Search Results (26,806)

Cotton leaf disease detection is essential for accurate identification and timely management of diseases. It plays a crucial role in enhancing cotton yield and quality while promoting the advancement of intelligent agriculture and efficient crop harvesting. This study proposes a novel method for detecting cotton leaf diseases based on large language model (LLM)-generated image synthesis and an improved DEMM-YOLO model, which is enhanced from the YOLOv11 model. To address the issue of insufficient sample data for certain disease categories, we utilize OpenAI’s DALL-E image generation model to synthesize images for low-frequency diseases, which effectively improves the model’s recognition ability and generalization performance for underrepresented classes. To tackle the challenges of large-scale variations and irregular lesion distribution, we design a multi-scale feature aggregation module (MFAM). This module integrates multi-scale semantic information through a lightweight, multi-branch convolutional structure, enhancing the model’s ability to detect small-scale lesions. To further overcome the receptive field limitations of traditional convolution, we propose incorporating a deformable attention transformer (DAT) into the C2PSA module. This allows the model to flexibly focus on lesion areas amidst complex backgrounds, improving feature extraction and robustness. Moreover, we introduce an enhanced efficient multi-dimensional attention mechanism (EEMA), which leverages feature grouping, multi-scale parallel learning, and cross-space interactive learning strategies to further boost the model’s feature expression capabilities. Lastly, we replace the traditional regression loss with the MPDIoU loss function, enhancing bounding box accuracy and accelerating model convergence. Experimental results demonstrate that the proposed DEMM-YOLO model achieves 94.8% precision, 93.1% recall, and 96.7% mAP@0.5 in cotton leaf disease detection, highlighting its strong performance and promising potential for real-world agricultural applications. Full article

Thermal cameras are becoming popular in several applications of precision agriculture, including crop and soil monitoring, for efficient irrigation scheduling, crop maturity, and yield mapping. Nowadays, these sensors can be integrated as payloads on unmanned aerial vehicles, providing high spatial and temporal resolution, to deeply understand the variability of crop and soil conditions. However, few commercial software programs, such as PIX4D Mapper, can process thermal images, and their functionalities are very limited. This paper reports on the implementation of a custom MATLAB^® R2024a script to extract agronomic information from thermal orthomosaics obtained from images acquired by the DJI Mavic 3T drone. This approach enables us to evaluate the temperature at each point of an orthomosaic, create regions of interest, calculate basic statistics of spatial temperature distribution, and compute the Crop Water Stress Index. In the authors’ opinion, the reported approach can be easily replicated and can serve as a valuable tool for scientists who work with thermal images in the agricultural sector. Full article

Background: Varicella remains a prevalent vaccine-preventable disease, but breakthrough infections are increasingly reported. However, long-term, population-based studies investigating the temporal and demographic characteristics of breakthrough varicella remain limited. Methods: This retrospective study analyzed surveillance data from Jinhua City, China, from 2016 to 2024. Varicella case records were obtained from the China Information System for Disease Control and Prevention (CISDCP), while vaccination data were retrieved from the Zhejiang Provincial Immunization Program Information System (ISIS). Breakthrough cases were defined as infections occurring more than 42 days after administration of the varicella vaccine. Differences in breakthrough interval were analyzed across subgroups defined by dose, sex, age, population category, and vaccination type. A bivariate cubic regression model was used to assess the combined effect of initial vaccination age and dose interval on the breakthrough interval. Results: Among 28,778 reported varicella cases, 7373 (25.62%) were classified as breakthrough infections, with a significant upward trend over the 9-year period (p < 0.001). Most cases occurred in school-aged children, especially those aged 6–15 years. One-dose recipients consistently showed shorter breakthrough intervals than two-dose recipients (M = 62.10 vs. 120.10 months, p < 0.001). Breakthrough intervals also differed significantly by sex, age group, population category, and vaccination type (p < 0.05). Regression analysis revealed a negative correlation between the initial vaccination age, the dose interval, and the breakthrough interval (R² = 0.964, p < 0.001), with earlier and closely spaced vaccinations associated with longer protection. Conclusions: The present study demonstrates that a two-dose varicella vaccination schedule, when initiated at an earlier age and administered with a shorter interval between doses, provides more robust and longer-lasting protection. These results offer strong support for incorporating varicella vaccination into China’s National Immunization Program to enhance vaccine coverage and reduce the public health burden associated with breakthrough infections. Full article

