Search Results (6,559)

Understanding how globalization, energy transition, and resource dependence shape environmental pressure remains critical for resource-rich economies seeking sustainable development. This study investigates the determinants of ecological footprint per capita in the United Arab Emirates from 1992Q1 to 2020Q4 by extending the STIRPAT framework to incorporate scale effects, structural composition, technological mitigation, and a globalization–renewable energy interaction channel. The empirical strategy combines ARDL cointegration modeling, Ridge regression and annual frequency estimations for robustness assessment, wavelet coherence analysis, and ARDL-ECM Granger causality tests. The results show that economic growth increases ecological footprint in the short run, reflecting persistent affluence-related scale effects. In the long run, economic globalization and natural resource rents significantly increase ecological footprint, suggesting that trade- and hydrocarbon-driven composition effects outweigh potential efficiency gains during the study period. Renewable energy consumption exerts a negative long-run elasticity, indicating its technological mitigation role. However, the positive globalization–renewable energy interaction indicates that expanding economic integration partially offsets the environmental benefits associated with renewable energy deployment. Wavelet coherence analysis reveals that these relationships vary across time and frequency horizons, with globalization exhibiting leading associations with ecological pressure at medium-term frequencies, while Granger causality identifies significant predictive pathways toward ecological footprint dynamics. The findings remain consistent across robustness assessments and suggest that renewable energy contributes to reducing ecological pressure, but achieving substantial ecological decoupling requires both fossil fuel substitution and structural transformation in globalization and resource-dependent development pathways. This study provides evidence-based insights for supporting sustainability transitions in resource-dependent economies and advancing progress toward the SDGs. Full article

Reliable traffic flow forecasting is a core component of intelligent transportation systems; however, many current approaches are still unable to simultaneously model spatial interdependencies and long-term temporal correlations, particularly in cross-sea corridors that exhibit directional heterogeneity and pronounced temporal variability. This study aims to develop an accurate and stable traffic flow prediction framework for cross-sea corridors. To achieve this, an HGTransformer model was proposed that constructed a hypergraph from traffic nodes based on spatial proximity and correlated flow variations, and used hypergraph convolution to extract spatial node representations. These representations were then fed into a Transformer equipped with multi-head self-attention and positional encoding, enabling the model to capture global temporal dependencies in the evolution of traffic flow. Using hourly traffic flow data from the Huangmaohai cross-sea corridor, the model was tested on 1 to 4 h forecasting horizons and compared with long short-term memory (LSTM), multi-layer perceptron (MLP), random forest (RF), support vector regression (SVR), and Bayesian regression (BR) models. The proposed model achieved the best overall performance, with average mean absolute percentage error (MAPE), mean absolute error (MAE), weighted mean absolute percentage error (WMAPE), and root mean square error (RMSE) of 0.178, 13.375, 0.140, and 20.538, respectively. At the 1 h horizon, these values further decreased to 0.172, 12.678, 0.132, and 19.401, while preserving peak–valley structures more accurately under both short- and longer-horizon forecasting. The main contribution of this study lies in the systematic application and validation of the Huangmaohai Corridor dataset, including a reproducible hypergraph construction strategy tailored specifically for this particular infrastructure. Full article

