Search Results (6,171)

Accurate traffic flow prediction is a core component of intelligent transportation systems, supporting proactive traffic management, resource optimization, and sustainable urban mobility. However, urban traffic networks exhibit heterogeneous multi-scale periodic patterns and time-varying spatial interactions among road segments, which are not sufficiently captured by many existing spatio-temporal forecasting models. To address this limitation, this paper proposes PDR-STGCN (Periodicity-Aware Dynamic Relational Spatio-Temporal Graph Convolutional Network), an enhanced STGCN framework that jointly models multi-scale periodicity and dynamically evolving spatial dependencies for traffic flow prediction. Specifically, a periodicity-aware embedding module is designed to capture heterogeneous temporal cycles (e.g., daily and weekly patterns) and emphasize dominant social rhythms in traffic systems. In addition, a dynamic relational graph construction module adaptively learns time-varying spatial interactions among road nodes, enabling the model to reflect evolving traffic states. Spatio-temporal feature fusion and prediction are achieved through an attention-based Bidirectional Long Short-Term Memory (BiLSTM) network integrated with graph convolution operations. Extensive experiments are conducted on three datasets, including Metro Traffic Los Angeles (METR-LA), Performance Measurement System Bay Area (PEMS-BAY), and a real-world traffic dataset from Guizhou, China. Experimental results demonstrate that PDR-STGCN consistently outperforms state-of-the-art baseline models. For next-hour traffic forecasting, the proposed model achieves average reductions of 16.50% in RMSE, 9.00% in MAE, and 0.34% in MAPE compared with the second-best baseline. Beyond improved prediction accuracy, PDR-STGCN reveals latent spatio-temporal evolution patterns and dynamic interaction mechanisms, providing interpretable insights for traffic system analysis, simulation, and AI-driven decision-making in urban transportation networks. Full article

This critical review explores the transformative impact of artificial intelligence (AI), particularly machine learning (ML) and computer vision (CV), on scanning electron microscopy (SEM) and energy dispersive spectroscopy (EDS) for metallic microstructure analysis, spanning research from 2010 to 2025. It critically evaluates how AI techniques balance automation, accuracy, and scalability, analysing why certain methods (e.g., Vision Transformers for complex microstructures) excel in specific contexts and how trade-offs in data availability, computational resources, and interpretability shape their adoption. The review examines AI-driven techniques, including semantic segmentation, object detection, and instance segmentation, which automate the identification and characterisation of microstructural features, defects, and inclusions, achieving enhanced accuracy, efficiency, and reproducibility compared to traditional manual methods. It introduces the Microstructure Analysis Spectrum, a novel framework categorising techniques by task complexity and scalability, providing a new lens to understand AI’s role in materials science. The paper also evaluates AI’s role in chemical composition analysis and predictive modelling, facilitating rapid forecasts of mechanical properties such as hardness and fracture strain. Practical applications in steelmaking (e.g., automated inclusion characterisation) and case studies on high-entropy alloys and additively manufactured metals underscore AI’s benefits, including reduced analysis time and improved quality control. Extending prior reviews, this work incorporates recent advancements like Vision Transformers, 3D Convolutional Neural Networks (CNNs), and Generative Adversarial Networks (GANs). Key challenges—data scarcity, model interpretability, and computational demands—are critically analysed, with representative trade-offs from the literature highlighted (e.g., GANs can substantially augment effective dataset size through synthetic data generation, typically at the cost of significantly increased training time). Full article

Hospitals are among the most energy-intensive buildings, yet their heating systems often operate below optimal efficiency due to outdated controls and limited sensing. Existing facilities often provide only a few accessible measurement points, many of which are locked within proprietary master controllers and not integrated into the Building Automation System (BAS). To address these limitations, this study proposes a data-driven feature selection approach that supports the development of gray-box emulators for complex, real-world central heating plants. A year of operational and weather data from a large hospital was used to train multiple machine learning models to predict the heating demand and return water temperature of a hospital heating plant system. The model’s performance was evaluated under reduced-sensor conditions by intentionally removing unpredictable values such as the VFD speed and flow rate. XGBoost achieved the highest accuracy with full sensor data and maintained a strong performance when critical sensors were omitted. An explainability analysis using Shapley Additive Explanations (SHAP) is applied to interpret the models, revealing that outdoor temperature and time of day (as an occupancy proxy) are the dominant predictors of boiler load. The results demonstrate that, even under sparse instrumentation, an AI-driven digital twin of the heating plant can reliably capture system dynamics. Full article

