Search Results (408)

In the domain of river engineering, estimating the total sediment load in rivers is a crucial challenge. For tens to hundreds of kilometers downstream, the additional sand and gravel in the sediment can raise the elevation of channel beds. For highly braided rivers like the Brahmaputra-Jamuna, the accurate prediction of the total sediment load depends on the complex relationships among different hydro-meteorological variables. As a result, manual selection of the lagged features from only antecedent sediment records can produce suboptimal predictions, which can be considered a significant research gap. In addition, the predictive accuracy can be further enhanced through the application of advanced decomposition techniques. To address these deficiencies, we implemented three sophisticated feature selection methodologies: SelectKBest, Mutual Information, and Random Forest utilizing the Boruta Algorithm as an alternative to manual feature selection. Furthermore, we investigated complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), variational mode decomposition (VMD), and the Hodrick–Prescott Filter (HPF) to improve data mining efficiency. Four distinct artificial neural network (ANN) training algorithms were considered: back propagation (BP), cascade correlation (CC), conjugate gradient (CG), and Levenberg–Marquardt (LM), as alternatives to the conventional BP-based training approach. The effectiveness of the variants of the ANN was assessed in comparison to a powerful ensemble learning model, specifically the decision tree (DT). Results indicate that the HPF-enhanced ANN-LM model exhibited the strongest performance metrics when compared to alternative techniques, with values of NRMSE = 0.004, MAE = 455.242 kg/s, NSE = 0.998, and KGE = 0.990. The outcomes from Sobol’s sensitivity analysis suggest that the sediment dynamics in this region can be better predicted through the inclusion of rainfall-based features. Full article

Background/Objectives: This study aims to evaluate the diagnostic performance of radiomic features derived from cone-beam computed tomography (CBCT) images in differentiating radicular cysts (RC) from periapical granulomas (PG). The study also compares the performance of traditional machine learning (ML) algorithms with a novel deep learning (DL) model, Radiomics Cyst Convolutional Neural Network (RadC-CNN). Methods: CBCT images of 98 patients (55 RC, 43 PG), confirmed by histopathological diagnosis, were retrospectively analyzed. Lesions were semi-automatically segmented in 3D Slicer, and 48 radiomic features were extracted. Features with high inter-observer agreement (Intraclass Correlation Coefficient ICC ≥ 0.80) were included in the analysis. Statistical tests and classification models (Decision Tree, K-Nearest Neighbors, Support Vector Machine) were used, and performance was compared to that of the proposed RadC-CNN architecture. Results: Among the 34 features with sufficient reliability, 18 showed statistically significant differences between RC and PG (p < 0.05). Shape, first-order, and texture-based features, including the Gray Level Co-occurrence Matrix (GLCM), Gray Level Run Length Matrix (GLRLM), Gray Level Size Zone Matrix (GLSZM), and Neighboring Gray Tone Difference Matrix (NGTDM), were extracted. The RadC-CNN model demonstrated superior classification performance with an accuracy of 90%, sensitivity of 90%, and precision of 91.3%, outperforming all traditional ML algorithms. Conclusions: CBCT-based radiomic analysis, particularly when combined with DL techniques like RadC-CNN, offers a promising non-invasive approach to distinguish RC from PG. Full article

This study examines the probabilistic patterns associated with casualty severity in collisions between commercial and fishing vessels in China’s coastal waters. Using 137 official accident investigation reports from 2013 to 2022, a structured dataset capturing vessel characteristics, environmental conditions, and human liability factors was constructed. A Tree-Augmented Bayesian Network (TAN-BN) was developed to model the probabilistic interactions among these variables and to identify the key drivers of casualty severity. Sensitivity analysis based on mutual information indicates that fishing vessel length is the most influential factor affecting casualty outcomes (MI = 0.322), followed by time of occurrence, wind speed, visibility, and season. Scenario analysis using MPE indicates that severe casualty scenarios are associated with adverse temporal and environmental conditions such as nighttime, poor visibility, and open-water environments, while liability-specific analysis further shows that collisions attributed primarily to commercial vessel errors are most likely to result in 4–10 casualties. The results highlight the structural vulnerability of small fishing vessels and the critical role of environmental exposure in heterogeneous vessel encounters. This study provides an interpretable probabilistic framework for examining casualty severity patterns in maritime collisions and offers risk-informed insights for improving sustainable maritime safety management in mixed-traffic coastal waters. Full article

