Search Results (4,066)

Although Least Squares Support Vector Regression (LSSVR) reduces the hyperparameter space to two, it sacrifices sparsity, causing all training samples to become support vectors and increasing storage costs. In contrast, standard Support Vector Regression (SVR) preserves sparsity but requires tuning three highly coupled hyperparameters, leading to higher computational burden. To address these limitations, this paper proposes a sparse ${\mathcal{L}}_{\infty }$-norm regularized least squares SVR framework that incorporates the infinity norm of approximation errors into both the objective function and inequality constraints. The resulting optimization problem minimizes model complexity while controlling the maximum prediction deviation through a single slack variable, thereby transforming the conventional three-hyperparameter SVR tuning task into a two-parameter problem involving only the regularization coefficient and kernel width. This formulation restores sparsity by enabling a compact support vector set, while preserving the stability and convexity advantages of LSSVR. Experiments on both static and dynamic datasets demonstrate that the proposed method consistently achieves higher predictive accuracy and improved robustness compared with standard SVR and LSSVR. These results indicate that the proposed ${\mathcal{L}}_{\infty }$-norm regularized framework offers a mathematically principled and computationally efficient alternative for sparse, robust, and scalable regression modeling. Full article

This study presents U-Net deep learning of total electron content (TEC) obtained from Global Ionosphere Maps (GIMs) to forecast ionospheric TEC over the African 0–40° N latitude sector during geomagnetic storms which have occurred between 2011 and 2024. Before being utilized in the deep learning procedure, the GIM-TEC data were improved by assimilating ground-based vertical TEC (VTEC) observations from available Global Navigation Satellite System (GNSS) receiver stations. The U-Net one-hour-ahead prediction of TEC was examined during the intense geomagnetic storm of May 2024. Additionally, the model’s accuracy and reliability were evaluated through quantitative comparison with established climatological models, including IRI-2020 and AfriTEC storm time models. The results indicate that the integration of data assimilation with the deep learning framework yields TEC estimates that closely agree with observations, achieving a RMSE of approximately 5 TECU. On the other hand, the IRI-2020 model exhibits substantially larger errors, with RMSE ~10–17 TECU, while the AfriTEC model shows the poorest performance, with RMSE reaching approximately 15–22 TECU. Further, the U-Net was validated using two equatorial and mid-latitude GNSS stations whose data were excluded from the assimilation process, achieving RMSE values of 4.44 and 6.75 TECU and correlation coefficients of 0.93 and 0.97, confirming the model forecasting capability for reproducing ionospheric TEC variability. These results establish the model as a precise, robust tool for TEC prediction in regions with sparse GPS coverage that is crucial for ionospheric monitoring and space weather applications. Full article

Compared with conventional synthetic aperture radar (SAR) three-dimensional (3D) imaging systems, distributed unmanned aerial vehicle (UAV) SAR systems offer enhanced flexibility and single-pass capability, enabling rapid 3D imaging. Their performance, however, critically depends on the spatial arrangement of UAVs. Improper configurations result in grating lobes and increase the sidelobe level, thereby degrading elevation reconstruction. Additionally, the coordinated operation of distributed UAVs imposes spatial constraints such as safety separation. To address these challenges, this paper formulates the configuration design as a multi-constraint, multi-objective optimization problem that simultaneously considers both imaging performance and operational feasibility. Based on compressive sensing (CS) theory, the influence of configuration on sparse imaging is analyzed, and practical constraints are integrated, including 3D span limits, safety separation, and mainlobe avoidance. A joint optimization model is established to minimize the cumulative coherence of the sensing matrix while maximizing system spatial compactness. To efficiently solve this high-dimensional problem, a decoupled recursive strategy is proposed. In the first stage, a hybrid algorithm combining particle swarm optimization (PSO) and covariance matrix adaptation evolution strategy (CMA-ES) performs global optimization in the baseline domain. In the second stage, a compact configuration is constructed within the feasible region via analytical spatial recursion. Experimental results demonstrate that the proposed approach effectively reduces sensing matrix coherence and improves 3D reconstruction quality. Full article

