Search Results (1,787)

Background/Objectives: Acute respiratory distress syndrome (ARDS) represents a critical complication in polytrauma patients, characterized by diffuse lung inflammation and bilateral pulmonary infiltrates with mortality rates reaching 45% in intensive care units (ICU). The heterogeneous nature of ARDS and complex clinical presentation in severely injured patients poses substantial diagnostic challenges, necessitating early prediction tools to guide timely interventions. Machine learning (ML) algorithms have emerged as promising approaches for clinical decision support, demonstrating superior performance compared to traditional scoring systems in capturing complex patterns within high-dimensional medical data. Based on the identified research gaps in early ARDS prediction for polytrauma populations, our study aimed to: (i) develop a balanced random forest (BRF) ML model for early ARDS prediction in critically ill polytrauma patients, (ii) identify the most predictive clinical features using ANOVA-based feature selection, and (iii) evaluate model performance using comprehensive metrics addressing class imbalance challenges. Methods: This retrospective cohort study analyzed 407 polytrauma patients admitted to the ICU of the Center of Traumatology and Major Burns of Ben Arous, Tunisia, between 2017 and 2021. We implemented a comprehensive ML pipeline that incorporates Tomek Links undersampling, ANOVA F-test feature selection for the top 10 predictive variables, and SMOTE oversampling with a conservative sampling rate of 0.3. The BRF classifier was trained with class weighting and evaluated using stratified 5-fold cross-validation. Performance metrics included AUROC, PR-AUC, sensitivity, specificity, F1-score, and Matthews correlation coefficient. Results: Among 407 patients, 43 developed ARDS according to the Berlin definition, representing a 10.57% incidence. The BRF model demonstrated exceptional predictive performance with an AUROC of 0.98, a sensitivity of 0.91, a specificity of 0.80, an F1-score of 0.84, and an MCC of 0.70. Precision–recall AUC reached 0.86, demonstrating robust performance despite class imbalance. During stratified cross-validation, AUROC values ranged from 0.93 to 0.99 across folds, indicating consistent model stability. The top 10 selected features included procalcitonin, PaO₂ at ICU admission, 24-h pH, massive transfusion, total fluid resuscitation, presence of pneumothorax, alveolar hemorrhage, pulmonary contusion, hemothorax, and flail chest injury. Conclusions: Our BRF model provides a robust, clinically applicable tool for early prediction of ARDS in polytrauma patients using readily available clinical parameters. The comprehensive two-step resampling approach, combined with ANOVA-based feature selection, successfully addressed class imbalance while maintaining high predictive accuracy. These findings support integrating ML approaches into critical care decision-making to improve patient outcomes and resource allocation. External validation in diverse populations remains essential for confirming generalizability and clinical implementation. Full article

This paper mainly studies tax inspection decision-making technology, aiming to improve the accuracy and robustness of target recognition, state estimation, and autonomous decision making in complex environments by constructing an application that integrates visual, radar, and inertial navigation information. Tax inspection is a universally complex phenomenon, but little is known about the use of innovative technology to arm tax auditors with tools in monitoring it. Thus, based on the legitimacy theory, there is an agreement between taxpayers and the tax authorities regarding adequate compliance with tax legislation. The use of systemic controls by tax authorities is essential to track stakeholders’ contracts and ensure the upholding of this mandate. The case study is exploratory, using participant observation, and interventionist approach to a tax auditing. The results indicated that partnership between experienced tax auditors and IT tax auditors offered several tangible benefits to the in-house development and monitoring of an innovative application. It also indicates that OCR supports a data lake for inspectors in which stored information is available on standby during inspection. Furthermore, auditors’ use of mobile applications programmed with intelligent perception and tracking resources instead of using searches on mainframes streamlined the inspection process. The integration of professional skepticism, empathy among users, and technological innovation created a surge in independence among tax auditors and ensured focus. This paper’s contribution lies in the discussion of the enhancement of tax inspection through target recognition, drawing on legitimacy theory to rethink the relationship between taxpayers and tax authorities regarding adequate compliance with tax legislation, and presenting an exploratory case study using a participant observation, interventionist approach focused on a tax auditor. The implications of this study for policy makers, auditors, and academics are only the peak of the iceberg, as innovation in public administration presupposes efficiency. As a suggestion for future dimensions of research, we recommend the infusion of AI into these tools for further efficacy and effectiveness to mitigate fraud in the undue appropriation of taxes and undue competition. Full article

