Search Results (1,525)

In the context of the rapid transformation of global agricultural production towards intensification and intelligence, the precise and intelligent management of horticultural crop production processes is key to enhancing resource utilization efficiency and industry profitability. Crop growth and development models, as digital representations of the interactions between environment, crops, and management, are core tools for achieving intelligent decision-making in facility production. This paper provides a comprehensive review of the advancements in intelligent management models and systems for horticultural crop growth and development. It introduces the developmental stages of horticultural crop growth models and the integration of multi-source data, systematically organizing and analyzing the modeling mechanisms of crop growth and development process models centered on developmental stages, photosynthesis and respiration, dry matter accumulation and allocation, and yield and quality formation. Furthermore, it summarizes the current status of expert decision-support system software development and application based on crop models, achieving comprehensive functionalities such as data and document management, model parameter management and optimization, growth process and environmental simulation, management plan design and effect evaluation, and result visualization and decision product dissemination. This illustrates the pathway from theoretical research to practical application of models. Addressing the current challenges related to the universality of mechanisms, multi-source data assimilation, and intelligent decision-making, the paper looks forward to future research directions, aiming to provide theoretical references and technological insights for the future development and system integration of intelligent management models for horticultural crop growth and development. Full article

Privacy is a major concern in the digital era and is intensively addressed in academic research, in industry, and by regulators. However, almost all references to privacy in the digital world relate to the Wide Area Network (WAN) environment, which is actually the Internet, whereas the Local Area Network (LAN) environment is neglected. While the Internet is widespread, almost every connection to the Internet is via a LAN. Given the increased interest in privacy, and the popularity of LANs, privacy threats on a LAN should have been extensively addressed. Nonetheless, significant research on LAN privacy issues is limited. Therefore, the focus of this study is on privacy vulnerabilities in the LAN environment. By conducting a literature meta-analysis and, particularly, by interviewing LAN managers and experts, we identified 18 vulnerabilities that may introduce privacy threats. The privacy risk assessment of the vulnerabilities was based on the FMEA approach. In an empirical study, we evaluated these vulnerabilities on 13 different LANs. Excluding one vulnerability, all the others were found on at least one LAN, and more than 50 percent of the vulnerabilities were identified as high-risk. The results show that the LAN is indeed a source of significant privacy concerns. Full article

Introduction: [¹⁸F]-DCFPyL (Piflufolastat [¹⁸F]) is a prostate-specific membrane antigen (PSMA)-targeted position emission tomography (PET) radiotracer for detecting the biochemical recurrence (BCR) of prostate cancer (PCa). This study evaluates its economic impact compared with [⁶⁸Ga]-PSMA-11, [¹⁸F]-FCH, and [¹⁸F]-PSMA-1007 from the Spanish National Healthcare System’s perspective. Methods: A cost–consequence model, over a 5-year time horizon, simulated the diagnostic and treatment pathway based on radiotracer-specific accuracy and disease localization. Treatment options included a radical prostatectomy, radiation therapy, androgen deprivation therapy (ADT), and radiation therapy + ADT. Costs were calculated for true/false positives and negatives. Due to limited data availability, key inputs were informed by expert opinions, supported by published meta-analyses, public sources, and literature. Officially published Spanish prices were applied: EUR 2000 for [¹⁸F]-DCFPyL, [⁶⁸Ga]-PSMA-11, and [¹⁸F]-PSMA-1007, and EUR 1144 for [¹⁸F]-FCH. Results: The use of [¹⁸F]-DCFPyL led to fewer unnecessary therapies; specifically, it led to 11,229 (74%) fewer than [⁶⁸Ga]-PSMA-11, and 5180 (56%) and 7771 (66%) fewer than [¹⁸F]-FCH and [¹⁸F]-PSMA-1007, respectively. It achieved significant cost savings for repeated testing: EUR 15M (43%) versus [⁶⁸Ga]-PSMA-11, EUR 37M (65%) versus [¹⁸F]-FCH, and EUR 27M (58%) versus [¹⁸F]-PSMA-1007. Cost savings for false positives were EUR 15M (50%) against [⁶⁸Ga]-PSMA-11, EUR 22M (60%) versus [¹⁸F]-FCH, and EUR 29M (66%) compared with [¹⁸F]-PSMA-1007. The cost per correct diagnosis was reduced by EUR 198 (8%) compared with [⁶⁸Ga]-PSMA-11 and EUR 377 (15%) relative to [¹⁸F]-PSMA-1007, while showing a EUR 635 (40%) increase compared with [¹⁸F]-FCH. Conclusions: [¹⁸F]-DCFPyL offers a cost-saving option for BCR detection within the Spanish National Healthcare System by reducing the number of unnecessary therapies, the cost of false positives, and repeat testing compared with alternative radiotracers. These improvements support the potential for better diagnostic outcomes and more informed downstream clinical decision-making. Full article