Postprandial plasma amino acid (AA) kinetics serve as essential indicators of digestive efficiency and systemic metabolic status in pigs. Traditional kinetic analysis relies on Non-Linear Least Squares (NLS) regression using compartmental models, yet these methods typically demand repeated blood sampling and precise initialization to ensure convergence. In this study, we developed a Physics-Informed Neural Network (PINN) framework by integrating mechanistic Ordinary Differential Equations (ODEs) directly into the deep learning loss function. The framework was evaluated using a benchmark dataset. Specifically, we performed a retrospective analysis by downsampling the original high-frequency data to simulate dense and sparse sampling strategies. The results demonstrate that while both models exhibit high fidelity under dense sampling, PINN maintains superior robustness and predictive accuracy under data-constrained conditions. Under the sparse sampling scenario, PINN reduced the Root Mean Square Error (RMSE) compared to NLS in key metabolic profiles, such as Methionine in the FAA group (p < 0.01) and Lysine in the HYD group (p < 0.05). Unlike NLS, which is sensitive to initial guesses, PINN successfully utilized physical laws as a regularization term to robustly solve the inverse problem, demonstrating superior parameter identification stability and predictive consistency under data-constrained conditions compared to NLS. We concluded that the PINN framework provides a reliable and consistent alternative for modeling the AA dynamics. In the future, it may be possible to reconstruct highly accurate physiological trajectories under optimized sparse sampling conditions. Full article

Cyberbullying demonstrates notable metaphorical and contextual traits, characterized by a high-dimensional sparse semantic space and dynamic evolution. Pre-trained models utilize extensive textual data for learning and employ transformer-based word vector generation techniques to accurately capture intricate semantics and nuanced syntax in text. However, although a single pre-trained model demonstrates strong performance in contextual modeling, it still faces challenges including inadequate feature representation and limited generalization capability in classifying cyberbullying texts. This study proposes a cyberbullying detection model employing BERT-BiGRU-CNN (BBGC) to address this issue. The BBGC model initially employs BERT to produce word embeddings, subsequently inputs them into a BiGRU layer to acquire sequence features, and finally utilizes a CNN for the extraction of local features. The features derived from BERT, BiGRU, and CNN are integrated, followed by the application of the softmax function to yield the final outcome of cyberbullying detection. Experimental findings indicate that the BBGC fusion model surpasses individual pre-trained models in the task of detecting cyberbullying text. Furthermore, in comparison to hybrid neural network models utilizing RoBERTa, ALBERT, DistilBERT and other pre-trained models, the BBGC model demonstrates considerable advantages. Full article

The application of vibration monitoring integrated with sparse Auto-Encoder (SAE) networks is investigated in this paper with the objective of detecting and localizing structural anomalies or damages. Unlike previous studies on SAE networks, the methodology proposed is based on the definition of a single SAE model, trained with the signals simultaneously collected from several sensors. Once the SAE has been trained using measurements that represent the baseline (undamaged) condition of the structure, the network is likely to reconstruct well newly collected data if the structure maintains its intact condition. When damage or structural degradation processes start developing, an increase in the reconstruction error—defined as the residual between the original input and the reconstructed output—has to be expected, so that a deviation from the normal state is highlighted. Moreover, this rise in reconstruction errors is typically more significant near the damaged areas, allowing for precise localization of the affected zones. The performance and robustness of the proposed approach are illustrated and validated using experimental data from two real-world bridge structures. Full article

Ground-based and space-based gravitational wave (GW) detectors cover complementary frequency bands, laying the foundation for future multi-band collaborative observations. Detecting weak signals within non-stationary noise remains challenging. To address this, we propose a Physics-Guided Dynamic Sparse Attention (PGDSA) framework. The framework introduces a differentiable wavelet layer to explicitly embed sensitive frequency bands and time–frequency priors while utilizing intra-block Top-K sparse attention for efficient long-range temporal modeling. Training is performed on space-based simulation data with joint optimization for signal detection and waveform reconstruction. We then evaluate detection performance and zero-shot transfer capability on ground-based data. Experimental results show that PGDSA achieves an ROC-AUC of 0.886 on the Kaggle G2Net private leaderboard. On GWOSC O3 real data, the model yields high confidence scores for confirmed binary black hole events. On LISA simulation data, the framework achieves detection rates exceeding 99% for multiple signal types (SNR = 50, FAR = 1%) with waveform reconstruction Overlap comparable to baseline methods. These results demonstrate that PGDSA enables unified modeling across both space-based and ground-based scenarios. Full article

