Search Results (4,414)

Similarity search on image embeddings is a common practice for image retrieval in machine learning and pattern recognition systems. Approximate nearest neighbor (ANN) methods enable scalable similarity search on large datasets, often approaching sub-linear complexity. Yet, little empirical work has examined how ANN neighborhood geometry differs from that of exact k-nearest neighbors (k-NN) search as the neighborhood size increases under constrained search effort. This study quantifies how approximate neighborhood structure changes relative to exact k-NN search as k increases across three experimental conditions. Using multiple random subsets of 10,000 images drawn from the STL-10 dataset, we compute ResNet-50 image embeddings, perform an exact k-NN search, and compare it to a Hierarchical Navigable Small World (HNSW)-based ANN search under controlled hyperparameter regimes. We evaluated the fidelity of neighborhood structure using neighborhood overlap, average neighbor distance, normalized barycenter shift, and local intrinsic dimensionality (LID). Results show that exact k-NN and ANN search behave nearly identically when $efSearch>k$. However, as the neighborhood size grows and $efSearch$ remains fixed, ANN search fails abruptly, exhibiting extreme divergence in neighbor distances at approximately $k\approx 2$–$3.5\times efSearch$. Increasing index construction quality delays this failure, and scaling search effort proportionally with neighborhood size ($efSearch=\alpha \times k$ with $\alpha \ge 1$) preserves neighborhood geometry across all evaluated metrics, including LID. The findings indicate that ANN search preserves neighborhood geometry within its operational capacity but abruptly fails when this capacity is exceeded. Documenting this behavior is relevant for scientific applications that approximate embedding spaces and provides practical guidance on when ANN search is interchangeable with exact k-NN and when geometric differences become nontrivial. Full article

Balancing protection and development is essential for mitigating anthropogenic threats and achieving sustainable development in coastal regions. However, integrated spatial planning that links marine protected areas (MPAs) with developed spaces and incorporates land–sea coordination remains insufficiently explored—despite global frameworks such as the “Post-2020 Global Biodiversity Framework” advocating for such integration. In this study, we used Xiamen, a typical bay city in China, as an example, assessed its habitat suitability through the MaxEnt model, and determined its key development areas through hotspot analysis, aiming to coordinate protection and development, as well as land and marine utilization in coastal areas. The results indicate the following: (1) existing protected areas require adjustments; (2) multiple development hotspots overlap, while several cold spots with limited potential for functional development were identified; (3) prioritizing MPAs in decision-making led to an approximate 42.8% increase in MPA coverage in Xiamen. Overall, this study produced a comprehensive plan that integrates both ecological and social objectives. Full article

A subset of patients with inflammatory bowel disease (IBD) remains refractory to treatment despite multiple lines of advanced therapies. These patients are often categorized as having difficult-to-treat (DTT) IBD. We retrospectively analyzed 354 patients with IBD (including 112 with Crohn’s disease [CD] and 242 with ulcerative colitis [UC]) from a real-world cohort. Baseline demographic and disease characteristics, treatment history, and outcomes were compared between the DTT-IBD and non-DTT-IBD groups. Logistic regression analysis was performed to identify factors associated with DTT-IBD in CD and UC cohorts. Approximately 10.6% of the patients exposed to advanced therapy fulfilled the definition of DTT-IBD (CD: 9.8%, UC: 11.4%). Compared with patients with non-DTT-IBD, those with DTT-IBD exhibited a significantly higher exposure to multiple biologic classes, including antitumor necrosis factor (94.1% vs. 59.0%), anti-integrin (94.1% vs. 47.2%), anti-interleukin-12/23 (88.2% vs. 19.4%), and Janus kinase inhibitors (35.3% vs. 0.7%). The DTT-IBD group had a significantly lower clinical remission rate at the last follow-up than the non-DTT-IBD group (52.9% vs. 85.4%, p = 0.001). A longer interval from diagnosis to the initiation of advanced therapy was independently associated with DTT-IBD in CD (OR: 1.014 per month, 95% CI: 1.001–1.026, p = 0.026). No significant predictors for UC were identified. In conclusion, DTT-IBD, characterized by extensive biologic exposure and suboptimal long-term remission rates, accounts for approximately 10% of patients with IBD receiving advanced therapy. In CD, delayed initiation of advanced therapy may contribute to refractoriness. These findings emphasize the unmet need for earlier therapeutic intervention, better predictive markers of treatment response, and novel therapeutic mechanisms. Full article

