A fiber-optic monitoring approach for safety assurance of anchor bolt support with application to deep mining roadways

Reliably predicting and characterising corrosion is a fundamental requirement for effective corrosion control in petrochemical plants, particularly for process pipelines that frequently experience corrosion leaks due to corrosive environmental influences. Traditional corrosion monitoring and detection methods have certain limitations in terms of timeliness and scope when identifying pipeline corrosion conditions. This paper proposes a data mining-based approach for predicting the corrosion state of process pipelines in petrochemical plants and further characterises the correlation relationships of key influencing factors. By analysing the characteristics of multi-source corrosion-related data from different types of petrochemical process pipelines and performing data preprocessing, a corrosion rate prediction model was established using genetic algorithm-optimised Gradient Boosting Regression Tree. The model achieved an RMSE of 0.0125, MAE of 0.0090 and R 2 of 0.940. Subsequently, through the Spearman correlation coefficient method and Apriori association rule mining algorithm, pressure, chloride ion concentration, temperature, flow rate, sulphide ion concentration and iron ion concentration were identified as key factors influencing the corrosion rate. Based on the proposed association rule construction method, quantitative patterns were revealed, such as a significant increase in corrosion rate (>0.3 mm/a) when the sulphide ion concentration exceeds 120 mg/L, the flow rate exceeds 80 m 3 /h or the pressure exceeds 0.8 MPa. This paper provides a scientific basis and guidance for identifying potential safety hazards and implementing precise corrosion control in petrochemical plants.

The increasing deployment of offshore infrastructure has raised concerns about the environmental impact of corrosion protection systems, particularly galvanic anodes, which release trace metals such as zinc and aluminium into the marine environment. Traditional monitoring methods often fail to capture the bioavailable fraction of these contaminants or provide adequate temporal resolution. Here, we investigate the brown macroalga Saccharina latissima as a bioindicator of metal emissions from galvanic anodes. Laboratory and mesocosm experiments demonstrated linear relationships between environmental concentrations and metal accumulation, particularly for zinc. Compared to grab and passive sampling, S. latissima provided more consistent and representative exposure estimates. These findings highlight the potential of S. latissima as a cost-effective and reliable bioindicator for offshore trace metal contamination monitoring and its integration into environmental assessment frameworks.

UAV-based deep learning for biodiversity monitoring: Advances, applications, and future directions

The discomfort, invasiveness, and inconvenience associated with traditional glucose monitoring methods continue to hinder patient compliance and the effectiveness of diabetes management. This simulation-driven feasibility study presents the design of the Photoacoustic Glucose Monitoring Device (PAGMD), a non-invasive glucose sensing system that integrates photoacoustic spectroscopy, machine learning, and IoT connectivity to enable real-time glucose estimation. PAGMD employs pulsed near-infrared light to induce glucose-dependent acoustic signals, which are detected by ultrasonic transducers and analyzed by machine learning algorithms for concentration prediction. The device features a hybrid energy harvesting system, combining thermoelectric and piezoelectric elements, to support continuous, battery-assisted operation and long-term usability. The system was theoretically validated using a multi-stage simulation pipeline that included Monte Carlo photon modeling, finite element acoustic simulation, and synthetic glucose dataset generation across a range of physiological conditions. The machine learning models achieved a coefficient of determination of 0.98 and a mean absolute relative difference of 6.97%, with 98.2% of predictions falling within clinically acceptable error zones. While current findings are based on simulated environments, a future validation roadmap encompassing in vitro, ex vivo, and in vivo studies is proposed to support clinical translation. This work should be regarded as a simulation-driven feasibility study; the reported benchmarks represent design targets for future prototyping rather than experimentally validated hardware results. By prioritizing non-invasiveness, ease of use, and adaptive intelligence, PAGMD represents a promising step toward inclusive, personalized metabolic health monitoring, especially for individuals with disabilities or limited dexterity.

