Search Results (22,613)

Accurate energy forecasting is essential for maintaining power system reliability, integrating renewable generation, and ensuring market stability. Although machine learning has improved forecasting accuracy, its operational deployment depends on Machine Learning Operations (MLOps) platforms that automate and scale the entire lifecycle of energy data pipelines. However, the capabilities of existing MLOps platforms for energy forecasting have not been systematically compared. This study adopts a PRISMA-informed review process to identify relevant end-to-end MLOps platforms for energy forecasting and then maps their documented capabilities using an established energy forecasting pipeline lifecycle as the reference structure. A total of 256 records were screened across vendor documentation, open-source repositories, and academic literature, of which 13 MLOps platforms were selected for comparative capability analysis. Platform capabilities are organised and presented across an end-to-end lifecycle covering project setup and governance, data ingestion and management, model development and experimentation, deployment and serving, and monitoring and feedback. Commercial platforms such as Amazon SageMaker and Google Vertex AI generally provide stronger end-to-end integration and production readiness, while open-source platforms such as Kubeflow and ClearML offer modular flexibility that typically requires additional integration effort to achieve end-to-end operation. The mapping identifies four priority areas where platform support remains limited, namely (i) governance workflow automation, (ii) automated data quality validation, (iii) feature management, and (iv) deployment and monitoring support under nonstationary conditions. These findings indicate that platform selection for energy forecasting should be treated as a lifecycle capability decision, balancing end-to-end integration, operational assurance, and long-term flexibility. Full article

Lower-limb rehabilitation exoskeletons must balance biomechanical compatibility, structural safety, and low mass to enable practical, repeatable gait assistance. This paper proposes a planar pantograph-derived exoskeleton leg driven by a Chebyshev Lambda linkage and develops an integrated workflow from mechanism synthesis to manufacturable optimization and experimental verification. A mannequin-coupled multibody model was built in MSC ADAMS to evaluate joint kinematics, end-point (foot) trajectories, and joint reaction forces under multiple scenarios (fixed-frame, ramp, stair ascent, and inclined-plane walking). The extracted joint loads were transferred to a parametric finite element model in ANSYS Workbench 2019, where response surface surrogates and a multi-objective genetic algorithm (MOGA) were used to minimize mass under stiffness and strength constraints. For the optimized load-bearing link, the selected minimum-mass design reached a component mass of 0.542 kg while respecting the imposed structural limits, i.e., a maximum total deformation below 0.2 mm and a maximum equivalent (von Mises) stress below 50 MPa (e.g., ~0.188 mm deformation and ~39 MPa stress in the optimal candidate). A rapid prototype was manufactured by 3D printing and experimentally evaluated using CONTEMPLAS high-speed video tracking, providing measured X_M(t) and Y_M(t) trajectories and joint-angle histories for quantitative comparison with simulations via RMSE metrics. Full article

To address the challenges of small targets, severe background clutter, and high deployment cost in UAV-based power-line defect detection, this paper proposes a lightweight defect detection model based on an improved YOLOv8n. In the downsampling stage, we design an improved lightweight adaptive downsampling module (ADownPro) to replace part of conventional convolutions, which uses a dual-branch parallel structure for stronger feature interaction and depthwise separable convolutions (DSConv) for complexity reduction. In the feature extraction stage, an integration of cross-stage partial connections and partial convolution (CSPPC) is proposed to replace the C2F module for efficient multi-scale feature fusion. In the detection head, mixed local channel attention (MLCA), which combines channel-spatial information and local–global contextual features, is introduced to strengthen defect-focused representations under complex backgrounds. For the loss function, a scale-annealed mixed-quality EIoU loss (SAMQ-EIoU) is proposed by combining iso-center scale transformation, scale factor annealing and focal-style quality reweighting to improve localization accuracy at high IoU thresholds. Experiments on a constructed dataset covering six typical defect categories show that the improved YOLOv8n achieves 91.4% mAP@0.50 and 64.5% mAP@0.50:0.95, with only 1.59 M parameters and 4.9 GFLOPs. Compared with mainstream detectors, the proposed model achieves a better balance between detection accuracy and lightweight design. In particular, compared with the recently proposed YOLOv8n-DSN and IDD-YOLO, it improves mAP@0.50 by 0.6% and 0.8%, and mAP@0.50:0.95 by 1.2% and 4.8%, respectively, while further reducing the parameter count by 1.00 M and 1.26 M, and the FLOPs by 1.7 G and 0.2 G. Moreover, the cross-dataset evaluation on the public UPID and SFID datasets further demonstrate the robustness and generalization ability of the proposed method. Full article

