Search Results (3,132)

Leaf water content (LWC) is a vital physiological indicator reflecting crop water status, crucial for precision irrigation and water management. Traditional monitoring methods are labor-intensive and costly, while unmanned aerial vehicle (UAV) remote sensing offers an efficient alternative with high spatiotemporal resolution. This study developed an inversion model for winter wheat LWC based on a stacking ensemble learning framework integrating multispectral and texture features to improve estimation accuracy. UAV multispectral images collected at different growth stages were used to extract 17 vegetation indices (VIs) and 32 texture features (TFs). The top 10 features most correlated with LWC were selected to construct a fused dataset, and five machine learning models (SVM, RF, XGB, PLSR, RR) were combined within a base–meta stacking architecture. Results showed that: (1) Using only multispectral features yielded R² values of 0.526–0.718 and rRMSE of 22.795–29.536%, while texture-only models performed worse (R² = 0.273–0.425, rRMSE = 34.7–36.6%), indicating that single data sources cannot fully represent LWC variability. (2) Combining multispectral and texture features notably improved accuracy (R² = 0.748–0.815; rRMSE = 18.5–21.6%), demonstrating the complementary advantages of spectral and spatial information. (3) Stacking ensemble learning outperformed all single models, achieving the highest precision under fused features (R² = 0.865; rRMSE = 16.3%). (4) LWC distribution maps derived from the stacking model effectively revealed field-scale moisture differences and spatial heterogeneity during different periods. This study confirms that multi-source feature fusion combined with ensemble learning enhances UAV-based crop water estimation, offering a reliable and scalable approach for precision agricultural water monitoring. Full article

Against the backdrop of China’s “carbon peaking” and “carbon neutrality” goals, as well as the advancement of new industrialization, the oil and gas industry is undergoing a critical transformation from resource-dependent growth toward innovation-driven, low-carbon, and high-quality development. The integrated advancement of high-end, intelligent, and green transformation—collectively referred to as the “Three Modernizations”—has become a vital pathway for promoting industrial upgrading and sustainable growth. Based on panel data from 30 Chinese provinces from 2009 to 2023, this study constructs a comprehensive evaluation index system covering 19 secondary indicators across three dimensions: high-end, intelligent, and green development. Using the entropy-weighted TOPSIS method, kernel density estimation, Dagum Gini coefficient decomposition, and σ–β convergence models, the study examines the spatiotemporal evolution, regional disparities, and convergence characteristics of HIG integration, and further explores its driving mechanisms through a two-way fixed effects model and mediation effect analysis. The results show that (1) the overall HIG integration index rose from 0.34 in 2009 to 0.46 in 2023, forming a spatial pattern of “high in the east, low in the west, stable in the center, and fluctuating in the northeast”; (2) regional disparities narrowed significantly, with the Gini coefficient declining from 0.093 to 0.058 and σ decreasing from 7.114 to 6.350; and (3) oil and gas resource endowment, policy support, technological innovation, and carbon emission constraints all positively promote integration, with regression coefficients of 0.152, 0.349, 0.263, and 0.118, respectively. Heterogeneity analysis reveals an increasing integration level from upstream to downstream, with eastern regions leading in innovation-driven development. Based on these findings, the study recommends strengthening policy and institutional support, accelerating technological innovation, improving intelligent infrastructure, deepening green and low-carbon transformation, promoting regional coordination, and establishing a long-term monitoring mechanism to advance the integrated high-quality development of China’s oil and gas industry. Overall, this study deepens the understanding of the internal logic and spatial dynamics of the “Three Modernizations” integration in China’s oil and gas industry, providing empirical evidence and policy insights for accelerating the construction of a low-carbon, secure, and efficient modern energy system. Full article

