Search Results (1,258)

Structural analysis using X-rays and electron beams has long provided the average arrangement of atoms and molecules—that is, “structural information”—with high precision. By contrast, static measurements cannot directly yield dynamic information on how a material changes over time; instead, information on motion is convolved into a single numerical value such as the B-factor (atomic displacement parameter). Taking this limitation as its starting point, this review surveys the recent trend of introducing a time axis into measurements to observe material dynamics directly. First, we outline the technological foundations that have made the transition from static to time-resolved measurement possible. It rests on the dramatic shortening of exposure times, enabled by the increased brilliance of X-ray and electron sources and by advances in detection technology such as direct photon-counting detectors. Next, we survey dynamic measurement techniques, including time-resolved X-ray crystallography, coherent X-ray scattering, neutron scattering, and time-resolved electron microscopy. We also point out the essential limitation that most of them still return ensemble or volume averages. Building on this, we systematically describe diffracted X-ray tracking (DXT), diffracted X-ray blinking (DXB), small-angle X-ray blinking (SAXB), transmitted X-ray blinking (TXB), and electron-beam molecular dynamics (EBMD), which use gold nanocrystals and gold nanoparticles as motion probes. We distinguish throughout between methods that follow individual objects—DXT and EBMD, which yield trajectories of single labeled molecules or single particles—and methods that analyze intensity fluctuations arising from many contributors within one pixel or illuminated volume—DXB, SAXB and TXB. The latter are not single-molecule measurements; rather, they replace a global ensemble average by a spatially localized statistical one, retaining local heterogeneity that a bulk measurement would average away. Finally, we discuss the implementation and prospects of the large-volume data analysis—principal component analysis, Bayesian inference, machine learning, and autonomous measurement—needed to handle the explosively increasing amount of information that the time axis introduces. We close with the outlook that time-resolved measurement incorporating AI and big-data analysis will become established as a new measurement platform that complements and extends conventional static structural analysis. Full article

Rock cohesion ($c$) and angle of internal friction ($\phi$) are core parameters for rock mass stability analysis and engineering design; however, traditional triaxial tests are costly and time-consuming, limiting their availability in preliminary engineering assessments. To address this limitation, this study develops a machine learning framework that predicts these parameters from easily measurable physical properties, enabling rapid and cost-effective estimation without the need for complex laboratory testing. Based on a total of 199 sets of measured data from four rock types (shale, limestone, quartzite, and quartz-mica schist) in the Himalayan region, this study uses P-wave velocity ($V_p$), density ($\rho$), uniaxial compressive strength (UCS), and tensile strength (TS) as input variables. It employs four models: Support Vector Regression (SVR), Random Forest (RF), Multi-Layer Perceptron (MLP), and extreme gradient boosting (XGBoost) to predict $c$ and $\phi$. Hyperparameters were tuned using grid search and Bayesian optimization. We compared unified modeling with rock-type-specific modeling, performed interpretability analysis using SHapley Additive exPlanations (SHAP), and tested robustness by introducing Gaussian noise. The results show that XGBoost produced the best predictions at $c$ (test set $R^2$ = 0.9901, RMSE = 0.512 MPa), while the Bayesian-optimized SVR model yielded the best results at $\phi$ ($R^2$ = 0.9776, RMSE = 0.744°). Rock-type-specific modeling improved the $R^2$ for limestone at $\phi$ by 0.3541; the SHAP contribution for UCS and TS exceeded 70%; Random Forest demonstrated the best noise resistance, with a decrease in $R^2$ of less than 0.04 under 10% noise. In summary, the strategy proposed in this paper allows for the selection of prediction schemes based on data quality and lithological differences, providing a feasible approach for rapidly obtaining rock strength parameters. Full article