In flood disaster emergency decision-making, the dynamic changes in expert trust relationships directly affects the efficiency of reaching a decision consensus. This paper constructs a dynamic evolution model of expert trust relationships in flood disaster emergency decision-making from the perspective of preference distance: the initial trust matrix and weights of experts based on four dimensions including cooperation intensity, social relations, background similarity, and subjective initial trust; the cognitive trust is quantified by using the intuitionistic fuzzy Hamming distance, and the trust relationship is dynamically update through the exponential fusion method; the Louvain community discovery algorithm is introduce to achieve dynamic clustering of experts and weight updates of experts in combination with the dynamic changes in trust relationships; and a consensus feedback adjustment mechanism is designed to optimize the preferences of experts with lower consensus. At the same time, the dynamic trust model is verified by combining a flood disaster case. Case validation shows that the model completes consensus iteration in just four rounds, with the maximum increase in cognitive trust due to opinion convergence reaching 0.18 during the evolution process. The model effectively captures changes in trust among experts during decision-making, improving consensus convergence speed while ensuring that the final solution aligns with the comprehensive considerations required in emergency scenarios. This study provides a quantitative tool for large-group decision-making in flood emergencies under high-pressure, information-poor environments; one that balances dynamic trust evolution with efficient consensus building. Full article

To address the challenges posed by the strong uncertainty of high-proportion renewable energy sources (RES) to the secure and stable operation of distributed real-time power dispatch (D-RTPD) in new-type power systems, this paper proposes an integrated solution combining a neighborhood feature aggregation-based graph attention network (NFA-GAT) and multi-agent deep deterministic policy gradient (MADDPG). First, the D-RTPD problem is modeled as a decentralized partially observable Markov decision process (Dec-POMDP), which effectively captures the stochastic game characteristics of multi-regional agents and the partial observability of grid states. Second, the NFA-GAT is designed to enhance agents’ perception of grid operating states: by introducing a spatial discount factor, it realizes rational aggregation of multi-order neighborhood information while modeling the attenuation of electrical quantity influence with topological distance. Third, a prior-guided mechanism is integrated into the MADDPG framework to eliminate constraint-violating actions by setting their actor logits to negative infinity, improving training efficiency and strategy reliability. Simulation validations on the IEEE 118-bus test system (75.2% RES installed capacity ratio) show that the proposed method achieves efficient training convergence. Compared with the multi-layer perceptron (MLP) structure, it attains higher cumulative reward values and scenario win rates. When compared with traditional model-driven (ADMM) and data-driven (Q-MIX) methods, the proposed method balances solution efficiency, operational safety (98.7% maximum line load rate, zero power flow violation rate), and economic performance ($12,845 daily dispatch cost), providing a reliable technical support for D-RTPD under high-proportion RES integration. Full article

Historical small towns (HSTs) embody irreplaceable cultural heritage and territorial identity, facing depopulation, economic marginalization, and infrastructure decay. Improving their liveability and attractiveness is essential to reverse these trends and boost sustainable development. In this context, HSTs are potential drivers of circular and sustainable socio-technical systems, where the circular economy (CE) offers a framework for local sustainability. However, HSTs lack adequate sustainable CE implementation tools. This study, the culmination of the H-SMA-CE project, develops a Decision Support System (DSS) to assist local policymakers in planning CE transitions in Italian HSTs. The DSS integrates three building blocks: context analysis (metabolic flows, stakeholder networks), an intervention library with cost–benefit data, and a composite Municipal Circular Economy Index (MCEI). The tool enables users to assess baseline circularity, simulate scenarios, and identify optimal investment portfolios through multi-objective optimization. This approach allows for the simultaneous evaluation of the benefits of each sustainability aspect, i.e., environmental, economic and social. Tested on the municipality of Taurasi (Italy), an HST with a wine-based economy, the results show that balanced intervention strategies yield greater circularity improvements than single-objective approaches. The paper contributes to the discourse on digital tools for sustainability transitions, offering a replicable model for evidence-based CE governance in heritage-rich territorial contexts. Full article