Ilex rotunda Thunb. is a prestigious ornamental tree renowned for its vibrant red fruits, yet the molecular mechanisms governing its fruit color variation remain poorly understood. The discovery of a rare yellow-fruited natural bud sport cultivar, ‘Peace Time’, provides an ideal model to investigate these processes compared to the wild-type red fruit. In this study, we integrated physiological evaluations, untargeted metabolomics, and de novo transcriptomics across multiple fruit developmental stages to elucidate the basis of this color transition. Our results demonstrated that the yellow phenotype is characterized by high lightness and yellowness values, driven by the profound suppression of anthocyanin biosynthesis. Biochemical and transcriptomic profiling revealed that DFR (dihydroflavonol 4-reductase), a critical “gatekeeper” gene, experiences severe transcriptional silencing in the yellow-fruited cultivar. This enzymatic bottleneck triggers a “passive substrate overflow,” redirecting shared precursors toward the parallel flavonol branch, resulting in the substantial accumulation of specific flavonols, including rutin and isoquercitrin. Furthermore, correlation network analysis highlighted a putative dual regulatory module associated with this metabolic reprogramming: the down-regulation of the putative activator bHLH30 coupled with the robust up-regulation of the putative repressor bHLH51, together likely contributing to the silencing of DFR transcription. These findings provide a comprehensive “dual-module” and “passive overflow” framework for fruit coloration in I. rotunda, highlighting a remarkable metabolic plasticity that reshapes this cultivar’s phytochemical profile and offers vital insights for future ornamental breeding. Full article

Radio network planning is critical for 5G deployments, particularly for temporary installations in rural areas where terrain and vegetation significantly impact signal propagation. While empirical path loss (PL) models characterize propagation environments through scenario-specific parameters—leading to inherently noisy predictions at individual sites—machine learning (ML) approaches can predict site-specific path loss from multiple features simultaneously. This study conducts a systematic literature review of rural path loss prediction methods and introduces a novel dataset collected via a 5G nomadic measurement platform in a vineyard environment, capturing real-world propagation characteristics. We present a comprehensive comparison of machine learning and interpretable machine learning techniques, demonstrating that vegetation dynamics (quantified through the Normalized Difference Vegetation Index, NDVI) is an important driver of path loss variability when combining data across seasonal campaigns—though not within individual campaigns, where distance dominates. Cross-campaign NDVI transfer, however, is sensitive to satellite resolution, which appears to conflate vine canopy with seasonally managed inter-row ground cover. In cross-campaign transfer, XGBoost proves substantially less susceptible to NDVI-induced degradation than Explainable Boosting Machines (EBM), and a hybrid Log-Normal Shadowing (LNS) and XGBoost model confirms that NDVI captures seasonal variability more effectively than empirical path loss parameters alone. Still, the data captured the expected seasonal trend between April and June 2025, from which our interpretable models derived useful propagation insights. Tree-based models like Random Forest and XGBoost achieved the highest prediction accuracy ($R^2$ up to 0.924 on individual campaigns, 0.891 on combined data, and up to 0.945 (individual) and 0.907 (combined) with antenna pattern-corrected path loss), while explainable boosting machines achieved near-parity ($R^2$ up to 0.919; 0.876 on combined data) with the advantage of interpretability. Among individual campaigns, June—with densest canopy cover—yielded the highest $R^2$ values. These findings provide actionable insights for optimizing temporary 5G networks in precision agriculture and other rural applications. Full article

