Search Results (3,104)

Dental caries remains one of the most prevalent chronic diseases worldwide, driven by complex interactions among dietary, hygienic, and biological factors. This study introduces a hybrid predictive framework that integrates mathematical modelling and artificial intelligence (AI) to estimate individual caries risk based on daily sugar intake, oral hygiene index, salivary pH, fluoride exposure, age, and sex. A first-order balance differential equation was applied to simulate demineralisation–remineralisation dynamics, while a feed-forward artificial neural network (ANN) was trained on simulated and literature-derived datasets. The hybrid model demonstrated strong predictive performance, achieving 91.2% accuracy and an AUC of 0.98 in classifying individuals into low-, moderate-, and high-risk categories. Sensitivity analysis identified sugar intake and oral hygiene as dominant determinants, while fluoride and salivary pH showed protective effects. These findings highlight the feasibility of combining mechanistic and data-driven approaches to enhance early risk assessment and support the development of intelligent, personalised screening tools in preventive dentistry. Full article

Amid the rapid evolution of the digital economy reshaping global competitiveness, China has advanced regional coordination through the Digital China initiative and the “Data Elements ×” Three-Year Action Plan (2024–2026). To further integrate digital transformation with high-quality growth in the urban agglomerations of the middle and lower Yellow River, this study aims to strengthen regional competitiveness, expand digital industries, foster new productivity, refine the development pathway, and safeguard balanced economic, social, and ecological progress. Taking the Yellow River urban clusters as the research object, a comprehensive assessment framework encompassing seven subsystems is established. By employing a mixed-weighting approach, entropy-based TOPSIS, hotspot analysis, coupling coordination models, spatial gravity shift techniques, and grey relational methods, this study investigates the spatiotemporal dynamics between the digital economy and high-quality development. The findings reveal that: (1) temporally, the coupling–coordination process evolves through three distinct phases—initial fluctuation and divergence (1990–2005), synergy consolidation (2005–2015), and high-level stabilization (2015–2022)—with the average coordination index rising from 0.21 to 0.41; (2) spatially, a persistent “core–periphery” structure emerges, while subsystem coupling consistently surpasses coordination levels, reflecting a pattern of “high coupling but insufficient coordination”; (3) hot–cold spot analysis identifies sharp east–west contrasts, with the gravity center shift and ellipse trajectory showing weaker directional stability but greater dispersion; and (4) grey correlation results indicate that key drivers have transitioned from economic scale and infrastructure inputs to green innovation performance and data resource allocation. Overall, this study interprets the empirical results in both temporal and spatial dimensions, offering insights for policymakers seeking to narrow the digital divide and advance sustainable, high-quality development in the Yellow River region. Full article

The low fertility of plinthosols is a major constraint on agricultural production, largely due to the presence of plinthite, which restricts the availability of water and nutrients. This study aimed to simulate the growth and yield of grain maize on a loosened plinthosol amended with termite mound (from Macrotermes falciger) material in the Lubumbashi region. A 660-hectare perimeter was established, subdivided into ten maize blocks (B1–B10) and a control block (B0), which received the same management practices as the other blocks except for subsoiling and termite mound amendment. The APSIM model was used for simulations. The leaf area index (LAI) was estimated from Sentinel-2 imagery via Google Earth Engine, using the Simple Ratio (SR) spectral index, and integrated into APSIM alongside agro-environmental variables. Model performance was assessed using cross-validation (2/3 calibration, 1/3 validation) based on the coefficient of determination (R²), Nash–Sutcliffe efficiency (NSE), and root mean square error (RMSE). Results revealed a temporal LAI dynamic consistent with maize phenology. Simulated LAI matched observations closely (R² = 0.85 − 0.93; NSE = 0.50 − 0.77; RMSE = 0.29 − 0.40 m² m⁻²). Maize grain yield was also well predicted (R² = 0.91; NSE > 0.80; RMSE < 0.50 t ha⁻¹). Simulated yields reproduced the observed contrast between treated and control blocks: 10.4 t ha⁻¹ (B4, 2023–2024) versus 4.1 t ha⁻¹ (B0). These findings highlight the usefulness of combining remote sensing and biophysical modeling to optimize soil management and improve crop productivity under limiting conditions. Full article

