prediction of train arrival times. To ensure feasibility on low-end hardware, a parallel-processing framework is introduced, enabling continuous data collection, Machine Learning (ML) inference, and wireless communication with strict timing and energy constraints. The decision-making process, including data preprocessing and ML prediction, completes in under 10 ms, and alerts are transmitted via LoRa, enabling kilometer-range communication. Field tests on active railway lines confirm that the system detects approaching trains 15 s in advance with no false negatives and a small number of explainable false positives. Power characterization demonstrates that the system can operate for more than 6 days on a 10 Ah battery, with potential for months of operation using wake-on-vibration modes. Full article

Background and Aim: Food hygiene is fundamental to public health, ensuring safe and nutritious food free from contaminants, and is vital for economic development and sustainability. The Hazard Analysis and Critical Control Points (HACCP) system is a crucial tool for managing risks in food production. Despite global recognition of food safety’s importance, significant disparities exist, especially in Southern Italy, where diverse food production, tourism, and economic factors pose challenges to enforcing hygiene standards. This study evaluates non-compliance with food hygiene regulations within a Local Health Authority (LHA) in Calabria, Southern Italy, to inform effective public health strategies. Materials and Methods Authorized by the Food Hygiene and Nutrition Service (FHNS) of the LHA, the study covers January 2022 to December 2024, analyzing 579 enterprises with 1469 production activities. Inspections followed EC Regulation No. 852/2004, verifying the correct application of procedures based on the Hazard Analysis and Critical Control Points (HACCP) principles, including the operator’s monitoring of Critical Control Points (CCPs), and adherence to Good Hygiene Practices (GHPs). Non-compliances were classified by severity, and corrective and punitive actions were applied. Data were analyzed annually and across the full period using descriptive statistics and chi-squared tests to assess trends. Results: Inspection coverage increased markedly from 29.8% of production activities in 2022 to 62.5% in 2023, sustaining 62.0% in early 2024, exceeding the growth of new activities. Inspections were mainly triggered by RASFF alerts (22.4%), routine controls (20.0%), and verification of previous prescriptions (14.3%). The most frequent corrective measures were long-term prescriptions (28.6%), violation reports (22.9%), and short-term prescriptions (20.0%). Enterprises averaged 4.61 production activities, highlighting operational complexity. Conclusions: This study provides a granular analysis of food hygiene non-compliance within a Local Health Authority (LHA) in Southern Italy, to inform effective public health strategies. While official control data may be publicly available in some contexts, our research offers a unique, in-depth view of inspection triggers, non-compliance patterns, and corrective measures, which is crucial for understanding specific regional challenges. The analysis reveals that the prevalence of long-term prescriptions and reliance on RASFF alerts indicate systemic challenges requiring sustained interventions. Full article

A new cascaded model is proposed to improve the accuracy and early warning capability of predicting mine water inrush accidents. The model sequentially applies a Bidirectional Long Short-Term Memory Network (BiLSTM) and a Variational Autoencoder (VAE) to capture the spatio-temporal dependencies between borehole water level data and water inrush events. First, the BiLSTM predicts borehole water levels, and the prediction errors are analyzed to summarize temporal patterns in water level fluctuations. Then, the VAE identifies anomalies in the predicted results. The spatial correlation between borehole water levels, induced by the cone of depression during water inrush, is quantified to assign weights to each borehole. A weighted comprehensive anomaly score is calculated for final prediction. In actual water inrush cases from Xin’an Coal Mine, the BiLSTM-VAE model triggered high-risk alerts 9 h and 30 min in advance, outperforming the conventional threshold-based method by approximately 6 h. Compared with other models, the BiLSTM-VAE demonstrates better timeliness and higher accuracy with lower false alarm rates in mine water inrush prediction. This framework extends the lead time for implementing safety measures and provides a data-driven approach to early warning systems for mine water inrush. Full article