Background/Objectives: A blunted growth hormone (GH) response in stimulation tests (GHSTs) in obese patients is well documented, with less evidence for insulin-like growth factor-1 (IGF-1) concentrations. The aim of this study was to assess the relationships between nutritional status, GH peak in GHST, and IGF-1 concentrations, and to develop machine learning prediction models of GH deficiency (GHD) in children with short stature. Methods: A case–control study included 1592 children with short stature, whose height, weight, body mass index (BMI), GH peak in two GHSTs, IGF-1 concentration and bone age (BA) were assessed. The cut-off of GH peak in two GHSTs between GHD and idiopathic short stature (ISS) was 10.0 µg/L; additionally, a lower cut-off of 7.0 µg/L was used in repeated analysis. Univariate statistical analyses and classification models were used to identify variables related to the normal and subnormal results of GHST. Results: Depending on the cut-off of GH peak (10.0 vs. 7.0 µg/L), GHD was diagnosed in 604 vs. 279 patients (37.9% vs. 17.5%). Children with GHD had significantly lower (p < 0.001) BMI SDS and IGF-1 SDS than ones with ISS for both cut-offs of GH peak. Overnutrition was associated with the lowest GH peak but the highest IGF-1 SDS; the opposite results were observed in undernutrition. A decision tree predicted GHD in 156 patients, in 149 based on BMI SDS > 0.91. A Naïve Bayes classifier predicted GHD in 118 cases, with BMI SDS and IGF-1 SDS being the only significant variables. The best multilayer perceptron (MLP) neural network predicted GHD in 310 patients, while a logistic regression model did so in 269 patients. Conclusions: Interpretation of GHST should include the patient’s nutritional status in order to avoid overdiagnosis of GHD in overweight and obese children. Full article

The discovery of dynamical quantum phase transitions (DQPTs) has fundamentally challenged the traditional view that phase transitions only occur in thermal equilibrium. Experimental platforms and 1D numerical methods, like matrix product states (MPS), have made great progress. However, exploring true 2D DQPTs remains difficult due to finite-size limitations and the geometric biases of quasi-1D cylinder mappings. Here, we bypass these limitations by deploying a tree tensor network (TTN) approach. This allows us to directly compute the quench dynamics of the transverse-field Ising model (TFIM) on an open 2D square lattice. Because the TTN architecture naturally mirrors 2D lattice connectivity, we can extract the global Loschmidt echo. Our simulations reveal that while deep quenches yield standard DQPTs, quenching within the ferromagnetic phase produces an anomalous dynamical response. In this regime, the rate function exhibits sharp non-analytic peaks even as the macroscopic order parameter maintains its initial sign. This decoupled behavior strongly indicates that local spin excitations drive 2D DQPTs, rather than the macroscopic domain-wall motions seen in 1D chains. These results provide a quantitative numerical baseline for understanding non-equilibrium quantum matter in higher dimensions. Full article

The identification of standing tree species, timber logs, and on-site assessment of their quality and value using images holds significant potential for forestry applications, including inventory management, traceability under EU regulations like the Deforestation Regulation, and market valuation amid growing demands for sustainable practices. This study addresses this by classifying images of timber logs by tree species and market value using the Orange data mining software, which leverages pre-trained convolutional neural networks (Inception v3 and SqueezeNet) to generate embeddings from a dataset of 5549 images collected at a real timber auction in Slovenia, followed by logistic regression image classification. Results show high accuracy for tree species classification (up to 92.6%), but substantially lower accuracy for market value classification (40%–55%), reflecting the greater complexity of value determination from visual features. These findings underscore the promise of deep learning for species identification while indicating the need for further methodological advancements to enhance value classification reliability, which offers the practical impact for operational forestry and bioeconomy value chains. Full article