Smart meter anomaly detection is critical for ensuring the security and stability of smart grids. However, existing detection methods face the following limitations: insufficient feature extraction, severe class imbalance, inefficient manual hyperparameter tuning, and poor model interpretability. To overcome these limitations, we propose an accurate and interpretable anomaly detection method based on Bayesian-optimized XGBoost and SHAP. Our method integrates multi-dimensional feature extraction to enrich feature information, Borderline-SMOTE to mitigate class imbalance, Bayesian optimization to tune XGBoost hyperparameters, and SHAP to quantify feature contributions and provide model interpretability. Experimental results on the public MAD dataset demonstrate that our method consistently outperforms both classical machine learning models, including decision tree, Random Forest, XGBoost, and LightGBM, as well as representative deep learning models such as CNN, TCN, LSTM, and CNN-LSTM in binary and multi-class classification tasks, achieving superior accuracy, precision, recall, and F1 scores. SHAP analysis further reveals that three-phase unbalance features are the dominant indicators of abnormal samples, a finding highly consistent with the physical mechanisms of power systems. Our method achieves both competitive detection performance and transparent decision-making, providing an actionable solution for smart meter anomaly detection in practical engineering applications. Full article

The nature of solar radiation and the high penetration of photovoltaic (PV) systems in the smart electrical grid necessitate the development of models driven by historical operational data capable of precisely estimating the performance of PV systems. In this work, six proposed models are applied to predict the conversion efficiency of a 7.98 kWp rooftop on-grid PV system in Jordan. The dataset comprises 179 daily samples obtained during a single spring–summer period (17 March–24 September 2014). The efficiency modeled is the combined efficiency of the modules and inverter as a system. The proposed models are Decision Tree (DT), Random Forest (RF), Support Vector Machine (SVM), Gradient Boosting (GB), Gaussian Process Regression (GPR), and Elastic Net (EN). The effectiveness of these proposed models is assessed by calculating four performance metrics, namely, the Mean Square Error, prediction accuracy, Coefficient of Determination (R²), and adjusted R², and benchmarking the results with those of six prediction models discussed in our previous work. The results from the unweighted Decision-Making Matrix show that RF showed the best overall performance among the proposed and benchmark models considered. By contrast, the SVM, DT, and GB models exhibited moderate predictive behavior. However, Elastic Net is the worst-performing model among the 12 proposed and benchmark models discussed in this work. Moreover, the RF model’s consistently low prediction error supports its practical utility for PV system performance estimation, despite a slightly higher training cost than simpler models. Full article

Magnetic shape memory alloys based on the Ni–Mn–Ga system are of strategic interest for aerospace and robotics applications due to their ability to respond to both thermal and magnetic stimuli. However, the NASA Shape Memory Materials Database a key resource for the community exhibits significant gaps in functional parameters, with up to 93.7% of records missing critical properties such as the Curie temperature, and over 88% lacking complete magnetic data. To address this limitation, this study proposes a data imputation strategy based on a stacking ensemble comprising twelve machine learning models (LGBM, XGBoost, CatBoost, GradientBoosting, RandomForest, MLP, BayesianRidge, KNN, SVR, GPR, MICE, and AutoEncoder), optimized via Optuna and evaluated using ten random seeds with 10 repetitions each. The approach was applied to reconstruct missing entries in NASA’s database. For heat treatment 1, the method achieved coefficients of determination ($R^2$) of 0.95 for duration (h) and 0.88 for temperature (°C), respectively. For the phase transformation temperatures (Mf, Ms, As, and Af), the method yielded $R^2$ values of 0.83, 0.82, 0.79, and 0.80, respectively. Magnetic properties saturation magnetization and maximum magnetic field were imputed with an $R^2$ of 0.92. In contrast, the Curie temperature exhibited limited predictive performance ($R^2$ = 0.15–0.35), primarily due to insufficient data availability. Overall, the proposed methodology integrates machine learning based imputation with physically supported constraints, providing a viable alternative to enhance the completeness and utility of materials databases. Full article

Forensic genetics is moving from locus-based DNA profiling toward genome-wide inference enabled by high-density single-nucleotide polymorphism (SNP) data. While short tandem repeats remain central to routine human identification, SNP-based technologies and massively parallel sequencing have expanded the analysis of distant kinship through detection of identity-by-descent (IBD) segments and shared autosomal DNA. This narrative review synthesizes the biological basis of SNP-based distant kinship inference, the statistical and computational frameworks used to model genomic relatedness, and the operational transition from relatedness detection to forensic genetic genealogy (FGG). It distinguishes genetic genealogy database matching from formal forensic kinship testing, targeted SNP panels, SNP capture, low-coverage sequencing, Bayesian and machine-learning approaches, and independent forensic confirmation. Applications in criminal investigations, unidentified human remains, historical identifications, and broader relationship-inference contexts are discussed. The review also examines limitations related to recombination, stochastic inheritance, marker density, genotype quality, degraded or mixed forensic samples, population structure, endogamy, database composition, and genealogical record availability. Ethical and regulatory issues involving consent, privacy, database governance, law-enforcement access, data retention, and non-consenting relatives are considered. Overall, SNP-based forensic genomics can generate powerful investigative leads, but its outputs must be interpreted within method-specific analytical and evidentiary boundaries. Full article

