Search Results (3,505)

Objectives: Emotional tears are generated in a distinct neurophysiological context from reflex tears, but their metabolic composition remains poorly understood. Methods: This exploratory paired targeted-metabolomics study compared emotional and reflex tears collected from 22 healthy volunteers using a 600-multiple-reaction-monitoring platform. Among 412 detected metabolites, 344 were retained after data preprocessing. Paired statistical analysis prioritized 23 candidate metabolites based on the combined criteria of unadjusted p-value, fold change, and consistency of within-subject change. Results: Seven candidates were lower, and 16 were higher in emotional tears. Salicylic acid was retained in the descriptive candidate set but excluded from the primary machine-learning analysis because a contribution from the reflex-tear induction procedure could not be ruled out. Among the remaining 22 candidates, 4-hydroxy-3-methylbenzoic acid, vanillic acid, cytidine-5′-monophosphate, and hydroxyphenyllactic acid were consistently ranked among the leading features. A fixed four-metabolite combination achieved an area under the receiver operating characteristic curve of 0.864 (95% CI, 0.756–0.957) under ordinary leave-one-subject-out cross-validation. When candidate screening, feature selection, and model fitting were repeated within each training fold, the best nested pipeline achieved an area under the curve of 0.725 (95% CI, 0.603–0.843). Pathway mapping further linked the candidate metabolites to histidine, tyrosine, fatty-acid, ether-lipid, and ubiquinone-related metabolism. Conclusions: These findings demonstrate measurable within-subject metabolic differences between emotional and reflex tears and identify a focused set of candidate metabolites for future validation. Because no individual metabolite remained significant after false discovery rate correction and no independent validation cohort was available, the candidate signals and discrimination models should be confirmed in larger, independently collected cohorts. Full article

Most existing driver behavior classification technologies have focused on highways and other primary road infrastructures, despite secondary roads accounting for a disproportionately large number of traffic fatalities worldwide. Compared with highways, secondary roads present greater variability in road geometry, infrastructure quality, and traffic interactions, making driver behavior recognition considerably more challenging. This paper investigates the classification of driver behavior on secondary roads using machine learning techniques. Naturalistic driving data obtained from the publicly available UAH-DriveSet dataset were analyzed using two complementary feature groups describing lane detection and traffic status. Four supervised machine learning algorithms, namely, Logistic Regression (LR), gradient boosting (GB), Random Forest (RF), and Artificial Neural Networks (ANNs), were evaluated to classify driving behavior into three categories: Normal, Aggressive, and Drowsy. The extracted features were first analyzed through statistical profiling and exploratory feature analysis before training and evaluating the classification models. The experimental results show that gradient boosting consistently achieved the highest performance for both feature groups, attaining an overall classification accuracy of approximately 67% while providing balanced precision, recall, and F1-scores across all behavioral classes. Logistic regression and random forest produced competitive but lower performance, whereas the Artificial Neural Network yielded the lowest classification accuracy. The obtained results demonstrate the effectiveness of ensemble learning methods for driver behavior recognition under secondary-road conditions and highlight their potential for integration into intelligent driver monitoring and Advanced Driver Assistance Systems (ADASs). By enabling earlier identification of aggressive and drowsy driving behaviors on secondary roads, the proposed approach could support timely driver warnings and safety interventions, potentially reducing accident risk. Furthermore, the findings provide a benchmark for future machine learning models designed for real-world secondary-road environments, where driving conditions are more variable and challenging than on highways. Full article

Machine learning (ML) algorithms can be used to extract clinically meaningful information from movement data captured by inertial measurement units (IMUs), but many human activity recognition (HAR) pipelines are developed on large laboratory datasets that may not reflect small, heterogeneous, real-world samples. The purpose of this study is to systematically compare the accuracy of multiple ML models, feature sets (both simple and expanded), class balancing strategies, null and transition period handling techniques, and sensor configurations for recognizing a set of four everyday activities extracted from IMU time series data from an age-diverse population. Six ML classifiers were trained and tested: multilayer perceptron, random forest, k-nearest neighbors, logistic regressor, CatBoost, and gaussian naive bayes. These approaches were used in a pipeline with differing sampling techniques including the synthetic minority oversampling technique or random undersampling, and feature handling steps including principal component analysis or a Select-From-Model metatransformer. Additionally, two deep learning methods, DeepConvLSTM and ResGCNN, were trained and tested. Accuracy, precision, recall, and area under the receiver operating characteristic curve were compared to a dummy classifier as a benchmark approximation to chance performance. All pipelines performed better than the dummy classifier, with model accuracy ranging between 0.427 and 0.644. This study demonstrated the ability of several ML algorithms to properly recognize a set of functional activities using limited IMU data from both children and adults. Full article

