Search Results (1,373)

Conventional diagnosis of chronic kidney disease (CKD) relies predominantly on invasive blood-based examinations, limiting the scalability of kidney health screening in resource-constrained environments. This study presents embedded engineering framework for non-invasive, breath-based CKD staging framework supported by machine learning and implemented on a low-cost embedded platform. To account for physiological sex differences in baseline creatinine production, estimated glomerular filtration rate (eGFR) values and breath ammonia concentrations were derived from two independent clinical cohorts using sex-specific MDRD equations (incorporating the standard male formula and the $0.742$ female correction factor, respectively) and creatinine–BUN conversion models, with male- and female-parameterized algorithms developed in parallel. The resulting feature space was analyzed using four unsupervised clustering approaches to stratify subjects into five clinically meaningful kidney function stages. Stage-specific ammonia thresholds were implemented within an Arduino Nano-based prototype equipped with an MQ-137 gas sensor and OLED display, enabling real-time point-of-care classification. Dataset-level classification accuracy reached 82% for the male algorithm and 92% for the female algorithm. Hospital-based validation on 29 patients (22 male, 7 female) yielded a real-world testing accuracy of 90.5% ($20/22$) for male patients and 71.4% ($5/7$) for female patients, a discrepancy largely attributable to the small female sample size. Because the current evaluation lacks healthy control subjects and is constrained by sample size, these empirical results serve primarily to demonstrate hardware-software functional integration and real-world deployment feasibility rather than definitive clinical efficacy. Despite these preliminary, sample-limited clinical datasets, results suggest this approach holds promise as an accessible, non-invasive screening complement to conventional diagnostic pathways, particularly in low-resource healthcare settings. Full article

Accelerating aridity and desertification driven by global climate change pose growing threats to dryland forest plantations, making it essential to understand transpiration dynamics across developmental stages for both forest-hydrology theory and the sustainable management of protective shelterbelts. This study compared transpiration characteristics, stomatal conductance (g_s), and water-regulation strategies between a 41-year-old mature stand and a 13-year-old young stand of Mongolian pine (Pinus sylvestris L. var. mongolica Litv.) on the southern margin of Horqin Sandy Land during the 2024 growing season, using thermal-dissipation sap-flow measurements combined with meteorological monitoring and water-potential sampling. Mean individual-tree daily transpiration in the mature stand (2.36 mm·d⁻¹) was approximately 2.6 times that of the young stand (0.90 mm·d⁻¹), yet the young stand showed a disproportionately stronger sap-flow response to small rainfall events. Sap flow in both stands was jointly driven by vapor pressure deficit (VPD) and photosynthetically active radiation, with a near-synchronous lag of ±10 min and tight canopy-atmosphere coupling (decoupling coefficients: 0.177 and 0.256, respectively), indicating transpiration was predominantly governed by stomatal regulation. Stomatal conductance declined with rising VPD in both stands, with a steeper decline in the mature stand. Water-potential analysis revealed pronounced anisohydric behavior in the mature stand (σ = 2.643, R² = 0.765, p < 0.01), and near-strict anisohydric regulation in the young stand (σ = 0.919, R² = 0.105, p > 0.05), indicating high tree-level hydraulic variability and precluding a definitive classification along the iso/anisohydric continuum for this developmental stage. Both g_s and transpiration increased with tree size, contradicting the hydraulic limitation hypothesis. These findings elucidate distinct water-use strategies between the young and mature Mongolian pine stands in this paired design and provide a physiological basis for stage-differentiated, precision water management of dryland shelterbelt plantations. Full article