Gibberellin (GA)-based seedless cultivation is widely used in the skin-edible interspecific table grape (Vitis labruscana × Vitis vinifera) ‘Shine Muscat’, yet when and how GA treatment reshapes fracture-type texture during berry development remains unclear. This study aimed to identify developmental stages and tissue/cell-wall features associated with GA-dependent differences in berry fracture behavior. We integrated intact-berry fracture testing at harvest (DAFB105), quantitative histology of pericarp/mesocarp tissues just before veraison (DAFB39) and at harvest, sequential cell-wall fractionation assays targeting pectin-rich (uronic acid) and hemicellulose/cellulose-related pools at cell division period, cell expansion period and harvest, and stage-resolved RNA-Seq across the same three developmental stages. GA-treated berries had a larger diameter and showed a higher fracture load and a lower fracture strain than non-treated berries at harvest, while toughness did not differ significantly. Histology revealed thicker pericarp tissues and lower mesocarp cell density in GA-treated berries, together with increased cell-size heterogeneity and enhanced radial cell expansion. Cell wall analyses showed stage-dependent decreases in uronic acid contents in water-, EDTA-, and Na₂CO₃-soluble fractions in GA-treated berries. Transcriptome profiling indicated GA-responsive expression of putative cell expansion/primary-wall remodeling genes, EXORDIUM and xyloglucan endotransglucosylase/hydrolases, at DAFB24 and suggested relatively enhanced ethylene-/senescence-associated transcriptional programs together with pectin-modifying related genes, Polygaracturonase/pectate lyase and pectin methylesterase, in non-treated mature berries. Collectively, GA treatment modifies mesocarp cellular architecture and pectin-centered wall status in a stage-dependent manner, providing a tissue- and cell wall–based framework for interpreting fracture-related texture differences under GA-based seedless cultivation in ‘Shine Muscat’. Full article

Accurate short-term forecasting of solar photovoltaic (PV) power output is essential for efficient grid integration and energy management, especially given the widespread global adoption of PV systems. To address this research gap, the present study introduces a scalable, interpretable ensemble learning model of PV power prediction with respect to a large PVOD v1.0 dataset, which encompasses more than 270,000 points representing ten PV stations. The proposed methodology involves data preprocessing, feature engineering, and a hybrid ensemble model consisting of Random Forest, XGBoost, and CatBoost. Temporal features, which included hour, day, and month, were created to reflect the diurnal and seasonal characteristics, whereas feature importance analysis identified global irradiance, temperature, and temporal indices as key indicators. The hybrid ensemble model presented has a high predictive power, with an R² = 0.993, a Mean Absolute Error (MAE) = 0.227 kW, and a Root Mean Squared Error (RMSE) = 0.628 kW when applied to the PVOD v1.0 dataset to predict short-term PV power. These findings were achieved on standardized, multi-station, open access data and thus are not in an entirely rigorous sense comparable to previous studies that may have used other datasets, forecasting horizons, or feature sets. Rather than asserting numerical dominance over other approaches, this paper focuses on the real utility of integrating well-known tree-based ensemble techniques with time-related feature engineering to derive real, interpretable, and computationally efficient PV power prediction models that can be used in smart grid applications. This paper shows that a mixture of conventional ensemble methods and extensive temporal feature engineering is effective in producing consistent accuracy in PV forecasting. The framework can be reproduced and run efficiently, which makes it applicable in the integration of smart grid applications. Full article

Litchi (Litchi chinensis Sonn.) is a pillar of the tropical agricultural economy in southern China, yet its production faces increasing instability due to climate change. Traditional agronomic models often fail to capture the complex, non-linear interactions between meteorological drivers and yield formation in perennial fruit trees. To address this challenge, the study constructed a yield prediction framework using an optimized Random Forest (RF) model integrated with interpretable machine learning (SHAP), based on a comprehensive dataset from 17 major production regions in Hainan Province (2000–2022). The model demonstrated robust predictive capability at the provincial scale (R² = 0.564, RMSE = 2.1 t/ha) and high consistency across regions (R² ranging from 0.51 to 0.94). Feature importance analysis revealed that heat accumulation (specifically growing degree days above 20 °C) is the dominant driver, explaining over 85% of yield variability. Crucially, scenario simulations uncovered asymmetric climate risks across phenological stages: while moderate warming generally enhances yield by promoting vegetative growth and ripening, it acts as a stressor during the Fruit Development stage, where temperatures exceeding 26 °C trigger yield decline. Furthermore, the yield penalty for drought during Flowering (−8.09%) far outweighed the marginal benefits of surplus rainfall, identifying this window as critically sensitive to water deficits. These findings underscore the necessity of phenology-aligned adaptation strategies—specifically, securing irrigation during flowering and deploying cooling interventions during fruit development—providing a data-driven basis for climate-smart management in tropical agriculture. Full article