Objectives: This study presents the development of a bilingual, expert-evaluated question–answer (Q&A) dataset, named PMR-Q&A, designed for training large language models (LLMs) in the field of Physical Medicine and Rehabilitation (PMR). Methods: The dataset was created through a systematic and semi-automated framework that converts unstructured scientific texts into structured Q&A pairs. Source materials included eight core reference books, 2310 academic publications, and 323 theses covering 15 disease categories commonly encountered in PMR clinical practice. Texts were digitized using layout-aware optical character recognition (OCR), semantically segmented, and distilled through a two-pass LLM strategy employing GPT-4.1 and GPT-4.1-mini models. Results: The resulting dataset consists of 143,712 bilingual Q&A pairs, each annotated with metadata including disease category, reference source, and keywords. A representative subset of 3000 Q&A pairs was extracted for expert validation to evaluate the dataset’s reliability and representativeness. Statistical analyses showed that the validation sample accurately reflected the thematic and linguistic structure of the full dataset, with an average score of 1.90. Conclusions: The PMR-Q&A dataset is a structured and expert-evaluated resource for developing and fine-tuning domain-specific large language models, supporting research and educational efforts in the field of physical medicine and rehabilitation. Full article

This article presents the development and validation process of a qualitative data collection instrument aimed at analysing natural sciences teachers’ perceptions of practical work in lower secondary education (third cycle) in Portugal. The methodological approach combined a systematic literature review following PRISMA guidelines with an analysis of relevant curricular frameworks and legal documents. Based on the triangulation of these sources, a semi-structured interview guide was constructed, validated by a panel of five experts from four Portuguese public universities, and tested through a pilot interview. The final instrument comprised seven dimensions and fourteen subdimensions, totalling 44 items. It demonstrated methodological rigour and practical applicability for qualitative data collection and analysis. Findings indicate that the instrument enables a comprehensive exploration of teachers’ practices and perceptions regarding practical work, offering a valuable contribution to the research on didactics of science and to the professional development of teachers. Also, the application of this instrument will enable teachers and researchers to characterise the dynamics of practical work carried out with young students in natural sciences education across seven structuring dimensions: (1) Conceptual; (2) Limitations; (3) Advantages; (4) Evaluative; (5) Operationalisation; (6) Textbook; and (7) Curricular. Full article

This study introduces an Impact Thinking Approach (ITA) as a strategic framework to strengthen traceability implementation in the fashion and textile industry. The research examines how ESG impact dimensions shape sustainable strategy definition and how traceability can act as a strategic enabler rather than a mere compliance tool. A mixed-method design combining a narrative literature review, content analysis of 69 sustainability sources, and a two-round Delphi study with 19 experts was employed to identify, evaluate, and prioritize impact drivers related to traceability adoption. The resulting ITA framework connects regulatory requirements, impact materiality, and traceability demands into a unified structure that clarifies the strategic relevance of environmental, social, and governance dimensions. Findings reveal that governance-related factors—particularly data transparency, stakeholder engagement, innovation capacity, and cross-sector partnerships—are the strongest enablers for activating effective traceability schemes. The framework provides practitioners with structured guidance for integrating traceability into sustainable business strategies and for developing impact-aligned KPIs and decision-making mechanisms. The study contributes theoretical insights into the ESG–traceability nexus and offers a practical model to support regulatory alignment, organizational readiness, and long-term strategic planning. Full article