Background/Objectives: Nonsurgical treatment for pancreatolithiasis is widely performed. However, treatment success remains difficult to predict before treatment initiation, complicating the selection of an appropriate treatment strategy. This study aimed to predict pancreatic stone clearance after nonsurgical treatment for pancreatolithiasis associated with chronic pancreatitis by integrating pretreatment computed tomography (CT) images and clinical information using deep learning and machine learning models. Methods: Of 195 patients with pancreatolithiasis associated with chronic pancreatitis who underwent nonsurgical treatment, including extracorporeal shock wave lithotripsy, at our institution between 1992 and 2024, only 91 (47%) had extractable pretreatment noncontrast abdominal CT images and were included in the AI analysis. Multiple deep learning models (VGG16/19, InceptionV3, ResNet50, DenseNet121/169/201, Vision Transformer, and Swin Transformer) were trained using CT images, and their predictive performance was compared. Imaging-derived and clinical predictors selected using only the training data in each patient-level cross-validation fold were combined and used as inputs for conventional machine learning models, including random forest, support vector machine, naïve Bayes, neural network, and gradient boosting. Results: Successful pancreatic stone clearance was achieved in 54 of 91 patients (59%). Compared with the 104 patients without extractable CT data, the analyzed cohort had a higher proportion of asymptomatic pancreatolithiasis (43% vs. 15%) and a markedly lower pancreatic stone clearance rate (59% vs. 88%), indicating potential selection bias. Asymptomatic pancreatolithiasis and a pancreatic stone size of ≥15 mm, defined using a data-derived exploratory cutoff, were significantly associated with unsuccessful stone clearance. Among the deep learning models, ResNet50 achieved the highest performance (area under the receiver operating characteristic curve [AUC], 0.718), followed by Vision Transformer (Large model, 16 × 16 patches) (AUC, 0.700). When image-derived features were combined with clinical features, the neural network achieved the best performance, with a mean AUC of 0.757, a median sensitivity of 0.568, a median specificity of 0.704, and a median accuracy of 0.659. Conclusions: A neural network integrating CT-derived image features with clinical information showed moderate internal predictive performance for pancreatic stone clearance. Because this was a single-center retrospective study without external validation, the present model should be regarded as a preliminary predictive model requiring validation in independent cohorts before clinical application. Full article

Background/Objectives: Differentiating high-grade glioma recurrence from treatment-related changes remains challenging on conventional MRI. This study evaluated non-contrast arterial spin labeling (ASL) perfusion MRI for this distinction and compared its performance with dynamic susceptibility contrast (DSC) perfusion MRI. Methods: Postoperative follow-up MRI examinations obtained between November 2019 and May 2021 were retrospectively reviewed. The cohort included 63 MRI examinations from 36 adults treated for high-grade glioma. ASL, routine MRI, and DSC images were independently assessed by two neuroradiologists. Final diagnosis was based on histopathology or longitudinal clinical and imaging follow-up. Reader agreement, diagnostic performance, and an exploratory patient-level grouped machine learning analysis using ASL-only, DSC-only, and combined ASL–DSC features were evaluated. Results: ASL- and DSC-derived perfusion parameters were significantly higher in tumor recurrence than in treatment-related changes (all p < 0.001). Both techniques showed high diagnostic performance; DSC achieved the highest accuracy, whereas ASL provided high specificity across readers. Inter-reader agreement ranged from substantial to almost perfect. In grouped cross-validation, ASL-only, DSC-only, and combined models achieved mean AUCs of 0.946, 0.997, and 0.997, respectively. Permutation testing confirmed that combined-model performance exceeded chance expectations (empirical p = 0.002). Conclusions: Non-contrast ASL perfusion showed diagnostic performance comparable to DSC for differentiating high-grade glioma recurrence from treatment effects. ASL may provide a reliable non-invasive alternative for longitudinal surveillance, particularly when gadolinium administration is undesirable or contraindicated. Full article