Background: Impaired glucose tolerance (IGT) is the principal prediabetic stage preceding type 2 diabetes mellitus (T2D), yet islet-specific biomarkers capable of tracking progressive molecular changes from normal glucose tolerance (NGT) through IGT to T2D remain unestablished. We sought to identify a multi-gene biomarker panel with monotonically increasing expression and causal support across the full glycemic continuum. Methods: Two human islet transcriptomic datasets (GSE76895, GSE164416; n = 181: NGT 50, IGT 56, T2D 75) were integrated following ComBat batch correction. Candidate biomarkers were identified at the intersection of limma differential expression and weighted gene co-expression network analysis (WGCNA), then refined through a five-algorithm machine learning consensus (LASSO, random forest, XGBoost, SVM-RFE, elastic net). Progressive expression was assessed by the Jonckheere–Terpstra (J–T) trend test. Two-sample Mendelian randomization (MR) with eQTLGen cis-eQTL instruments, Steiger directionality testing, and Bayesian colocalization provided causal inference. A diagnostic model was internally validated via 1000-iteration bootstrap resampling. Cell-type specificity was verified using single-cell RNA sequencing (GSE200044; 127,919 cells). Results: A 12-gene biomarker panel (ALDOB, DKK3, PCOLCE2, KCNE4, INHBA, IRF8, ITGB2, LAPTM5, MYOF, RAMP3, RUNX2, S100A4) was identified, with all members passing Bonferroni-corrected J–T trend testing across the NGT–IGT–T2D axis (p ≤ 2.4 × 10⁻³). Notably, a direct IGT-versus-NGT transcriptome-wide comparison (11,948 genes) yielded no significant DEGs after FDR correction, indicating that prediabetic islet signals are subtle and detectable only through progressive trend analysis on preselected candidates. Nevertheless, the mean IGT-stage effect size of the 12 hub genes reached 41.9% of the T2D value, with KCNE4 achieving 94.0% (nominal p = 1.75 × 10⁻⁴), identifying it as the earliest-altered biomarker. Two-sample MR using whole-blood eQTLs suggested protective effects of genetically proxied MYOF (OR 0.999, FDR = 1.68 × 10⁻⁴) and RUNX2 (OR 0.998, FDR = 1.68 × 10⁻⁴) on T2D risk, with Steiger testing supporting an expression-to-disease direction (p < 10⁻³⁶). However, Bayesian colocalization indicated independent causal variants at both loci (PP.H3 > 0.76, PP.H4 < 0.001), substantially weakening the causal interpretation and suggesting that the MR associations may reflect linkage disequilibrium rather than shared causal biology. The panel achieved a bootstrap-corrected AUC of 0.833 (apparent 0.879) with PR-AUC of 0.951. Single-cell validation confirmed upregulation of 7 hub genes in β cells and revealed cell-type-specific patterns invisible in bulk data, including bidirectional INHBA regulation between β and α cells and progressive α-cell proportion expansion (28.97% → 46.41%). Pathway enrichment converged on three mechanistic axes: extracellular matrix remodeling, immune activation, and autoimmune-like responses, with direct enrichment of the type 1 diabetes pathway (hsa04940). Conclusions: This study establishes a 12-gene progressive islet biomarker panel spanning the NGT–IGT–T2D continuum, supported by machine learning robustness, genetic causal evidence, diagnostic modeling, and single-cell biological validation. KCNE4 emerges as a candidate early-warning biomarker for prediabetes, while MYOF and RUNX2 represent causally supported compensatory targets, collectively providing a multilayered foundation for T2D risk stratification and precision intervention. From a clinical perspective, the identification of progressive islet biomarkers at the prediabetic stage provides molecular support for early lifestyle intervention, reinforcing that timely detection and behavioral modification remain the most effective strategies to prevent T2D progression. Full article