Background: The COVID-19 pandemic has been associated with increased psychological distress globally. However, the independent psychological impact of prior COVID-19 infection remains heterogeneous, particularly in primary healthcare populations. This study aimed to examine differences in anxiety and depressive symptoms between individuals with and without a history of COVID-19 infection in a primary healthcare setting. Methods: A cross-sectional study was conducted in April 2022 in five family medicine practices in the primary health care facility of Sarajevo Canton. A total of 279 participants without previously diagnosed mental disorders completed an online questionnaire. Anxiety and depressive symptoms were assessed using the GAD-7 and PHQ-9 scales. Multivariable regression models were performed, and propensity score matching (1:1 nearest-neighbor matching, caliper = 0.2) was conducted to address baseline imbalance. Results: No statistically significant independent association was detected between prior COVID-19 infection and anxiety or depressive symptoms in multivariable models. Propensity score matching yielded 84 well-balanced pairs. In the matched sample, no significant differences were observed in GAD-7 (p = 0.229) or PHQ-9 scores (p = 0.139), nor in clinically relevant cut-offs. Female sex and chronic disease were independently associated with higher anxiety levels. Conclusions: In this primary healthcare population, we did not observe an independent association between prior COVID-19 infection and anxiety or depressive symptoms after covariate adjustment and propensity score matching. These findings should be interpreted cautiously given the cross-sectional design, possible exposure misclassification, and residual confounding. Full article

Age estimation based on facial images is a challenging task due to the complex and nonlinear nature of facial aging, which is influenced by both genetic and environmental factors. To address this challenge, we propose a hybrid ConvNeXt–Transformer framework that combines convolutional local feature extraction with attention-based global contextual modeling within a unified age regression pipeline. The methodological contribution of this work lies in the sequential integration of these two complementary paradigms for facial age estimation, allowing the model to capture both fine-grained textural cues—such as wrinkles and skin spots—and long-range spatial dependencies. We evaluate the proposed framework on benchmark datasets including MORPH II, CACD, UTKFace, and AFAD. The results show competitive performance across these datasets and confirm the effectiveness of the proposed hybrid design through extensive ablation analyses. Experimental results demonstrate that our approach achieves state-of-the-art MAE on MORPH II (2.26), CACD (4.35), and AFAD (3.09) under the adopted benchmark settings while remaining competitive on UTKFace. To address computational efficiency, we employ ImageNet pre-trained backbones and explore different architectural configurations, including fusion strategies and varying depths of the Transformer module, as well as regularization techniques such as stochastic depth and label smoothing. Ablation studies confirm the contribution of each component, particularly the role of attention mechanisms, in enhancing the model’s sensitivity to age-relevant features. Overall, the proposed hybrid framework provides a robust and accurate solution for facial age estimation, effectively balancing performance and computational cost. Full article

The formulation of rhizobial bioinoculants remains a critical bottleneck for the large-scale deployment of biological nitrogen fixation in sustainable agriculture, mainly due to limitations in the stability and viability of conventional liquid products. In this study, a spray-drying-based process was developed and optimized to produce a stable and functional bioinoculant using Ensifer meliloti Rm8530, an EPS II–producing strain with enhanced stress tolerance. Strain robustness was evaluated through thermal and osmotic stress assays, together with growth performance across relevant temperature and pH ranges. Six carrier-based formulations combining polysaccharides and proteins were then tested under controlled spray-drying conditions. Process performance was assessed in terms of powder recovery, residual moisture, bacterial survival, yield, and storage stability over 16 weeks. The morphological integrity of spray-dried particles and rehydrated cells was analyzed by scanning electron microscopy. The biological functionality of selected formulations was subsequently validated in planta using alfalfa as a host model. Among the formulations tested, a mixed alginate–gum Arabic matrix showed the best overall balance between process efficiency, post-drying viability, long-term stability, and symbiotic performance. Spray-dried cells retained the ability to induce nodulation and support early plant responses under the conditions evaluated. These results demonstrate that spray drying, combined with appropriate strain selection and formulation design, constitutes a viable and scalable platform for producing stable, functional rhizobial bioinoculants. Full article

