ABSTRACT Self-piercing riveting (SPR) is increasingly applied in lightweight structures; however, reliable non-destructive evaluation of its fatigue service state remains challenging due to inaccessible internal damage. In this study, the fatigue behavior of TA1 titanium alloy SPR joints was investigated through dynamic response characterization and strength degradation tests. The evolution of natural frequency under cyclic loading exhibited a distinct three-stage degradation behavior corresponding to damage initiation, stable crack propagation, and rapid failure. Based on this relationship, a frequency-based residual life prediction model was developed using a Weibull framework, achieving prediction errors below 5% over the entire fatigue process. In addition, residual strength tests conducted at representative fatigue stages enabled the establishment of a strength degradation model with errors below 3%. By coupling natural frequency variation with strength attenuation, a dual-parameter prediction model was proposed to simultaneously estimate residual life and residual strength from real-time dynamic response data. Experimental validation confirmed that the predicted results consistently fell within the 95% confidence intervals, demonstrating the robustness and accuracy of the proposed method.

Rural farming communities are constantly facing issues related to inconsistent access to electricity, changing climate, and inefficient manual irrigation methods which result in wasted water, low yields, and reliance on labor. Farmers struggle with making irrigation scheduling decisions with climate variability affecting their ability to predict soil moisture, rainfall, or other changes to the environment. This project will propose a low-cost device with IoT-based EMS for agriculture farmers that smart irrigation management. Sensors are collect real-time field data, which is processed by an Arduino and sent to a PC for AI-based preprocessing, classification, and weather prediction. The system autonomously controls an irrigation valve to optimize water use, avoiding overwatering and conserving resources. It displays status on an LCD and enables remote monitoring via communication modules, promoting sustainable and data-driven farming.

ABSTRACT In the heavy production process of manufacturing enterprises, it is difficult to effectively share resource data, which leads to relatively scattered production resources and low utilization rates. This study combined product lifecycle knowledge with time series data and put forward the Framework of Dynamic Manufacturing Knowledge Graph Construction (FDMKG) for the production process of manufacturing enterprises. Specifically, the production process data was divided into two dimensions: static resources and dynamic data stream. The static resources and the production data stream were semantically associated to generate a dynamic knowledge graph. Then, taking the production line of a packaging company as an example, the FDMKG was applied to construct the dynamic knowledge graph. The results show that FDMKG achieves query performance improvements ranging from 1.3 to 26.4 times and attains high diagnostic accuracy with a precision of 0.92, a recall of 0.90, and an F1-score of 0.91. Furthermore, FDMKG efficiently organizes and reuses knowledge throughout the production process, enhancing manufacturing knowledge traceability and reasoning. This study provides valuable practical guidance for knowledge management applications in manufacturing enterprises. Nevertheless, this study focuses on manufacturing production processes, future research should incorporate real-time data from diverse industries to construct a cross-industry dynamic knowledge graph.

This qualitative study examined the integration of Artificial Intelligence (AI) in sustainable freshwater fishery management within the Okavango River ecosystem, combining primary field research with a comprehensive document review. The investigation explored how AI technologies, including machine learning and predictive analytics, can enhance fish stock assessment, habitat monitoring, and resource administration to achieve ecological and socio-economic sustainability. The study emphasizes the Okavango River's unique biodiversity and its critical importance to local communities while assessing AI's potential to transform traditional fishery management approaches. The research employs a dual-method approach, utilizing both face-to-face semi-structured interviews with key stakeholders (fishers, vendors, and officials) and a systematic review of relevant policy documents and documentary reviews. Thematic analysis of interview data and document content reveals key insights about AI adoption challenges, implementation opportunities, and practical applications in freshwater fisheries. Findings demonstrate AI's transformative potential in enabling real-time data collection, predictive population modeling, and overfishing prevention. However, significant barriers emerge, including technological infrastructure gaps, institutional resistance, and capacity-building needs among local stakeholders. By synthesizing field data with existing literature, this study makes a novel contribution to sustainable fishery management discourse, offering context-specific, AI-integrated strategies for the Okavango River ecosystem. The research proposes policy recommendations that address both technical implementation challenges and ethical considerations, grounded in empirical evidence from multiple data sources. Ultimately, this study highlights the critical role of AI in balancing ecosystem conservation with socio-economic development, while demonstrating how mixed-method approaches can strengthen research outcomes in environmental technology studies.

Enhanced cardiovascular disease classification using the mayfly algorithm and real-time data

ParetoInvest: Integrating real-time financial data and multi-objective meta-heuristics for portfolio optimization

Exploring biosensors: Distinctive features and emerging applications.

Real-time synthetic data generation and segmentation of railway fasteners using an attention guided dual-phase diffusion-aided model

Assessment of ultralow emission standards and emission abatement potential of China's coking industry via real-time monitoring data

Tear-based glucose monitoring: A non-invasive approach to diabetes control in resource-limited settings.