This paper presents an adaptive noise-aware bearing fault diagnosis framework that integrates Fast Fourier Transform (FFT)-windowed feature extraction, wavelet-based Signal-to-Noise Ratio (SNR) estimation, and Long Short-Term Memory (LSTM) classification to maintain high diagnostic accuracy under both clean and severely noisy operating conditions. The core novelty of the proposed framework lies in its adaptive model selection mechanism, which automatically selects the most appropriate LSTM classifier according to the estimated SNR, thereby improving diagnostic robustness across different noise environments. Experiments were conducted on two benchmark datasets, the Case Western Reserve University (CWRU) dataset and the Huazhong University of Science and Technology (HUST) bearing dataset, to evaluate the generalization capability of the proposed approach. Two preprocessing pipelines were examined: time-domain normalization before FFT and frequency-domain normalization after FFT. Vibration signals were segmented without overlap to ensure unbiased evaluation. The results demonstrate that both the choice of window function and the normalization strategy significantly influence classification accuracy and robustness. Under noise-free conditions, several window types achieved accuracies above 99%, with triangular and Hamming windows providing the best performance. The combination of triangular windowing and time-domain normalization achieved the highest accuracy of 99.69%. Furthermore, time-domain normalization combined with triangular windowing exhibited superior stability and noise resistance compared with frequency-domain normalization. Under noisy conditions, noise-augmented training was found to be essential for achieving robust generalization. Models trained with moderate noise levels (8–12 dB) provided the best trade-off between accuracy and robustness, whereas excessive noise during training degraded performance. To accommodate varying noise environments, a lightweight wavelet-based SNR estimator was used to categorize operating conditions into low-, medium-, and high-SNR regions and select the corresponding LSTM classifier. The proposed framework was successfully implemented on a ZedBoard FPGA (Field-Programmable Gate Array) development board using a System-on-Chip (SoC) architecture. Experimental results show that, with a sampling frequency of 48 kHz and a processing window of 2048 samples, the proposed system updates the diagnostic result every 42.7 ms, demonstrating its suitability for real-time industrial condition monitoring and intelligent predictive maintenance applications. Full article

Rapid urbanization has increasingly posed risks of inducing land subsidence in newly developed urban districts, posing growing threats to infrastructure safety. This study focuses on a selected rectangular area within the Shannan New District of Huainan City. Based on 94 Sentinel-1A images acquired from 2023 to 2025, the SBAS-InSAR technique was employed to obtain high-density spatiotemporal surface deformation data. The discrete monitoring points were mapped onto a 100 × 100 regular grid according to their spatial coordinates, with null-value cells retained. A spatial attention mechanism was then embedded into the Convolutional Long Short-Term Memory (ConvLSTM) network to construct a Spatial Attention–ConvLSTM (SA-ConvLSTM) model for spatiotemporal prediction, which was systematically compared with LSTM, CNN-LSTM (Convolutional Neural Network combined with Long Short-Term Memory), and standard ConvLSTM. The results demonstrate that SA-ConvLSTM achieves optimal prediction performance on the temporal hold-out test set, with a root mean square error of 2.09 mm and a coefficient of determination (R²) of 0.77. For subsidence hotspot identification, the intersection over union (IoU) reaches 0.56, and the F1-score reaches 0.72—substantially improving from 0.25 for standard ConvLSTM, confirming that the spatial attention mechanism effectively enhances the model’s capability to focus on key deformation areas. Rolling predictions of the deformation field for 2026 (12 time steps, each covering one Sentinel-1A acquisition interval of approximately 12 days) yield an estimated deformation trend ranging from −16.58 to 0.28 mm over the 12-step forecast period (approximately 144 days). This integrated framework provides a methodological reference for subsidence risk identification and mitigation in the Shannan New District. Full article

Background: Dry eye disease (DED) impairs quality of life. Artificial tears are the first-line treatment, but compliance is generally poor. Patients forget to instil drops or underestimate the importance of regular use. Mobile health (mHealth) applications improve adherence in other chronic conditions, but their role in DED remains unclear. This study evaluated the effectiveness of a smartphone reminder application in improving compliance to a four-times-daily artificial tear regimen and the associated symptom relief among patients with DED. Methods: A masked randomised crossover trial was conducted in 29 women with DED (mean ± SD age 21.2 ± 3.0 years). Participants completed two 14-day study phases: one with app-based reminders and one without, separated by a 7-day washout period. The primary outcome was mean daily drop frequency. Secondary outcomes were self-reported symptom frequency and severity assessed using the Symptom Assessment iN Dry Eye (SANDE). Results: The mean daily drop frequency was higher during the app phase compared with the non-app phase (F = 22.906, p < 0.001) but declined in both phases over time (F = 3.023, p < 0.001). Symptom frequency did not differ between phases but decreased over time (F = 1.993, p = 0.021). Symptom severity remained unchanged with no significant effects by phase or time. Baseline clinical measures did not predict drop use frequency or app-related improvement (p > 0.05). Conclusions: The reminder application increased short-term compliance to artificial tear use, but there was no corresponding reduction in symptoms or signs over two weeks’ usage. Compliance waned over time despite active reminders, suggesting that prompts alone are insufficient for sustaining behaviour change. Future digital interventions for DED should incorporate strategies to enhance motivation, support long-term engagement, and provide personalised education. Full article