This study constructed an integrated underwater pipeline monitoring system, which combines pipeline posture sensing modules and pipeline leakage detection modules. The proposed system can achieve the real-time monitoring of pipeline posture and the comprehensive assessment of pipeline damage. By deploying pipeline posture sensing and leakage detection modules in array configurations along an underwater pipeline, information related to pipeline posture and flow variations is continuously collected. An array of inertial sensor nodes that form the pipeline posture sensing system is used for real-time pipeline posture monitoring. The system measures underwater motion signals and obtains bending and buckling postures using posture algorithms. Pipeline leakage is evaluated using flow and water temperature data from Hall sensors deployed at each node, assessing pipeline health while estimating the location and area of pipeline damage based on the flow values along the nodes. The human–machine interface designed in this study for underwater pipelines supports automated monitoring and alert functions, so as to provide early warnings for pipeline postures and the analysis of damage locations before water supply abnormalities occur in the pipelines. Underwater experiments validated that this system can precisely capture real-time postures and damage locations of pipelines using sensing modules. By taking flow changes at these locations into consideration, the damage area with an error margin was estimated. In the experiments, the damage areas were 8.04 cm² to 25.96 cm², the estimated results were close to the actual area trends (R² = 0.9425), and the area error was within 5.16 cm² (with an error percentage ranging from −20% to 26%). The findings of this study contribute to the management efficiency of underwater pipelines, enabling more timely maintenance while effectively reducing the risk of water supply interruption due to pipeline damage. Full article

This paper proposes a hybrid predictive maintenance framework that combines the discriminative power of XGBoost with the interpretability of a Bayesian Network automatically learned from sensor data. Targeted at textile manufacturing equipment operating under Industry 4.0 conditions, the system addresses the trade-off between early fault detection and decision transparency. Sensor data, including vibration, temperature, and electric current, were collected from a multi-needle quilting machine using a custom IoT-based platform. A degradation-aware labeling scheme was implemented using historical maintenance logs to assign semantic labels to sensor readings. A Bayesian Network structure was learned from this data via a Hill Climbing algorithm optimized with the Bayesian Information Criterion, capturing interpretable causal dependencies. In parallel, an XGBoost model was trained to improve classification accuracy for incipient faults. Experimental results demonstrate that XGBoost achieved an F1-score of 0.967 on the high-degradation class, outperforming the Bayesian model in raw accuracy. However, the Bayesian Network provided transparent probabilistic reasoning and root cause explanation capabilities—essential for operator trust and human-in-the-loop diagnostics. The integration of both models yields a robust and interpretable solution for predictive maintenance, enabling early alerts, visual diagnostics, and scalable deployment. The proposed architecture is validated in a real production line and demonstrates the practical value of hybrid AI systems in bridging performance and interpretability for predictive maintenance in Industry 4.0 environments. Full article

The paper presents AgriMicro, a modern Farm Management Information System (FMIS) designed to help farmers monitor and optimize corn crops from sowing to harvest, by leveraging cloud technologies and machine learning algorithms. The platform is built on a modular architecture composed of multiple components implemented through microservices such as the weather and soil service, recommendation and alert engine, field service, and crop service—which continuously communicate to centralize field data and provide real-time insights. Through the ongoing exchange of data between these services, different information pieces about soil conditions, crop health, and agricultural operations are processed and analyzed, resulting in predictions of crop evolution and practical recommendations for future interventions (e.g., fertilization or irrigation). This integrated FMIS transforms collected data into concrete actions, supporting farmers and agricultural consultants in making informed decisions, improving field productivity, and ensuring more efficient resource use. Its microservice-based architecture provides scalability, modularity, and straightforward integration with other information systems. The objectives of this study are threefold. First, to specify and design a modular FMIS architecture based on microservices and cloud computing, ensuring scalability, interoperability and adaptability to different farm contexts. Second, to prototype and integrate initial components and Internet of Things (IoT)-based data collection with machine learning models, specifically Random Forest and XGBoost, to provide maize yield forecasting as a proof of concept. Model performance was evaluated using standard predictive accuracy metrics, including the coefficient of determination (R²) and the root mean square error (RMSE), confirming the reliability of the forecasting pipeline and validated against official harvest data (average maize yield) from the Romanian National Institute of Statistics (INS) for 2024. These results confirm the reliability of the forecasting pipeline under controlled conditions; however, in real-world practice, broader regional and inter-annual variability typically results in considerably higher errors, often on the order of 10–20%. Third, to present a Romania based case study which illustrates the end-to-end workflow and outlines an implementation roadmap toward full deployment. As this is a design-oriented study currently under development, several services remain at the planning or early prototyping stage, and comprehensive system level benchmarks are deferred to future work. Full article