Wind gusts pose an increasing threat to sustainable development, damaging resilient infrastructure (SDG 9), disrupting clean energy systems (SDG 7), and endangering community safety (SDG 11). However, the reliability of early warning systems remains limited by systematic biases in Numerical Weather Prediction (NWP) models and insufficient uncertainty quantification, particularly in regions with sparse monitoring networks. To address these challenges in sustainable disaster risk reduction, this study proposes a physics-informed deep learning framework—the Physics-Informed Spatial Attention Network (PISA-Net). The model integrates high-resolution WRF-UPP forecasts as a physical prior within a Transformer-based architecture, enabling effective bias correction and spatial dependency learning under data-sparse conditions. A hybrid probabilistic learning objective is employed to simultaneously improve deterministic gust predictions and provide calibrated uncertainty estimates. Evaluated on 61 extratropical cyclone events in the northeastern United States, PISA-Net substantially outperforms baseline NWP and conventional deep learning models, reducing the mean absolute error and root mean square error to 1.75 m/s and 2.26 m/s, respectively. In addition, the resulting 95% prediction intervals are well calibrated and offer reliable risk-based guidance. By improving both the accuracy and credibility of wind gust forecasts, PISA-Net provides a practical decision-support tool for infrastructure maintenance, wind farm operations, and public safety planning. This work demonstrates the potential of physics-informed deep learning to strengthen sustainable early warning systems in data-sparse regions. Full article

Globally, the swine industry is a major component of agricultural production, and the increasing scale and intensification of pig farming have heightened concerns about NH₃ emissions. As farms expand and adopt smart farming technologies, there is a need for reliable prediction of NH₃ concentrations without relying solely on costly physical sensors. In this study, we developed an artificial intelligence-based prediction model for NH₃ concentration in commercial pig houses and examined the effects of data collection intervals and learning strategies. We compared a standalone model trained only on local data with a transfer learning model that adapts a pre-trained model to a target farm with limited data. Transfer learning consistently outperformed the standalone approach across all data collection intervals (10, 20, 30 and 60 min). The best-performing Random Forest and XGBoost models achieved a coefficient of determination (R²) of 0.969, root mean square error (RMSE) of about 1.0 ppm and mean absolute percentage error (MAPE) below 5%. These results show that transfer learning can provide accurate NH₃ predictions in swine housing even with sparse data, supporting more sustainable and data-efficient environmental management. Full article

The Three-River Connectivity Zone in the lower Tarim River Basin (TRCZ) is a typical area that has experienced decades of river cut-off, followed by artificial ecological water transfers and vegetation restoration. However, the long-term patterns of ecological water requirements and their response mechanisms to ecosystem services in this region remain unclear. This study aims to quantify the spatiotemporal dynamics and driving factors of ecological water requirements in the TRCZ from 1990 to 2020. We integrated multi-temporal remote sensing land cover data with the FAO Penman–Monteith equation to estimate vegetation evapotranspiration (as a proxy for ecological water requirement) and coupled the InVEST model with Random Forest modeling to identify key climatic and hydrological drivers. Unlike previous studies that focused primarily on precipitation inputs, our approach explicitly considers the ecosystem’s water yield function alongside water demand, offering new insights into the constraints on ecosystem services. Key findings reveal: (1) During the period of 2005–2010, the land cover types underwent significant changes, characterized by a marked expansion of sparse forest (14–21%) and a pronounced decline in forest land, which fundamentally reconfigured the ecosystem’s water demand structure. (2) Accordingly, the multi-year average ecological water requirement quota in the study area is 2.95 × 10⁷ m³, and the total ecological water requirement exhibited a fluctuating decline at a rate of −1.39 × 10⁵ m³/yr, yet sparse forest persisted as the dominant water-consuming component. (3) The Random Forest model (R² = 0.942) identified water yield (importance: 0.527) and precipitation (0.255) as the primary drivers, establishing the ecosystem’s water yield function rather than precipitation input alone as the critical constraint. (4) A widespread increase in the unit area ecological water requirement across vegetation types signaled escalating pressures from climate change. This research provides a quantitative framework and a transferable methodology for adaptive water resource management and ecological restoration in arid regions, emphasizing the balance between ecosystem water demand and supply functions. Full article