The operational reliability of shaft systems in hydropower units has become increasingly critical as these units are frequently engaged in grid regulation under new power systems. This paper presents a sensor-driven method for operational status assessment and trend prediction of Francis turbine generator unit shaft systems using vibration and swing signals. Time domain features are extracted from the sensor-acquired signals to construct a multi-dimensional quantitative index system for characterizing the operational state, and a combined Entropy Weight–Coefficient of Variation–TOPSIS model with dynamic health thresholds is established for adaptive condition assessment. To address the nonlinear and non-stationary characteristics inherent in such signals, a decomposition–prediction–reconstruction fusion framework is developed, incorporating Variational Mode Decomposition (VMD) for signal decomposition and noise reduction, iTransformer for capturing global multi-variable interactions, and Bidirectional Long Short-Term Memory (BiLSTM) for bidirectional temporal feature extraction. The hybrid model achieves a coefficient of determination R² of 0.9845 on complex vibration and swing signals, demonstrating its superior prediction capability. Based on the prediction results, health scores and dynamic thresholds are calculated to perform trend analysis and health early warning. A case study is conducted using real-world monitoring data from a 306 MW Francis turbine unit. The results demonstrate that the proposed method effectively characterizes the shaft system operational state, achieving a closed-loop integration from condition monitoring to fault diagnosis and predictive maintenance. The operational status assessment and trend prediction analyses are in good agreement with actual operating conditions, providing reliable technical support for the intelligent health management of hydropower units. Full article

Pumped storage hydropower (PSH) is a key regulating resource for renewable energy integration and power system stability. Due to frequent start-stop operations, deep peak-load regulation, and bidirectional operating conditions, stator winding insulation degradation, rotor inter-turn short circuits, and end-winding vibration have become the dominant failure modes of pumped storage units. Conventional monitoring systems are limited by single-source sensing, asynchronous data acquisition, high misdiagnosis rates, and maintenance decisions that rely heavily on expert experience, making traditional periodic maintenance increasingly inadequate. To address these challenges, this study proposes an intelligent diagnosis and decision support system based on multi-source data fusion and hybrid intelligent algorithms. An Intelligent Electronic Device (IED)-based condition monitoring platform is developed by integrating multiple sensing technologies. Complete Variational Mode Decomposition (CVMD) and Kernel Principal Component Analysis (KPCA) are employed to extract representative features from multi-physical-field data, while an attention-enhanced Long Short-Term Memory (LSTM) network is introduced for accurate fault identification. In addition, adaptive time-alignment and joint denoising algorithms are developed to improve data quality and diagnostic robustness. A predictive maintenance framework incorporating health assessment and remaining useful life prediction is further established to optimize maintenance scheduling. Results demonstrate that the proposed system achieves a fault prediction accuracy of over 90% and reduces annual maintenance costs by approximately 15–20%. The proposed framework provides an effective solution for intelligent operation and maintenance of modern pumped storage units. Full article

Remaining useful life (RUL) estimation is a fundamental task in Prognostics and Health Management (PHM), supporting condition-based and predictive maintenance of engineering systems. Data-driven methods contribute to many effective strategies for RUL prediction. However, two problems need to be solved when they are used in industrial applications: (1) The amount of data under one working condition is limited, and data from different working conditions suffer from domain discrepancies. These methods are constrained by distribution differences in data under different working conditions. (2) There is an urgent need to quickly achieve prediction with much less computing resources. To address these issues, a lightweight RUL prediction method called a knowledge transfer-based heterogeneous distillation network is proposed by combining knowledge distillation and transfer learning. First, the adversarial training mechanism is introduced for the extraction of domain-invariant features. Subsequently, a heterogeneous knowledge distillation framework is further designed for remaining useful life prediction, in which a bi-directional long short-term memory model serves as the teacher network and a compact fully connected network acts as the student model. The teacher model is used to learn informative degradation patterns and guide the training of the lightweight student model through knowledge transfer. Results obtained on the N-CMAPSS dataset verify that the proposed method achieves promising effectiveness and strong generalizability, reducing the average RMSE and MAE by 44.83% and 41.30%, respectively. Full article