Large Language Models (LLMs) have been rapidly evolving lately, resulting in the need for strong, explainable models to detect the difference between human-generated and machine-generated articles. Existing approaches which are mostly based on fine-tuned transformers suffer from several drawbacks such as rapid obsolescence, paraphrasing attacks, and lack of interpretability. To improve their ability to detect, this paper proposes a novel paradigm called Human vs. LLM Identification (HLI) which introduces a Retrieval-Augmented Generation (RAG)-inspired evidence-based detection strategy alongside a fine-tuned transformer classifier. Our core model, DeBERTa-Sentinel, is built on top of a fine-tuned Microsoft DeBERTa-v3-small model, which uses a disentangled attention mechanism to better capture subtle syntactic and stylistic deviations characteristic of AI-generated text. We evaluate our framework on a balanced dataset of 43,456 text samples, curated from the OpenGPTText corpus and covering AI-generated and human-authored content across diverse domains including news, education, and creative text. The experimental results show improved performance over the selected baselines, with our framework achieving an accuracy of 97.53%, precision of 95.89%, recall of 99.34%, and ROC-AUC of 99.53%. In addition, explainability is integrated into our framework through Local Interpretable Model-agnostic Explanations (LIME) analysis, providing token-level insight into classification decisions. This study establishes a benchmark for scalable, explainable AI text detection, with implications for academic integrity, content moderation, and combating misinformation. Full article

Accurately predicting transportation accident severity is critical for targeted risk governance, yet research based on accident investigation reports is often hampered by small sample sizes and skewed class distributions. This study develops a dual-track feature fusion and interpretable prediction framework to overcome these constraints. More than 1000 candidate documents were screened, yielding a reconstructed analytical sample of 157 eligible accident investigation reports for a three-class accident severity classification task. The methodology integrates HFACS-Lite vertical hierarchy and DEMATEL-Lite horizontal coupling to construct high-order fused features, employing the TabPFN foundation model as the backbone learner alongside SMOTENC and post hoc dual-threshold adjustments. Empirical results show that the final SMOTENC-enhanced dual-track TabPFN achieved an accuracy of 0.783 and a Macro-F1 of 0.717, while post hoc dual-threshold adjustment increased major-and-above recall to 0.6429. SHAP attribution indicates that high-consequence accidents are associated with joint patterns of micro-level operations, operating scenarios, and safety governance. The proposed framework supports association-based severity classification and risk screening under constrained data conditions. Full article

Municipal dog shelters are often grouped as outsourced facilities despite operator differences. We analyzed 33,875 dog admissions and 90 municipality-year observations from 2016 to 2025 across nine Korean municipalities, with three per operator category; operator type was fixed and nested within municipality. Among 32,838 known outcomes, live-release rates were 69.1%, 58.1%, and 40.0%, and euthanasia rates were 14.0%, 22.8%, and 42.5% in corporation-operated, veterinary hospital-operated, and individually operated shelters, respectively. The corporation live-release estimate ranged from 62.6% to 72.0% under alternative classifications of unresolved records. Small-sample cluster-robust comparisons were imprecise: the individually versus corporation-operated euthanasia odds ratio was 4.72 (95% confidence interval, 0.40–56.35), and every operator interval included 1.0. Contextual adjustment yielded odds ratios of 0.97 for both outcomes for veterinary hospital- versus corporation-operated shelters. Among 33,836 admissions with common 180-day follow-up, live-release rates were 59.9%, 53.0%, and 39.8%, and euthanasia rates were 9.1%, 16.7%, and 42.0%; annual odds ratios were 1.05 (0.93–1.19) and 0.90 (0.78–1.05), respectively. Results describe operator-linked municipal systems, not causal effects. Standardized follow-up, complete reporting, capacity monitoring, and larger prospective studies are needed. Full article

Increasing the accuracy of age-at-death estimation using two skeletal-characteristic stages can enhance confidence in biological identification using forensic science. Transition analysis and the inverse prediction method with a Bayesian approach was proposed in this study to estimate age from skeletal characteristics measured as binary variables. The Bayesian approach with adaptive rejection sampling was employed to derive the posterior distributions of the transition model parameters and the age classification threshold in order to reverse the age-at-death estimation from a binary predictor. The posterior odds ratio was proposed to assess the value of observed evidence for the age estimation. Subsequently, the efficiency of our proposed method, measured by the percentage of correct classification, was evaluated by Monte Carlo simulation and compared with the Maximum Likelihood Estimation with the inverse prediction method. The simulation results supported the advantages of our proposed method, especially when using small sample sizes. In an application involving chest X-ray images with two chest plate ossification stages, the results showed that our method could identify suitable features of the chest plate, providing good age-prediction performance with a high percentage of accuracy. Full article