In urban underground space construction using shield tunnelling, the geological conditions ahead of the tunnel face are often uncertain. Without timely and accurate classification of the ground type, mismatches in operational parameters, uncontrolled costs, and schedule risks are likely to occur. Using observations from an earth pressure balance (EPB) project on an urban railway, a data-driven classification framework is developed that integrates shield tunnelling operating measurements with physically derived quantities to discriminate among soft soil, hard rock, and mixed strata. Principal component analysis (PCA) is performed on the training set, followed by a systematic comparison of tree-based classifiers and hyperparameter optimization strategies to explore the attainable performance. Under unified evaluation criteria, a categorical bosting (CatBoost) model optimized by a Nevergrad combination strategy (NGOpt) attains the highest test accuracy of 0.9625, with macro-averaged precision and macro-averaged recall of 0.9715 and 0.9716, respectively. To mitigate optimism from single-point estimates, stratified bootstrap intervals are reported for the test set. A Monte Carlo experiment applies independent perturbations to the PCA-transformed features, producing low label-flip rates across the three classes, with only minor changes in probability calibration metrics, which suggests consistent decisions under sensor noise and sampling bias. Overall, within the scope of the considered EPB project, the study delivers a compact workflow that demonstrates the feasibility of uncertainty-aware ground-type classification and provides a methodological reference for developing decision-support tools in underground tunnel construction. Full article

The wildland fire management system is increasingly complex and uncertain, which challenges suppression actions and increases stress on an already strained system. Researchers and managers have called for the use of strategic, risk-informed decision making and decision support tools (DSTs) in wildfire management to manage complexity and mitigate uncertainty. This paper evaluated the use of an emerging wildfire DST, the Risk Management Assistance (RMA) dashboard, during the 2021 and 2022 wildfire seasons. We used a mixed-method approach, consisting of an online survey and in-depth interviews with fire managers. Our objectives were the following: (1) to determine what factors at multiple scales facilitated and frustrated the adoption of RMA; and (2) to identify actionable recommendations to facilitate uptake of RMA. We situate our findings within the diffusion of innovations literature and use-inspired research. Most respondents indicated RMA tools were easy to use, accurate, and relevant to decision-making processes. We found evidence that the tools were used throughout the fire management cycle. Previous experience with RMA and training in risk management, trust in models, leadership support, and perceptions of current and future fire risk affected RMA adoption. Recommendations to improve RMA included articulating how the tools integrate with existing wildland fire DSTs, new tools that consider dynamic forecasting of risk, and both formal and informal learning opportunities in the pre-season, during incidents, and in post-fire reviews. We conclude with research and management considerations to increase the use of RMA and other DSTs in support of safe, effective, and informed wildfire decision making. Full article