Fatigue assessment of floating offshore wind turbines (FOWTs) remains challenging because fatigue-sensitive regions may occur outside conventional predefined hotspots. This study applies a previously numerically verified full-field fatigue-screening workflow combining Unit Load Response, submodeling, and Virtual Test Rig concepts to the TaidaFloat semi-submersible FOWT under Taiwan Strait environmental conditions. Reconstructed nodal stress histories are used to map hull fatigue and evaluate occurrence-weighted contributions from 182 environmental bins, including operational and typhoon conditions. The results identify fatigue-sensitive regions not only at conventional column–bracing and column–pontoon connections but also in the upper main column and along the turbine–hull load path. Upper column fatigue is mainly associated with turbine-induced bending, whereas lower column and waterline-adjacent regions are more sensitive to wave-induced global hull bending. Frequently occurring near-rated operational conditions dominate the occurrence-weighted hull fatigue contribution, while selected typhoon conditions produce high short-term damage but limited long-term contributions within the four-year dataset. Approximately 94.6% of hull fatigue damage is captured by 28% of the bins, and a common hull–mooring set captures 97.0% of both contributions using 62% of the bins. These findings support hotspot screening and environmental-bin prioritization rather than detailed or certification-level fatigue life prediction. Full article

Background/Objectives: Human gait analysis is essential for identifying biomechanical alterations associated with pathological conditions. However, conventional laboratory systems that combine optical motion capture and force plates remain costly, space-demanding, and difficult to implement in routine or accessible settings. This study proposes a dual-model artificial intelligence framework designed to bridge kinematics and dynamics and subsequently support gait health-status classification from motion data. Methods: The first model was developed to estimate ground reaction forces (GRF) and center of pressure (CoP) signals from kinematic inputs. Public datasets containing synchronized kinematics and dynamics were used to train and evaluate long short-term memory (LSTM) and one-dimensional convolutional neural network (CNN1D) architectures. A robustness stage further adapted the dynamic prediction model to markerless-like kinematic inputs through domain-adaptation training. The second model was implemented as a multichannel convolutional classifier using normalized GRF/CoP signals and metadata. Three variants were compared: signals only, signals with minimal metadata, and signals with rich metadata. Finally, a bridge block connected both models, and a proof-of-concept deployment was performed using markerless kinematics obtained with Move AI and Blender. Results: The final dynamic prediction model achieved an overall RMSE of 0.0676, with reconstructed-signal RMSE of 0.0500 and reconstructed contact accuracy of 0.9736. The best classification variant achieved a balanced accuracy of 0.9608, while the minimal-metadata variant was selected for pipeline integration due to its compatibility with accessible data acquisition. In the full pipeline evaluation, the predicted dynamics correctly classified the healthy-control samples. In the Move AI/Blender proof-of-concept, all five healthy participants were classified as healthy controls, with a mean non-pathological classification probability consistent with this outcome. Conclusions: The proposed dual-model framework demonstrates the operational feasibility of linking kinematic acquisition, dynamic prediction, and gait classification within a single artificial intelligence pipeline. The Move AI/Blender stage represents a preliminary proof of concept rather than clinical validation, and further evaluation with pathological participants and synchronized force-plate measurements is required. Full article

Accurate gait event detection using inertial measurement units (IMUs) is essential for temporal gait analysis, but frame-level detection is challenged by sparse initial contact (IC) and foot-off (FO) events. This study evaluated recurrent neural network architectures and training strategies for simultaneous IC and FO detection using a single shank-mounted smartphone IMU. The internal dataset included 28 healthy older adults and 18 individuals with non-specific low back pain (NSLBP). Temporal label expansion substantially improved validation performance for gated recurrent unit (GRU) and long short-term memory models, whereas point-label and class-weighted training performed poorly. The selected label-expanded GRU (LE-GRU) achieved $F_1$ scores above 0.95 for both events and mean absolute temporal errors below 12 ms on held-out internal test folds, with high performance in both cohorts. On an external dataset with different sensor and acquisition characteristics, high performance required full-network fine-tuning, indicating the need for adaptation across datasets. Stance phase and stride time calculated from LE-GRU-predicted events showed high agreement with reference-derived values, with Lin’s concordance correlation coefficients from $0.980$ to $0.994$. These findings demonstrate that temporal label expansion enables accurate GRU-based gait event detection and temporal gait analysis from data collected with a single smartphone IMU. Full article