Background/Objectives: Retinal imaging has considerable potential for monitoring Alzheimer’s disease (AD) neurodegeneration, as retinal ganglion cell dendritic atrophy within the inner plexiform layer (IPL) is an early event. We tested whether quantitative optical coherence tomography (OCT) speckle texture analysis combined with supervised machine learning could discriminate AD-related IPL alterations without exogenous contrast agents in a mouse model. Methods: Retinal explants from triple-transgenic AD mice (n = 7, aged 12 months) and C57BL/6 controls (n = 3, aged 15 months) were imaged ex vivo using a custom 1040 nm spectral-domain OCT system. Five grey-level co-occurrence matrix (GLCM) features were extracted from IPL volumes of interest (VOIs) and classified using a linear support vector machine (SVM). Results: AD and control IPL textures formed two completely separable clusters in a two-dimensional feature space defined by contrast and entropy (0°), achieving 100% VOI-level classification accuracy (95% CI: 96.4–100%). However, given the small sample size, VOI-level rather than animal-level validation, lack of histological confirmation, non-interleaved image acquisition, and differences in age/strain between groups, these results represent exploratory dataset separability rather than a validated diagnostic test. Conclusions: These findings demonstrate the feasibility of the ligand-free, texture-based OCT discrimination of IPL alterations, indicating a strong underlying optical signal. Adequately powered, in vivo longitudinal studies with matched controls, interleaved acquisition, animal-level cross-validation, and histological validation are required before any clinical translation. Full article

Machine learning and statistical classification methods are widely applied to microbiome data for diagnostic, prognostic, and phenotypic insights. However, the complex, multivariate nature of microbiome communities makes it difficult to assess the relative performance of these methods. Most comparisons rely on a small number of published datasets, without considering their underlying ecological properties or how these properties may, in turn, influence classification performance. We introduced a coenocline-based simulation framework to generate synthetic microbiome datasets that incorporate realistic ecological variation arising from species’ responses to host-associated gradients such as disease severity. To evaluate the ecological fidelity of these simulations, we compared synthetic datasets to five widely used real-world microbiome datasets: Cirrhosis, Colorectal Cancer (CRC), Type 2 Diabetes (Chinese and Women cohorts), and the Human Microbiome Project (HMP). Comparisons across α-diversity (species richness), β-diversity (species composition and turnover), and abundance distributions demonstrated that coenocline simulations closely recapitulate the key ecological structures of empirical data. Synthetic datasets exhibited similar richness and abundance patterns to disease-associated microbiomes, with realistic distributions of few dominant and many rare taxa. Moreover, community composition analyses (Bray–Curtis index) revealed that the simulated datasets captured natural levels of compositional dissimilarity among samples, spanning the same variability range observed in real data. When compared against 100 independently simulated datasets, the coenocline model consistently reproduced empirical ranges of species diversity, relative abundance, and between-group compositional differences (ANOSIM-R values), confirming the model’s robustness and reproducibility. This coenocline-based simulation framework provides a novel, flexible, and ecologically grounded approach for generating synthetic microbiome data with controlled complexity. By reproducing realistic ecological gradients and community structures, the framework supplies the controlled test beds needed for systematic future benchmarking of machine learning and statistical classification methods across diverse and biologically meaningful scenarios. In doing so, it will help bridge the gap between ecological realism and computational modeling, thereby supporting more reliable and generalizable inference from microbiome data. Full article