Background and Objectives: Acute and obstructive pyelonephritis (AOP) management, despite advancements in diagnostic imaging and antimicrobial therapy, is characterized by delayed recognition and increasing antimicrobial resistance. This review aimed to summarize current evidence regarding the clinical characteristics, microbiological spectrum, biomarkers, and imaging findings associated with AOP. Materials and Methods: A systematic review was conducted according to PRISMA guidelines and registered in PROSPERO (CRD420251162736). Literature searches were performed across the PubMed, Scopus, and Web of Science databases for articles published between January 2014 and 31 March 2025 using the term “acute obstructive pyelonephritis”. Inclusion criteria comprised original full-text English-language studies, published in the last 10 years and conducted in adults, reporting clinical, laboratory, microbiological, and imaging characteristics. Exclusion criteria are letters to the editor, expert opinions, case reports, conference or meeting abstracts, reviews, and redundant publications; having unclear or incomplete data; and being performed on cell cultures or on mammals. The quality of included studies was assessed using the Newcastle–Ottawa Scale. Results: Twenty-three studies met the inclusion criteria. AOP predominantly affected elderly patients with comorbidities, especially diabetes mellitus and urinary tract obstruction. Predictors of septic shock included thrombocytopenia, hypoalbuminemia, elevated procalcitonin (>1.12 µg/L), presepsin, and a neutrophil-to-lymphocyte ratio ≥ 8.7. Escherichia coli remained the leading pathogen (60–95%) with extended-spectrum β-lactamase (ESBL) rates between 20 and 70%, followed by Klebsiella pneumoniae. CT demonstrated 71–100% sensitivity for detecting obstructive complications, confirming its superiority over ultrasound, while MRI provided comparable diagnostic accuracy in selected cases. Source control through double-J stenting or percutaneous drainage significantly improved survival. Conclusions: AOP requires prompt recognition and early decompression to prevent sepsis-related mortality. Biomarkers such as procalcitonin, presepsin, and neutrophil to lymphocyte ratio enhance risk stratification, while CT remains the gold-standard imaging modality. The increasing prevalence of ESBL-producing pathogens underscores the need for antimicrobial stewardship and individualized therapeutic strategies guided by local resistance data. Full article

Understanding how investors maintain positions during adverse market conditions, investment grip, is increasingly important as retail participation rises and information environments diversify. While prior research identifies demographic, psychological, and economic determinants of investment grip, little is known about how information sources influence investors’ tolerance for losses. This study examines the relationship between investment information channels and investment grip among Japanese retail investors using a large-scale dataset of 161,677 respondents from the 2025 Survey on Life and Money. Investment grip is measured through a hypothetical loss scenario, and ordered probit and probit models are used to analyze associations between loss tolerance, information sources, and investor characteristics. Results show that reliance on professional information sources such as outsourced independent financial advisors, one’s own securities company, other securities firms, and external financial experts is negatively associated with investment grip. Free information sources, including mass media and personal networks, are also linked to lower loss tolerance. In contrast, reliance on social media is consistently associated with higher investment grip. Financial literacy, wealth, and age increase investment grip, whereas risk aversion, short-term outlooks, and family responsibilities reduce it. These results have implications for policy design, advisory practices, and digital and AI-enhanced investment platforms. Full article

Against the backdrop of global climate change and China’s “dual-carbon” goals, carbon emissions from the construction phase of transportation infrastructure, particularly the rapidly expanding railway network, have garnered significant attention. However, systematic research and general evaluation models targeting the factors influencing carbon emissions during the railway bridge construction phase remain insufficient. To address this gap, this study presents a novel low-carbon evaluation model that integrates the analytic network process (ANP) and the fuzzy comprehensive evaluation (FCE) method. First, a carbon accounting model covering four stages—material production, transportation, construction, and maintenance—is established based on life cycle assessment (LCA) theory, providing a data foundation. Second, an innovative low-carbon evaluation index system for railway bridges, comprising 5 criterion layers and 23 indicator layers, is constructed. The ANP method is employed to calculate weights, effectively capturing the interdependencies among indicators, while the FCE method handles assessment ambiguities, forming a comprehensive evaluation framework. A case study of the bridge demonstrates the model’s effectiveness, yielding an evaluation score of 82.38 (“excellent” grade), which is consistent with expert judgement. The ranking of indicator weights from the model is highly consistent with the actual carbon emission inventory ranking (Spearman coefficient of 0.714). Key indicators—C21 (use of high-performance materials), C22 (concrete consumption), and C25 (transportation energy consumption)—collectively account for approximately 60% of the total impact, accurately identifying the major emission sources. This research not only verifies the model’s efficacy in pinpointing critical carbon sources but also provides a scientific theoretical basis and practical tool for low-carbon decision-making and optimization in the planning and design stages of railway bridge projects. Full article