Background: Cervical cancer remains a major global health challenge, ranking fourth among malignancies in women, with an estimated 660,000 new cases and 350,000 deaths in 2022. Despite advances in vaccination and screening, incidence and mortality remain disproportionately high in low- and middle-income countries. The disease is strongly linked to persistent infection with high-risk human papillomavirus (HPV) types, predominantly HPV 16 and 18, whose E6 and E7 oncoproteins drive cervical intraepithelial neoplasia (CIN) and invasive cancer. This review summarizes current evidence on clinically relevant biomarkers in HPV-associated CIN and cervical cancer, emphasizing their role in screening, risk stratification, and disease management. Methods: We analyzed the recent literature focusing on validated and emerging biomarkers with potential clinical applications in HPV-related cervical disease. Results: Biomarkers are essential tools for improving early detection, assessment of progression risk, and personalized management. Established markers such as p16 immunostaining, p16/Ki-67 dual staining, and HPV E6/E7 mRNA assays increase diagnostic accuracy and reduce overtreatment. Prognostic indicators, including squamous cell carcinoma antigen (SCC-Ag) and telomerase activity, provide information on tumor burden and recurrence risk. Novel approaches—such as DNA methylation panels, HPV viral load quantification, ncRNAs, and cervico-vaginal microbiota profiling—show promise in refining risk assessment and supporting non-invasive follow-up strategies. Conclusions: The integration of validated biomarkers into clinical practice facilitates more effective triage, individualized treatment decisions, and optimal use of healthcare resources. Emerging biomarkers, once validated, could further improve precision in predicting lesion outcomes, ultimately reducing the global burden of cervical cancer and improving survival. Full article

The energy–water–carbon (EWC) nexus has become a critical concern for industrial systems seeking sustainable development, yet existing assessment approaches often require intensive computation and lack practical adaptability. This study proposes a probability-pinch analysis (P-PA) framework that enhances conventional pinch analysis (PA) by integrating allocation-based correction factors to account for system inefficiencies across all time intervals explicitly. The framework incorporates PA tools, specifically the Power Cascade Table (PCT), Water Cascade Table (WCT), and Energy Planning Pinch Diagram (EPPD), to design ideal energy–water systems that do not consider losses. Correction factors based on probable energy and water flows are then incorporated to capture system inefficiencies, with design modifications proposed to meet annual carbon reduction targets. Results from an industrial plant case study validate the effectiveness of P-PA in establishing minimum resource targets while achieving a 46% reduction in carbon emissions through system modifications. Deviations from conventional PA were within 10%, confirming the framework’s accuracy and reliability in designing integrated energy–water systems within the EWC nexus. It could serve as a handy tool for designing large-scale energy–water systems that require substantial computational effort, but it may be less accurate for small-scale applications. Nevertheless, compared with conventional PA-based approaches, P-PA offers a balanced combination of rigor, simplicity, and adaptability, making it well-suited for industrial EWC nexus analysis and decision support in sustainable process design. Full article

The increasing complexity of networked research demands approaches that combine rigor, efficiency, and collaboration. In this context, artificial intelligence (AI) emerges as a strategic ally in the analysis and organization of scientific literature, facilitating the construction of a robust state-of-the-art framework to support decisions. The present study focuses on evaluating a model for the use of AI that facilitates collaborative literature review by integrating AI tools. The present study employed a descriptive, non-experimental, cross-sectional design. Participants (N = 10) completed a purpose-built questionnaire comprising twenty-five indicators on specific aspects of the model’s use. The participants indicated a high level of knowledge regarding ICT use (M = 8.3; SD = 1.25). The results showed that the System Usability Scale for the tools demonstrated variability; Google Drive scored the highest (M = 77.75; SD = 11.45), while Rayyan.AI scored the lowest (M = 66.00; SD = 20.69). While the findings indicated that AI enhances the efficiency of documentary research and the development of ethical and digital competencies, the participants expressed a need for further training in AI tools to optimize the usability of those integrated into the model. The proposed model CAIM-REL proves to be replicable and holds potential for collaborative research. Full article

This study presents a replicable methodology for identifying and evaluating the tourism potential of natural and cultural heritage through a comprehensive inventory. It aims to enhance regional competitiveness and foster sustainable destination development. The methodology combines bibliographic review, field observation, and local surveys, and it was validated through its application in a tourist destination city in Colombia, where resources were systematically classified and evaluated using qualitative and quantitative criteria, focusing on preservation quality and market relevance. The results revealed a rich and underutilized heritage portfolio with exceptional potential in categories such as religious architecture, goldsmithing traditions, local festivals, and natural riverine ecosystems. The city demonstrated a high capacity for developing tourism products grounded in cultural identity and environmental preservation. This methodology offers a robust, adaptable tool for tourism planning, bridging heritage valuation with market relevance. By integrating structured evaluation with local knowledge, the model supports data-driven decision-making and inclusive governance—essential for combating overtourism and promoting long-term resilience in heritage towns. Full article