Background/Objectives: Sepsis remains one of the leading causes of mortality worldwide, characterized by a complex and heterogeneous clinical presentation. Despite advances in patient monitoring and biomarkers, early detection of sepsis in the intensive care unit (ICU) is often hampered by incomplete data and diagnostic uncertainty. In recent years, machine learning models have been proposed as predictive tools, but many function as opaque “black boxes”, meaning that humans are unable to understand algorithmic reasoning, poorly suited to the uncertainty-laden clinical environment of critical care. Even when post-hoc interpretability methods are available for these algorithms, their explanations often remain difficult for non-expert clinicians to understand. Methods: In this clinical perspective, we explore the specific advantages of probabilistic graphical models, particularly Bayesian Networks (BNs) and their dynamic counterparts (DBNs), for sepsis prediction. Results: Recent applications of AI models in sepsis prediction have demonstrated encouraging results, such as DBNs achieving an AUROC of 0.94 in early detection, or causal probabilistic models in hospital admissions (AUROC 0.95). These models explicitly represent clinical reasoning under uncertainty, handle missing data natively, and offer interpretable, transparent decision paths. Drawing on recent studies, including real-time sepsis alert systems and treatment-effect modeling, we highlight concrete clinical applications and their current limitations. Conclusions: We argue that BNs present a great opportunity to bridge the gap between artificial intelligence and bedside care through human-in-the-loop collaboration, transparent inference, and integration into clinical information systems. As critical care continues to move toward data-driven decision-making, Bayesian models may offer not only technical performance but also the epistemic humility needed to support clinicians facing uncertain, high-stakes decisions. Full article

Traditional academic monitoring practices rely on retrospective data analysis, generally identifying at-risk students too late to take meaningful action. To address this, this paper proposes a real-time, rule-based decision support system designed to increase student achievement by early detection of disengagement, meeting the growing demand for prompt academic intervention in online and blended learning contexts. The study uses the Open University Learning Analytics Dataset (OULAD), comprising over 32,000 students and millions of virtual learning environment (VLE) interaction records, to simulate weekly assessments of engagement through clickstream activity. Students were flagged as “at risk” if their participation dropped below defined thresholds, and these flags were associated with assessment performance and final course results. The system demonstrated 72% precision and 86% recall in identifying failing and withdrawn students as major alert contributors. This lightweight, replicable framework requires minimal computing power and can be integrated into existing LMS platforms. Its visual and statistical validation supports its role as a scalable, real-time early warning tool. The paper recommends integrating real-time engagement dashboards into institutional LMS and suggests future research explore hybrid models combining rule-based and machine learning approaches to personalize interventions across diverse learner profiles and educational contexts. Full article

This study explores the impact of the 2022 Mw 6.8 Luding Earthquake on various geo-hazards and their corresponding rainfall thresholds. Focusing on the seismic intensity VI zone in Sichuan Province, China, we analyzed 1979 geo-hazard records and hourly precipitation data from 475 stations between 2010 and 2024. Empirical ID (intensity–duration) and AC (accumulated rainfall–continuous rainfall duration) rainfall threshold models are established based on these datasets. By comparing pre- and post-earthquake data, this study assesses changes in the spatial distribution and triggering rainfall thresholds of landslides, rockfalls, and debris flows. The results indicate a significant increase in geo-hazard risks post-earthquake, particularly near the Xianshuihe Fault, with rockfall risks exhibiting the most pronounced rise. Statistical analysis reveals that the rainfall thresholds required to trigger geo-hazards decreased notably after the earthquake: ID models indicate a decrease of approximately 20%, while AC models show a reduction of about 20% in the western zone and 10% in the eastern zone. A four-level early warning system is developed using empirical rainfall threshold models, offering tailored hazard alerts for different regions and geo-hazard types. The variation in threshold values between the east and west zones highlights the influence of differing topographic and climatic conditions. These findings provide critical insights for post-seismic hazard assessment and inform more effective, sustainable early warnings, thereby supporting more reliable and sustainable disaster risk management in earthquake-affected regions. Full article

Background: Mobile health (mHealth) applications have shown promise for the primary and secondary prevention of diseases in high-risk individuals. Implementing mHealth solutions for secondary prevention and early alert systems in patients with acute coronary syndrome (ACS) could have significant societal benefits. However, the attitudes of at-risk populations towards these technologies, including concerns about technological literacy and privacy, have not been thoroughly investigated. As technology incorporation expands, these issues are expected to change. This study aimed to evaluate the attitudes of post-ACS patients towards varying levels of intrusive mHealth applications and how these attitudes evolved over a five-year period. Methods: A cross-sectional study was carried out with two cohorts of post-ACS inpatients (110 patients each from 2014 and 2019), who were surveyed using a 39-item questionnaire assessing their technological literacy and opinions on support tools and intrusive technologies, such as wearables and GPS tracking. Results: The two cohorts exhibited stable demographic characteristics, but in 2019, participants showed higher technological literacy and increased engagement in travel and physical activities. Notably, there was a significant rise in hypertension, hyperlipidemia, and family history of Coronary Artery Disease (CAD) in the 2019 cohort. Acceptance of remote health monitoring improved significantly in 2019, influenced by technological literacy. Conclusions: Attitudes towards eHealth solutions and remote biosignal monitoring post-ACS may change over time with increased technological literacy. Future research should address patient-specific concerns that could affect the acceptance of new technological solutions to enhance post-ACS outcomes. Our findings emphasize the importance of improving technological literacy to boost the adoption and effectiveness of eHealth interventions. Full article