Bridges, crucial for surface transportation networks, carry continuous vehicle loads in varying weather conditions. Throughout the service life, bridges accumulate damage due to increased traffic, fatigue, harsh environmental conditions, and natural hazards. The accumulation of damage poses a potential fatality risk if not promptly monitored. Therefore, regular safety assessments and immediate post-disaster evaluations have become standard practice. In this context, the bridge weigh-in-motion (B-WIM) system emerges as a promising alternative to traditional bridge health monitoring (BHM) methods. B-WIM utilizes moving vehicle loads to estimate the bridge influence line (BIL), which provides critical structural information for effective BHM. A recent state-of-the-art review highlights ongoing research primarily focused on detecting and localizing damage along the span, rarely along the width, and with limited studies addressing damage quantification. However, localization and quantification of damage across the bridge width are seldom studied. This paper proposes an approach for novel localization of damage across the bridge width and quantification of damage using a relationship between flexural rigidity and deflection influence line (DIL). To achieve this, the concept of bridge influence surface (BIS), a 2D expansion of individual BILs across the bridge’s width, is utilized. Through a brief description of the B-WIM algorithm, this paper introduces the flexural rigidity estimation (FRE) method for damage quantification. In addition, a static-like DIL reconstruction is proposed to enhance robustness under dynamic bridge response. The proposed approach is initially verified with a 2D finite-element (FE) beam model, followed by a detailed simulation study using a full-scale 3D FE model of a real bridge. Results from comprehensive numerical analyses are further verified through experimental investigation on a scaled-down model of the same bridge. The findings demonstrate promising BIS-based damage localization across the width and FRE-based damage severity assessment. These insights contribute to the enhancement of BHM systems and outline potential avenues for future research.

The rapid advancement of the Internet of Things (IoT) has significantly transformed traditional methods of environmental monitoring by enabling intelligent, automated, and real-time data acquisition systems. In agriculture and plant care, continuous monitoring of temperature, humidity, and soil moisture is essential for ensuring optimal plant health. This paper presents a cost-effective IoT-based plant growth and health monitoring system using the NodeMCU ESP8266 platform, integrated with a DHT11 and soil moisture sensor. A machine learning model further classifies plant leaf conditions into four health categories: Healthy, Rust, Slug damage, and Powdery Mildew. Sensor data is processed and served through an embedded web server, enabling remote real-time monitoring via any standard web browser. Experimental results validate system accuracy, reliability, and suitability for smart agriculture applications

To address the low efficiency of traditional pig behavior monitoring methods, this study proposes a swine motion information recognition algorithm and develops a corresponding monitoring system. The system adopts a front-end/back-end separated architecture. The front-end provides video playback and control, multi-target identification, and trajectory visualization. The back-end performs motion detection and background modeling using the MOG2 algorithm and generates trajectory heatmaps through DBSCAN-based clustering. Two operational workflows are supported, namely manual annotation and automatic feature extraction. The system calculates key motion parameters, including velocity and momentum, and enables the export of the processed data. Experimental results demonstrate that the proposed system can effectively analyze swine motion characteristics and trajectory information, providing an accurate and efficient monitoring solution for large-scale pig farming, with practical value for optimizing husbandry management and improving animal health.

Early detection of corn earworm (Helicoverpa zea) is crucial for subsiding corn crop losses and make sure supportable agricultural productivity. Traditional monitoring methods, composed of manual field inspections and pheromone traps, are often time-consuming, labor-intensive, and prone to hindered detection. This study develops an unmanned aerial vehicle (UAV)-based, real-time detection system for corn earworm infestations using progressive artificial intelligence techniques. Multispectral and thermal images were collected from three corn fields throughout the 2024 growing season, including numerous pest life stages. The dataset includes 2,000 high-resolution images, with metadata as well as geographical coordinates, collection date, and pest stage annotations, authorized by entomological experts. Image preprocessing, as well as normalization, augmentation, and segmentation, was smeared to develop data quality and model generalization. EfficientNet, a convolutional neural network, was engaged for feature extraction, and its outputs were classified using a hybrid method combining Random Forest and Support Vector Machine algorithms to improve detection accuracy and robustness. The system succeeded 90% classification accuracy, with inference times suitable for real-time field application. Field trials recognized the practical applicability of the method under variable ecological conditions. This research shows that fitting UAV imaging with AI-based models can be responsible for suitable, accurate detection of corn earworm, assisting proactive pest management decisions. The methodology can be adjusted to other pest species and crop systems, posturing a scalable solution for precision agriculture and backing sustainable crop protection practices. These findings highlight the potential of connecting AI, remote sensing, and entomological validation for modern, data-driven pest management.