Efficient water management is increasingly critical in vineyard operations, particularly in the context of climate change and the rising demand for sustainable agricultural practices. Regulated deficit irrigation has emerged as a promising technique that allows significant water savings while sustaining or improving the quality of grapes. However, its effective implementation requires timely and precise information on vine water status and environmental conditions (pluviometry, humidity, radiation, etc.). This study presents the methodology of a decision-support tool that tested the application of several artificial intelligence regression models. Among the algorithms evaluated, an Extreme Gradient Boosting (XGBoost) regression model showed the best performance and was adopted as the core predictive engine of the ViñAI tool to optimize deficit irrigation in vineyards. Based on the developed methodology, the ViñAI tool integrates open-access environmental data such as weather forecasts and satellite-based estimates of evapotranspiration. Furthermore, ViñAI is designed with the potential to integrate sensor-based field data. Overall, the results demonstrate that ViñAI offers a scalable, data-driven approach to support climate-smart irrigation decisions in vineyards, particularly in sensor-sparse or resource-limited contexts, and provides a robust basis for further multi-season and multi-region validation. Full article

Regional disparities pose persistent challenges for balanced and sustainable development in Türkiye, where provinces exhibit prominently heterogeneous socioeconomic structures, capacities, and investment needs. This study proposes an integrated, data-driven framework for allocating public investments across provinces by jointly addressing development efficiency and spatial equity. A dataset of 109 indicators for 81 provinces was compiled and standardized, and Principal Component Analysis, followed by multiple clustering algorithms (K-Means, Gaussian Mixture Model, Fuzzy C-Means), was used to derive robust provincial development profiles. National policy priorities were quantified through a document-based assessment of the 12th Development Plan (2024–2028), enabling the construction of nine strategic investment categories aligned with national objectives. These components were incorporated into a multi-objective optimization model formulated using the ε-constraint method, where total utility is maximized subject to an adjustable equity constraint based on a Gini-like parameter. Results reveal a clear efficiency–equity trade-off: low inequality tolerance yields uniform but low-return allocations, whereas relaxed equity constraints amplify concentration in high-capacity metropolitan provinces. Intermediate equity levels (G = 0.3–0.5) generate the most balanced outcomes, supporting both development potential and spatial cohesion. The proposed framework offers a transparent, reproducible decision support tool for more equitable and strategy-aligned public investment planning in Türkiye. Full article

Socio-ecological systems (SESs) exhibit nonlinear feedback across environmental, social, and economic processes, requiring integrative analytical tools capable of representing such coupled dynamics. This study presents a quantitative framework that integrates a compartmental model of a global human–ecosystem with two complementary optimization approaches (Fisher Information (FI) and Multi-Objective Optimization (MOO)) to evaluate policy strategies for sustainability. The model represents biophysical and socio-economic interactions across 15 compartments, incorporating feedback loops between greenhouse gas (GHG) accumulation, temperature anomalies, and trophic–economic dynamics. Six policy-relevant decision variables were selected (wild plant mortality, sectoral prices (agriculture, livestock, and industry), base wages, and resource productivity) and optimized under temporal (25-year) and magnitude (±10%) constraints to ensure policy realism. FI-based optimization enhances system stability, whereas the MOO framework balances environmental, social, and economic objectives using the Ideal Point Method. Both approaches prevent the systemic collapse observed in the baseline scenario. The FI and MOO strategies reduce terminal global temperature by 11.4% and 15.0%, respectively, relative to the baseline (35 °C → 31.0 °C under FI; 35 °C → 29.7 °C under MOO). Resource-use efficiency, measured through the resource requirement coefficient (λ), improves by 8–10% under MOO (0.6767 → 0.6090) and by 6–7% under FI (0.6668 → 0.6262). These outcomes offer actionable guidance for long-term climate policy at national and international scales. The MOO framework provided the most balanced outcomes, enhancing environmental and social performance while maintaining economic viability. Overall, the integration of optimization and information-theoretic approaches within SES models can support evidence-based public policy design, offering actionable pathways toward resilient, efficient, and equitable sustainability transitions. Full article