A post-flight analysis of unmanned aerial vehicle (UAV) imagery has the potential to result in a delay in the inspection of source water. This delay can occur when visible debris or changes in the water surface necessitate a prompt response. The present study does not evaluate in-flight operation; rather, it presents a bench-level feasibility assessment of two deployment tasks—broad two-class screening and close-range debris classification—using lightweight YOLO detectors on an edge-AI camera in a host-fed configuration that approximates the timing constraints of a future UAV workflow. The YOLOv8, YOLO11, and YOLO26 models were lightweighted through structural pruning (YOLOv8) or architecture scaling (YOLO11 and YOLO26). These models were then refined through a process of fine-tuning, exported to the camera, and evaluated in terms of several metrics. The metrics encompassed training-environment accuracy, the accuracy of device-returned outputs, round-trip latency, and snapshot-based operating-load estimates. The dataset under consideration is extensive, comprising 4813 training images and 575 validation images, accompanied by 13,051 and 1615 annotations, respectively. The depth-pruned YOLOv8s variant demonstrated a significant reduction in mean round-trip latency, from 426.87 milliseconds to 231.58 milliseconds (45.75%), while the mAP@0.5 metric exhibited a decrease from 0.7018 to 0.6650, and the mAP@0.5:0.95 metric demonstrated a decline from 0.5433 to 0.5290. A class-level analysis reveals that aggregate accuracy is primarily influenced by the weaker floating-debris class, whose AP@0.5 ranges from 0.29 to 0.46, in contrast to the 0.82 to 0.94 range observed for pond/reservoir. In comparison to a matched baseline that was trained for an equivalent number of epochs with the sampler disabled, debris-biased sampling contributes 1.5 ± 0.6 mAP@0.5 points for YOLO11 and 3.6 ± 0.2 points for YOLO26 across three seed-matched pairs. The primary effect of this method is to increase floating-debris recall by 4.7–5.9 percentage points, with a concomitant small reduction in precision. The latency reduction increased the broad-inspection rate by 1.85×, provided approximately 195 milliseconds of idle margin within a 1-hertz cycle, and increased the paired far/near rate by 1.59× with two models resident on the camera. Three-seed repetitions of compact-model fine-tuning yielded 0.6717 ± 0.0033 and 0.6290 ± 0.0028 mAP@0.5. These results express detector compression in terms of operational monitoring capacity rather than model-size reduction alone, while also showing that compression by itself does not resolve the weak-class limitation that governs source-water inspection accuracy. Full article

To explore the significant systematic deviations of FENSAP-ICE numerical simulations under supercooled large droplet (SLD) conditions, a ridge regression correction method that integrates numerical priors and domain-knowledge-aided features for ice shape geometric parameters is presented in this manuscript. The FENSAP-ICE predictions of eight geometric ice shape parameters are incorporated as numerical priors into the machine learning model, transforming the learning objective from “predicting from scratch” to “correcting systematic bias.” Six engineering auxiliary features are constructed based on SLD icing physics to provide physically meaningful adjustable dimensions for small-sample modeling. A two-stage model combining Logistic Regression classification and Ridge Regression is designed for zero-ice cases on the lower-surface icing limit. Evaluated via Leave-One-Out Cross-Validation on 29 sets of NACA0012 airfoil SLD icing wind tunnel experimental data, the improved system reduces the sMAPE of total ice area from 79.47% to 34.65%, lower-surface ice horn angle from 105.19% to 28.08%, upper-surface icing limit from 61.75% to 35.48%, and average ice thickness from 42.12% to 20.89%, all compared with FENSAP-ICE predictions. Ablation experiments further reveal that the introduction of the numerical prior alone reduces prediction error by approximately 10 percentage points, serving as the primary performance driver. The proposed method features low computational cost and strong physical consistency, providing a practical bias-correction framework for SLD ice shape prediction under small-sample conditions. Furthermore, to address the potential optimistic bias arising from small-sample cross-validation, nested cross-validation together with multiple linear baseline models are additionally employed to verify the robustness and relative competitiveness of the proposed correction method. Full article

Background: Accurate identification and classification of white blood cell (WBC) subtypes in peripheral blood smears (PBS) is essential for the diagnosis and monitoring of hematological malignancies, including leukemia. Conventional manual microscopy, although clinically established, is labor-intensive and subject to inter- and intra-observer variability. Deep learning-based object detection offers a route to automation, yet most prior studies are limited by small datasets, restricted cell taxonomies, or single-microscope acquisition. This study evaluates a YOLOv11-large (YOLOv11L) detector for simultaneous localization and classification of 13 leukemia-relevant WBC subtypes plus an artifact class (14 classes total), trained on the large-scale, multi-domain, open-source LeukemiaAttri dataset. Methods: From the LeukemiaAttri dataset, 18,664 annotated images (67,347 objects) acquired at 40× and 100× magnification were partitioned by stratified sampling into training (70%), validation (15%), and test (15%) sets. The training set was expanded to 65,785 images through extensive geometric, photometric, and AugMix augmentation. A YOLOv11L model pretrained on MS COCO was fine-tuned for 250 epochs (640 × 640 input) on a single NVIDIA H200 SXM GPU, using an auto-selected optimizer (momentum 0.9; weight decay 5 × 10⁻⁴), automatic mixed precision (AMP), and mosaic augmentation for the first 240 epochs. Results: On an internal held-out test set, the model achieved an mAP50 of 93.9%, mAP50-95 of 77.9%, precision of 94.1%, recall of 88.8%, and an F1 score of 0.913, with similar performance in the validation and test sets. Class-wise average precision (AP) ranged from 89.3% (monocyte) to 98.2% (monoblast), confirming consistent detection across morphologically diverse subtypes. Conclusions: The YOLOv11L detector achieved high performance across all 14 categories on the internal test set, with metrics exceeding those previously reported for subset-specific baselines. These findings support further evaluation of the model as a decision-support tool for peripheral blood smear analysis. External validation is required to determine its clinical utility and generalizability. Full article