INTRODUCTION: With the emergence of new equipment and technologies, the difficulty of operation and maintenance (O&M) of power distribution equipment (PDE) has been continuously increasing. Traditional manual supervision and monitoring methods have been unable to meet the requirements of real-time performance and accuracy. OBJECTIVES: In order to effectively reduce operational safety risks, we propose an intelligent O&M violation detection method. METHODS: This paper optimizes the architecture of YOLOv12 and constructs three models: a security tool violation carrying recognition model, a general violation operation behavior recognition model, and a specific task violation operation behavior recognition model, this paper also uses the 3D electronic fence and real-time acquisition of each operator's 3D joint coordinates, and predicts the 3D joint coordinates of operation and maintenance personnel based on the Kalman filter. RESULTS: The method achievies accurate detection of O&M violations. In addition, this paper successfully establishes a 3D electronic fence for the O&M environment of PDE, and also achieves the recognition and early warning of violations related to spatial locations. CONCLUSION: The intelligent analysis and evaluation system for power distribution equipment operation and maintenance safety based on multimodal data fusion developed based on this method has been deployed and applied in the PDE O&M environment, achieving intelligent recognition of violations in power distribution equipment operation and maintenance and significantly improving the level of intelligence in on-site safety control.

Hand hygiene is a fundamental measure for preventing healthcare-associated infections, yet traditional monitoring methods are significantly limited by the Hawthorne effect, high resource demands, and an inability to assess procedural quality. Artificial intelligence (AI) technology has emerged as a transformative, automated, and objective approach to address these long-standing challenges. This scoping review sought to systematically map the existing evidence, technical pathways, performance metrics, and implementation challenges of AI for monitoring hand hygiene compliance in healthcare settings. Following the Joanna Briggs Institute (JBI) methodological framework and PRISMA-ScR guidelines, we searched five major databases (PubMed, Scopus, Embase, Web of Science, and IEEE Xplore) for articles published between January 2000 and September 2025, supplemented by grey literature searching and backward citation tracking. Two reviewers independently screened records, assessed full-text reports for eligibility, and extracted data, which were synthesized using descriptive statistics and thematic analysis. Of 800 records identified through database and supplementary searches, 45 studies (2007-2025) were included. The primary technical pathways identified were computer vision (53.3%), wearable sensors (24.4%), Internet of Things-integrated systems (13.3%), and radar/radio frequency-based systems (8.9%). While computer vision achieved high accuracy (95%) in setting-specific ICU models, performance dropped to 56% in generalizable models. Wearable systems demonstrated portability but showed 5%-10% lower specificity than vision-based approaches. Most evidence is derived from small-scale technical validations, with a significant lack of formal fairness analysis and evaluation of clinical workflows or cost-effectiveness. AI-based hand hygiene monitoring shows promise for supporting more objective and scalable hand hygiene surveillance in healthcare settings. However, the field remains at a largely pre-translational stage. Future research should shift from technical feasibility toward implementation science, focusing on establishing standardized motion databases, evaluating ethical governance (e.g., privacy and automation bias), and conducting pragmatic trials to demonstrate sustained clinical benefit and organizational sustainability.

The safe and stable operation of urban water supply networks is critical to ensure urban functionality and sustainable economic development. However, the frequent occurrence of pipeline damage incidents highlights the limitations of traditional monitoring methods based on water quality, flow rate, and pressure. This study employs a wireless monitoring system that overcomes the constraints of traditional monitoring approaches by collecting real-time multi-source data on pipeline structure and operating environments. Support vector regression, feedforward neural networks, and physics-informed machine learning model (PIML) were used to quantitatively analyze the impact of various environmental factors on pipeline structural deflection angles and to train a high-accuracy machine learning prediction model. The results reveal significant variations in earth pressure, soil structure, temperature at the pipe crown and invert, and pore water pressure during pipeline operation, reflecting characteristics of backfilling, foundation settlement, and groundwater dynamics. Machine learning models trained on the monitoring data exhibited outstanding predictive accuracy, with PIML achieving the highest performance—showing an R 2 of 0.985 and a 96.9% overlap between predicted and actual distributions. Furthermore, interpretative analyses identified soil structure variation and burial depth as the primary driving factors influencing pipeline structural deflection angles. Building on this, monitoring strategies can be optimized to provide robust support for improving the safety and operational efficiency of urban water supply pipeline systems.