Ultra-short-term effects of fine particulate matter (PM2.5) exposure on heart rate variability in susceptible and vulnerable individuals using real-time personal monitoring.

Integration of quantum artificial intelligence in disease diagnosis: A review of methods and applications.

AI-based automated weight prediction in cattle for herd health surveillance.

The global healthcare landscape is entering the data-driven era of Industry 4.0, challenging nursing with profound structural transformations within increasingly complex clinical environments. The nursing profession in Taiwan is now confronting a "dual crisis" marked by a critical workforce shortage and unsustainable clinical workloads. This crisis permeates both clinical practice and nursing education, necessitating proactive and effective reform strategies. Digital technologies, including artificial intelligence (AI), AI-driven virtual avatars, digital twins, and virtual reality offer significant potential to augment clinical decision-making, enhance educational outcomes, and optimize patient self-management. Therefore, digital empowerment, more than simply the integration of technologies, represents a strategic pathway forward to reshaping nursing values and promoting professional dignity. Topol (2019) emphasized that alleviating clinical dilemmas is the primary aim of smart technology integration in the field of healthcare. By leveraging technology to solve practical issues, clinicians can reclaim time for direct patient care, facilitating humanistic, compassionate care and elevating the intrinsic value of nursing. In clinical practice, several healthcare institutions have already implemented virtual agents and remote monitoring systems to assist in clinical problem-solving, disease progression monitoring, and the provision of individualized health education and psychological support. Furthermore, digital twin technology is emerging as a cornerstone of this transformation. Integrating electronic health records with real-time data streams to create "virtual personas" is allowing nurses to detect subtle physiological changes prior to the onset of clinical deterioration, achieving precision care and optimizing healthcare operations. Carroll and Garcia-Dia (2025) argued that digital twins are not only predictive tools but also catalysts for redefining care delivery processes. In the realm of nursing education, academic institutions are actively developing digital curricula that incorporate metaverse elements such as virtual reality and augmented reality to bolster student engagement and learning efficacy. AI virtual humans and immersive virtual reality are at the forefront of pioneering new pedagogical models designed to enable students to cultivate core competencies within engaging and targeted learning environments. Using no-code platforms, educators are increasingly able to independently develop simulation scenarios that incorporate interactive voice response capabilities. These virtual environments allow students to practice nurse-patient communication and clinical decision-making in low-stakes, repeatable settings that effectively mitigate the "reality shock" traditionally experienced during the transition from academic to actual clinical environments. Ultimately, the goal of digital empowerment is to support professional judgment and return time to nursing professionals, ensuring the core of nursing remains centered on care and compassion, aspects that technology remains largely unable to handle. We hope this column will inspire readers to reflect on how technology can be harnessed to construct a sustainable and professionally valuable future for nursing amidst the smart healthcare wave.

Digital twin platform for real-time data communication in UAV environment

Pharmacokinetic analysis is essential for examining how drugs are absorbed, distributed, metabolized, and eliminated from the body. It involves measuring drug concentrations in biological samples, such as plasma, urine, or tissues, over time to assess its behavior and efficacy. Recent advancements in software applications have significantly enhanced the precision and efficiency of pharmacokinetic data analysis. These tools utilize mathematical models and algorithms to process complex datasets, providing insights into key parameters like clearance, half-life, bioavailability, and volume of distribution. Specialized pharmacokinetic software, such as Phoenix WinNonlin, Kinetica, and GastroPlus, allows researchers to perform non-compartmental and compartmental modeling, population pharmacokinetics, and simulation studies with greater accuracy. Additionally, these tools facilitate regulatory compliance by supporting standard bioanalytical guidelines. Integration with bioanalytical methods, including liquid chromatography-mass spectrometry (LC-MS), Ensure seamless data transfer and analysis, minimizing manual errors. The use of such software also streamlines decision-making in drug development by enabling real-time data visualization and reporting. Moreover, automation in data processing saves time and resources while maintaining high analytical quality. This approach not only accelerates the pharmacokinetic evaluation process but also enhances the reliability of results, contributing to the optimization of dosage regimens and improved therapeutic outcomes. In conclusion, the application of advanced pharmacokinetic software has revolutionized bioanalytical studies, making them more efficient, accurate, and compliant with global regulatory standards. This progress underscores the importance of integrating technology in modern pharmacological research.