We aimed to establish a rapid and precise method for identifying and quantifying multi-species vegetable oil (corn oil, olive oil (OLO), soybean oil, and sunflower oil (SUO)) adulterations in camellia oil (CAO), using soft ionization by chemical reaction in transfer–high-resolution mass spectrometry (SICRIT-HRMS) and machine learning methods. The results showed that SICRIT-HRMS could effectively characterize the volatile profiles of pure and adulterated CAO samples, including binary, ternary, quaternary, and quinary adulteration systems. The low m/z region (especially 100–300) exhibited importance to oil classification in multiple feature-selection methods. For qualitative detection, binary classification models based on convolutional neural networks (CNN), Random Forest (RF), and gradient boosting trees (GBT) algorithms showed high accuracies (98.70–100.00%) for identifying CAO adulteration under no dimensionality reduction (NON), principal component analysis (PCA), and uniform manifold approximation and projection (UMAP) strategies. The RF algorithm exhibited relatively high accuracy (96.25–99.45%) in multiclass classification. Moreover, the five models, including CNN, RF, support vector machines (SVM), logistic regression (LR), and GBT, exhibited different performances in distinguishing pure and adulterated CAO. Among 1093 blind oil samples, under NON, PCA, and UMAP: 10, 5, and 67 samples were misclassified by CNN model; 6, 7, and 41 samples were misclassified by RF model; 8, 9, and 82 samples were misclassified by SVM model; 17, 18, and 78 samples were misclassified by LR model; 7, 9, and 43 samples were misclassified by GBT model. For quantitative prediction, the PCA-CNN model performed optimally in predicting adulteration levels in CAO, especially with respect to OLO and SUO, exhibiting a high coefficient of determination for calibration ($R_C^2$, 0.9664–0.9974) and coefficient of determination for prediction ($R_p^2$, 0.9599–0.9963) values, low root mean square error of calibration (RMSEC, 0.9–5.3%) and root mean square error of prediction (RMSEP, 1.1–5.8%) values, and RPD (5.0–16.3) values greater than 3.0. These results indicate that SICRIT-HRMS combined with machine learning can rapidly and accurately identify and quantify multi-species vegetable oil adulterations in CAO, which provides a reference for developing non-targeted and high-throughput detection methods in edible oil authenticity. Full article

Renewable energy sources like wind turbines and solar panels are integrated into modern power grids as Distributed Energy Resources (DERs). These DERs can operate independently or as part of microgrids. Interconnecting multiple microgrids creates Networked Microgrids (NMGs) that increase reliability, resilience, and independent power generation. However, the trustworthiness of individual DERs remains a critical challenge in NMGs, particularly when integrating previously deployed or geographically distributed units managed by entities with varying expertise. Assessing DER trustworthiness ensuring reliability and security is essential to prevent system-wide instability. Thisresearch addresses this challenge by proposing a lightweight trust metric generation system capable of processing structured and semi-structured DER data to produce key trust indicators. The system employs a Small Language Model (SLM) with approximately 16 million parameters for textual data understanding and metric extraction, followed by a regression head to output bounded trust scores. Designed for deployment in computationally constrained environments, the SLM requires only 64.6 MB of disk space and 200–250 MB of memory that is significantly lesser than larger models such as DeepSeek R1, Gemma-2, and Phi-3, which demand 3–12 GB. Experimental results demonstrate that the SLM achieves high correlation and low mean error across all trust metrics while outperforming larger models in efficiency. When integrated into a full neural network-based trust framework, the generated metrics enable accurate prediction of DER trustworthiness. These findings highlight the potential of lightweight SLMs for reliable and resource-efficient trust assessment in NMGs, supporting resilient and sustainable energy systems in smart cities. Full article

This paper presents a hybrid pipeline based on zero-shot vision models for automatic node count estimation in Lisianthus (Eustoma grandiflorum) cultivation and a system for real-time growth information sharing. The multistage image analysis pipeline integrates Grounding DINO for zero-shot leaf-region detection, MiDaS for monocular depth estimation, and a YOLO-based classifier, using daily time-lapse images from low-cost fixed cameras in commercial greenhouses. The model parameters are derived from field measurements of 2024 seasonal crops (Trial 1) and then applied to different cropping seasons, growers, and cultivars (Trials 2 and 3) without any additional retraining. Trial 1 indicates high accuracy (R² = 0.930, mean absolute error (MAE) = 0.73). Generalization performance is confirmed in Trials 2 (MAE = 0.45) and 3 (MAE = 1.14); reproducibility across multiple growers and four cultivars yields MAEs of approximately ±1 node. The model effectively captures the growth progression despite variations in lighting, plant architecture, and grower practices, although errors increase during early growth stages and under unstable leaf detection. Furthermore, an automated Discord-based notification system enables real-time sharing of node trends and analytical images, facilitating communication. The feasibility of combining zero-shot vision models with cloud-based communication tools for sustainable and collaborative floricultural production is thus demonstrated. Full article