As renewable energy sources and variable demand increase, maintaining the stability of smart grids (SGs) helps guarantee that electricity systems continue to operate effectively and uninterrupted. More intelligent solutions are required since traditional monitoring methods frequently examine the initial indications of instability. This study proposes a machine learning (ML) methodology for classification and prediction of SG stability to obtain effectiveness in system operations and increase reliability. Fourteen ML models are used in this study for classification and prediction tasks. These ML models are tested under eight evaluation metrics. This study uses the features of engineering and selection to improve the model's performance and accuracy and reduce the dimensionality. Different feature selection methods are used, such as filter, wrapper, and embedded methods. We used two hyperparameter optimization methods, such as Bayesian optimization (tree-structured Parzen estimator, TPE) and metaheuristic optimization (grey wolf optimizer, GWO), to improve ML performance. The results show that light gradient boosting machine achieves near-perfect predictive performance under both optimization strategies, with the TPE-based model reaching 99.95% accuracy and the GWO-based model reaching 99.90%. We use different explainable AI methods to ensure the model is trustworthy. This study improves SG resilience and supports energy efficiency.

Public health systems around the world are facing increasing challenges due to rapid urbanization, emerging infectious diseases, aging populations, and limited healthcare resources. Traditional public health monitoring methods often rely on retrospective data collection and delayed reporting systems, which can limit the ability of health authorities to respond quickly to emerging health threats. In recent years, advances in artificial intelligence (AI), machine learning, and big data analytics have created new opportunities for transforming public health surveillance systems. AI-enabled predictive analytics allows healthcare institutions and government agencies to monitor population health trends in real time, identify potential disease outbreaks early, and design targeted interventions to improve community wellness. This study explores the role of AI-driven predictive models in enhancing public health monitoring systems and improving community-level healthcare outcomes. The proposed framework integrates multiple data sources including electronic health records, wearable health devices, environmental sensors, and social media analytics to develop a comprehensive AI-based health monitoring platform. By applying machine learning algorithms and predictive analytics techniques, the system can detect abnormal health patterns, forecast disease spread, and assist policymakers in making data-driven public health decisions. The research adopts a multidisciplinary approach that combines perspectives from public health informatics, data science, epidemiology, and healthcare management. Empirical analysis demonstrates that AI-enabled monitoring systems can significantly improve early detection of health risks, enhance disease prevention strategies, and optimize resource allocation within healthcare systems. The study also highlights important challenges related to data privacy, algorithmic bias, and infrastructure limitations that must be addressed to ensure responsible and ethical implementation of AI in public health. Overall, the findings emphasize that integrating artificial intelligence into public health monitoring frameworks can strengthen healthcare systems, improve disease prevention capabilities, and promote sustainable community wellness in the digital health era.