Accurate weather classification plays a vital role in disaster management and minimizing economic losses. However, satellite-based weather classification remains challenging due to high inter-class similarity; the computational complexity of existing deep learning models, which limits real-time deployment on resource-constrained edge devices; and the limited interpretability of model decisions in practical environments. To address these challenges, this study proposes SatNet-B3, a quantized, lightweight deep learning framework that integrates an EfficientNetB3 backbone with custom classification layers to enable accurate and edge-deployable weather event recognition from satellite imagery. SatNet-B3 is evaluated on the LSCIDMR dataset and demonstrates high-precision performance, achieving 98.20% accuracy and surpassing existing benchmarks. Ten CNN models, including SatNet-B3, were experimented with to classify eight weather conditions, Tropical Cyclone, Extratropical Cyclone, Snow, Low Water Cloud, High Ice Cloud, Vegetation, Desert, and Ocean, with SatNet-B3 yielding the best results. The model addresses class imbalance and inter-class similarity through extensive preprocessing and augmentation, and the pipeline supports the efficient handling of high-resolution geospatial imagery. Post-training quantization reduced the model size by 90.98% while retaining accuracy, and deployment on a Raspberry Pi 4 achieved a 0.3 s inference time. Integrating explainable AI tools such as LIME and CAM enhances interpretability for intelligent climate monitoring. Full article

Decarbonizing heavy-duty freight transport is essential for achieving climate neutrality targets. Although internal combustion engine (ICE) trucks currently dominate logistics, they contribute substantially to greenhouse gas emissions. Zero-emission alternatives, such as battery electric vehicles (BEVs) and hydrogen fuel cell vehicles (H2), provide different decarbonization pathways; however, their relative roles remain contested, particularly in small economies. While BEVs benefit from technological maturity and declining costs, hydrogen offers advantages for high-payload, long-haul operations, especially within energy-intensive cold supply chains. The aim of this paper is to examine the gradual transition from ICE trucks to hydrogen-powered vehicles with a specific focus on cold-chain logistics, where reliability and energy intensity are critical. The hypothesis is that applying a system dynamics forecasting approach, incorporating investment costs, infrastructure coverage, government support, and technological progress, can more effectively guide transition planning than traditional linear methods. To address this, the study develops a system dynamics economic model tailored to the structural characteristics of a small economy, using a European case context. Small markets face distinct constraints: limited fleet sizes reduce economies of scale, infrastructure deployment is disproportionately costly, and fiscal capacity to support subsidies is restricted. These conditions increase the risk of technology lock-in and emphasize the need for coordinated, adaptive policy design. The model integrates acquisition and maintenance costs, fuel consumption, infrastructure rollout, subsidy schemes, industrial hydrogen demand, and technology learning rates. It incorporates subsystems for fleet renewal, hydrogen refueling network expansion, operating costs, industrial demand linkages, and attractiveness functions weighted by operator decision preferences. Reinforcing and balancing feedback loops capture the dynamic interactions between fleet adoption and infrastructure availability. Inputs combine fixed baseline parameters with variable policy levers such as subsidies, elasticity values, and hydrogen cost reduction rates. Results indicate that BEVs are structurally more favorable in small economies due to lower entry costs and simpler infrastructure requirements. Hydrogen adoption becomes viable only under scenarios with strong, sustained subsidies, accelerated station deployment, and sufficient cross-sectoral demand. Under favorable conditions, hydrogen can approach cost and attractiveness parity with BEVs. Overall, market forces alone are insufficient to ensure a balanced zero-emission transition in small markets; proactive and continuous government intervention is required for hydrogen to complement rather than remain secondary to BEV uptake. The novelty of this study lies in the development of a system dynamics model specifically designed for small-economy conditions, integrating industrial hydrogen demand, policy elasticity, and infrastructure coverage limitations, factors largely absent from the existing literature. Unlike models focused on large markets or single-sector applications, this approach captures cross-sector synergies, small-scale cost dynamics, and subsidy-driven points, offering a more realistic framework for hydrogen truck deployment in small-country environments. The model highlights key leverage points for policymakers and provides a transferable tool for guiding freight decarbonization strategies in comparable small-market contexts. Full article