In high-speed railways, the reliability of jointless track circuits largely hinges on the operational integrity of compensation capacitors. These capacitors are periodically installed along the track to mitigate rail inductive impedance and stabilize signal transmission. The induced voltage response, referred to as the compensation-capacitor signal, serves as a critical diagnostic indicator of circuit health. Yet it is often distorted by electromagnetic interference and structural resonance, posing significant challenges for robust feature extraction. To address this challenge, we propose a Disturbance-Robust Feature Distillation (DRFD) framework that performs multi-perspective modeling and validation of robust features. The framework formulates a unified multi-objective optimization model that jointly considers statistical significance, environmental stability, and structural separability. These objectives are harmonized through an adaptive Bayesian weighting mechanism, enabling automatic identification of disturbance-resistant and discriminative features under complex operating conditions. Experimental evaluations on real-world datasets collected at a 100 kHz sampling rate from roadbed, tunnel, and bridge environments demonstrate that the DRFD framework achieves 96.2% accuracy and 95.4% F1-score, outperforming the best-performing baseline by 4.2–7.8% in accuracy and 6.5% in F1-score. Moreover, the framework achieves the lowest cross-condition relative variance (RV < 0.015), confirming its high robustness against electromagnetic and structural disturbances. The extracted core features—Root Mean Square (RMS), Peak Factor (PF), and Center Frequency (CF)—faithfully capture the intrinsic electromagnetic behaviors of compensation capacitors, thus linking statistical robustness with physical interpretability for enhanced reliability assessment of railway signal systems. Full article

This paper presents the results of a comprehensive technological study of three bronze sculptures from the Jin Empire period (1115–1234 AD) from the collection of the Museum of Archaeology and Ethnography at the Institute of History, Archaeology and Ethnography of the Peoples of the Far East, Far Eastern Branch of the Russian Academy of Sciences (IHAE FEB RAS). Using photon-counting computed tomography (PCCT) and energy-dispersive X-ray spectroscopy (EDS), the production techniques were reconstructed, differences in alloy composition were identified, and specific features of the casting processes were determined. Tomographic analysis revealed two fundamentally different manufacturing approaches: a multi-stage technology involving the use of different alloys and the assembly of separately cast elements, and a single-cast technology with a homogeneous structure. Elemental analysis of the three sculptures using EDS demonstrated significant compositional variability—from 21% to 67% copper and from 9% to 69% tin in different parts of the objects—confirming the complexity of the technological processes. An expanded study of 20 bronze sculptures using portable X-ray fluorescence analysis (pXRF) allowed for the identification of four typological alloy groups: classic balanced lead–tin bronzes (Cu 30–58%, Sn 16–23%, Pb 16–28%), high-lead bronzes (Pb up to 52%), high-tin bronzes (Sn up to 30%), and low-tin alloys (Sn less than 11%). The morphological features of the sculptures suggest one of their possible interpretations as ancestor spirits used in ritual practices. The research findings contribute to the study of Jurchen metallurgical traditions and demonstrate the potential of interdisciplinary, non-destructive analytical methods for reconstructing the technological, social, and cultural aspects of medieval Far Eastern societies. Full article

Focusing on the challenges posed by the strong randomness, weak manifestation, and difficulty in diagnosing intermittent faults (IFs) in high-density integrated circuits (HDICs)—often induced by bonding wire defects—this paper takes the GPIO interfaces of a typical DSP chip as the research object. It systematically analyzes the response characteristics of intermittent short-circuit and open-circuit faults and proposes a hybrid intelligent diagnosis method based on the Sparrow Search Algorithm-optimized Variational Mode Decomposition and Attention-based Support Vector Machine (SSA–VMD–Attention–SVM). A dedicated fault injection circuit is designed to accurately replicate IFs and acquire the power supply current response signals. The Sparrow Search Algorithm (SSA) is employed to adaptively optimize the parameters of Variational Mode Decomposition (VMD) for effective extraction of frequency-domain features from fault signals. A three-level attention mechanism is introduced to adaptively weight multi-domain features, thereby highlighting the key fault components. Finally, the Support Vector Machine (SVM) is utilized to achieve high-precision fault classification under small-sample conditions. Experimental results demonstrate that the proposed method achieves a diagnostic accuracy of 97.78% for intermittent short-circuit and open-circuit faults in the GPIO interfaces of the DSP chip, significantly outperforming traditional methods and exhibiting notable advantages in terms of diagnostic accuracy, robustness, and interpretability. Full article