Trajectory data contain numerous sensitive attributes. Unauthorized disclosure of precise user trajectory information generates persistent privacy and security concerns that significantly impact daily life. Most existing trajectory privacy protection schemes focus on geographic trajectories while neglecting the critical importance of semantic trajectories, resulting in ongoing privacy vulnerabilities. To address this limitation, we propose the Semantic Behavior Sequence-based Trajectory Privacy Protection method (SBS-TPP). Our approach integrates short-term and long-term behavioral patterns within a user behavior modeling layer to identify user preferences. A dual-model framework (geographic and semantic) generates noise-injected trajectories with maximized noise potential. This methodology applies symmetric noise addition to both geographic trajectory fragments and semantic trajectory segments, optimizing trajectory data utility while ensuring robust protection of sensitive information. The SBS-TPP framework operates in the following two phases: firstly, behavior modeling, which comprises interest extraction from behavioral trajectory sequences, and secondly, noise generation, which creates synthetic noise locations with maximal semantic expectation from original locations, yielding privacy-enhanced trajectories for publication. Experimental results demonstrate that our interest extraction model achieves 93.7% accuracy while maintaining 81.6% data utility under strict privacy guarantees. The proposed method significantly enhances data usability and enables effective recommendation services without compromising user privacy or security. Full article

Background/Objectives: Men have historically contributed significantly to mental health nursing, particularly in inpatient settings, where their presence has supported patient recovery and safety. Despite this legacy, men remain under-represented in the nursing workforce, and addressing this imbalance is critical to workforce sustainability. This study offers a novel contribution by exploring the lived experiences, motivations, and professional identities of men in mental health nursing, an area that has received limited empirical attention. The aim of the study is to examine the characteristics, qualities, and attributes of mental health nurses who are male, which contributes to their attraction to and retention within the profession. Methods: A qualitative interpretive inquiry was conducted among nurses who were male and either currently or previously employed in mental health settings. Two focus groups were conducted using semi-structured questions to explore their career pathways, motivations, professional identities, and perceived contributions. Thematic analysis was used to identify key themes and patterns in their narratives. Results: Seven participants, with 10–30 years of experience, participated. They had entered the profession through diverse pathways, expressing strong alignment between personal values and professional roles. Five themes emerged and centred on mental health being the heart of health, personal and professional fulfillment, camaraderie and teamwork, a profound respect for individuals and compassion, and overcoming and enjoying the challenge. Conclusions: Mental health nurses who are male bring unique contributions to the profession, embodying compassion, resilience, and ethical advocacy. Their experiences challenge traditional gender norms and redefine masculinity in health care. Fostering inclusive environments, mentorship, and leadership opportunities is essential to support their growth. These insights inform strategies to strengthen recruitment, retention, and the future of mental health nursing. Full article

Observing building changes in remote sensing images plays a crucial role in monitoring urban development and promoting sustainable urbanization. Mainstream change detection methods have demonstrated promising performance in identifying building changes. However, buildings have large intra-class variance and high similarity with other objects, limiting the generalization ability of models in diverse scenarios. Moreover, most existing methods only detect whether changes have occurred but ignore change types, such as new construction and demolition. To address these issues, we present a building change-type detection network (BCTDNet) based on the Segment Anything Model (SAM) to identify newly constructed and demolished buildings. We first construct a dual-feature interaction encoder that employs SAM to extract image features, which are then refined through trainable multi-scale adapters for learning architectural structures and semantic patterns. Moreover, an interactive attention module bridges SAM with a Convolutional Neural Network, enabling seamless interaction between fine-grained structural information and deep semantic features. Furthermore, we develop a change-aware attribute decoder that integrates building semantics into the change detection process via an extraction decoding network. Subsequently, an attribute-aware strategy is adopted to explicitly generate distinct maps for newly constructed and demolished buildings, thereby establishing clear temporal relationships among different change types. To evaluate BCTDNet’s performance, we construct the JINAN-MCD dataset, which covers Jinan’s urban core area over a six-year period, capturing diverse change scenarios. Moreover, we adapt the WHU-CD dataset into WHU-MCD to include multiple types of changing. Experimental results on both datasets demonstrate the superiority of BCTDNet. On JINAN-MCD, BCTDNet achieves improvements of 12.64% in IoU and 11.95% in F1 compared to suboptimal methods. Similarly, on WHU-MCD, it outperforms second-best approaches by 2.71% in IoU and 1.62% in F1. BCTDNet’s effectiveness and robustness in complex urban scenarios highlight its potential for applications in land-use analysis and urban planning. Full article