Accurate aboveground biomass (AGB) estimation in subtropical forests is critical for regional carbon accounting and sustainable forest management. However, standardized multi-source feature screening and integrated machine learning–geostatistical analysis of AGB remain limited. This study integrated six heterogeneous datasets: Landsat-8 optical imagery, Sentinel-1 SAR, topographic, meteorological, soil data and the 2014 National Forest Inventory (NFI), and established 48 predictors in subtropical forests of Anhui Province, China. A two-stage variable selection framework was applied, with Pearson correlation screening reducing the initial 48 predictors to 36 less-correlated variables, followed by the recursive feature elimination (RFE) with 5-fold spatial block cross-validation for further predictor selection. Random Forest (RF), eXtreme Gradient Boosting (XGB), Empirical Bayesian Kriging Regression Prediction (EBKRP), hybrid RF_EBKRP and XGB_EBKRP models were evaluated. Stand age and stand density were dominant predictors in both RF and XGB, contributing 33.6% and 24.0% in RF and 36.5% and 17.3% in XGB, respectively. Elevation, precipitation, and canopy cover showed secondary importance, whereas vegetation indices contributed relatively little. RF_EBKRP achieved the highest prediction accuracy (R² = 0.77), reducing RMSE by 17.20% and 43.75% compared with RF and EBKRP, respectively. This study provides a reproducible RF–EBKRP workflow integrating nonlinear machine-learning prediction with geostatistical residual correction, supporting improved subtropical forest AGB mapping and management. Full article

This paper proposes a priority-aware EP-ALOHA framework with predictive radio resource allocation for heterogeneous machine-to-machine (M2M) devices in 5G massive machine-type communication (mMTC) networks. The proposed framework extends conventional EP-ALOHA by introducing M2M priority classes, priority-dependent delay constraints, and Exploration Phase resource block (RB) allocation. The RB-allocation problem is formulated as an integer-constrained optimization problem, where the objective is to improve effective radio channel utilization while satisfying delay constraints for different priority classes. A Genetic Algorithm-based optimization procedure is used to generate optimization-derived RB-allocation targets under different traffic and system parameter settings. These targets are then used to train and evaluate predictive RB-allocation models, including Random Forest, Neural Network, Gradient Boosting, and Linear Regression. The simulation results show that the proposed priority-aware EP-ALOHA method achieves a higher successful access probability than the considered baseline schemes within the feasible operating region. For predictive RB allocation, the Neural Network achieved the best test-set performance, with MSE = 25.5002, RMSE = 5.0498 RBs, MAE = 3.2629 RBs, and R² = 0.9810. A separate computational evaluation showed that Random Forest inference reduced the mean allocation-decision time from 213.54 ms for GA-based optimization to 15.20 ms, corresponding to a 14.05-fold speed-up on the evaluated platform. In addition, M2M device activity probability forecasting is evaluated using Bayesian estimation, LSTM, moving average, and exponential smoothing. LSTM achieves the lowest forecasting error, while exponential smoothing provides a close and computationally simpler alternative. The results indicate that the proposed framework can support proactive and priority-aware resource management for heterogeneous M2M traffic, while the learning-based components are used as approximation and forecasting tools rather than as universally superior solutions. Full article

Whereas environmental effects on driver cognition have been extensively studied in ground transportation, research linking low-altitude visual environment characteristics to pilot cognitive load (CL) in urban air mobility (UAM) remains scarce. This study combines multimodal physiological data with explainable machine learning to elucidate how low-altitude visual environments influence pilots’ CL. First, a CL quantification framework integrating electroencephalography (EEG) and eye-tracking data is developed to capture real-time cognitive dynamics during flight. Second, multidimensional visual environment indicators are extracted from low-altitude urban landscape images captured during simulated flights using computer vision techniques. These indicators, combined with flight dynamics features, serve as input variables for constructing pilot CL prediction models via machine learning approaches. The results demonstrate that a Bayesian-optimized XGBoost model achieves superior predictive performance. Further interpretability analysis based on SHAP reveals that environmental contrast and the visibility of buildings and water bodies are key factors influencing pilot CL. Additionally, significant interaction effects are also identified among spatial morphology, color characteristics, and landscape typology, with certain landscape elements exhibiting marked variations in both importance and directional influence across different low-altitude flight scenarios. These findings inform low-altitude route optimization, urban morphological regulation, and blue-green infrastructure configuration, advancing an air-ground synergistic planning paradigm. Full article