Background: Although advances in critical care have improved short-term outcomes, sepsis survivors continue to face substantial chronic morbidity and impaired long-term survival. Conventional threshold-based tools such as the Sequential Organ Failure Assessment (SOFA) and Modified Early Warning Score (MEWS) show moderate and variable discrimination across cohorts. Reported areas under the receiver operating characteristic curve (AUROCs) must therefore be interpreted in relation to the population, prediction horizon, and outcome used in each study rather than as direct head-to-head comparisons. Objectives: This review evaluates how artificial intelligence (AI) could be linked with dynamic plasma metabolites, particularly citrulline and β-hydroxybutyrate (3-HB), to support biologically informed sepsis phenotyping, while critically examining mechanistic evidence, clinical limitations, and translational readiness. Data Synthesis: Machine-learning and natural language processing architectures have shown promising discrimination in many early-detection studies, with pooled AUROCs near 0.87 and reported prediction windows extending to 48 h. However, performance estimates vary with cohort composition, outcome definition, and validation design, and they should not be ranked against unrelated biomarker studies. Human sepsis studies generally associate low or persistently low citrulline with impaired intestinal function and organ injury, but no sepsis-specific decision cutoff has been externally validated. For 3-HB, an AUROC of 0.8429 for septic liver injury was derived from a cohort of 57 patients and has not been shown to add value beyond routine liver tests or illness-severity measures. Murine experiments provide mechanistic hypotheses for ketone-mediated organ protection, but model-specific and sometimes opposing nutritional effects limit direct translation. These metabolites are therefore best considered candidate longitudinal features for multimodal phenotyping rather than stand-alone clinical triggers. Conclusions: Biologically informed algorithmic surveillance is a promising direction, but clinical implementation requires prospective serial sampling, explicit adjustment for renal, hepatic and nutritional confounders, head-to-head comparison with routine markers, and external validation of calibration and clinical utility. Until these requirements are met, citrulline and 3-HB should support research phenotyping rather than direct treatment selection. Full article

The evaluation of the ultimate bearing capacity (UBC) of foundation systems remains a fundamental challenge in geotechnical engineering because of the complex interactions among soil properties, foundation geometry, loading conditions, embedment depth, and soil–foundation behavior. In recent years, artificial intelligence (AI) and deep learning (DL) techniques have emerged as powerful data-driven tools for modeling nonlinear geotechnical systems and improving bearing-capacity prediction. This study presents a comprehensive state-of-the-art review of AI- and DL-based approaches for foundation systems, including shallow foundations, deep foundations, pile foundations, and other geotechnical applications. Major models, including Artificial Neural Networks (ANNs), Deep Neural Networks (DNNs), Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM) networks, Transformer models, Graph Neural Networks (GNNs), hybrid AI frameworks, and physics-informed deep learning approaches, are critically reviewed and compared. Particular attention is given to the integration of AI models with numerical methods, including the finite element method (FEM) and finite element limit analysis (FELA). The reviewed studies frequently report lower prediction errors than conventional empirical, numerical, and machine-learning approaches within the evaluated datasets. However, many of the highest reported accuracies are based on laboratory-scale experiments, simulation-generated data, or random train–test partitions of a single database. Consequently, these results may demonstrate effective interpolation within controlled data distributions rather than reliable performance under independent field conditions. Model performance is strongly influenced by dataset origin and diversity, feature selection, validation strategy, overfitting control, and generalization capability. Hybrid datasets combining field, laboratory, and numerical data offer a promising route toward more reliable prediction, but genuine external validation using independent sites, projects, or institutions remains uncommon. Moreover, architectural suitability should reflect the physical structure of the problem: CNNs are appropriate for spatial heterogeneity, LSTMs for time-dependent behavior, Transformers for long-range interactions, and GNNs for mechanically connected systems. Limited field-scale datasets, weak external validation, limited model interpretability, inadequate uncertainty quantification, and persistent data scarcity continue to restrict widespread engineering implementation. Future research should prioritize explainable AI, physics-informed learning, transfer learning, hybrid data frameworks, open benchmark datasets, and multi-site field validation to improve the robustness, transparency, and practical applicability of intelligent bearing-capacity prediction for diverse foundation systems. Full article