Background: Axonal misdirection remains a major limitation in peripheral nerve repair. While nerve guidance conduits (NGCs) and nerve scaffolds (NSCs) have advanced structurally, it is unclear whether these designs effectively reduce misdirection compared to autografts (ANGs). This systematic review evaluates the impact of NGC and NSC structural features on axonal dispersion and reinnervation accuracy using retrograde tracing animal models. Methods: A systematic search was performed through Medline (PubMed), Scopus (EBSCOhost), and the Cochrane Library from inception to December 2024. Eligible studies included mammalian in vivo models of peripheral nerve transection repaired by direct coaptation, autografts, or artificial conduits and assessed with retrograde axonal tracing. Data on neurons labeling, innervation accuracy, and histomorphometric parameters were extracted, and misdirection rates were calculated. Risk of bias was assessed using the SYRCLE tool. Due to heterogeneity, data were synthesized narratively following the SWiM framework. Results: Out of 4043 records identified through database searching and 37 through citation searching, 19 studies (49 experimental groups) met the inclusion criteria. Motoneuron counts were consistently reported across all arms, but no outcome assessing axonal misdirection was reported in more than half. Structured designs resulted in outcomes more closely aligned with ANG repair, while unstructured generally underperformed, and certainty of evidence was very low. Discussion: The evidence in this study was limited by high risk of bias, substantial inconsistency across heterogeneous study designs and outcomes, and imprecision from small animal models with sparse outcome measures. Despite the trend for structured designs to improve over basic hollow designs, current evidence does not support any structure as superior. Future research should be more standardized to provide reliable knowledge translational into clinical practice. Full article

Hydrogen embrittlement poses a critical threat to the durability of metallic components in emerging hydrogen energy infrastructure. Reliable fatigue life assessment in hydrogen-rich environments is, however, severely constrained by the high cost and low throughput of high-pressure testing, resulting in characteristically sparse experimental datasets. Conventional empirical fatigue models struggle to capture hydrogen–mechanical coupling effects, while purely data-driven approaches often suffer from severe overfitting under data-scarce conditions. To address this challenge, this study develops a physics-enhanced learning framework that integrates established fracture mechanics principles with machine learning. Using high-strength GS80A steel as a case study, two complementary strategies are introduced. First, a physically augmented input strategy reformulates raw experimental variables into dimensionless physical descriptors derived from the Basquin and Goodman relations, thereby reducing the complexity of the learning space. Second, a physics-regularized ensemble strategy combines deterministic physical predictions with neural network outputs through a dual-pathway inference scheme, ensuring physically admissible behavior during extrapolation. An automated hyperparameter selection module is further employed to establish a robust data-driven baseline. Comparative evaluation against optimized multi-layer perceptron and support vector regression models demonstrates that the proposed framework significantly improves predictive robustness in small-sample regimes. Specifically, the coefficient of determination ($R^2$) exceeds 0.975, with the root mean square error (RMSE) reduced by approximately 70% compared to the pure data-driven baseline. By systematically embedding mechanistic priors into the learning process, the proposed approach provides a reliable and interpretable tool for fatigue assessment of metallic components operating in hydrogen environments. Full article