Background: Predicting recurrence after liver transplantation (LT) for hepatocellular carcinoma (HCC) remains important for post-transplant risk stratification and surveillance planning. The Milan criteria discriminate only moderately and some machine-learning re-analyses report overly optimistic results because of information leakage. Aim: The current study aimed to re-evaluate a previously published transplant cohort under a leakage-free survival-analysis framework and to benchmark post-transplant, explant-informed survival learners against the Milan criteria as a fixed pre-transplant reference. We hypothesised moderate rather than near-perfect discrimination, similar performance across learners of differing complexity, and better discrimination than the Milan criteria. Methods: This secondary analysis included 356 patients with HCC who underwent LT. The primary endpoint was recurrence-free survival, analysed from the observed event indicator and follow-up time rather than from a derived risk label. Seven survival learners were benchmarked with repeated nested cross-validation, using three repeats of a five-fold outer loop with a three-fold inner tuning loop. All data-dependent preprocessing, including robust multivariable outlier handling and imputation, was fitted within training folds only. Performance was assessed by the concordance indices of Harrell and Uno, the time-dependent area under the curve, the integrated Brier score, calibration, decision-curve analysis and descriptive competing-risk assessment. Results: Recurrence developed in 183 of the 356 patients over a median follow-up of 52 months. Discrimination was moderate rather than near-perfect and similar across learners; the random survival forest ranked highest and the Elastic-Net Cox model performed comparably. All learners showed higher descriptive concordance than the Milan criteria, and dependency-corrected comparisons supported higher concordance for the full-feature Cox model than for the Milan criteria, whereas the random survival forest and Cox did not differ materially. Out-of-fold calibration of the Elastic-Net Cox model at 36 months was acceptable, decision-curve analysis indicated positive net benefit across clinically relevant thresholds, and tumour size and alpha-fetoprotein were the leading contributors to prediction. Findings were stable in ablation and threshold-sensitivity analyses. Conclusions: Leakage-free survival modelling gave moderate but internally validated prediction of post-transplant recurrence and higher concordance than the Milan criteria in this cohort, supporting the stated hypotheses. Careful study design may matter more than architectural complexity in this setting, and leakage-free survival analysis is a practical standard for prognostic modelling in transplant oncology. Full article

The construction sector faces a critical need to minimize its carbon footprint, which is currently stimulating the development of geopolymer concrete using recycled coarse aggregates as an eco-friendly material compared with Portland cement. Accurate prediction of the compressive strength of this eco-efficient concrete is complex, however, as a result of the complex, non-linear interactions between many of the mix-design and curing parameters. Although modern scientific literature and engineering practices have increasingly adopted machine learning (ML) for concrete strength prediction, a significant scientific gap remains. Most existing studies rely on “black-box” models that lack sufficient interpretability and frequently overlook the severe risk of data leakage during validation, limiting their practical engineering application. To address this gap, this study proposes a robust, data-leakage-aware framework driven by a rigorous nested GroupKFold cross-validation strategy. By grouping concrete samples by their unique Mix_ID, this approach ensures genuine generalization to entirely unseen mixtures. Within this reliable validation scheme, the CatBoost algorithm is utilized for compressive-strength prediction, with the Dung Beetle Optimizer (DBO) serving as an effective tool for hyperparameter tuning. The evaluation results across multiple random seeds show that the DBO–CatBoost model significantly outperforms the default CatBoost, rigorously tuned baseline models (Support Vector Regression and Random Forest), and a comparative metaheuristic benchmark (PSO–CatBoost). It achieves the most stable distribution of errors and excellent predictive accuracy (Test ${\mathrm{R}}^2=0.9995\pm 0.0002$, RMSE = $0.3828\pm 0.0909$). In addition, the model predictions were demystified using the methods of SHapley Additive exPlanations (SHAP) and partial dependence plots (PDPs). The interpretability analysis revealed strong statistical associations, showing that Curing Time and Coarse Aggregate are the most prominent predictive features and the strongest pairwise interaction between each other; the NaOH molar concentration is the most important second-level influence on optimization of strength. Overall, the framework provides a robust data-driven screening tool that can assist in preliminary mix-design evaluation. By reducing the reliance on extensive empirical “trial and error” approaches, this predictive model supports more efficient material usage and facilitates preliminary optimization of low-carbon concrete formulations. Theoretically, this study advances the fundamental science of geopolymer materials by explicitly quantifying the complex, non-linear interactions between alkaline activators, curing conditions, and recycled aggregates. This provides a robust data-driven theoretical foundation for designing and optimizing next-generation eco-friendly concrete products and structures. Full article