Portfolio optimization remains a challenging problem due to the dynamic, nonlinear, and uncertain characteristics of financial markets. Traditional portfolio construction approaches, including mean variance optimization and conventional Black–Litterman models, often suffer from inaccurate estimation of expected returns and unstable allocation caused by parameter uncertainty. These limitations become more significant under structural breaks, regime transitions, volatility clustering, and extreme market events. This study proposes a Transformer-GAN enhanced Black–Litterman framework (TG-BL) that integrates temporal representation learning, uncertainty-aware scenario generation, and Bayesian portfolio optimization. The proposed framework consists of three complementary components. First, a Transformer-based encoder is employed to extract long- range temporal dependencies and latent market representations from historical financial sequences. Second, a conditional Generative Adversarial Network (GAN) is introduced to generate diverse future return scenarios conditioned on Transformer- derived market representations, enabling probabilistic modeling of future uncertainty rather than deterministic prediction. Third, the generated return distributions are incorporated into the Black–Litterman framework through dynamically calibrated views and confidence estimation. Unlike conventional approaches that directly replace equilibrium returns with machine-generated predictions, the proposed method preserves the Bayesian structure of Black–Litterman by adjusting the influence of model- generated views according to predictive uncertainty. This mechanism allows AI- based forecasts to complement rather than dominate market equilibrium information. Extensive experiments are conducted using historical financial data under multiple market conditions. The evaluation framework includes portfolio performance comparison, GAN-generated scenario validation, robustness analysis under volatility and liquidity stress, and component- wise ablation experiments. The results demonstrate that the proposed TG-BL framework improves risk-adjusted portfolio performance while maintaining robustness against market uncertainty. The findings indicate that the integration of temporal feature extraction, uncertainty modeling, and Bayesian portfolio allocation provides an effective decision-support framework for quantitative investment management. Full article

Sustainable food systems are increasingly challenged by climate change, resource constraints, market volatility, and growing food demand, making accurate forecasting of food production essential for food security and long-term sustainability. Despite the growing use of machine learning in agricultural forecasting, studies directly modeling the Food Production Index (FPI) within a sustainable food systems framework remain limited, particularly in emerging economies. This study addresses this gap by forecasting Türkiye’s Food Production Index using agricultural, macroeconomic, and trade-related indicators covering the period 1962–2023. Seven predictive approaches, including Multiple Linear Regression (MLR), Bayesian Ridge Regression, Support Vector Regression (SVR), Random Forest, Gradient Boosting, Artificial Neural Networks (ANNs), and K-Nearest Neighbors (KNN), were comparatively evaluated using R², RMSE, and MAE metrics. The results demonstrate that Bayesian Ridge Regression (R² = 0.968) and MLR (R² = 0.918) significantly outperform more complex machine learning algorithms, indicating that model–data compatibility is more critical than algorithmic complexity in long-term food production forecasting. The findings reveal that economic growth, agricultural inputs, and structural transformation processes play a decisive role in shaping food production dynamics. By integrating machine learning with sustainability-oriented food system analysis, this study provides a robust evidence base for supporting food security strategies, resource-efficient agricultural planning, and resilient food system governance. The proposed framework offers macro-level decision-support insights for policymakers engaged in long-term food system planning, strategic risk monitoring, and evidence-based policy evaluation. Full article

Laser directed energy deposition (LDED) can fabricate Ti-6Al-4V thin-walled structures efficiently, but the deposited sidewalls usually contain adhered particles, layer steps, and waviness that limit surface quality. This study combined square-spot laser surface reshaping with machine learning-assisted parameter design to control sidewall roughness. Sixteen single-factor experiments were first conducted to clarify the effects of laser power, scanning speed, spot overlap ratio, and scan number. An 80-sample dataset was then established to train and compare random forest (RF), support vector regression (SVR), and eXtreme Gradient Boosting (XGBoost) models, and SHapley Additive exPlanations (SHAP) were used to interpret feature contributions. RF showed the best predictive performance, with R² = 0.940 and RMSE = 1.760 μm, and was coupled with Bayesian optimization (BO) for inverse parameter design. For a target arithmetic mean roughness (Ra) of 5 μm, the optimized condition was 500 W, 2.57 mm/s, 48.09% overlap, and five scans. The predicted Ra was 5.02 μm, while the validation experiment yielded 5.76 μm, reducing the initial roughness from 28.98 μm by 80.1%. These results demonstrate that interpretable machine learning can support target-driven square-spot laser reshaping for LDED Ti-6Al-4V thin-walled structures. Full article