To accurately characterize the complex coupling and nonlinear interactions between meteorological and oceanic variables in offshore wind power scenarios, this study proposes a novel forecasting model based on a “multi-scale fusion-decomposition-reconstruction-optimization-prediction” framework. This model integrates Variational Modal Decomposition (VMD) with the feature-interaction Informer framework, employing an enhanced Honey Badger Algorithm (HBA) for the collaborative optimization of their key parameters. The enhanced HBA integrates cubic chaotic mapping, random perturbation strategy, elite tangent search, and differential mutation operations to strengthen its global optimization capability and convergence efficiency. The model construction process proceeds as follows: First, sample entropy (SE) is applied to evaluate the entropy values and reconstruct sequences of the modal components obtained from VMD. Subsequently, the dynamic adjustment of the maximum information coefficient (DE-MIC) is employed to select key input variables from multi-source features. Subsequently, the feature interaction-probabilistic sparse attention mechanism (FI-ProbSparse-AM) unique to the feature interaction-based Informer is employed to construct an attention architecture capable of explicitly modeling dependencies among multidimensional variables, thereby effectively capturing the spatiotemporal latent correlations between wind power output and multi-source features. Experiments based on real offshore wind farm data demonstrate that the MAPE values are reduced by approximately 11% compared to existing benchmark models. The proposed method demonstrates significant advantages in both prediction accuracy and stability. Full article

In complex urban traffic scenes, reliable pedestrian trajectory prediction is essential for Automated and Connected Electric Vehicles (ACEVs) and active safety systems. Despite recent progress, many existing approaches still suffer from limited long-term prediction accuracy, redundant temporal features, and high computational cost, which restricts their deployment on vehicles with constrained onboard resources. To address these issues, this paper presents a lightweight trajectory prediction framework named BiTraP-DGF. The model adopts parallel Gated Recurrent Unit (GRU) and Long Short-Term Memory (LSTM) temporal encoders to extract motion information at different time scales, allowing both short-term motion changes and longer-term movement tendencies to be captured from observed trajectories. A conditional variational autoencoder (CVAE) with a bidirectional GRU decoder is further employed to model multimodal uncertainty, where forward prediction is combined with backward goal estimation to guide trajectory generation. In addition, a gated sparse attention mechanism is introduced to suppress irrelevant temporal responses and focus on informative time segments, thereby reducing unnecessary computation. Experimental results on the JAAD dataset show that BiTraP-DGF consistently outperforms the BiTraP-NP baseline. For a prediction horizon of 1.5 s, CADE is reduced by 20.9% and CFDE by 22.8%. These results indicate that the proposed framework achieves a practical balance between prediction accuracy and computational efficiency for autonomous driving applications. Full article

Global Solar Radiation (Rs) is essential for ecological and climatic modeling, yet its spatialization is often hampered by sparse observation networks. Conventional methods demand a well-distributed set of stations with global representativeness—a requirement rarely met in practice. To address this gap, we propose a spatialization method based on environmental similarity and spatial proximity (ES-SP), which integrates the Law of Geographic Similarity and Tobler’s First Law of Geography. Using monthly Rs data from 11 stations in Tropical China (2015), we evaluated ES-SP against Ordinary Kriging (OK) and Local Polynomial Interpolation (LP) through leave-one-out cross-validation (LOOCV), with root mean square error (RMSE), relative RMSE, and mean absolute percentage error (MAPE) as accuracy metrics. Topographic and monthly meteorological covariates were selected dynamically via random forest (RF), and the performance differences among the three methods were tested statistically using the Wilcoxon signed-rank test. Results show that ES-SP outperforms both OK and LP in accuracy and stability, achieving the lowest error metrics in most months—e.g., RMSE as low as 37.23 MJ·m⁻² in December and MAPE as low as 4.34% in August—along with a narrow interquartile range, indicating consistent performance across seasons. Spatially, ES-SP accurately reproduces the coastal–inland gradient during the rainy season (May) and the latitudinal gradient in the dry season (January), whereas OK yields overly smooth distributions that obscure local details, and LP exhibits extreme instability and unrealistic spatial discontinuities. The study demonstrates that the ES-SP method effectively overcomes the reliance on globally representative station samples, providing a robust technical pathway for generating continuous Rs datasets in data-sparse regions such as Tropical China. Further research should focus on extending the geographic scope and refining the covariate set to enhance generalizability. Full article