We propose stateful order-preserving encryption (SOPE), a novel framework designed to realize human-centric data security and privacy, the fundamental values of the Fifth Industrial Revolution. Conventional order-preserving encryption supports efficient queries in cloud databases but fundamentally leaks plaintext distributions, leaving data vulnerable to inference attacks. To mitigate this vulnerability while maintaining query efficiency, SOPE introduces a partition-based dynamic density adjustment mechanism under an honest-but-curious threat model. This mechanism offsets density imbalances between partitions in real time by inserting decoy ciphertexts, thereby limiting the leakage scope to the order of data while obscuring frequency information. Our analysis and empirical evaluations demonstrate that SOPE’s ciphertexts consistently approach a uniform distribution by adaptively compensating for the underlying plaintext distribution through decoy insertion. While the continuous insertion of decoy ciphertexts inevitably incurs additional storage overhead (controlled by a tunable parameter $\lambda$), our evaluations demonstrate practical performance. By striking an optimal balance between efficiency and human privacy rights, SOPE provides a trustworthy infrastructure for secure data utilization. Full article

Postural balance is a foundational component of human motor behavior, yet it remains conceptually ambiguous and methodologically heterogeneous across the clinical, educational, and sport sciences. This narrative review aims to provide an integrative framework that clarifies key concepts (postural control vs. postural balance), synthesizes the main sensorimotor and biomechanical mechanisms underpinning balance, and organizes current assessment approaches and functional implications across populations. Narrative literature synthesis was conducted to integrate evidence covering multisensory integration and sensory reweighting, central neural control (spinal, brainstem, cerebellar, and cortical contributions), neuromuscular and biomechanical strategies (e.g., ankle/hip/stepping), and cognitive influences (e.g., dual-task effects). We further summarize commonly used instrumental outcomes derived from force-platform center-of-pressure metrics and widely adopted clinical and functional balance tests, highlighting their typical applications and limitations across the lifespan including pediatric, general adults, older adults, and athletic populations. This review proposes a closed-loop, systems-based model in which postural balance is conceptualized as an emergent functional outcome arising from distributed postural control processes shaped by task, environmental, and individual constraints. In conclusion, integrating mechanistic understanding with population-specific assessment enhances interpretability and supports more precise, context-sensitive balance evaluation and intervention in both health and performance settings. Full article

Scour has been a topic of significant concern among coastal geotechnical engineers in recent years. The Shields number serves as a crucial parameter for erosion calculations, reflecting the balance between sediment particle conditions and hydrodynamic forces, derived from the mechanics of sediment particle equilibrium. Seepage flow, a common phenomenon driven by pressure in soil, further influences the movement of sediment particles. Building upon the classical three-dimensional two-slope angle erosion model, this study incorporates the vertical seepage force. It comprehensively considers slope angles, sediment response angles, incident current angles, and vertical seepage intensities to adjust the Shields number for sediment particles on slopes. The calculation encompasses both transverse and longitudinal slope configurations. Based on the derived formula and parametric analysis, the study draws the following conclusions: 1. The modified Shields number (${\theta }_{cr}/{\theta }_{cr0}$) decreases non-linearly with the increase of slope angle; 2. ${\theta }_{cr}/{\theta }_{cr0}$ is central and has axial symmetry about 180° incident current angles for transverse and longitudinal slopes, respectively; 3. ${\theta }_{cr}/{\theta }_{cr0}$ increases non-linearly with the increase of soil angle of response; 4. ${\theta }_{cr}/{\theta }_{cr0}$ decreases linearly with the increase of seepage intensity; 5. There exists an approximately zero ${\theta }_{cr}/{\theta }_{cr0}$ area when the response angle approaches the slope angle, and the area increases non-linearly as the seepage intensity becomes greater. Full article