This paper develops a unified asymptotic theory for inverse-probability-weighted conditional U-statistics of arbitrary fixed order in the presence of missing-at-random responses and infinite-dimensional functional covariates. The target is a conditional higher-order functional generated by a measurable response kernel and evaluated locally on a separable Banach space. Localization is formulated through delta sequences, providing a common framework for kernel, partition, regressogram, orthogonal series, and related smoothing procedures without recourse to finite-dimensional density arguments. For bounded kernels, we establish uniform almost-complete convergence over pseudo-compact functional domains and obtain a sharp decomposition into deterministic localization bias and stochastic fluctuation. The latter is governed by the localized-kernel variance, the envelope of the delta sequence, the metric complexity of the indexing domain, and the small-ball concentration of the functional covariate. Unbounded kernels are treated under explicit weighted moment, truncation, and summability conditions. The feasible theory quantifies the additional perturbation induced by estimating the propensity score and identifies conditions under which this first-stage uncertainty is asymptotically negligible. Pointwise distributional theory is derived through a denominator linearization combined with the Hoeffding decomposition of the centered localized kernel. The Gaussian limit is driven by the first projection, while the higher-order canonical components are shown to be negligible under explicit local-mass, moment, and noncancellation assumptions. This yields oracle-equivalent feasible inference, a consistent first-projection variance estimator, and asymptotically valid studentized confidence intervals. A finite-grid adaptive comparison principle is also developed for data-driven resolution selection. The scope of the theory is illustrated through conditional rank functionals, discrimination with incomplete labels, metric-learning criteria, and functional prediction. Synthetic and semi-synthetic studies based on functional classification, phoneme log-periodograms, and growth trajectories document the finite-sample interaction between covariate-dependent label observation, local information loss, propensity estimation, and inverse-weighting variance. Full article

Background: Metabolomics data is inherently characterized by high dimensionality and small sample size. Existing multi-objective particle swarm optimization (MOPSO)-based feature selection algorithms suffer from two critical limitations: they generally neglect the stability of selected feature subsets and exhibit poor adaptability when processing high-dimensional data, which restricts their practical application in biomedical research. Methods: To address these challenges, this paper proposes a novel MPR-MOPSO-ASFS algorithm. Specifically, we first construct a stability-driven bi-objective optimization model. Then, we integrate a Maximum Pattern Recognition (MPR) filter to achieve rapid dimensionality reduction of high-dimensional features. Finally, an improved Adaptive Sparsity Feature Selection mechanism is designed to simultaneously optimize the compactness, classification accuracy, and stability of the selected feature subsets. Results: Extensive experiments were conducted on three metabolomics datasets and five public high-dimensional small-sample datasets. The results demonstrate that the proposed MPR-MOPSO-ASFS algorithm outperforms mainstream algorithms including CMDPSOFS and MOEAD-FS in core evaluation metrics such as Pareto front quality and classification accuracy. Additionally, we clarify the optimal configuration of the algorithm’s core parameters and verify the collaborative effectiveness of its key design components. Conclusions: This study makes the first attempt to incorporate the harmonic mean of accuracy and stability into the multi-objective optimization framework. The two-stage combination of the proposed MPR strategy and MOPSO breaks through the performance bottleneck of traditional algorithms and significantly enhances their adaptability and robustness to high-dimensional small-sample data. The proposed algorithm provides an efficient new solution for feature selection in high-dimensional biomedical data and offers a technical reference for the application of swarm intelligence optimization algorithms in the biomedical field. Full article