Background: Research in behavioral genetics has demonstrated that genetic factors significantly contribute to individual differences in behavior, while environmental exposures shape gene expression through epigenetic mechanisms. This interaction is also relevant to the development of antisocial behavior and psychopathic traits. One of the first evidence of gene–environment interaction was the association between low-activity variants of the MAOA gene, childhood maltreatment, and increased risk of antisocial behavior [¹]. Similarly, our research in incarcerated populations showed that adverse paternal parenting is associated with higher levels of psychopathy and the HTR1B rs13212041 TT genotype appears to modulate the individual susceptibility to negative experiences [²]. Single genetic variants, however, exert only modest effects and current evidence supports a polygenic model in which multiple genetic factors interact with environmental adversity to influence neurodevelopment and behavioral outcomes. Using a genome-wide/endophenotype informed analysis, for example, we identified novel gene–environment interactions as risk factors for psychopathy, involving three independent genetic loci in interaction with paternal maltreatment, which were previously associated with disruptive behavior, temperament, and neuroticism [³]. More recently, we also evaluated whether machine-learning models, integrating behavioral, environmental, and genetic variables, could be helpful to predict psychopathic traits. Methods: We compared logistic regression, random forest, support vector machine, XGBoost, and multilayer perceptron. Results: Support vector machine showed the highest accuracy for predicting Psychopathy Check List-Revised (PCL-R) Factor 2 (antisocial lifestyle). Feature-importance analyses identified impulsivity (BIS-11), empathy (IRI), childhood maltreatment (MOPS), and 12 SNPs as the most informative predictors. Notably, removing genetic variables or MOPS scores substantially reduced the model accuracy, indicating that both genetic and environmental information meaningfully contributed to prediction of antisocial behavior. Conclusions: These findings confirm that genetic influences are neither deterministic nor sufficient to explain criminal behavior but may contribute to interindividual differences in vulnerability, particularly through their interaction with environmental and psychosocial factors. In forensic psychiatry, the integration of genetic and environmental information into behavioral assessment may provide additional objective correlates that complement, rather than replace, traditional clinical and psychosocial evaluations. Such an integrated approach could potentially contribute to a more comprehensive understanding of individual vulnerability and behavioral trajectories. However, the use of genetic information in assessments of criminal responsibility should be approached with caution and proven expertise, given the complex, multifactorial nature of antisocial and criminal behavior. Full article

This paper presents a comparative study of two approaches for solving second-order ordinary differential equations arising from the membrane theory of shells of revolution. The considered equations originate from the rotational symmetry of shell structures, which enables the reduction of the governing partial differential equations to a sequence of ordinary differential equations corresponding to individual circumferential harmonics. The study compares the classical Differential Transform Method (DTM) with Physics-Informed Neural Networks (PINNs). Both initial value and boundary value problems are investigated, including benchmark examples with known analytical solutions and a systematic analysis of the influence of PINN architecture on the solution accuracy. For the PINN approach, the effects of the number of collocation points, hidden layers, and neurons per layer on the approximation error and training time are examined. The results demonstrate that DTM provides an efficient framework for constructing analytical solutions of initial value problems with minimal computational cost. However, its application to boundary value problems requires the introduction of additional auxiliary parameters and the solution of supplementary nonlinear equations, considerably increasing the analytical complexity of the procedure. In contrast, PINNs achieve high accuracy for both initial and boundary value problems while naturally incorporating boundary conditions through the loss function. The presented results demonstrate how the exploitation of geometric symmetry, combined with modern scientific machine learning techniques, provides an effective computational framework for solving differential equations arising in shell mechanics. Full article