Background: Laryngeal cancer (LC), a common subtype of head and neck cancers (HNC), is most frequently represented by laryngeal squamous cell carcinoma (LSCC). Prognosis largely depends on early detection; however, traditional prognostic tools, including tumor-node-metastasis (TNM) staging, often show limited predictive accuracy. Artificial intelligence (AI), including machine learning (ML), natural language processing, and deep learning (DL), has emerged as a promising approach to improving cancer diagnosis, prognosis, and treatment planning by analyzing clinical data and medical imaging. Objective: This systematic review assesses the role of AI in prognosis, recurrence prediction, and treatment outcomes in LC. Methods: PubMed, MEDLINE, Scopus, Web of Science, IEEE Xplore, and ScienceDirect were searched up to January 2025. A total of 1062 records were identified; after title/abstract screening and full-text assessment, 29 studies were included. Eligible studies involved adult patients with LC and applied AI to diagnose, prognose, predict recurrence, or assess treatment outcomes using human datasets. Study quality and risk of bias were evaluated using the QUADAS-2 and QUIPS. Results: The 29 included studies were mostly retrospective, with sample sizes ranging from 10 to 63,000 patients. Most focused on LSCC, with a higher prevalence in males. The studies utilized various AI techniques, including deep learning models such as convolutional neural networks (CNNs) and DeepSurv, as well as ML algorithms like random survival forest, gradient boosting machines, random forest, k-nearest neighbors, naïve Bayes, and decision trees. AI models demonstrated strong prognostic performance, surpassing Cox regression and TNM staging in predicting survival and recurrence. Several studies reported outcomes related to treatment, such as chemotherapy response, occult lymph node metastasis, and the need for salvage surgery. Methodological quality varied, with biases related to patient selection and confounding factors. Conclusions: AI has the potential to improve prognosis estimation, recurrence prediction, and treatment outcome assessment in LC. However, although AI can be a helpful addition to clinical decision-making, more prospective studies, external validation, and standardized evaluation are necessary before these technologies can be confidently adopted in everyday clinical practice. Full article

Passive Optical Networks (PONs) play a vital role in providing high-speed broadband access in the 5G and F5G generation. However, their shared nature makes them vulnerable to physical-layer attacks like fiber bending, tapping and fiber cut. The problem is more serious in high-density PONs, where high split ratios result in high optical loss and overlapping back-scattered light, making it difficult to distinguish small attacks from background noise. Contrary to most existing works that neglect class imbalance and signal interference in high-density networks, this paper proposes a robust hierarchical two-stage attack detection scheme. First, we employ a binary classifier to distinguish eavesdropping attacks from normal traffic. Then, a second stage focuses on the specific eavesdropping categories (C1–C4). To address the small amount of attack samples, SMOTE is utilized for oversampling the minority class, and PCA-SVM is used to refine feature selection. Finally, the output of both stages is combined using probability score to obtain reliable decision. The experimental results show the effectiveness of our approach, achieving a classification accuracy of 89.07%. When evaluated on the same data, it has shown superior results in comparison to conventional machine learning algorithms, including decision tree (86.3%), k-nearest neighbors (79%), logistic regression (60%), and Naïve Bayes (52.6%). Full article

Castanopsis hystrix (C. hystrix) is one of the most dominant and ecologically important species in subtropical evergreen broad-leaved forests of China. Interactions between its root and rhizosphere microorganisms play a pivotal role in nutrient acquisition and in mediating plant response s to environmental stresses. In this study, high-throughput 16S ribosomal RNA (16S rRNA) sequencing combined with untargeted metabolomics was employed to systematically characterize the rhizosphere microbial community and root exudates in C. hystrix. The results showed that, compared with non-rhizosphere soil, bacterial diversity in the rhizosphere of C. hystrix was significantly reduced, while several specialized and potentially efficient taxa were selectively enriched, particularly Candidatus_Solibacter, Candidatus_Xiphinematobacter, and Candidatus_Koribacter, thereby reshaping a distinct rhizosphere-specific community structure. Metabolomic analyses further revealed that 129 metabolites were significantly enriched in the rhizosphere, including four major classes of compounds associated with plant stress resistance: lipids and lipid-like molecules, organoheterocyclic compounds, organic acids and derivatives, and phenylpropanoids and polyketides. The enrichment of these metabolites likely contributes substantially to stress tolerance in C. hystrix. Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analysis identified six defense-related metabolic pathways, including pyrimidine metabolism, steroid biosynthesis, nucleotide metabolism, plant hormone signal transduction, ATP-binding cassette transporter (ABC transporters), and the biosynthesis of various plant secondary metabolites. Further correlation analysis and co-occurrence network analysis suggested that C. hystrix may potentially influence the enrichment of beneficial microorganisms through rhizosphere metabolites selectively, which could reduce the reliance on external nutrient acquisition and enhance the stress resilience of C. hystrix. Our study provides a comprehensive perspective for elucidating rhizosphere interaction networks and their ecological functions in C. hystrix, thereby enhancing our understanding of the environmental adaptability of dominant tree species in subtropical forests. Full article