Evaluating artificial intelligence (AI) models in clinical medicine requires more than conventional metrics such as accuracy, Area Under the Receiver Operating Characteristic (AUROC), or F1-score, which often overlook key considerations such as fairness, reliability, and real-world utility. We introduce CUES as a multiplicative composite score for clinical prediction models; it is defined as $\mathrm{CUES}=(C\cdot U\cdot E\cdot S{)}^{1/4}$, where C represents calibration, U integrated clinical utility, E equity across patient subpopulations, and S sampling stability. We formally establish boundedness, monotonicity, and differentiability on the domain ${\left(\mathrm{0,1}\right]}^4$, derive first-order sensitivity relations, and provide asymptotic approximations for its sampling distribution via the delta method. To facilitate inference, we propose bootstrap procedures for constructing confidence intervals and for comparative model evaluation. Analytic examples illustrate how CUES can diverge from traditional metrics, capturing dimensions of predictive performance that are essential for clinical reliability but often missed by AUROC or F1-score alone. By integrating multiple facets of clinical utility and robustness, CUES provides a comprehensive tool for model evaluation, comparison, and selection in real-world medical applications. Full article

Eutrophication remains a persistent challenge in the Romanian Black Sea coastal zone, driven by excess nutrient inputs from riverine and coastal sources and further intensified by climate change. This study assesses eutrophication dynamics and explores mitigation options using an integrated framework that combines in situ observations, satellite-derived chlorophyll a data, machine learning, and system dynamics modelling. Water samples collected during two field campaigns (2023–2024) were analyzed for nutrient concentrations and linked with chlorophyll a products from the Copernicus Marine Service. Random Forest analysis identified dissolved inorganic nitrogen, phosphate, salinity, and temperature as the most influential predictors of chlorophyll a distribution. A system dynamics model was subsequently used to explore relative ecosystem responses under multiple management scenarios, including nutrient reduction, enhanced zooplankton grazing, and combined interventions. Scenario-based simulations indicate that nutrient reduction alone produces a moderate decrease in chlorophyll a (45% relative to baseline conditions), while restoration of grazing pressure yields a comparable response. The strongest reduction is achieved under the combined scenario, which integrates nutrient reduction with biological control and lowers normalized chlorophyll a levels by approximately two thirds (71%) relative to baseline. In contrast, a bloom-favourable scenario results in a several-fold increase in chlorophyll a of 160%. Spatial analysis highlights persistent eutrophication hotspots near the Danube mouths and urban discharge areas. These results demonstrate that integrated strategies combining nutrient source control with ecological restoration are substantially more effective than single-measure interventions. The proposed framework provides a scenario-based decision-support tool for ecosystem-based management and supports progress toward achieving Good Environmental Status under the Marine Strategy Framework Directive. Full article

Current research on landslide susceptibility modeling is often constrained by reliance on conventional topographic and geological features, potentially overlooking the discriminative power of surface material properties derived from multi-source remote sensing. This study aims to enhance the accuracy and reliability of susceptibility assessment by innovatively integrating spectral information and advanced machine learning techniques. Focusing on Chongqing, a landslide-prone mountainous region in China, this work conducted three innovative investigations: it (i) introduced 12 spectral features into the feature set; (ii) systematically evaluated spectral features contribution, redundancy, and set completeness through feature engineering; and (iii) implemented a comprehensive Stacking ensemble framework with multiple meta-learners and enhancement strategies (Bagging and Cross-Training) to identify the optimal integration scheme. The key results show that spectral features provided a significant positive impact, boosting the AUC of tree-based ensemble models by up to 4.52%. The optimal model, a Stacking ensemble with Bagging_XGBoost as the meta-learner, achieved a superior test AUC of 0.8611, outperforming all individual base learners. Furthermore, the spatial analysis revealed a concentration of high and very high susceptibility areas in Engineering Geological Zone I, which represents approximately 38% of such areas. This study provides a replicable framework for enhancing landslide susceptibility mapping through the integration of spectral features and ensemble learning, offering a scientific basis for targeted risk management and mitigation planning in complex mountainous terrains. Full article