Digitalization is rapidly reshaping the global construction industry; however, its adoption in developing countries, such as Pakistan, remains limited and uneven. Hence, this study investigates and evaluates the current status of digital technology integration in Pakistan’s construction industry, with a primary focus on key tools, implementation challenges, and necessary policy interventions. Using a three-phase mixed-method approach involving a literature review, expert interviews, and a nationwide survey, this research identifies Building Information Modeling, Geographic Information Systems, and E-Procurement as essential technologies with strong potential to improve transparency, efficiency, and collaboration. However, adoption is hindered by a lack of awareness, limited technical expertise, and the absence of a cohesive national policy. This study also highlights that the private sector shows greater readiness compared to the public sector; however, systemic barriers persist across both sectors. Based on stakeholder insights, a three-part policy strategy was also proposed. This includes establishing a national regulatory framework, investing in capacity-building programs, and providing financial or institutional incentives to encourage the adoption of these measures. The findings emphasize that digitalization is not just a technical upgrade; it represents a pathway to improved governance and more efficient infrastructure delivery. With timely and coordinated policy action, the construction industry in Pakistan can align itself with global innovation trends and move toward a more sustainable and digitally empowered future. Full article

This paper investigates the error rate performance of simultaneous wireless information and power transfer (SWIPT) systems employing opportunistic amplify-and-forward (OAF) relaying under Rayleigh fading conditions. To support both data forwarding and energy harvesting at relays, a power splitting (PS) mechanism is applied. We derive exact and asymptotic symbol error rate (SER) expressions using moment-generating function (MGF) methods, providing analytical insights into how the power splitting ratio $\rho$ and the quality of source–relay (SR) and relay–destination (RD) links jointly affect system behavior. Additionally, we propose a novel approximation that interprets the SWIPT-OAF configuration as an equivalent non-SWIPT OAF model. This enables tractable performance analysis while preserving key diversity characteristics. The framework is extended to include scenarios with partial channel state information (CSI) and $N_{\mathrm{th}}$ best relay selection, addressing practical concerns such as limited relay availability and imperfect decision-making. Extensive simulations validate the theoretical analysis and demonstrate the robustness of the proposed approach under a wide range of signal-to-noise ratio (SNR) and channel conditions. These findings contribute to a flexible and scalable design strategy for SWIPT-OAF relay systems, making them suitable for deployment in emerging wireless sensor and internet of things (IoT) networks. Full article

Interest in gold nanoclusters (AuNCs) has grown significantly in recent decades. AuNCs, with a core size smaller than 2 nm, represent a unique class of functional nanomaterials. Their distinctive properties enable innovative applications across various interdisciplinary fields. Here, we introduce BioGoldNCDB, a freely available, fully annotated, and manually curated database of mainly about AuNCs and related AuNPs. Despite the rapid growth in biomedical applications of gold nanoclusters (AuNCs), the lack of a centralized and structured data resource hinders comparative analysis and rational design. Researchers face challenges in accessing standardized information on AuNCs’ structures, properties, and biological activities, which limits data-driven development in this emerging field. The database provides essential information, including CAS numbers and PubMed IDs, as well as specific details such as biomedical applications, cell lines used in research, particle size, and excitation/emission wavelengths. It currently covers 247 articles from 104 journals. Designed with a user-friendly and intuitive web interface, BioGoldNCDB is accessible on multiple devices, including phones, tablets, and PCs. Users can refine searches with multiple filters, and a help page is available for guidance. While offering quick insights for newcomers, BioGoldNCDB also serves as a valuable resource for researchers across various fields. Full article