The codling moth Cydia pomonella (L.) represents a substantial threat to the apple tree industry, with its cellular content being agronomically vital as it serves as the final immunological and toxicological barrier of the pest. Key hemocyte types identified in the hemolymph include plasmatocytes, granulocytes, spherulocytes, and oenocytoids. Hemolymph samples were in vitro suspended in various salt buffers (physiological saline, phosphate saline buffer (PBS) and Galleria mellonella anticoagulant buffer) to determine the most suitable one for agricultural monitoring purposes. The pH influenced the total hemocyte counts and the type of cells that adhered to the slides. PBS (pH 6.5) was found to be optimal for such studies due to its high levels of cellular attachment, cell viability, absence of melanization, and cellular degeneration effects. The supplementation of 5% CaCl₂ to PBS did not enhance the functional utility of the buffer. The in vivo bacterial challenge of larval hemolymph with 4 × 10⁸ sp/mL Bacillus subtilis provided complete clearance from the microbial invader within 30 min. Hemocytes released antimicrobial lysozyme as part of their innate immune responses. Hemocytic examination of larvae as an agricultural practice is strongly recommended for baseline insecticide resistance avoidance and predictive efficiency of integrated pest management in the apple farm. Full article

As the transformative influence of novel technologies sweeps across industries, organisations are called upon to position their staff in the equally dynamic operational environment, which includes embedding technical and legal communication skills in their training programs. For many organisations, internal and external communication of data modelling and related concepts, reporting, and monitoring still pose major challenges. The aim of this research is to develop an effective data training framework for learners with or without mathematical or computational maturity. It also addresses subtle aspects such as the legal and ethical implications of dealing with organisational data. Data was collected from a training course in Python, delivered to government employees in different departments in the United Arab Emirates (UAE). A structured questionnaire was designed to measure the effectiveness of the training program using Python, from the employees’ perspective, based on three key attributes: their personal characteristics, professional characteristics, and technical knowledge. A descriptive analysis of aggregations, deviations, and proportions was used to describe the data attributes gathered for the study. The main findings revealed a huge knowledge gap across disciplines regarding the core skills of big data analytics. In addition, the findings highlighted that previous knowledge about statistical methods of data analysis along with prior programming knowledge made it easier for employees to gain skills in data analytics. While the results of this study showed that their training program was beneficial for the vast majority of participants, responses from the survey indicate that providing a solid knowledge of technical communication, legal and ethical aspects would offer significant insights into the big data analytics field. Based on the findings, we make recommendations for adapting conventional data analytics approaches to align with the complexity or the attainment of the non-orthogonal United Nations Sustainable Development Goals (SDG). Associations of selected responses from the survey with some of the key data attributes indicate that the research highlights vital roles that technology and data-driven skills will play in ensuring a more prosperous and sustainable future for all. Full article

Change detection in remote sensing imagery plays a vital role in urban planning, resource monitoring, and disaster assessment. However, current methods, including CNN-based approaches and Transformer-based detectors, still suffer from false change interference, irregular regional variations, and the loss of fine-grained details. To address these issues, this paper proposes a novel building change detection network named Dense Cross-Fusion and Spatial Compensation Mamba (DCSC Mamba). The network adopts a Siamese encoder–decoder architecture, where dense cross-scale fusion is employed to achieve multi-granularity integration of cross-modal features, thereby enhancing the overall representation of multi-scale information. Furthermore, a spatial compensation module is introduced to effectively capture both local details and global contextual dependencies, improving the recognition of complex change patterns. By integrating dense cross-fusion with spatial compensation, the proposed network exhibits a stronger capability in extracting complex change features. Experimental results on the LEVIR-CD and SYSU-CD datasets demonstrate that DCSC Mamba achieves superior performance in detail preservation and robustness against interference. Specifically, it achieves F1 scores of 90.29% and 79.62%, and IoU scores of 82.30% and 66.13% on the two datasets, respectively, validating the effectiveness and robustness of the proposed method in challenging change detection scenarios. Full article

Road traffic accidents are a major global public health concern, ranking among the top three causes of death worldwide and constituting the leading cause of death among individuals aged 15–29. Monitoring traffic safety status and trends is a vital element of effective road safety management. This study investigates road traffic casualties involving young car drivers (aged 18–24) in the Republic of Serbia from 1997 to 2024, analyzing historical patterns and introducing a predictive model for casualty outcomes. The analytical framework employs machine learning techniques, specifically Long Short-Term Memory (LSTM) networks, to estimate the number of casualties (FSI = Fatal + Serious Injuries) based on various contributing factors. Accurate prediction of accident outcomes is essential for designing targeted road safety measures and reducing casualty numbers. Full article