Background: Despite the adoption of the integrated disease surveillance and response strategy (IDSRS), Chad faces various health challenges, particularly regarding the detection and recording of events; case notification; data collection, processing and transmission; and response. The main of this study is to analyse the evolution and effectiveness of the integrated epidemiological surveillance system in Chad between 2010 and 2024. Methods: This is a retrospective descriptive study. It considers the 6 priority diseases with epidemic potential under surveillance in Chad between 2010 and 2024. The main indicator for monitoring the epidemiological situation is the annual case fatality. Results: Between 2010 and 2024 in Chad, meningitis mortality doubled from 6% to 12% despite a decline in cases, while measles (1.1% mortality before 2019) experienced a surge linked to COVID-19, which was quickly brought under control. There were four cholera outbreaks with fatality rates of 3% (2010-2011), 5.8% (2014), 6.4% (2017) and 4.1% (2019). Neonatal tetanus remained rare but highly fatal (approximately 30% mortality on average), and yellow fever had an average mortality rate of 2.7%. Malaria causes approximately 1,843 deaths each year out of more than 1.2 million suspected cases (mortality rate=0.15%). Conclusions: To strengthen Chad's resilience to epidemiological threats, it is crucial to improve the integration and representativeness of real-time data, training, vaccination coverage, access to difficult areas, infrastructure, and intersectoral coordination, while regularly evaluating the integrated surveillance system.

The Mahalakshmi Scheme is a welfare initiative introduced to provide free public transportation for women, aimed at improving accessibility, safety, and social inclusion. However, the existing manual and semi-digital methods suffer from challenges such as identity misuse, lack of real-time tracking, manual verification errors, and inefficient monitoring of travel limits. To overcome these limitations, this paper proposes a secure and intelligent Digital Bus Pass Management System that automates beneficiary registration, travel validation, and monitoring using modern web and mobile technologies. The proposed system enables female beneficiaries to register using Aadhaar-based identity verification and mobile OTP authentication, ensuring authenticity and eliminating duplicate entries. Upon successful registration, a unique Mahalakshmi ID along with a QR code is generated for each beneficiary. Conductors use a dedicated application to scan the QR code, validate user credentials, and record journey details such as source, destination, and travel distance. The system automatically calculates the traveled distance and enforces a monthly free travel limit, beyond which fare calculation is performed dynamically. A centralized backend manages real-time data processing, maintains travel history, and supports administrative monitoring. The admin dashboard provides insights into beneficiary usage, conductor activity, total distance traveled, and revenue generated from excess travel. Security mechanisms such as role-based access control, encrypted data storage, and authenticated QR validation ensure data integrity and prevent fraudulent usage. The proposed solution enhances transparency, efficiency, and accountability in public transport management while reducing manual workload and operational errors. By integrating mobile applications, cloud-based services, and automated analytics, the system provides a scalable and reliable digital infrastructure for effective implementation of the Mahalakshmi Scheme and serves as a model for smart governance in public transportation systems

This study examines the integration of a rainwater harvesting system with a smart greenhouse for hydroponic lettuce (Lactuca sativa L.) cultivation to improve water-use efficiency and support sustainable precision agriculture. The system incorporates IoT-based environmental monitoring and automated irrigation using real-time data on temperature, humidity, light intensity, water quality, and nutrient conditions. A 30-day comparative experiment was conducted using two irrigation sources: filtered harvested rainwater and groundwater. Measurements included environmental parameters, water use, and plant traits such as leaf number, leaf size, biomass, root length, and chlorophyll content (SPAD). Independent Sample T-Test results showed that groundwater significantly enhanced vegetative growth, increasing fresh weight by up to 62.5% and root length by 44.45% compared to rainwater treatment. In contrast, rainwater-grown plants exhibited 16.67% higher SPAD values, suggesting greater chlorophyll concentration and physiological quality. Laboratory analysis indicated that filtration improved rainwater pH and TDS but increased turbidity and total hardness, while groundwater demonstrated more stable quality across all parameters. These findings highlight the potential of integrating smart irrigation and alternative water sources to support climate-resilient agriculture. Future work should optimize filtration processes and investigate nutrient uptake and physiological responses under varying water qualities in hydroponic systems.

During extracorporeal membrane oxygenation (ECMO) management, early recognition and intervention are essential in cases of membrane oxygenator (MO) oxygenation failure. However, because the MO oxygen transfer (O2 transfer) capacity is influenced by various factors, clear evaluation criteria are lacking. Theoretical O2 transfer values provided by manufacturers are commonly used to assess MO performance; however, these values are presented only under standardized conditions. In this study, to develop an O2 transfer model for real-world ECMO settings, we conducted perfusion experiments using bovine blood under various venous blood compositions (hemoglobin concentration and oxygen saturation) and operational conditions (blood flow and fraction of delivered oxygen). Although substantial variability was observed in the relationships between O2 transfer and individual parameters, partial correlation analysis revealed significant associations with all factors, underscoring the need to incorporate them into the model. A multilayer feedforward neural network was employed to construct the model, achieving a high coefficient of determination (R2 = 0.992), demonstrating excellent predictive performance. The proposed O2 transfer model provides a framework for evaluating the oxygenation performance of MO under diverse ECMO conditions. By enabling comparison with real-time clinical data, it has the potential to support clinical decision-making and enhance the safety of ECMO management.