Synthetic Aperture Radar (SAR) technology has the characteristics of all-day and all-weather functionality; accordingly, it is not affected by rainy weather, overcoming the limitations of optical remote sensing, and it provides irreplaceable technical support for efficient water body extraction. To address the issues of low accuracy and unstable results in water body extraction from Sentinel-1 SAR images using a single method, a water body extraction method fusing the Sentinel-1 dual-polarized water index and random forest is proposed. This novel method enhances water extraction accuracy by integrating the results of two different algorithms, reducing the biases associated with single-method water body extraction. Taking Dalu Lake, Yinfu Reservoir, and Huashan Reservoir as the study areas, water body information was extracted from SAR images using the dual-polarized water body index, the random forest method, and the fusion method. Taking the normalized difference water body index extraction results obtained via Sentinel-2 optical images as a reference, the accuracy of different water body extraction methods when used with SAR images was quantitatively evaluated. The experimental results show that, compared with the dual-polarized water body index and the random forest method, the fusion method, on average, increased overall water body extraction accuracy and Kappa coefficients by 3.9% and 8.2%, respectively, in the Dalu Lake experimental area; by 1.8% and 3.5%, respectively, in the Yinfu Reservoir experimental area; and by 4.1% and 8.1%, respectively, in the Huashan Reservoir experimental area. Therefore, the fusion method of the dual-polarized water index and random forest effectively improves the accuracy and reliability of water body extraction from SAR images. Full article

In this study, we propose a novel approach for human pose estimation (HPE) in occluded scenes by progressively fusing features extracted from RGB-D images, which contain RGB and depth images. Conventional bottom-up human pose estimation models that rely solely on RGB inputs often produce erroneous skeletons when parts of a person’s body are obscured by another individual, because they struggle to accurately infer body connectivity due to the lack of 3D topological information. To address this limitation, we modify the traditional OpenPose that is a bottom-up HPE model to take a depth image as an additional input, thereby providing explicit 3D spatial cues. Each input modality is processed by a dedicated feature extractor. Each input modality is processed by a dedicated feature extractor. In addition to the two existing modules for each stage—joint connectivity and joint confidence map estimations for the color image—we integrate a new module for estimating joint confidence maps for the depth image into the initial few stages. Subsequently, the confidence maps derived from both depth and RGB modalities are fused at each stage and forwarded to the next, ensuring that 3D topological information from the depth image is effectively utilized for both joint localization and body part association. Subsequently, the confidence maps derived from both depth and RGB modalities are fused at each stage and forwarded to the next to ensure that 3D topological information is effectively utilized for estimating both joint localization and their connectivity. The experimental results on the NTU 120+ RGB-D Dataset verify that our proposed approach achieves a 13.3% improvement in average recall compared to the original OpenPose model. The proposed method can enhance the performance of the bottom-up HPE models for the occlusion scenes. Full article

The construction industry is a cornerstone of New Zealand (NZ)’s economic growth, yet strategic infrastructure planning is constrained by fragmented and inconsistent pipeline data. Despite the increasing availability of construction pipeline datasets in NZ, their limited clarity, interoperability, and standardisation impede effective forecasting, policy development, and investment alignment. These challenges are compounded by disparate data structures, inconsistent reporting formats, and semantic discrepancies across sources, undermining cross-agency coordination and long-term infrastructure governance. To address this issue, the study begins by assessing the quality of four prominent pipeline datasets using Wang and Strong’s multidimensional data quality framework. This evaluation provides a necessary foundation for identifying the structural and semantic barriers that limit data integration and informed decision-making. The analysis examines four dimensions of data quality: accessibility, intrinsic quality, contextual relevance, and representational clarity. The findings reveal considerable inconsistencies in data fields, classification systems, and levels of detail across the datasets. Building on these insights, this study also develops a conceptual minimum dataset (MDS) framework comprising three core thematic categories: project identification, project characteristics, and project budget and timing. The proposed conceptual MDS includes unified data definitions, standardised reporting formats, and semantic alignment to enhance cross-platform usability and data confidence. This framework applies to the New Zealand context and is designed for replication in other jurisdictions, supporting the global push toward open, high-quality infrastructure data. The study contributes to the construction informatics and infrastructure planning by offering a practical solution to a critical data governance issue and introducing a transferable methodology for developing minimum data standards in the built environment to enable more informed, coordinated, and evidence-based decision-making. Full article