Comprehensive highway scene understanding and robust traffic risk inference are vital for advancing Intelligent Transportation Systems (ITS) and autonomous driving. Traditional approaches often struggle with scalability and generalization, particularly under the complex and dynamic conditions of real-world environments. To address these challenges, we introduce a novel structured prompting and multi-agent collaborative knowledge distillation framework that enables automatic generation of high-quality traffic scene annotations and contextual risk assessments. Our framework orchestrates two large vision–language models (VLMs): GPT-4o and o3-mini, using a structured Chain-of-Thought (CoT) strategy to produce rich, multiperspective outputs. These outputs serve as knowledge-enriched pseudo-annotations for supervised fine-tuning of a much smaller student VLM. The resulting compact 3B-scale model, named VISTA (Vision for Intelligent Scene and Traffic Analysis), is capable of understanding low-resolution traffic videos and generating semantically faithful, risk-aware captions. Despite its significantly reduced parameter count, VISTA achieves strong performance across established captioning metrics (BLEU-4, METEOR, ROUGE-L, and CIDEr) when benchmarked against its teacher models. This demonstrates that effective knowledge distillation and structured role-aware supervision can empower lightweight VLMs to capture complex reasoning capabilities. The compact architecture of VISTA facilitates efficient deployment on edge devices, enabling real-time risk monitoring without requiring extensive infrastructure upgrades. Full article

Monitoring respiratory activity is a key indicator of physiological health and an essential component in smart textile systems for unobtrusive vital sign assessment. In this work, we present a one-dimensional convolutional recurrent neural network (1D-CRNN) for automatic classification of breathing activity from inertial data acquired by a smart e-textile of 59 subjects. The proposed method integrates convolutional layers for local feature extraction with recurrent layers for temporal context modeling, enabling robust segmentation of breathing and noise segments. The model was trained and evaluated using a stratified five-fold cross-validation scheme to account for inter-subject variability and class imbalance. Across different window sizes, the classifier achieved a mean accuracy of 0.88 and an F1-score of 0.92 at a window size of 2000 samples. The best-performing configuration for a single fold, reached an accuracy of 0.995 and an F1-score of 0.99. Furthermore, near-real-time feasibility was demonstrated, with a total processing time—including data loading, classification, segmentation, and visualization—of only 1.76 s for a 250 s measurement, corresponding to more than 100× faster than the recording time. These results indicate that the proposed approach is highly suitable for embedded, on-device inference within wearable systems. Full article

Dioxins are legacy and persistent environmental pollutants that pose complex and far-reaching risks to human, animal, and ecosystem health. As unintentional byproducts of industrial and combustion processes, dioxins accumulate in the environment, biomagnify through food webs, and exert toxic effects even at low concentrations. This review applies a One Health lens to synthesize current knowledge on dioxin sources, environmental fate, exposure pathways, and toxicological impacts across species. We have critically examined existing surveillance systems, regulatory frameworks, and policy responses, highlighting both achievements and persistent gaps. A fully integrated One Health approach, linking environmental, animal, and human health domains, is essential for effective monitoring, risk assessment, and mitigation. It includes cross-sectoral collaboration, harmonized biomonitoring, evidence-based policy interventions, and transparent risk communication. Emerging evidence on climate-driven dioxin remobilization and microplastic interactions further underscores the urgency of adaptive, system-based strategies. Strengthening global capacity through such integrative approaches is vital to safeguard planetary health from these enduring contaminants. Quantitative insights and illustrative examples support these conclusions. Full article

Accurate and continuous, non-invasive blood pressure (BP) monitoring plays a vital role in the long-term management of cardiovascular diseases. Advances in wearable and flexible sensing technologies have facilitated the transition of non-invasive BP monitoring from clinical settings to ambulatory home environments. However, the measurement consistency and algorithm adaptability of existing devices have not yet reached the level required for routine clinical practice. To address these limitations, comprehensive innovations have been made in material development, sensor design, and algorithm optimization. This review examines the evolution of non-invasive continuous BP measurement, highlighting cutting-edge advances in flexible electronic devices and BP estimation algorithms. First, we introduce measurement principles, sensing devices and limitations of traditional non-invasive BP measurement, including arterial tonometry, arterial volume clamp, and ultrasound-based methods. Subsequently, we review the pulse wave analysis-based BP estimation methods from two perspectives: flexible sensors based on optical, mechanical, and electrical principles, and estimation models that use physiological features or raw waveforms as input. Finally, we conclude the existing challenges and future development directions of flexible electronic technology and intelligent estimation algorithms for non-invasive continuous BP measurement. Full article