The coordinated scheduling of diesel generators, photovoltaic (PV) systems, and energy storage systems (ESS) is essential for improving the reliability and resilience of islanded microgrids in remote and mission-critical applications. This review systematically analyzes diesel–PV–ESSs from an “energy symbiosis” perspective, emphasizing the complementary roles of diesel power security, PV’s clean generation, and ESS’s spatiotemporal energy-shifting capability. A technology–time–performance framework is developed by screening advances over the past decade, revealing that coordinated operation can reduce the Levelized Cost of Energy (LCOE) by 12–18%, maintain voltage deviations within 5% under 30% PV fluctuations, and achieve nonlinear resilience gains. For example, when ESS compensates 120% of diesel start-up delay, the maximum disturbance tolerance time increases by 40%. To quantitatively assess symbiosis–resilience coupling, a dual-indicator framework is proposed, integrating the dynamic coordination degree (ζ ≥ 0.7) and the energy complementarity index (ECI > 0.75), supported by ten representative global cases (2010–2024). Advanced methods such as hybrid inertia emulation (200 ms response) and adaptive weight scheduling enhance the minimum time to sustain (MTTS) by over 30% and improve fault recovery rates to 94%. Key gaps are identified in dynamic weight allocation and topology-specific resilience design. To address them, this review introduces a “symbiosis–resilience threshold” co-design paradigm and derives a ζ–resilience coupling equation to guide optimal capacity ratios. Engineering validation confirms a 30% reduction in development cycles and an 8–12% decrease in lifecycle costs. Overall, this review bridges theoretical methodology and engineering practice, providing a roadmap for advancing high-renewable-penetration islanded microgrids. Full article

Background: The pathological response to neoadjuvant chemotherapy (NAC) is an established predictor of long-term outcomes in breast cancer. However, conventional binary assessment based solely on pathological complete response (pCR) fails to capture prognostic heterogeneity across molecular subtypes. This study aimed to develop an interpretable deep learning model that integrates multiple clinical and pathological variables to predict both recurrence and metastasis development following NAC treatment. Methods: We conducted a retrospective analysis of 832 breast cancer patients who received NAC between 2013 and 2022. The analysis incorporated five key variables: tumor size changes, nodal status, Ki-67 index, Miller–Payne grade, and molecular subtype. A Multi-Layer Perceptron (MLP) model was implemented on the PyTorch platform and systematically benchmarked against SVM, Random Forest, and XGBoost models using five-fold cross-validation. Model performance was assessed by calculating the area under the curve (AUC), accuracy, precision, recall, and F1-score, and by analyzing confusion matrices. Results: The MLP model achieved AUC values of 0.86 (95% CI: 0.82–0.93) for HER2-positive cases, 0.82 (95% CI: 0.70–0.92) for triple-negative cases, and 0.76 (95% CI: 0.66–0.82) for HR+/HER2-negative cases. SHAP analysis identified post-NAC tumor size, Ki-67 index, and Miller–Payne grade as the most influential predictors. Notably, patients who achieved pCR still had a 12% risk of developing recurrence, highlighting the necessity for ongoing risk assessment beyond binary response evaluation. Conclusions: The proposed deep learning system provides precise and interpretable risk assessment for NAC patients, facilitating individualized treatment approaches and post-treatment monitoring plans. Full article

Avalanche susceptibility mapping is vital for disaster prevention and infrastructure safety in cold mountain regions under climate change. Traditional machine learning (ML) approaches have demonstrated strong predictive capacity, yet their limited interpretability and difficulty in identifying threshold effects hinder their broader application in geohazard risk management. To overcome these limitations, this study develops an explainable ML framework that integrates remote sensing data, topographic and climatic variables, and SHapley Additive exPlanations for the Kanas Scenic Area transportation corridor in the Chinese Altay Mountains. The framework evaluates five classifiers: Random Forest, XGBoost, LightGBM, Soft Voting, and Stacking, and using sixteen conditioning factors that capture topography, climate, vegetation, and anthropogenic influences. Results show that LightGBM achieved the best performance, with an AUC of 0.9428, accuracy of 0.8681, F1-score of 0.8750, and Cohen’s kappa of 0.7366. To ensure transparency for risk decisions, SHAP analyses identify Terrain Ruggedness Index, wind speed, slope, aspect and NDVI as dominant drivers. The dependence plots reveal actionable thresholds and interactions, including a TRI plateau near 5–7, a slope peak between 30° and 40°, a wind effect that saturates above about 2.5 m s⁻¹, and a near-river high-risk belt within 0–2 km. The five-class map aligns with independent field observations, with more than three quarters of events falling in moderate to very high zones. By integrating explainable ML with remote sensing, this study advances avalanche risk assessment in cold region transportation corridors and strengthens the robustness of regional susceptibility mapping. Full article