Background: Human Immunodeficiency Virus type 1 (HIV-1) remains a major global health challenge. Despite advances in antiretroviral therapy, new prevention strategies are needed, particularly topical microbicides capable of blocking the earliest steps of viral entry. HIV-1 attachment relies on interactions with heparan sulfate proteoglycans on host cell surfaces; therefore, sulfated heparan-mimetic polymers have been explored as antiviral agents. In this context, sulfated chitosan microparticles are designed to mimic natural glycosaminoglycan receptors, acting as biomimetic decoys that prevent viral attachment and entry. Methods: Low-molecular-weight sulfated chitosan (LMW Chi-S) microparticles were synthesized and characterized (SEM, EDS, DLS, FTIR) following US Patent No. 11,246,839 B2. Their antiviral activity was evaluated by incubating the microparticles with high-viral-load HIV-1-positive plasma (~3.5 × 10⁶ copies/mL) to enable viral binding and removal by pull-down. The performance of the synthesized Chi-S microparticles was compared with established heparinoid controls, including soluble heparin and heparin microparticles. Results: Chi-S microparticles exhibited stronger virus-binding and neutralizing capacity than all heparinoid comparators, achieving up to 70% reduction in viral load relative to untreated HIV-1 plasma. In comparison, soluble heparin and heparin microparticles reduced viral load by approximately 53% and 60%, respectively. Subsequent evaluation across multiple tested concentrations confirmed a consistent antiviral effect, indicating that the synthesized Chi-S microparticles maintain robust virus–particle interactions throughout the concentration range examined. Conclusions: These findings demonstrate that LMW Chi-S microparticles possess potent antiviral properties and outperform classical heparinoid materials, supporting their potential application as topical microbicides targeting early HIV-1 entry mechanisms. Full article

This study evaluates the performance of several machine learning models in predicting dissolved oxygen concentration in the surface layer of the Mar Menor coastal lagoon. In recent years, this ecosystem has suffered a continuous process of eutrophication and episodes of hypoxia, mainly due to continuous influx of nutrients from agricultural activities, causing severe water quality deterioration and mortality of local flora and fauna. In this context, monitoring the ecological status of the Mar Menor and its watershed is essential to understand the environmental dynamics that trigger these dystrophic crises. Using field data, this study evaluates the performance of eight predictive modelling approaches, encompassing regularised linear regression methods (Ridge, Lasso, and Elastic Net), instance-based learning (k-nearest neighbours, KNN), kernel-based regression (support vector regression with a radial basis function kernel, SVR-RBF), and tree-based ensemble techniques (Random Forest, Regularised Random Forest, and XGBoost), under multiple experimental settings involving spatial variability and varying time lags applied to physicochemical and meteorological predictors. The results showed that incorporating time lags of approximately two weeks in physicochemical variables markedly improves the models’ ability to generalise to new data. Tree-based regression models achieved the best overall performance, with eXtreme Gradient Boosting providing the highest evaluation metrics. Finally, analysing predictions by sampling point reveals spatial patterns, underscoring the influence of local conditions on prediction quality and the need to consider both spatial structure and temporal inertia when modelling complex coastal lagoon systems. Full article

Engineering is suffering a significant change driven by the integration of artificial intelligence (AI) into engineering optimization in design, analysis, and operational efficiency across numerous disciplines. This review synthesizes the current landscape of AI-driven optimization methodologies and their impacts on engineering applications. In the literature, several frameworks for AI-based engineering optimization have been identified: (1) machine learning models are trained as objective and constraint functions for optimization problems; (2) machine learning techniques are used to improve the efficiency of optimization algorithms; (3) neural networks approximate complex simulation models such as finite element analysis (FEA) and computational fluid dynamics (CFD) and this makes it possible to optimize complex engineering systems; and (4) machine learning predicts design parameters/initial solutions that are subsequently optimized. Fundamental AI technologies, such as artificial neural networks and deep learning, are examined in this paper, along with commonly used AI-assisted optimization strategies. Representative applications of AI-driven engineering optimization have been surveyed in this paper across multiple fields, including mechanical and aerospace engineering, civil engineering, electrical and computer engineering, chemical and materials engineering, energy and management. These studies demonstrate how AI enables significant improvements in computational modelling, predictive analytics, and generative design while effectively handling complex multi-objective constraints. Despite these advancements, challenges remain in areas such as data quality, model interpretability, and computational cost, particularly in real-time environments. Through a systematic analysis of recent case studies and emerging trends, this paper provides a critical assessment of the state of the art and identifies promising research directions, including physics-informed neural networks, digital twins, and human–AI collaborative optimization frameworks. The findings highlight AI’s potential to redefine engineering optimization paradigms, while emphasizing the need for robust, scalable, and ethically aligned implementations. Full article