Postoperative stroke is a serious and fatal condition that often affects elderly surgical patients. This rare but severe complication arises from complex interactions between comorbidities, physiologic instability and demographic disturbances that traditional risk tools often fail to capture.This study aims to develop and validate a machine learning model with an improved ability to predict the risk of postoperative stroke in elderly patients utilising the comprehensive clinical and demographic ICU data from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database. External validation was performed on MIMIC-III and the eICU Collaborative Research Database, with eICU being the primary validation set. We identified postoperative surgical intensive care unit (SICU) patients aged 55 years or older from all databases. A strict temporal window of the first 24 h of ICU admission was applied across all three datasets while extracting features like laboratory measurements and vital sign summaries in order to ensure that all predictor values were derived from a fixed observation period at the beginning of ICU stay. After preprocessing, applying Multivariate Imputation by Chained Equations (MICE) imputation and initial screening of 88 candidate variables, 20 clinically meaningful predictors were selected through a multistage feature selection pipeline incorporating RFECV and permutation importance. SHAP analysis and LIME analysis were used for interpretability. We evaluated ten machine learning techniques, including Logistic Regression, Decision Tree, Random Forest, K-Nearest Neighbors (KNNs), Support Vector Machine (SVM–RBF Kernel), Gradient Boosting (GBDT), Neural Network, XGBoost, CatBoost, Naive Bayes. Among them, Random Forest demonstrated strong predictive performance by achieving an AUROC of 0.8072 (95% CI [0.7890, 0.8253]) on the internal validation set. The model also achieved AUROC of 0.7557 (95% CI [0.7267, 0.7794]) and 0.9144 (95% CI [0.8893, 0.9378]) on the external validation sets eICU and MIMIC-III, respectively. Mean systolic blood pressure, Elixhauser score, minimum calcium, and minimum INR (PT) were consistently identified as the most influential predictors through both SHAP analysis and LIME analysis, thus strengthening model interpretability. Our findings suggest that a Random Forest-based predictive model can provide an accurate and generalisable prediction of postoperative stroke in elderly ICU patients using routinely collected physiologic and laboratory data. This also supports early risk stratification and targeted postoperative monitoring. Full article

Background: The CONSTANS, CONSTANS-like, and TIMING OF CAB EXPRESSION 1 (CCT) domain proteins are key regulators of flowering time and circadian rhythms in annual plants, but their diversity and temporal expression patterns in perennial trees remain poorly understood. Methods: Here, we performed a genome-wide characterization of CCT family genes and analyzed their seasonal and circadian expression dynamics in Populus. Using an HMM-based search, we identified 49 putative CCT genes (PtCCTs) in the Populus genome and classified them into five subfamilies (COL, CMF, PRR, ALSM and ZIM) based on domain composition and phylogeny. Results: Synteny and duplication analyses showed that most PtCCTs arose from segmental duplication and have predominantly evolved under purifying selection. Promoter analyses revealed a rich repertoire of cis-regulatory elements, with a marked enrichment of light- and hormone-responsive motifs, particularly G-box and ABRE elements, in PtPRR and a subset of PtCOL promoters. Transcriptome data indicated that many PtCCTs display distinct tissue-specific expression patterns, with PtPRRs and PtZIMs being strongly enriched in dormant buds. Seasonal transcriptomes from leaves and shoot apices revealed discrete expression profiles associated with growth, bud set, and winter dormancy, and most PtPRRs showed increasing transcript levels from September to December. Diurnal time-series data further identified 19 PtCCTs with significant rhythmic expression, separating COL and PRR members into night- and day-phased groups. Network analysis using STRING indicated that PtPRRs interact with photoperiodic pathway components such as PtGI, and re-analysis of diurnal data from wild-type and lhy-RNAi hybrid aspen showed that several PtPRRs exhibit phase and amplitude changes when LHY expression is reduced. Conclusions: Together, these results provide a comprehensive overview of the CCT gene family in Populus and highlight PtPRRs and specific PtCOLs as promising candidates that link the circadian clock and light signaling to seasonal growth cessation and bud dormancy in perennial trees. Full article