Fiber reinforcement is a promising solution to several problems, however, the impact of fiber characteristics on the mechanical behavior and reinforcement mechanisms of asphalt mixtures remains unclear. Therefore, two distinct forms of basalt fiber—chopped basalt fiber (CBF) and flocculent basalt fiber (FBF)—were employed. A comprehensive experimental program was conducted, encompassing macroscopic and microscopic analyses through semi-circular bending tests integrated with digital image correlation, four-point bending fatigue tests, and dynamic modulus tests. Results indicate that both fiber types significantly improve crack resistance, with FBF demonstrating superior performance. Compared with the ordinary mixture, the flexibility index and fracture energy of the FBF-reinforced asphalt mixture increased by 59.7% and 30.6%, respectively. Fibers exert a crack-bridging effect, delaying the transition of the crack propagation stage by 1.25–2.21 s and reducing the crack propagation rate by 39.6–55.4%. Although fatigue life decreased with increasing strain levels, basalt fibers substantially enhanced fatigue resistance, with FBF-reinforced asphalt mixture achieving 20–40% higher N_f,50 values than CBF. Dynamic modulus tests revealed that fibers reduce modulus at low temperatures while increasing it at high temperatures, with more pronounced reinforcement effects observed in high-frequency regions. These findings underscore the importance of fiber morphology in optimizing asphalt mixture design and provide a theoretical basis for optimizing fiber-reinforced pavement materials to achieve long-term durability under complex environmental and traffic load conditions. Full article

The Retrieval-Augmented Generation (RAG) framework shows great potential in terms of improving the reasoning and knowledge utilization capabilities of language models. However, most existing RAG systems heavily rely on large language models (LLMs) and suffer severe performance degradation when using small language models (SLMs), which limits their efficiency and deployment in resource-constrained environments. To address this challenge, we propose Retrieval-Adaptive-Planning RAG (RAP-RAG), a lightweight and high-efficiency RAG framework with adaptive retrieval task planning that is compatible with both SLMs and LLMs simultaneously. RAP-RAG is built on three key components: (1) a heterogeneous weighted graph index that integrates semantic similarity and structural connectivity; (2) a set of retrieval methods that balance efficiency and reasoning power; and (3) an adaptive planner that dynamically selects appropriate strategies based on query features. Experiments on the LiHua-World, MultiHop-RAG, and Hybrid-SQuAD datasets show that RAP-RAG consistently outperforms representative baseline models such as GraphRAG, LightRAG, and MiniRAG. Compared to lightweight baselines, RAP-RAG achieves 3–5% accuracy improvement while maintaining high efficiency and maintains comparable efficiency in both small and large model settings. In addition, our proposed framework reduces storage size by 15% compared to mainstream frameworks. Component analysis further confirms the necessity of weighted graphs and adaptive programming for robust retrieval under multi-hop reasoning and heterogeneous query conditions. These results demonstrate that RAP-RAG is a practical and efficient framework for retrieval-enhanced generation, suitable for large-scale and resource-constrained scenarios. Full article

Within the current administrative boundaries of the city of Lublin, fragments of roadside tree avenues of various historical origins and periods of establishment have been preserved, including former tree-lined roads leading to rural and suburban residences from the 18th and 19th centuries. This avenue once led to the manor in Konstantynów and now serves as the main road through the campus of the John Paul II Catholic University of Lublin (Katolicki Uniwersytet Lubelski—KUL). As one of the last surviving elements of the former rural landscape, the Konstantynów avenue represents a symbolic link between past and future. The research combines acoustic tomography and chlorophyll fluorescence analysis, providing a precise and non-invasive evaluation of the internal structure and physiological performance of 34 small-leaved linden trees (Tilia cordata Mill.). This methodological approach allows for early detection of stress symptoms and structural degradation, offering a significant advancement over traditional visual assessments. The study area is an intensively used urban campus, where extensive surface sealing beneath tree canopies restricts rooting space. The degree of surface sealing (paving) directly beneath the tree canopies was also measured. Based on the statistical analysis, a weak a non-significant weak negative correlation (r = −0.117) was found between the proportion of sealed surfaces within the Tree Protection Zone (TPZ) and the Fv/Fm vitality index, indicating that higher levels of surface sealing may reduce tree vitality; however, this relationship was not statistically significant (p = 0.518). The study provides an evidence-based framework for conserving historic trees by integrating advanced diagnostic tools and quantifying environmental stress factors. It emphasizes the importance of improving rooting conditions, integrating heritage trees into urban planning strategies, and developing adaptive management practices to increase their resilience. The findings offer a model for developing innovative conservation strategies, applicable to historic green infrastructure across Europe and beyond. Full article