The rapid spread of climate change misinformation across digital platforms undermines scientific literacy, public trust, and evidence-based policy action. Advances in Natural Language Processing (NLP) and Large Language Models (LLMs) create new opportunities for automating the detection and correction of misleading climate-related narratives. This study presents a multi-stage system that employs state-of-the-art large language models such as Generative Pre-trained Transformer 4 (GPT-4), Large Language Model Meta AI (LLaMA) version 3 (LLaMA-3), and RoBERTa-large (Robustly optimized BERT pretraining approach large) to identify, classify, and generate scientifically grounded corrections for climate misinformation. The system integrates several complementary techniques, including transformer-based text classification, semantic similarity scoring using Sentence-BERT, stance detection, and retrieval-augmented generation (RAG) for evidence-grounded debunking. Misinformation instances are detected through a fine-tuned RoBERTa–Multi-Genre Natural Language Inference (MNLI) classifier (RoBERTa-MNLI), grouped using BERTopic, and verified against curated climate-science knowledge sources using BM25 and dense retrieval via FAISS (Facebook AI Similarity Search). The debunking component employs RAG-enhanced GPT-4 to produce accurate and persuasive counter-messages aligned with authoritative scientific reports such as those from the Intergovernmental Panel on Climate Change (IPCC). A diverse dataset of climate misinformation categories covering denialism, cherry-picking of data, false causation narratives, and misleading comparisons is compiled for evaluation. Benchmarking experiments demonstrate that LLM-based models substantially outperform traditional machine-learning baselines such as Support Vector Machines, Logistic Regression, and Random Forests in precision, contextual understanding, and robustness to linguistic variation. Expert assessment further shows that generated debunking messages exhibit higher clarity, scientific accuracy, and persuasive effectiveness compared to conventional fact-checking text. These results highlight the potential of advanced LLM-driven pipelines to provide scalable, real-time mitigation of climate misinformation while offering guidelines for responsible deployment of AI-assisted debunking systems. Full article

We present a new method for mapping global gas flaring using a multiyear spatio-temporal database of VIIRS Nightfire (VNF) nighttime infrared detections from the Suomi NPP, NOAA-20, and NOAA-21 satellites. The method is designed to resolve closely spaced industrial combustion sources and to produce a stable, physically meaningful flare catalog suitable for long-term monitoring and emissions analysis. The method combines adaptive spatial aggregation of high-temperature detections with a hierarchical clustering that super-resolves individual flare stacks within oil and gas fields. Post-processing yields physically consistent flare footprints and attraction regions, allowing separation of closely spaced sources. Flare clusters are assigned to operational categories (e.g., upstream, midstream, LNG) using prior catalogs combined with AI-assisted expert interpretation. In this step, a multimodal large language model (LLM) provides contextual classification suggestions based on geospatial information, high-resolution daytime imagery, and detection time-series summaries, while final attribution is performed and validated by domain experts. Compared with annual flare catalogs commonly used for national flaring estimates, the new catalog demonstrates substantially improved performance. It is more selective in the presence of intense atmospheric glow from large flares, identifies approximately twice as many active flares, and localizes individual stacks with ~50 m precision, resolving emitters separated by ~400–700 m. For the well-defined class of downstream flares at LNG export facilities, the catalog achieves complete detectability. These improvements support more accurate flare inventories, facility-level attribution, and policy-relevant assessments of gas flaring activity. Full article

The purpose of this study is to determine the optimal location for siting an onshore wind farm on the island of Skyros, thereby maximizing performance and minimizing the project’s environmental impacts. Seven evaluation criteria are defined across various sectors, including environmental and economic sectors, and six criteria weighting methods are applied in combination with four multicriteria decision-making (MCDM) ranking methods for suitable areas, resulting in twenty-four ranking models. The alternatives considered in the analysis were defined through the application of constraints imposed by the Specific Framework for Spatial Planning and Sustainable Development for Renewable Energy Sources (SFSPSD RES), complemented by exclusion criteria documented in the international literature, as well as a minimum area requirement ensuring the feasibility of installing at least four wind turbines within the study area. The correlations between their results are then assessed using the Spearman coefficient. Geographic information systems (GISs) are utilized as a mapping tool. Through the application of the methodology, it emerges that area A9, located in the central to northern part of Skyros, is consistently assessed as the most suitable site for the installation of a wind farm based on nine models combining criteria weighting and MCDM methods, which should be prioritized as an option for early-stage wind farm siting planning. The results demonstrate an absolute correlation among the subjective weighting methods, whereas the objective methods do not appear to be significantly correlated with each other or with the subjective methods. The ranking methods with the highest correlation are PROMETHEE II and ELECTRE III, while those with the lowest are TOPSIS and VIKOR. Additionally, the hierarchy shows consistency across results using weights from AHP, BWM, ROC, and SIMOS. After applying multiple methods to investigate correlations and mitigate their disadvantages, it is concluded that when experts in the field are involved, it is preferable to incorporate subjective multicriteria analysis methods into decision-making problems. Finally, it is recommended to use more than one MCDM method in order to reach sound decisions. Full article