Monitoring bottom-hole pressure (BHP) is critical for reservoir management and flow assurance, especially in offshore fields where challenging conditions and production losses are more impactful. However, reliability issues and high installation costs of Permanent Downhole Gauges (PDGs) often limit access to this vital data. Soft sensors offer a cost-effective and reliable alternative, serving as backups or replacements for physical sensors. This study proposes a novel data-driven methodology for estimating flowing BHP using wellhead and topside measurements from plant monitoring systems. The framework employs ensemble methods combined with clustering techniques to partition datasets, enabling tailored supervised training for diverse production conditions. Aggregating results from sub-models enhances performance, even with simpler machine learning algorithms. We evaluated Linear Regression, Neural Networks, and Gradient Boosting (XGBoost and LightGBM) as base models. A case study of a Brazilian Pre-Salt offshore oilfield, using data from 60 wells across nine platforms, demonstrated the methodology’s effectiveness. Error metrics remained consistently below 2% across varying production conditions and reservoir lifecycle stages, confirming its reliability. This solution provides a practical, economical alternative for studies and monitoring in wells lacking PDG data, improving operational efficiency and supporting reservoir management decisions. Full article

Introduction: Individuals residing in long-term care facilities (LTCFs) often experience poor sleep quality. Emerging sensor technologies may improve resident sleep quality and reduce staff workload. This evaluation assessed the impact of a bed sensor technology on LTCF staff experiences and resident outcomes. Methods: A mixed-methods evaluation examined the impact of a pilot implementation of Toch Sleepsense, a non-wearable sensor placed under residents’ beds, which monitors sleep patterns, movement, and vital signs. Data were gathered from staff surveys, interviews, and focus groups from three LTCFs in Western Canada. Descriptive statistics of survey data and thematic analysis of qualitative survey responses and focus groups were used to identify themes in staff experiences with Toch Sleepsense. Results: Staff valued the utility of Toch Sleepsense in providing alerts that support timely interventions and fall prevention. Staff further recognized the value of sensor devices in decreasing repetitive nighttime checks and providing vital sign monitoring. Toch Sleepsense data informed care planning and improved resident comfort. Inconsistent internet connectivity, sensor realignments, and limited training posed challenges to reliability. Conclusions: Sensor technologies like Toch Sleepsense show potential to improve safety, support staff workload management, and improve care practices. Sustained benefits require reliable technical infrastructure, comprehensive staff training, and strong leadership support. Full article

Objectives: This study evaluated changes in serum sodium (S Na) 24 h after the administration of isotonic versus hypotonic intravenous fluids (IVFs) and the incidences of dysnatremia and hyperchloremic metabolic acidosis. Methods: This double-blind, randomized controlled trial involved children aged 3 months to 5 years who were admitted to a general ward between November 2020 and September 2022 and required IVF. We randomly assigned patients (1:1) to receive either an isotonic solution (D₅0.9%NaCl) or hypotonic solution (D₅0.45%NaCl). Serum electrolyte and venous blood gas levels were obtained at the time of IVF administration and 24 and 48 h after IVF administration. During this study, all participants were monitored for vital signs, body weight, fluid intake and output, and clinical symptoms of dysnatremia. Results: Totals of 69 and 68 patients received isotonic and hypotonic solutions, respectively. The mean age was 1.95 ± 1.25 years in the isotonic group and 1.91 ± 1.32 years in the hypotonic group. The initial degrees of dehydration and biochemical indicators were not different. The change in serum sodium level at 24 h was 2.97 (2.32–3.62) mmol/L in the isotonic group and 2.19 (1.54–2.84) mmol/L in the hypotonic group. In both groups, no significant hyponatremia nor hypernatremia occurred. The incidence of hyperchloremic metabolic acidosis was not different between the groups. Neither group showed any complications. Conclusions: Isotonic fluids may be a preferred option for IVFs in pediatric patients under 5 years of age with medical conditions on a general ward, especially within 24 h, due to their potential to better maintain serum sodium levels without increasing the risk of fluid overload or electrolyte complication. Full article