This study focuses on reducing harmonic distortion in residential electrical systems caused by the use of nonlinear household appliances. A combined prediction and control framework is proposed to estimate and reduce total harmonic distortion (THD) under different operating conditions. Measurements were collected from common domestic appliances, along with environmental factors such as temperature and humidity. An auto-optimized neighborhood fuzzy rough set (AO-NFRS) method is used to identify important input features. These features are then used in a physics-informed machine learning model to predict THD. Based on the predicted values, a Bayesian-optimized ANFIS controller is applied to decide the suitable filtering mode in real time. The results show that the proposed method improves prediction accuracy and reduces harmonic distortion compared to existing methods. It also provides stable filter switching under changing load conditions. The study demonstrates that combining measurement data, physical relationships, and adaptive control can improve power quality in residential systems. Full article

Temperature–time profiles obtained through thermistor-based monitoring provide a rich but noise-sensitive source of information for estimating kinetic and thermal parameters in exothermic batch reactions. Conventional workflows typically combine deterministic smoothing with numerical differentiation, an approach that can amplify measurement noise and fail to propagate preprocessing uncertainty into the resulting reaction-rate and parameter estimates. To address these limitations, this study presents an uncertainty-aware Bayesian machine-learning framework that integrates scalable random-Fourier-feature Gaussian-process (RFF–GP) smoothing, analytical differentiation, temperature-derived apparent conversion, Bayesian parameter inference, posterior validation, predictive calibration, model comparison, ablation, sensitivity analysis, probabilistic benchmarking, simulation of thermal nonideality, and endpoint diagnostics. The framework was applied to $379,631$ cleaned thermistor observations. The production RFF–GP achieved a validation root-mean-square error of $0.04805\mathrm{K}$, yielding a stable latent temperature trajectory and an uncertainty-aware estimate of $dT/dt$. On a smaller matched subset, exact Gaussian-process regression achieved the highest predictive accuracy and the best probabilistic scores, whereas the RFF–GP reduced central-processing-unit runtime by approximately $4.1$-fold and remained applicable to the larger production fit. A Monte Carlo dropout neural comparator produced larger prediction errors and substantially wider predictive intervals. Six apparent thermokinetic structures were evaluated using mean-field variational inference, after which the nth-order and autocatalytic structures were validated using the No-U-Turn Sampler (NUTS). Under mean-field variational inference, the apparent autocatalytic structure achieved the lowest point estimate of the widely applicable information criterion (WAIC), the lowest derivative-domain error, and the lowest full-profile temperature-reconstruction root-mean-square error of $0.2920\mathrm{K}$. Its posterior obtained using NUTS yielded $E_a=40.98\mathrm{kJ}{\mathrm{mol}}^{-1}$, $k_{\mathrm{ref}}=0.005815{\min }^{-1}$, $\Delta T_{\mathrm{ad}}=56.11\mathrm{K}$, $m=0.1694$, and $n=1.0784$. The sampling diagnostics indicated satisfactory convergence, large effective sample sizes, and no divergent transitions. Although the MFVI posterior means and NUTS posterior medians were similar, variational inference produced narrower uncertainty intervals for several correlated parameters. Moving-block bootstrap intervals did not establish a decisive separation in WAIC among the leading structures. Expanded sensitivity, ablation, imperfect-insulation simulation, and endpoint-holdout analyses further showed that the apparent parameter estimates were sensitive to optimization, thermal nonideality, sensor response, and Gaussian-process boundary behavior. The autocatalytic formulation should therefore be interpreted as the best-performing apparent structure among the candidates tested rather than as evidence of a unique chemical mechanism. Overall, the framework extracted physically plausible apparent thermokinetic information from noisy temperature-only measurements while explicitly quantifying uncertainty arising from prediction, parameter estimation, model form, computation, thermal nonideality, and boundary behavior. Full article