Alzheimer’s disease is a growing global health concern, demanding innovative solutions for early detection, continuous monitoring, and patient support. This article reviews recent advances in Smart Wearable Medical Devices (SWMDs), Internet of Things (IoT) systems, and mobile applications used to monitor physiological, behavioral, and cognitive changes in Alzheimer’s patients. We highlight the role of wearable sensors in detecting vital signs, falls, and geolocation data, alongside IoT architectures that enable real-time alerts and remote caregiver access. Building on these technologies, we present LumiCare, a conceptual, context-aware mobile system that integrates multimodal sensor data, chatbot-based interaction, and emerging 6G network capabilities. LumiCare uses machine learning for behavioral analysis, delivers personalized cognitive prompts, and enables emergency response through adaptive alerts and caregiver notifications. The system includes the LumiCare Companion, an interactive mobile app designed to support daily routines, cognitive engagement, and safety monitoring. By combining local AI processing with scalable edge-cloud architectures, LumiCare balances latency, privacy, and computational load. While promising, this work remains at the design stage and has not yet undergone clinical validation. Our analysis underscores the potential of wearable, IoT, and mobile technologies to improve the quality of life for Alzheimer’s patients, support caregivers, and reduce healthcare burdens. Full article

Traditional landslide monitoring systems struggle to capture the spatiotemporal dynamics of rainfall-induced hydro-mechanical processes, with a significant risk of signal loss during critical “unsaturated-saturated” state transitions. To address this issue, we propose an integrated framework that utilizes FLAC3D numerical simulation to dynamically optimize multi-sensor deployments. Through coupled seepage-stress analysis under different rainfall scenarios in China’s Tianshan Mountains, this study achieved the following objectives: (1) risk-based sensor deployment by precisely identifying shallow shear strain concentration zones (5–15 m) through FLAC3D simulation (with FBG density of 0.5 m/point in the core sliding belt and GNSS spacing ≤ 50 m); (2) establishment of a multi-parameter cooperative early warning system (displacement > 50 mm/h, pore water pressure > 0.4 MPa, strain > 6400 με), where red alerts are triggered when at least two parameters exceed thresholds, reducing false alarm rates; and (3) development of an adaptive sampling framework based on three rainfall intensity scenarios, which increases measurement frequency during heavy rainfall to capture transient critical points (GNSS sampling rate enhanced to 10 Hz). This approach significantly enhances the capture capability of critical hydro-mechanical transition processes while reducing the monitoring redundancy. The framework provides a scientifically robust and reliable solution for slope disaster-risk prevention and management. Full article

Background/Objectives: Adolescent idiopathic scoliosis (AIS) often requires prolonged brace use to prevent curve progression. However, adherence is challenging due to discomfort, mobility restrictions, and psychosocial stressors. This study evaluated the feasibility and clinical utility of a mobile health (mHealth) system for real-time tracking of brace adherence and treatment-related experiences in adolescents with AIS. Methods: Thirty adolescents with AIS (mean age = 12.9, SD = 1.8) undergoing brace treatment at a tertiary care center used a custom app for 90 days. The app collected daily self-reports on brace wear duration, discomfort, movement limitations, emotional distress, and social challenges. A clinical alarm system alerted providers when patient input indicated potential concerns. Primary outcomes were feasibility (adherence to daily use and usability ratings) and brace adherence. Secondary outcomes included the app’s capacity to identify treatment-related challenges and its association with changes in stress, quality of life, anxiety, and depression. Results: Participants reported meeting recommended brace wear time (≥16 h/day) on 84.8% of days. The app triggered 186 clinical alarms, with the most frequent related to emotional distress (23.1%) and pain (15.6%). Alarm frequency declined over time. Improvements of ≥20% in psychological outcomes were observed in 20–26.7% of participants, while group-level changes were nonsignificant. Conclusions: mHealth-based monitoring appears feasible and acceptable for digitally engaged adolescents with AIS. The app supported early detection of treatment barriers and prompted timely clinical responses. Despite limitations, it shows promise as a tool to improve treatment engagement and address psychosocial challenges in scoliosis care. Full article