The coastal environment is a dynamic system shaped by both natural processes and human activities. In recent decades, increasing anthropogenic pressure and climate change—manifested through sea-level rise and more frequent extreme events—have accelerated coastal retreat, highlighting the need for improved management strategies and standardized tools for coastal risk assessment. Existing approaches remain highly heterogeneous, differing in structure, input data, and the range of factors considered. To address this gap, this study proposes an index-based methodology of general validity designed to quantify coastal erosion risk through the combined analysis of hazard, vulnerability, and exposure factors. The approach was developed for multi-scale and multi-risk applications and implemented across 54 representative sites along the Calabrian coast in southern Italy, demonstrating strong adaptability and robustness for regional-scale assessments. Results reveal marked spatial variability in coastal risk, with the Tyrrhenian sector exhibiting the highest values due to the combined effects of energetic wave conditions and intense anthropogenic pressure. The proposed framework can be easily integrated into open-access GIS platforms to support evidence-based planning and decision-making, offering practical value for public administrations and stakeholders, and providing a flexible, accessible tool for integrated coastal risk management. Full article

The coffee leaf miner (Leucoptera coffeella) is a major pest of coffee crops and can cause significant economic losses. Early monitoring is essential to support decision-making for its control. This study aimed to evaluate the potential of fuzzy logic for detecting leaf miner infestation using a 2.5-year historical series of Sentinel-2A satellite images processed on the Google Earth Engine platform. Field monitoring of coffee leaf miner infestation was carried out at the EPAMIG Experimental Field, located in São Sebastião do Paraíso, Minas Gerais, Brazil. The period evaluated was from September 2022 to April 2025. Vegetation indices were calculated using the Google Earth Engine platform, and a database was built with eight indices (NDVI, EVI, GNDVI, SR, IPVI, NDMI, MCARI, and CLMI) along with coffee leaf miner infestation data. Principal Component Analysis (PCA) was applied to reduce data dimensionality and identify the most relevant indices for distinguishing infested from healthy plants, explaining 90.9% of the total variance in the first two components (PC1 and PC2). The indices CLMI, IPVI, GNDVI, and MCARI showed the greatest contribution to class separation. A fuzzy inference model was implemented based on the mean index values and validated through performance metrics. The results indicated an overall accuracy of 79.1%, a sensitivity (recall) of 86.6%, a specificity of 66.6%, an F1-score of 0.838, a Kappa coefficient of 0.545, and an area under the curve (AUC) of 0.766. These findings confirm the potential of integrating orbital spectral data via Google Earth Engine with fuzzy logic analysis as an efficient tool, contributing to the adoption of more sustainable monitoring practices in coffee farming. The fuzzy logic system received as input the spectral values derived from Sentinel-2A imagery, specifically the indices identified as most relevant by the PCA (CLMI, IPVI, GNDVI, and MCARI). These indices were computed and integrated into the inference model through processing routines developed in the Google Earth Engine platform, enabling a direct connection between satellite-derived spectral patterns and the detection of coffee leaf miner infestation. Full article