Addressing the thermal management challenges of prismatic aluminum shell lithium battery modules in electric vehicles under high-rate charge–discharge conditions, this study proposes a multi-objective optimization design method for integrated biomimetic liquid cooling plates. By integrating various highly efficient heat transfer structures from nature, including fractal-tree-like networks, leaf vein branching systems, and spider web radial distribution, a novel biomimetic liquid cooling plate topology was constructed. A multi-physics coupled numerical model considering electrochemical heat generation, thermal conduction, convective heat transfer, and thermal stress deformation was established. The NSGA-II algorithm was employed to globally optimize 12 design variables including channel geometric parameters, operating conditions, and structural dimensions, achieving collaborative optimization objectives of maximum temperature minimization, temperature uniformity maximization, pressure drop minimization, and structural lightweighting. The weight coefficients for the four optimization objectives were determined through the Analytic Hierarchy Process (AHP) with verified consistency (CR = 0.02 < 0.10), ensuring rational priority allocation aligned with automotive safety standards. The optimization results demonstrated that compared to the initial design, the optimal solution reduced the maximum temperature under 3C discharge conditions by 9.9% to 34.7 °C, decreased the temperature difference by 31.3% to 3.3 °C, lowered the pressure drop by 24.6% to 2150 Pa, reduced structural mass by 4.0%, and decreased maximum stress by 16.7%. Quantitative comparison with single biomimetic structures under identical boundary conditions showed that the integrated design achieved a 3.3% lower maximum temperature and 25.7% better flow uniformity than the best-performing single structure, demonstrating the synergistic advantages of multi-biomimetic integration. These synergistic performance improvements can be attributed to the hierarchical multi-scale architecture where fractal networks provide macro-scale flow distribution, leaf vein branches ensure meso-scale coverage, and spider web radials achieve micro-scale thermal matching. Long-term cycling tests conducted at 1C/1C rate with 25 ± 1 °C ambient temperature showed that the optimized design maintained a capacity retention rate of 92.3% after 1000 charge–discharge cycles, demonstrating excellent durability. The complex biomimetic channel structure can be fabricated using selective laser melting technology with minimum feature sizes below 0.3 mm, indicating promising manufacturing feasibility. The research findings provide theoretical guidance and technical support for the engineering design of high-performance battery thermal management systems. Full article

Cities are complex land systems where spatial form mediates welfare, connectivity, and community-based adaptation. This study compares two Haredi neighbourhoods in Jerusalem, Ezrat Torah (an organically evolved semilattice) and Ramat Shlomo (a planned tree-type enclave), to examine how urban morphology interacts with planning logics to shape sustainability trade-offs. We integrated graph-based meshedness (α-index), aggregate isovist cascade analysis, and a geodesign-supported negotiation to evaluate the land-use mix, visibility structure, and network redundancy and to co-design 2045 scenarios across housing, transport, green, and social infrastructure. Findings showed that semilattice fabrics support richer overlaps among social and spatial subsystems, enabling incremental, lower-conflict adjustments towards sustainability objectives, whereas tree-like structures lock units into hierarchical compartments, constraining adaptation. Methodologically, the paper operationalises Alexander’s structure–life hypothesis with reproducible indicators and demonstrates how geodesign can align community preferences with broader sustainability goals. The contribution is twofold: (i) empirical evidence on how neighbourhood morphology conditions welfare–connectivity–resilience outcomes; and (ii) a transferable, negotiation-centred workflow for planning in culturally cohesive urban enclaves. Full article