Rainfall–runoff modeling is a key challenge in hydrological research. Despite the extensive application of long short-term memory (LSTM) networks in rainfall–runoff modeling, our understanding of the influence of different hyperparameter configurations on various hydrograph components, as well as the linkages between hydrological concepts and LSTM architectures, remains elusive. Here, we integrated Multi-Objective Particle Swarm Optimization (MOPSO) with LSTM hyperparameter optimization by targeting the root mean square error of the overall hydrograph (RMSE_all), high-flow (RMSE_high) and low-flow (RMSE_low) dynamics, and water volume deviation (Dv). The MOPSO-LSTM framework was applied to the upstream catchments of the Miyun Reservoir in Beijing, China. At a lead time of 1d, the optimal solution achieved an NSE of 0.920 in the Chaohe River Basin, with a minimum RMSE_all of 0.848 m³/s, RMSE_high of 2.081 m³/s, RMSE_low of 0.382 m³/s, and Dv of 0.002%. However, as the lead time increased to 3 and 7 days, the maximum NSE declined to 0.747 and 0.560, respectively, with process-related metrics deteriorating more substantially than water balance-related metrics. The Baihe River Basin performed better, with maximum NSE and KGE values of 0.949 and 0.970 at a lead time of 1d. Clear trade-offs among different evaluation objectives were further identified, particularly the competitive relationship between RMSE_high and RMSE_low, as well as the coupling between RMSE_low and Dv. SHAP (Shapley additive explanation) and partial dependence plots (PDPs) were used to quantify and interpret the effects of hyperparameters on model performance, and the results showed that learning rate, number of units, and lookback window served as the most influential hyperparameters. Moreover, optimization preferences resulted in distinct hyperparameter configurations, where Dv-oriented solutions favored smaller learning rates, longer lookback windows, and larger batch sizes than RMSE-oriented solutions. Compared with the Chaohe River Basin, the larger Baihe River Basin favored LSTM configurations with longer lookback windows, more hidden units, higher learning rates, and lower dropout rates, which was associated with the hydrological memory of the catchment. Overall, this study provides a novel multi-objective LSTM optimization framework, improving the understanding of LSTM hyperparameters and offering practical guidance for hydrological prediction and water resource management. Full article

Accurate continuous prediction of lower-limb joint angles from surface electromyography (sEMG) remains challenging because of the nonlinear, non-stationary, and subject-specific nature of sEMG signals, which can reduce robustness and lead to degraded prediction accuracy during highly dynamic gait phases. In this study, we propose RTGNet, a dual-branch deep learning framework for lower-limb joint-angle prediction from multichannel sEMG. The method constructs two feature views from the same sEMG stream: recurrence-plot (RP)-based representations for nonlinear texture characterization and time-series sequences for long-term temporal dependency modeling. These views are processed by a convolutional neural network (CNN) with a convolutional block attention module (CBAM) and a bidirectional long short-term memory network (BiLSTM), respectively, and integrated through an adaptive gated fusion mechanism. An enhanced Huber-TopK loss is further employed to emphasize samples with large prediction errors. Experiments on the SIAT-LLMD dataset under an offline cross-subject evaluation setting show that RTGNet achieves a mean absolute error (MAE) of 3.87°, a root mean square error (RMSE) of 5.25°, and an $R^2$ of 0.81 during walking, as well as an MAE of 4.53°, an RMSE of 6.47°, and an $R^2$ of 0.84 during stair ascent. The proposed framework outperforms temporal-only and RP-based baselines, and ablation results further support the effectiveness of the gated fusion strategy and CBAM attention. Overall, these results suggest that integrating recurrence texture and temporal dynamics is a promising strategy for sEMG-driven joint-angle prediction and provides a useful basis for future exoskeleton control-oriented studies. Full article