Under the dual pressures of global climate change and accelerated urbanization, the impacts of flood disasters on urban systems are becoming increasingly pronounced. Enhancing regional resilience has emerged as a critical factor in achieving sustainable urban development. Compared with existing methods such as CRITIC–Entropy, PCA–AHP, or SWMM-based resilience evaluations, grounded in urban resilience theory, this study takes Fangshan District in Beijing as empirical research to construct a post-flood disaster resilience evaluation index system spanning five dimensions (ecological, social, engineering, economic, and institutional) and leverages the integrated DEMATEL-TOPSIS-AISM model to synergistically identify key drivers, evaluate performance, and uncover internal hierarchies, thereby overcoming the limitations of existing research approaches. The findings indicate that the DEMATEL analysis identified the frequency of heavy rainfall (a12 = 0.889) and the proportion of flood disaster information databases (c51 = 1.153) as key driving factors. The TOPSIS assessment reveals that Fangshan District exhibits the strongest resilience in the economic dimension (Relative Closeness C = 0.21200), while the institutional dimension is the weakest (C = 0.00000), the AISM model constructs a hierarchical topology from a cause–effect priority perspective, elucidating the causal relationships and transmission mechanisms among factors across different dimensions. This study pioneers a novel perspective for urban resilience assessment, thereby establishing a theoretical foundation and practical references for enhancing flood resilience and advancing resilient city development. Full article

As global attention to sustainable development grows, the role of Environmental, Social, and Governance (ESG) practices is becoming increasingly prominent across various industries, particularly in export-oriented sectors. This paper examines the impact of ESG performance on the export competitiveness of Chinese manufacturing enterprises. By analyzing data from 9641 A-share listed manufacturing companies between 2011 and 2021, along with ESG ratings from the Huazheng database, this study investigates how ESG performance influences export competitiveness through financing constraints and risk-taking behavior. In the baseline regressions, ESG performance is positively associated with both the export sophistication index (ESI, coefficient = 0.0132, p < 0.05) and the log of export value (EXPORT, coefficient = 0.0241, p < 0.01). The findings show that superior ESG performance significantly enhances export competitiveness by reducing financing constraints and increasing risk tolerance. Further analysis reveals that the effect of ESG performance is stronger in regions with poorer business environments and among firms with lower institutional investor ownership. This study provides empirical evidence on how Chinese enterprises can enhance their international competitiveness through ESG practices, offering valuable insights for policymakers and business leaders seeking to integrate ESG and boost export competitiveness. Full article

Groundwater represents a critical global resource, increasingly threatened by overexploitation and pollution from contaminants such as arsenic (As), fluoride (F), nitrates (NO₃⁻), and heavy metals in arid to semi-arid regions like Mexico. Traditional Water Quality Indices ($WQIs$), while useful, suffer from subjectivity in assigning weights, which can lead to misinterpretations. This study addresses these limitations by developing a novel, objective Groundwater Quality Index ($GWQI$) through the seamless integration of Machine Learning (ML) models. Utilizing a database of 775 wells from the Mexican National Water Commission (CONAGUA), Principal Component Analysis (PCA) was applied to achieve significant dimensionality reduction. We successfully reduced the required monitoring parameters from 13 to only three key indicators: total dissolved solids (TDSs), chromium (Cr), and manganese (Mn). This reduction allows for an 87% decrease in the number of indicators, maximizing efficiency and generating potential savings in monitoring resources without compromising water quality prediction accuracy. Six $WQI$ methods and six ML models were evaluated for quality prediction. The Unified Water Quality Index (${WQI}_u$) demonstrated the best performance among the $WQIs$ evaluated and exhibited the highest correlation (R² = 0.85) with the traditional $WQI$ based on WHO criteria. Furthermore, the ML Support Vector Machine with polynomial kernel (svmPoly) model achieved the maximum predictive accuracy for ${WQI}_u$ (R² = 0.822). This robust $GWQI$-ML approach establishes an accurate, objective, and efficient tool for large-scale groundwater quality monitoring across Mexico, facilitating informed decision-making for sustainable water management and enhanced public health protection. Full article