Climate change increasingly threatens global food security through disrupted precipitation patterns and extreme weather events, requiring resilient systems for assessing agricultural vulnerability. This study developed and compared machine learning approaches for predicting cropland vulnerability using Earth Observation data, operationalized through NDVI anomalies as a defensible biophysical metric. We employed both a dual-stream deep learning architecture and a Random Forest model to predict 2023 NDVI anomalies across Bangladesh croplands using a 22-year time series (2001–2023) of MODIS vegetation indices, ERA5 climate variables, and static environmental covariates. A spatially aware block cross-validation strategy ensured rigorous, independent performance evaluation. Results demonstrated that the Random Forest model (R² = 0.70, RMSE = 197.03) substantially outperformed the deep learning architecture (R² = 0.02, RMSE = 357.57), explaining 70% of cropland stress variance and enabling early detection of vulnerable areas three months before harvest. Feature importance analysis identified recent climate variables, March precipitation, February NDVI, and vapor pressure deficit as primary vulnerability drivers. Spatial analysis revealed distinct vulnerability patterns, with Natore and Magura districts exhibiting elevated stress consistent with 2023 drought conditions, threatening the productivity of the region’s critical irrigation-dependent rice cultivation. These findings demonstrate that simpler, interpretable models can sometimes outperform complex architectures while providing useful information for early warning systems and precision targeting of climate adaptation interventions. Full article

Background: Chest X-ray (CXR) is widely used for the assessment of thoracic diseases, yet automated multi-label interpretation remains challenging due to subtle visual patterns, overlapping anatomical structures, and frequent co-occurrence of abnormalities. While recent deep learning models have shown strong performance, limitations in interpretability, anatomical awareness, and robustness continue to hinder their clinical adoption. Methods: The proposed framework employs a hybrid ConvNeXtV2–Vision Transformer (ViT) architecture that combines convolutional feature extraction for capturing fine-grained local patterns with transformer-based global reasoning to model long-range contextual dependencies. The model is trained exclusively using image-level annotations. In addition to classification, three complementary post hoc components are integrated to enhance model trust and interpretability. A segmentation-aware Gradient-weighted class activation mapping (Grad-CAM) module leverages CheXmask lung and heart segmentations to highlight anatomically relevant regions and quantify predictive evidence inside and outside the lungs. An ontology-driven neuro-symbolic reasoning layer translates Grad-CAM activations into structured, rule-based explanations aligned with clinical concepts such as “basal effusion” and “enlarged cardiac silhouette”. Furthermore, a lightweight out-of-distribution (OOD) detection module based on confidence scores, energy scores, and Mahalanobis distance scores is employed to identify inputs that deviate from the training distribution. Results: On the VinBigData test set, the model achieved a macro-AUROC of 0.9525 and a Micro AUROC of 0.9777 when trained solely with image-level annotations. External evaluation further demonstrated strong generalisation, yielding macro-AUROC scores of 0.9106 on NIH ChestXray14 and 0.8487 on CheXpert (frontal views). Both Grad-CAM visualisations and ontology-based reasoning remained coherent on unseen data, while the OOD module successfully flagged non-thoracic images. Conclusions: Overall, the proposed approach demonstrates that hybrid convolutional neural network (CNN)–vision transformer (ViT) architectures, combined with anatomy-aware explainability and symbolic reasoning, can support automated chest X-ray diagnosis in a manner that is accurate, transparent, and safety-aware. Full article

This study aimed to develop machine learning models based on conventional MRI features to classify HER2 expression levels in invasive breast cancer and explore their association with disease-free survival (DFS). A total of 678 patients from two centers were included, with Center 1 divided into training and internal test sets and Center 2 serving as an external test set. Random Forest models were trained to distinguish HER2-positive vs. HER2-negative (Task 1) and HER2-low vs. HER2-zero tumors (Task 2) using BI-RADS–based MRI features. SHapley Additive exPlanations were applied to rank feature importance, assist feature selection, and enhance model interpretability. DFS was analyzed using Kaplan–Meier curves and log-rank tests. In Task 1, key features included tumor size, axillary lymph nodes, fibroglandular tissue, peritumoral edema, and multifocal, achieving AUCs of 0.75 and 0.73 in the internal and external test sets, respectively. In Task 2, tumor size, peritumoral edema, and multifocal yielded AUCs of 0.73 and 0.72, respectively. Higher task-specific model scores were associated with shorter DFS in Task 1 (p = 0.037) and longer DFS in Task 2 (p = 0.046). MRI-based machine learning models can noninvasively stratify HER2 expression levels, with potential for prognostic stratification and clinical application. Full article