Recent progress in intelligent, adaptive, and security-aware Software-Defined Wireless Sensor Networks (SDWSNs) is driven by the integration of Machine Learning (ML) with Software-Defined Networking (SDN) and Wireless Sensor Networks (WSNs). This systematic survey analyzes 46 peer-reviewed articles published between 2024 and 2025, providing a problem-oriented synthesis of ML-SDWSN research. Emphasizing security, routing, and performance optimization, with a particular focus on deployment architectures, the survey identifies three major trends: increased adoption of ensemble and Reinforcement Learning (RL) methods for security and adaptive control; broader implementation of edge-based ML to minimize inference latency; and greater emphasis on privacy-preserving techniques, especially Federated Learning (FL). The survey presents a structured taxonomy encompassing seven thematic areas: Distributed Denial-of-Service (DDoS) mitigation, Intrusion Detection Systems (IDSs), routing optimization, Quality of Service (QoS) management, privacy preservation, data integrity, and network-efficiency optimization. Findings are synthesized from over 120 experimental configurations reported in the literature. Due to substantial differences among the reviewed studies in terms of datasets, network topologies, hardware platforms, measurement definitions, and validation methodologies, the reported values are presented as descriptive cross-study aggregates rather than direct comparative benchmarks or formal effect-size estimates. Within these constraints, the survey identifies recurring trade-offs among accuracy, latency, scalability, and privacy. It provides evidence-based design considerations for researchers and practitioners. The survey also highlights eight critical research gaps, including limited multi-dataset validation, a lack of real-world deployments, insufficient scalability analysis, and the need for rigorous evaluation of RL-based SDWSN control. Full article

Accurate forecasting of electricity prices is essential for efficient operation and decision-making in deregulated power markets, particularly in the Indian electricity market, characterized by high volatility and dynamic pricing. This study presents a comparative analysis of statistical, machine learning, and deep learning methods for electricity price prediction in the Indian market, with a focus on feature dimensionality. The evaluated models include autoregressive-integrated-moving average, seasonal autoregressive-integrated-moving average, seasonal autoregressive-integrated-moving average with exogenous variables, categorical boosting, random forest, long short-term memory, bidirectional long short-term memory, and a hybrid convolutional neural network-bidirectional long short-term memory model. Historical data available on the Indian Energy Exchange webpage are deployed in this study. The models are analyzed for varying input vector sizes with features that include date, type of day, day of the week, previous day, month, and year market prices. The results indicate improved predictive performance of all model while increasing the input feature dimensionality from five to seven. The results indicate that while increasing the feature size from five to seven increases the prediction accuracy, the gains become marginal beyond seven, emphasizing the importance of feature relevance over feature quantity. From a theoretical perspective, the study highlights the dominance of short-term temporal dependencies in MCP prediction and provides empirical evidence for the point of diminishing returns in feature expansion. From a practical standpoint, the results endorse the choice of computationally efficient and interpretable models for real-world deployment. Full article

Gravity-matching navigation is one of the important means for the covert navigation of underwater vehicles. The production and application of gravity reference maps as core key technologies have a very significant impact on the accuracy of underwater navigation. Firstly, this paper adopts the factor analysis method to obtain the comprehensive results of nine characteristic parameters such as the standard deviation and roughness of the gravity reference map by setting a range sliding window. Secondly, the TERCOM algorithm is introduced to conduct simulation verification calculations within the sliding window. After comparing and verifying with the comprehensive results of the factor analysis characteristic parameters, the limitations of statistical methods in the evaluation of the adaptability of gravity reference maps are analyzed. Thirdly, intelligent processing methods such as the learning vector quantization neural network algorithm and the extreme learning machine are proposed. The characteristic parameters of some sliding window gravity reference maps and the simulation verification results of the TERCOM algorithm are used as training samples to predict the adaptability evaluation effect of underwater gravity navigation for other sliding windows. The results show that the prediction results are generally in good agreement with the simulation verification results of the TERCOM algorithm. Compared with the learning vector quantization neural network algorithm, the extreme learning machine algorithm exhibits superior performance in terms of classification accuracy and computational efficiency. Full article