The European Union air transport sector has been repeatedly exposed to major disruptions such as the 2008 financial crisis, the COVID-19 pandemic, the war in Ukraine, and volatile energy prices. Strengthening resilience has, therefore, become a strategic priority. This study examines how strategic energy investments—covering renewable energy, sustainable aviation fuels (SAFs), electrification, hydrogen technologies, and advanced infrastructure—contribute to the resilience of the EU air transport system. The methodology integrates both primary and secondary data from EU policy documents, ICAO and IATA databases, Eurostat, and national statistics. A multi-criteria evaluation was applied using four key performance indicators: emission reduction efficiency (ER), annual exposure index (AEI), investment performance index (IPI), and net present value (NPV). Projects were assessed through Simple Additive Weighting (SAW) and the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS), complemented by sensitivity analysis. The results show that the Pioneer project delivers the strongest environmental and financial outcomes, ranking first in ER, AEI, and NPV. Hermes performs best in job creation and social impact, while BioOstrand achieves substantial absolute CO₂ reductions but lower cost efficiency. TULIPS shows limited effectiveness across all indicators. Sensitivity analysis confirmed that rankings remain robust under alternative weighting scenarios. The findings underscore that project design and alignment with resilience objectives matter more than investment size. Strategic energy investments should, therefore, be prioritized not only for decarbonization but also for their ability to reinforce both technological and socio-economic resilience, providing a reliable foundation for a sustainable and crisis-resistant EU air transport sector. Full article

This paper presents a mathematics-focused AI iterative prediction framework that combines Extreme Gradient Boosting (XGBoost) for nonlinear function approximation with nonlinear autoregressive model with exogenous inputs (NARXs) for time-series modeling, applied to analyzing the Remaining Useful Life (RUL) and availability of Unmanned Aerial Vehicle (UAV) Brushless DC (BLDC) motors. The framework integrates nonlinear regression, temporal recursion, and survival analysis into a unified system. The dataset includes five UAV motor types, each recorded for 10 min at 20 Hz, totaling approximately 12,000 records per motor for validation across these five motor types. Using grouped K-fold cross-validation by motor ID, the framework achieved mean absolute error (MAE) of 4.01 h and root mean square error (RMSE) of 4.51 h in RUL prediction. Feature importance and SHapley Additive exPlanation (SHAP) analysis identified temperature, vibration, and HI as key predictors, aligning with degradation mechanisms. For availability assessment, survival metrics showed strong performance, with a C-index of 1.00 indicating perfect risk ranking and a Brier score at 300 s of 0.159 reflecting good calibration. Additionally, Conformalized Quantile Regression (CQR) enhanced interval coverage under diverse operating conditions, providing mathematically guaranteed uncertainty bounds. The results demonstrate that this framework improves both accuracy and interpretability, offering a reliable and adaptable solution for UAV motor prognostics and maintenance planning. Full article

Background: Heart failure (HF) is common and deadly, affecting over 60 million people worldwide, and it remains a leading cause of hospitalization and post-discharge death. One-year mortality after an acute decompensated HF (ADHF) admission often approaches 40%. Prognostic models are critical for stratifying mortality risk in heart failure (HF) patients. This study compared the performance of the MAGGIC and BCN Bio-HF models in predicting 1-year and 3-year all-cause mortality (ACM) in patients discharged after acute decompensated HF (ADHF). Methods: A retrospective analysis was conducted on 229 patients hospitalized for ADHF at the Clinical University Hospital of Zaragoza. The required variables were extracted from medical records, and ACM risks were calculated using web-based tools. Calibration, discrimination (AUC), and Kaplan–Meier survival analysis and calibration curves assessed risk stratification and alignment with observed outcomes. Reclassification metrics (Net Reclassification Index [NRI], Integrated Discrimination Improvement [IDI]) were used to compare the models’ predictive performances. Results: Both of the models demonstrated robust discrimination for 1-year ACM (AUC: MAGGIC = 0.738, BCN Bio-HF = 0.769) but showed lower performance for 3-year predictions. Calibration was poor, with both models exhibiting significant risk underestimation at the individual level. MAGGIC achieved higher sensitivity (1-year: 0.911; 3-year: 0.685), favoring high-risk patient identification, whereas BCN Bio-HF offered superior specificity (1-year: 0.679; 3-year: 0.746) and a positive prediction value, reducing false positives. BCN Bio-HF showed a significant 12.7% reclassification improvement for 1-year mortality prediction. Conclusions: BCN Bio-HF did not outperform MAGGIC in our cohort. MAGGIC is preferable for the initial high-risk patient identification, requiring more intense short-term follow-up, while BCN Bio-HF’s higher specificity is best-suited to avoid overtreatment. Altogether, the clinical utility of both models was limited in our cohort by severe miscalibration, which may render adequate risk stratification difficult. Full article