Effective engineering modeling requires simultaneously addressing feature selection and hyperparameter interdependence, a challenge exacerbated by high-dimensional data characteristics in complex engineering modeling. Traditional optimization methods typically address these two aspects separately, which limits overall model performance. This study introduces a hybrid framework to enhance the performance of extreme gradient boosting (XGBoost) in engineering applications. The framework comprises two main phases: first, preliminary feature selection guided by prior domain knowledge and statistical analysis to reduce data dimensionality while preserving interpretability; second, a discrete symbiotic organisms search algorithm with adaptive feature mutation (DMSOS) simultaneously optimizes feature subsets and XGBoost hyperparameters. The DMSOS employs a discretization strategy to separate feature selection from hyperparameter tuning, facilitating focused searches within distinct spaces. An adaptive mutation mechanism dynamically adjusts exploration intensity based on iteration progress and feature importance. Additionally, evaluations on 1414 field-measured blasting vibration data demonstrate that the proposed DMSOS-XGBoost model achieves superior prediction performance, with an r² of 0.96696 and RMSE of 0.02636, outperforming models optimized via traditional sequential approaches. Further interpretability analysis highlights spatial geometry and explosive load as critical features, offering actionable insights for environmental risk management. This research provides a valuable methodological reference for engineering modeling scenarios requiring simultaneous optimization of features and hyperparameters. Full article

This work proposes a data-driven design framework for high-pressure die-cast (HPDC) aluminum alloys that integrates robust data refinement, machine learning (ML) modeling, explainability, and inverse design. A total of 1237 tensile-test records from T5-aged HPDC alloys were aggregated into a curated dataset of 382 unique composition–heat-treatment combinations. Four regression models—Ridge regression, Random Forest (RF), XGBoost (XGB), and a multilayer perceptron (MLP)—were trained to predict yield strength (YS), ultimate tensile strength (UTS), and elongation (EL). Tree-based ensemble models (XGB and RF) achieved the highest accuracy and stability, capturing nonlinear interactions inherent to industrial HPDC data. In particular, the XGB model exhibited the best predictive performance, achieving test R² values of 0.819 for UTS and 0.936 for EL, with corresponding RMSE values of 15.23 MPa and 1.112%, respectively. Feature-importance and SHapley Additive exPlanations (SHAP) analyses identified Mn, Si, Mg, Zn, and T5 aging temperature as the most influential variables, consistent with metallurgical considerations such as microstructural stabilization and precipitation strengthening. Finally, RF-based inverse design suggested new composition–process candidates satisfying UTS > 300 MPa and EL > 8%, a region scarcely represented in the experimental dataset. These results illustrate how interpretable ML can expand the feasible design space of HPDC aluminum alloys and support composition–process optimization in industrial applications. Full article

Effective and transparent medical diagnosis relies on accurate and interpretable classification of medical images across multiple modalities. This paper introduces an explainable multi-modal image analysis framework based on a dual-stream architecture that fuses handcrafted descriptors with deep features extracted from a custom MobileNet. Handcrafted descriptors include frequency-domain and texture features, while deep features are summarized using 26 statistical metrics to enhance interpretability. In the fusion stage, complementary features are combined at both the feature and decision levels. Decision-level integration combines calibrated soft voting, weighted voting, and stacking ensembles with optimized classifiers, including decision trees, random forests, gradient boosting, and logistic regression. To further refine performance, a hybrid class-specific feature selection strategy is proposed, combining mutual information, recursive elimination, and random forest importance to select the most discriminative features for each class. This hybrid selection approach eliminates redundancy, improves computational efficiency, and ensures robust classification. Explainability is provided through Local Interpretable Model-Agnostic Explanations, which offer transparent details about the ensemble model’s predictions and link influential handcrafted features to clinically meaningful image characteristics. The framework is validated on three benchmark datasets, i.e., BTTypes (brain MRI), Ultrasound Breast Images, and ACRIMA Retinal Fundus Images, demonstrating generalizability across modalities (MRI, ultrasound, retinal fundus) and disease categories (brain tumor, breast cancer, glaucoma). Full article