Abstract Real-time Precise Point Positioning with Ambiguity Resolution (PPP-AR) critically depends on high-quality State Space Representation (SSR) products for satellite orbit, clock, and code/phase bias corrections. These products, however, often contain errors that can severely degrade user positioning performance. Existing network-based quality monitoring methods primarily rely on phase residuals to detect product errors. However, phase residuals are only effective in revealing SSR product errors after ambiguities have been fixed. Before ambiguities are fixed, the stable or slowly varying components of SSR product errors are absorbed into the float ambiguities, rendering such phase residuals insufficient to fully reveal SSR product errors. As a result, the products with unfixed ambiguities are typically tagged as unreliable due to their uncertain quality. This practice however reduces the availability of SSR products and limit user PPP-AR performance, particularly in challenging environments where fewer satellites are visible. To address this limitation, this study proposes a method that effectively monitors SSR product quality by jointly considering the deviations of float ambiguities from their true integer values and phase residuals associated with float ambiguities. Unlike the ambiguity-fixed phase residuals, these indicators are derived directly from the float PPP solution and provide a unified measure of SSR product errors, regardless of whether the ambiguities remain float or are subsequently fixed. Furthermore, by leveraging the spatial common-mode characteristics of the SSR product errors across a wide-area network, the method derives the corrections to mitigate product error. After correction, the ambiguity-float phase residuals serve as a unified quality indicator applicable to both ambiguity-fixed and ambiguity-float SSR products, enabling reliable quality assessment and anomaly detection. Validation using one month of real-time SSR products from CNES demonstrates that the proposed method significantly improves the availability and reliability of SSR products. Compared with traditional monitoring methods based on ambiguity-fixed phase residuals, the proposed method achieves a comparable and slightly higher ambiguity fixing rate (95.56% versus 92.83%), while significantly reducing the incorrect fixing rate from 0.69 to 0.09%. This improvement substantially mitigates the positioning degradation caused by incorrect ambiguity fixing, reducing the three-dimensional Root Mean Square Error (RMSE) from 15.1 to 4.6 cm.

Modern industries operate in environments where factors such as hazardous gases, high temperatures, humidity variations, and machine vibrations can directly affect worker safety and equipment performance. Continuous monitoring of these parameters is essential to prevent accidents, reduce equipment damage, and ensure smooth industrial operation. However, traditional monitoring methods mainly depend onmanual inspection or basic control systems, which are time- consuming, less accurate, and unable to provide real-time remote access. These limitations can delay fault detection and increase the risk of industrial hazards. To overcome these issues, this project proposes a human-centered and cost effective IoT-based Industrial SCADA (Supervisory Control and Data Acquisition) system for real-time monitoring andautomated alerts. The system uses multiple sensors such as the MQ7 sensor to detect carbon monoxide, the MQ6 sensor toidentifycombustible gases, the DHT11 sensor to measure temperature and humidity, and a vibration sensor to monitor abnormalmachine movements. These sensors continuously collect datafrom the industrial environment and send it to the NodeMCUmicrocontroller, which acts as the main processing and communication unit. The NodeMCU transmits the collecteddata to the ThingSpeak cloud platform through Wi-Fi,allowing users to monitor the system remotely using graphsand dashboards. This helps operators understandenvironmental conditions clearly and take timely action whenrequired.Keywords: Io T , SCADA, Node MCU, IndustrialMonitoring, Thing Speak c l oud, GSM Alerts, GasSensor, DHT 11 , MQ 6 & 7 , Flamesensor , VibrationSensor.

This study developed and evaluated iTrack QR: An Intelligent Faculty Attendance Monitoring System with QR Code and Business Intelligence Integration for the University of Perpetual Help System Manila. The system was designed to address the limitations of traditional attendance monitoring methods, which are often inefficient, error-prone, and lack real-time data processing and analytical capabilities. Specifically, the study aimed to improve attendance accuracy, enhance security through multi-layer validation, and support data-driven decision-making using Business Intelligence tools. A descriptive-developmental research design was employed to guide the design, development, implementation, and evaluation of the system. The system integrates QR code scanning, device UID validation, and selfie-based identity verification to ensure secure and accurate attendance recording. It also includes Business Intelligence dashboards for generating reports and analyzing attendance trends. The system was evaluated using ISO/IEC 25010:2023 software quality standards. Data were collected from IT experts and faculty members through structured survey questionnaires using a Likert scale, and results were analyzed using weighted mean. Findings revealed that iTrack QR achieved high levels of effectiveness in terms of functionality, performance efficiency, reliability, usability, and security, as evaluated by IT experts. Faculty members also demonstrated strong acceptance of the system, confirming that it is practical, user-friendly, and efficient in real-world use. The integration of QR technology with multi-layer validation mechanisms significantly reduced the risk of proxy attendance, while the Business Intelligence component enabled meaningful interpretation of attendance data. The study concludes that iTrack QR is a reliable, secure, and effective solution for modernizing faculty attendance monitoring systems. It contributes to improving operational efficiency, ensuring data accuracy, and supporting evidence-based decision-making in higher education institutions. Future enhancements may focus on improving system scalability, cross-platform compatibility, and advanced analytics to further strengthen its institutional impact.