Background/Objectives: Early identification of complicated appendicitis in children remains challenging. We developed and internally validated laboratory-based machine-learning models for severity stratification using age and routine admission laboratory data. Methods: This retrospective study included 628 children with surgically confirmed appendicitis treated between 2020 and 2024. Complicated appendicitis was defined by operative or pathological evidence of perforation, gangrene, abscess, phlegmon, diffuse peritonitis, or comparable advanced inflammation. Fifteen candidate predictors were evaluated using five prespecified models. Models were tuned in the training set and evaluated once on an isolated test set. Pairwise DeLong comparisons, decision curve analysis, SHAP, and permutation importance were performed. Results: Complicated appendicitis occurred in 93 patients (14.8%). The prespecified primary CatBoost model achieved a ROC AUC of 0.867, a precision-recall AUC of 0.677, a sensitivity of 0.750, a specificity of 0.863, a positive predictive value of 0.488, and an F1-score of 0.592. Formal comparisons did not demonstrate statistically significant AUC superiority over the other algorithms after Holm correction. Exploratory decision curve analysis showed a greater net benefit than treat-all and treat-none strategies across threshold probabilities of 0.06–0.35. ESR, age, CRP, and CRP-derived indices were the most influential model features. Conclusions: Routine laboratory data may provide adjunctive information for severity stratification, but the modest event count, limited positive predictive value, and absence of external validation preclude stand-alone clinical use. Full article

Operator diagnosis level in a main control room (MCR) of Nuclear Power Plants (NPPs) is a core factor in preventing human errors and ensuring the safe operation of NPPs. Due to the high uncertainty of human behaviors and the scarcity of relevant data, traditional analysis methods mainly rely on empirical judgment, which suffer from insufficient dynamics and poor engineering adaptability. To address the issues, this paper conducts a study on an AI prediction model for operator diagnosis level in a MCR of NPPs based on the SACADA database and machine learning technology. The model adopts a probabilistic neural network (PNN) as the main architecture, and proposes a hybrid method of network search considering density distribution combined with K-fold cross-validation, which breaks the traditional mode of a single smoothing factor adapting to an entire dataset. The analysis results show that the performance of the hybrid method proposed in this paper outperforms network search + K-fold cross-validation and particle swarm optimization + K-fold cross-validation methods in terms of accuracy, precision, recall, and F1-score. The five-fold cross-validation verifies that the model has good stability and good generalization ability. Further, the model is compared with common AI models such as BP neural network and RBF neural network. The results demonstrate that the proposed model has advantages in core indicators including overall accuracy (0.9444), macro-precision (0.9783), macro-recall (0.9063), and macro-F1-score (0.9362), and can effectively solve the problems of insufficient recognition of minority-class samples, overfitting, and underfitting. This research achieves professional and in-depth application of the SACADA database for diagnosis level prediction, extends existing research on prediction tasks, and delivers valuable theoretical insights and practical application significance. Full article

Background: Insulin resistance (IR) indices—C-reactive protein–triglyceride–glucose index (CTI), triglyceride–glucose (TyG) index, and weight-adjusted waist index (WWI)—are linked to cardiovascular disease (CVD), but their comparative utility in prediabetic populations remains unclear. To evaluate the associations and exploratory mediating roles of CTI, TyG and WWI with prevalent CVD in middle-aged and elderly patients with prediabetes. Methods: The study included 3121 NHANES participants aged ≥45 with prediabetes. Four machine learning algorithms identified key variables. Multivariable logistic regression and restricted cubic spline analyses examined the associations between IR and CVD. Model performance was assessed via receiver operating characteristic curves, net reclassification improvement, integrated discrimination improvement, calibration, and decision curve analysis. Subgroup analyses tested robustness. Mediation analysis assessed the mediating roles of IR in the WWI–CVD relationship. External validation used CHARLS. Results: Individuals in the highest tertiles of TyG, TyG–WWI, and CTI had approximately twofold higher CVD risk (ORs: 1.80–1.97). RCS showed a significant linear increase in CVD risk with higher IR index levels. In fully adjusted models, AUCs improved markedly over baseline: TyG–WWI 0.771 vs. 0.579. Mediation analyses indicated that CTI and TyG mediated 22.13–26.30% of the WWI–CVD association. Subgroup analyses and external validation in CHARLS supported the robustness. Conclusions: IR, as captured by TyG, TyG–WWI, and CTI, independently elevates CVD risk among middle-aged and older adults with prediabetes. WWI is associated with greater odds of prevalent CVD, potentially driven by adiposity accumulation, with CTI and TyG partially mediating this effect. Full article