The quality and safety supervision of agricultural products at the grassroots level has long faced the triple superposition dilemma of small-sample sampling, multi-source evidence conflict, and risk chain evolution. Although existing data-driven models have considerable accuracy, they are difficult to leverage for intervention decisions, and the simple serial connection of traditional Bayesian networks and evidence theory cannot respond to dynamic scenarios. Aiming at this research gap, this paper constructs a dynamic risk assessment model, CIBE-DR, that deeply couples Bayesian networks with evidential reasoning. It contains three core innovations. First, the structure learning method of the causally identifiable Bayesian network embeds a graded do-calculus identifiability score covering both back-door and front-door criteria into the BDeu scoring function and combines this reward with an expert-prior divergence penalty that breaks Markov equivalence so as to realize the transition from relevance modeling to intervention decision modeling. Second, the conflict-aware adaptive evidence synthesis rule orthogonally decomposes multi-source conflict into an epistemic component and an ontological component, which are modeled respectively by Tsallis belief entropy and abductive inference over a discrete twenty-seven-point heterogeneity hypothesis space and are then fused under a reparameterized Dempster–Yager interpolation in which the two endpoints recover the two named rules under a single consistent interpretation. Third, the bidirectional closed-loop coupling mechanism between BN and ER realizes the mutual calibration between the conditional probability table and the evidence credibility prior under a Lyapunov monotone descent argument with the explicit Lipschitz bound $L_{\theta }$ ≤ 0.028 < 1, endowing the model with time-varying self-correction ability. Based on experiments on 156,847 sampling samples from counties and townships in East China, Central China, and Southwest China from 2021 to 2024, the proposed method achieved the best value in six of the seven evaluation indicators, with a minority recall of 0.864 ± 0.014, an intervention effect estimation error of 0.063 ± 0.005, and a dynamic response delay of 2.8 ± 0.3 days, significantly ahead of eleven mainstream baselines under the McNemar test on classification ($p$ < 0.001) and the Wilcoxon signed-rank test on intervention-effect estimation ($p$ < 0.001). The only indicator on which CIBE-DR does not lead is overall accuracy, which is 0.002 lower than that of Transformer; this difference does not reach statistical significance under the McNemar test ($p$ = 0.32) and does not weaken the value of grassroots supervision in the strong-imbalance scenario where the positive rate is only 1.04%. The robustness advantage of the model is particularly prominent in the scenarios of sparse data, adversarial perturbation, and prior-graph incompleteness, and the intervention-effect estimates were additionally validated against two post-2022 policy interventions with absolute deviations of 1.4 and 1.2 percentage points respectively. These results verify the product gain and grassroots deployability of the three mechanisms. Full article

Multimodal classification often suffers from recognition reliability that is asymmetric across data sources and classes, and its evaluation is frequently complicated by information leakage from overlapping sampling windows. This paper proposes a class-wise-optimized reliability fusion model (CORF), using the classification of multimodal driver responses under four controlled weather conditions as a validation case. Electroencephalogram, electrocardiogram, and vehicle signals were recorded for 30 participants, and two leakage-free protocols were adopted: leave-one-subject-out (LOSO) cross-validation and a purged temporal-block cross-validation, with all preprocessing, probability calibration, and weight estimation refitted inside every fold. Under LOSO, CORF achieved an accuracy of 0.356 (chance = 0.25) and a 0.630 macro-average area under the curve (AUC), whereas the originally used random overlapping-window split inflated accuracy to 0.92; the fused adverse-class probability discriminated adverse- from clear-weather windows with an AUC of 0.73. The fusion retains a symmetric reliability-weighting structure across classes, and its moderate symmetry-breaking difficulty emphasis significantly improved the most challenging adverse-weather class over equal-weight fusion (snow F1 +9.8 percentage points, Holm-corrected p < 0.001) at a small, statistically non-significant overall accuracy cost. CORF therefore provides a probability-calibrated, interpretable mechanism for controlling class-specific performance tradeoffs, highlighting the necessity of leakage-free validation in multimodal physiological classification. Full article