Background: Patient monitors assist caregivers in identifying deterioration earlier by using threshold alarms. Not all of the threshold alarms necessitate immediate action, but some are a result of the triggering of a physiological event. We aim to use pattern recognition techniques to identify threshold alarm signal patterns before the onset of critical illness, thereby enabling the faster and more effective detection of clinical deterioration and supporting better clinical decision-making. Method: Secondary data from 774 pediatric patients were extracted from the IMPALA Project conducted in the High Dependency Unit (HDU) at Queen Elizabeth and Zomba Central Hospitals in Malawi. The threshold alarm data were generated from the vital signs using WHO age cut-offs and GOAL3 age cut-offs. Time-segmented alarm analysis was conducted to examine the distribution of threshold alarms around each vital sign 8 h before the onset of critical illness events. Density-Based Spatial Clustering of Applications with Noise (DBSCAN) was used to generate threshold alarm signal patterns for each signal per individual before the onset of a critical illness event. We used three machine learning approaches, random forest, support vector machine, and decision tree, to learn threshold alarm patterns in signals preceding critical illness events. Results: The total threshold alarm summed up to (3,910,083) in total for WHO and (2,041,740) for GOAL3. Temporal distributions of ECGRR, ECGHR and oxygen saturation rate (SPO2) threshold alarms were observed, revealing patterns before the onset of the critical illness events. A pattern of most threshold alarms was distributed around (40–60) for ECGRR upper threshold alarms and (0–20) for ECGRR lower threshold alarms, (80–85) for ECGHR lower threshold alarms and (140–160) for ECGHR upper threshold alarms, and (85–90) for SPO2 for death (CPR and PICU), around WHO threshold alarms. For sepsis, most of these threshold alarms were distributed around (40–50) of ECGRR upper threshold alarms and (0–20) for ECGRR lower threshold alarms, (150–180) for ECGHR upper threshold alarms, and (85) for SPO2 for WHO threshold alarms, and most of the threshold alarms had a duration of less than 30 s. The results indicate that the random forest classifier performed better in learning the threshold patterns, with an accuracy of 93% and an area under the curve of 92, compared to using the support vector machine learning model and decision tree, which had an accuracy from a classification report of 85% and 94%, with low death and sepsis precision, recall, and F1-Score. Conclusions: The analysis of threshold alarm data before critical illness events has provided valuable insights into threshold alarm patterns associated with death and sepsis. The data revealed distinct patterns in ECGRR, ECGHR, and SPO2 signals, and most of the threshold alarms were in the lower duration. The random forest classifier effectively distinguished these learned patterns around death and sepsis events compared to other algorithms. Further studies are required on the use of algorithms on all vital sign signal features in clinical settings. Full article

Sustainable aquaculture is increasingly vital to meet global protein demands while ensuring fish product safety and environmental stewardship from a One Health perspective. This review addresses fish hygiene as a comprehensive, multi-stage challenge encompassing water quality management, pathogen control, antimicrobial stewardship, feeding practices, humane slaughter, post-harvest handling, and monitoring systems. We examined current practices and technologies that promote hygienic standards and reduce contamination risks across production cycles. The integration of biosecurity measures and alternative health-promoting agents contributes to disease prevention and reduces reliance on antimicrobials. Responsible drug administration aligned with regulatory frameworks minimizes residues and antimicrobial resistance. Feeding strategies incorporating sustainable and safe ingredients further support fish health and product quality. Critical control points during slaughter and post-harvest processing ensure microbial safety and prolong shelf life. Advanced monitoring and traceability systems enable real-time oversight and enhance food safety assurance. Finally, certification programs and robust regulatory policies are essential to standardize practices and facilitate access to international markets. Collectively, these strategies foster sustainable aquaculture that safeguards public health, maintains ecological integrity, and supports economic viability. This holistic approach positions fish hygiene not as a final quality check, but as an integral, continuously managed component of responsible aquaculture production. Full article