Background: Thallium is a metal that is ubiquitous in our natural environment. Despite its potential for high toxicity, thallium is understudied and not regulated in food. The California Department of Public Health was alerted to a household cluster of elevated urine thallium levels noted among a mother (peak 5.6 µg/g creatinine; adult reference: ≤0.4 µg/g creatinine) and her three young children (peak 10.5 µg/g creatinine; child reference: ≤0.8 µg/g creatinine). Objectives: This case report identifies questions raised after a public health investigation linked a household’s thallium exposure to a commercially available food product. We provide an overview of the public health investigation. We then explore concerns, such as gaps in toxicological data and limited surveillance of thallium in the food supply, which make management of individual and population exposure risks challenging. Methods: We highlight findings from a cross-agency investigation, including a household exposure survey, sampling of possible environmental and dietary exposures (ICP-MS analysis measured thallium in kale chips at 1.98 mg/kg and 2.15 mg/kg), and monitoring of symptoms and urine thallium levels after the source was removed. We use regulatory and research findings to describe the challenges and opportunities in characterizing the scale of thallium in our food supply and effects of dietary exposures on health. Discussion: Thallium can bioaccumulate in our food system, particularly in brassica vegetables like kale. Thallium concentration in foods can also be affected by manufacturing processes, such as dehydration. We have limited surveillance data nationally regarding this metal in our food supply. Dietary reviews internationally show increased thallium intake in toddlers. Limited information is available about low-dose or chronic exposures, particularly among children, although emerging evidence shows that there might be risks associated at lower levels than previously thought. Improved toxicological studies are needed to guide reference doses and food safety standards. Promising action towards enhanced monitoring of thallium is being pursued by food safety agencies internationally, and research is underway to deepen our understanding of thallium toxicity. Full article

Surrogate modelling is increasingly used in engineering to improve computational efficiency in complex simulations. However, traditional data-driven surrogate models often face limitations in generalizability, physical consistency, and extrapolation—issues that are especially critical in safety-sensitive fields such as fire safety engineering (FSE). To address these concerns, physics-informed surrogate modelling (PISM) integrates physical laws into machine learning models, enhancing their accuracy, robustness, and interpretability. This systematic review synthesises existing applications of PISM in FSE, classifies the strategies used to embed physical knowledge, and outlines key research challenges. A comprehensive search was conducted across Google Scholar, ResearchGate, ScienceDirect, and arXiv up to May 2025, supported by backward and forward snowballing. Studies were screened against predefined criteria, and relevant data were analysed through narrative synthesis. A total of 100 studies were included, covering five core FSE domains: fire dynamics, wildfire behaviour, structural fire engineering, material response, and heat transfer. Four main strategies for embedding physics into machine learning were identified: feature engineering techniques (FETs), loss-constrained techniques (LCTs), architecture-constrained techniques (ACTs), and offline-constrained techniques (OCTs). While LCT and ACT offer strict enforcement of physical laws, hybrid approaches combining multiple strategies often produce better results. A stepwise framework is proposed to guide the development of PISM in FSE, aiming to balance computational efficiency with physical realism. Common challenges include handling nonlinear behaviour, improving data efficiency, quantifying uncertainty, and supporting multi-physics integration. Still, PISM shows strong potential to improve the reliability and transparency of machine learning in fire safety applications. Full article

Interferometric scattering microscopy (iSCAT) is widely used for label-free tracking of nanoparticles and single molecules. However, its ability to identify small molecules is limited by low imaging contrast blurred with noise. Frame-averaging methods are widely used for reducing background noise but require hundreds of frames to produce a single frame as a trade-off. To address this, we applied a spatial–frequency domain deconvolution algorithm to suppress background noise and amplify the signal for each frame, achieving an improvement of ∼ 3-fold without hardware modification. This enhancement is achieved by compensating for missing information within the optical transfer function (OTF) boundary, while high-frequency components (noise) beyond this boundary are filtered. The resulting deconvolution process provides linear signal amplification, making it ideal for quantitative analysis in mass photometry. Additionally, the localization error is reduced by 20%. Comparisons with traditional denoising algorithms revealed that these methods often extract the side lobes. In contrast, our deconvolution approach preserves signal integrity while enhancing sensitivity. This work highlights the potential of image processing techniques to significantly improve the detection sensitivity of iSCAT for small molecule analysis. Full article