This paper studies the intelligent identification and location method of crop diseases based on multispectral images of unmanned aerial vehicles. With the development of precision agriculture, traditional crop disease monitoring methods have become difficult to meet the demands of large-scale, high-efficiency and early warning. The article first constructs a multispectral image dataset including visible light, near-infrared and red-edge bands, covering common types of crop diseases. Subsequently, an improved deep learning network architecture was proposed. The attention mechanism was adopted to enhance the model's ability to extract disease features, and a multi-scale feature fusion strategy was introduced to handle disease spots of different sizes. The research designed a data augmentation method based on spectral-spatial joint optimization, which effectively solved the problem of unbalanced samples of crop diseases. To improve positioning accuracy, this paper proposes a disease area positioning algorithm combined with geographic information system, achieving centimeter-level positioning accuracy. The experimental results show that the proposed method improves the accuracy of disease identification by 15.3% compared with the traditional methods, reduces the positioning error to an average of 3.2 centimeters, and can maintain high stability in complex field environments. In addition, this paper has established a complete technical system covering data collection, disease identification and information visualization, and has conducted application verification on crops such as wheat and rice. It has been confirmed that this method can effectively support precise pesticide application decisions in agricultural production and has significant economic and ecological benefits

Soil moisture content (SMC) is a critical factor in agricultural management; however, traditional monitoring methods face limitations regarding spatial resolution and the acquisition of regional dynamics. Unmanned Aerial Vehicle (UAV) remote sensing offers new opportunities for precision monitoring. This study proposes a UAV-based multi-modal remote sensing method for soil moisture estimation. Specifically, novel dual-band and three-band hyperspectral (HS) indices were constructed, and visible (RGB) and thermal infrared (TIR) information were integrated to form a multi-modal data system; simultaneously, multi-modal estimation models were developed by combining four AutoML methods: TPOT, AutoGluon, H2O AutoML, and FLAML. The results indicate that the H2O AutoML model, fusing multi-modal data, exhibited the best performance in estimating soil moisture at depths of 0–20 cm and 20–40 cm (R ≥ 0.72, RMSE 1.99–2.17%), demonstrating superior stability and generalization capabilities compared to other models. This study has made progress in hyperspectral index construction, multi-modal fusion, and soil moisture retrieval, providing a new technical approach for the refined management of agricultural water resources.

Infection remains a leading cause of death in patients with hematologic malignancies, necessitating better strategies to monitor for and identify infections earlier. In this study, we investigated whether an electronic patient-reported outcome (ePRO)-based remote therapeutic monitoring (RTM) platform can reduce infection-related health care utilization compared with traditional monitoring methods. This was a retrospective cohort study of adults with hematologic malignancies receiving anticancer therapy at five community clinics with the Canopy ePRO-based RTM platform integrated into their electronic medical record. The dual primary outcomes of this study were infection-related health care utilization (emergency department [ED] visits and hospital admissions) and outpatient antibiotic use during follow-up. Propensity score weighting was used to balance patient characteristics between groups. Health care costs were estimated by applying unit costs to weighted event rates for ED visits and hospitalizations. A total of 349 patients were enrolled and active in the ePRO program (active ePRO) and 1,296 were not enrolled. In both unadjusted and weighted adjusted analyses, patients in the active ePRO group had significantly higher rates of outpatient antibiotic use (weighted relative risk ratio [RR], 1.20 [95% CI, 1.02 to 1.42]) and lower incidences of infection-related ED visits (weighted RR, 0.66 [95% CI, 0.46 to 0.96]) and hospital admissions (weighted RR, 0.48 [95% CI, 0.25 to 0.89]). Estimated combined savings with ePRO was USD$977,695 for every 1,000 patients per year. ePRO RTM during treatment for hematologic malignancies was associated with a significant reduction in infection-related health care utilization and cost of care. ePRO monitoring may be increasingly beneficial as therapies with more complex toxicity profiles gain traction.