The fungal pathogen Candida albicans coordinated metabolism, organelle homeostasis, and stress responses for adapting to diverse host environments and maintaining virulence. While transcriptional control of these processes has been extensively studied, the contribution of post-transcriptional regulation remains incompletely understood. Here, we identify the P-body component Lsm1 as a critical factor of metabolic adaptation, mitochondrial homeostasis, and pathogenicity in C. albicans. Transcriptomic analysis revealed that loss of Lsm1 causes global transcriptional imbalance, leading to dysfunction of amino acid metabolism, mitochondrial function, endocytic trafficking, and autophagy processes. This dysfunction is accompanied by diminished TORC1 activity. Due to the aberrant TORC1 regulation caused by loss of Lsm1, ATG mRNA stability and autophagy flux was impaired under nutrient-rich condition and nitrogen starvation condition. In this context, the lsm1Δ/Δ cells established an adaptive metabolic and redox state characterized by altered NAD⁺/NADH and NADP⁺/NADPH balance, and enhanced antioxidant capacity. Moreover, the lsm1Δ/Δ cells displayed the defects in hyphal development, biofilm formation, and host cell interaction, and exhibited the attenuated virulence in a murine infection model. Together, our findings revealed that Lsm1-mediated post-transcriptional regulation is associated with the maintenance of amino acid metabolism, mitochondrial function, and TORC1 activity to fungal virulence, revealing a potential therapeutic target for C. albicans infections. Full article

Virtual Learning Environments (VLEs) have become increasingly popular in education, particularly with the rise of remote learning during the COVID-19 pandemic. Assessing student performance in VLEs is challenging, and the accurate prediction of final results is of great interest to educational institutions. Machine learning classification models have been shown to be effective in predicting student performance, but the accuracy of these models depends on the dataset’s size, diversity, quality, and feature type. Class imbalance is a common issue in educational datasets, but there is a lack of research on addressing this problem in predicting student performance. In this paper, we present an experimental design that addresses class imbalance in predicting student performance by using the Synthetic Minority Over-sampling Technique (SMOTE) and Generative Adversarial Network (GAN) technique. We compared the classification performance of seven machine learning models (i.e., Multi-Layer Perceptron (MLP), Decision Trees (DT), Random Forests (RF), Extreme Gradient Boosting (XGBoost), Categorical Boosting (CATBoost), K-Nearest Neighbors (KNN), and Support Vector Classifier (SVC)) using different dataset combinations, and our results show that SMOTE techniques can improve model performance, and GAN models can generate useful simulated data for classification tasks. Among the SMOTE resampling methods, SMOTE NN produced the strongest performance for the RF model, achieving a Region of Convergence (ROC) Area Under the Curve (AUC) of 0.96 and a Type II error rate of 8%. For the generative data experiments, the XGBoost model demonstrated the best performance when trained on the GAN-generated dataset balanced using SMOTE NN, attaining a ROC AUC of 0.97 and a reduced Type II error rate of 3%. These results indicate that the combined use of class balancing techniques and generative synthetic data augmentation can enhance student outcome prediction performance. Full article

Remote sensing (RS) images are often degraded by atmospheric haze, which compromises both visual interpretation and downstream applications. To address this, we introduce CSGL-Former, a novel Cross-Stripes Global–Local Fusion Transformer for RS image dehazing. Our model efficiently captures anisotropic long-range dependencies using cross-stripes attention (CSA) and aggregates hierarchical global semantics via a Multi-Layer Global Aggregation (MLGA) module. In the decoder, global context is adaptively blended with fine-grained local features to restore intricate textures. Finally, inspired by the atmospheric scattering model, a soft reconstruction head restores the clear image by predicting spatially varying affine parameters, strictly preserving content fidelity while effectively removing haze. Trained end-to-end, CSGL-Former demonstrates a compelling balance of accuracy and efficiency. Extensive experiments on the RRSHID and SateHaze1K benchmarks show that our model achieves state-of-the-art or highly competitive performance against representative baselines. Ablation studies further validate the effectiveness of each proposed component. Full article