Continuous human-mediated introduction of colonies and queens promotes genetic introgression and reshapes the genetic diversity and structure of local honeybee populations. According to reports, multiple non-native honeybee colonies and queens have been introduced into the DL region, leading to continuous genetic introgression. Here, we assessed the effects of continuous introgression on indigenous Apis cerana in the DL region using mtDNA and genome-wide SNP markers. We sequenced the mitochondrial tRNA ^leu-COII from 217 individuals sampled at 7 DL sites and identified 26 haplotypes defined by 18 polymorphic sites. The ΦST values indicated no internal differentiation within the Apis cerana populations in the DL region. Phylogenetic, network, ABBA-BABA test, and f3 statistic suggested introgression from both northern and southern sources. The f4-ratio indicates that approximately 16% of the ancestry in the DL group is derived from the Aba group. Genetic diversity varied widely within the DL region (Hd: 0.2907–0.8220; π: 0.0009–0.0038; K: 0.3140–1.3980), indicating different stages of introgression. The genetic structure within the DL group appears to be unstable, necessitating long-term monitoring of evolutionary processes and genetic diversity dynamics in A. c. cerana for further insights. Full article

Modifications in leaf architecture disrupt optical properties and internal light-scattering dynamics. Accurate modeling of leaf-scale light scattering is therefore essential not only for understanding how disease affects the availability of light for chlorophyll absorption, but also for evaluating its potential as an early optical marker for plant disease detection prior to visible symptom development. Conventional ray-tracing and radiative-transfer models rely on high-frequency approximations and thus fail to capture diffraction and coherent multiple-scattering effects when internal leaf structures are comparable to optical wavelengths. To overcome these limitations, we present a GPU-accelerated finite-difference time-domain (FDTD) framework for full-wave simulation of light propagation within plant leaves, using anatomically realistic dicot and monocot leaf cross-section geometries. Microscopic images acquired from publicly available sources were segmented into distinct tissue regions and assigned wavelength-dependent complex refractive indices to construct realistic electromagnetic models. The proposed FDTD framework successfully reproduced characteristic reflectance and transmittance spectra of healthy leaves across the visible and near-infrared (NIR) ranges. Quantitative agreement between the FDTD-computed spectral reflectance and transmittance and those predicted by the reference PROSPECT leaf optical model was evaluated using Lin’s concordance correlation coefficient. Higher concordance was observed for dicot leaves ($C_b=0.90$) than for monocot leaves ($C_b=0.79$), indicating a stronger agreement for anatomically complex dicot structures. Furthermore, simulations mimicking an early-stage fungal infection in a dicot leaf—modeled by the geometric introduction of melanized hyphae penetrating the cuticle and upper epidermis—revealed a pronounced reduction in visible green reflectance and a strong suppression of the NIR reflectance plateau. These trends are consistent with experimental observations reported in previous studies. Overall, this proof-of-concept study represents the first full-wave FDTD-based optical modeling of internal light scattering in plant leaves. The proposed framework enables direct electromagnetic analysis of pre- and post-penetration light-scattering dynamics during early fungal infection and establishes a foundation for exploiting leaf-scale light scattering as a next-generation, pre-symptomatic diagnostic indicator for plant fungal diseases. Full article

Accurate prediction of drilling fluid rheological parameters under high-temperature and high-pressure (HTHP) conditions is critical for reliable drilling hydraulics and wellbore pressure control in deep and ultra-deep wells. However, most existing empirical and semi-empirical rheological models are developed for limited temperature–pressure ranges and specific fluid formulations, which restrict their applicability and accuracy under HTHP conditions. In this study, systematic rheological experiments were conducted on multiple drilling fluid systems over wide temperature–pressure ranges (20–200 °C and 0.1–200 MPa). Based on the experimental data, a unified predictive model for key rheological parameters was developed using a symbolic regression (SR) algorithm. The model performance was evaluated using standard statistical metrics and compared with commonly used conventional models. Compared with conventional models, the proposed model shows stronger applicability for predicting the rheological parameters of the investigated oil-based and water-based drilling fluids over a wider temperature–pressure range. It effectively overcomes the limitations of existing models under HTHP conditions (150–200 °C and 80–200 MPa) and demonstrates improved prediction accuracy and robustness for both high- and low-density drilling fluids. The overall prediction errors are generally within approximately 10%. The results indicate that the proposed unified model provides a reliable and computationally efficient tool for predicting drilling fluid rheological parameters under HTHP conditions, facilitating its integration into wellbore hydraulics, wellbore pressure, and equivalent circulating density calculations in deep and ultra-deep well applications. Full article