This article examines the trajectory of secularization and desecularization in Turkey through the lens of Imam Hatip high schools, focusing on how religion has been reintroduced into the public sphere and reshaped educational exposure. While secularism in Turkey historically emerged as a state-driven project imposed from above, recent decades have witnessed a marked process of desecularization under the Justice and Development Party, facilitated by institutional reforms in law, education, and bureaucracy. The study draws on qualitative interviews with experts, analyzed through grounded theory, to capture their perceptions of religious schooling and its impact. The analysis is organized into three themes: the persistence of top-down secularism, the institutionalized reintroduction of religion, and the intersection of religionized politics with educational practices. Findings indicate that while family socialization remains a primary source of religious identity, Imam Hatip schools function as a symbolic site of religiosity and political contestation. The study concludes that Turkey’s current desecularization is not merely a grassroots revival but a state-mediated restructuring of the secular–religious balance, with education serving as a central arena for negotiating visibility, autonomy, and identity. At the same time, the legacy of top-down secularism has paradoxically contributed to alienating younger generations from religion, shaping ambivalent attitudes toward faith and schooling. Full article

In modern construction, natural materials with a low carbon footprint and full recyclability are becoming increasingly important. A typical group here is products made from solid wood, including glued wood, plywood, and wood-based composites. With their many advantages, however, they all burden the environment with the costs of production processes, as well as the need to use harmful chemicals (adhesives and impregnants). Solid wood is devoid of these disadvantages; however, it is often treated as a rather archaic material. One of the arguments here is its low durability compared to, e.g., glued wood. The article discusses the durability of solid wood using the example of a group of wooden churches preserved in Poland, in Upper Silesia. Some of these buildings are over five hundred years old, making them a reliable source of information about the durability of the material from which they were built. A total of 85 churches, at least 200 years old, were analyzed, evaluating the technical state of the main load-bearing elements of their structures. In view of the number of facilities and the inability to conduct tests in most of them, the assessment was limited to a visual inspection of the technical condition, carried out by an experienced building expert. The assessment estimated the area of corrosion damage, probed its depth, and measured the depth of cracks. The relationship between their technical condition and the environmental conditions in which they were used was described and discussed. In this way, both the threats to the durability of solid wood and the ways to keep it in good condition for hundreds of years were identified, refuting the thesis that solid wood is a material with low durability. Its use in structural elements therefore supports efficient resource management and contributes to sustainable construction, especially in small and medium-sized buildings. Full article

With Transformers achieving outstanding performance on individual remote sensing (RS) tasks, we are now approaching the realization of a unified model that excels across multiple tasks through multi-task learning (MTL). Compared to single-task approaches, MTL methods offer improved generalization, enhanced scalability, and greater practical applicability. Recently, vision-language models (VLMs) have achieved promising results in RS image understanding, grounding, and ultra-high-resolution (UHR) image reasoning, respectively. Moreover, the unified text-based interface demonstrates significant potential for MTL. Hence, in this work, we present RSCoVLM, a simple yet flexible VLM baseline for RS MTL. Firstly, we create the data curation procedure, including data acquisition, offline processing and integrating, as well as online loading and weighting. This data procedure effectively addresses complex RS data enviroments and generates flexible vision-language conversations. Furthermore, we propose a unified dynamic-resolution strategy to address the diverse image scales inherent in RS imagery. For UHR images, we introduce the Zoom-in Chain mechanism together with its corresponding dataset, LRS-VQA-Zoom. The strategies are flexible and effectively mitigate the computational burdens. Additionally, we significantly enhance the model’s object detection capability and propose a novel evaluation protocol that ensures fair comparison between VLMs and conventional detection models. Extensive experiments demonstrate that RSCoVLM achieves state-of-the-art performance across diverse tasks, outperforming existing RS VLMs and even rivaling specialized expert models. All the training and evaluating tools, model weights, and datasets have been fully open-sourced to support reproducibility. We expect that this baseline will promote further progress toward general-purpose RS models. Full article