Search Results (10,381)

In high-speed parachuting, complex turbulent phenomena (i.e., deadly vortices) may cause problems such as parachute inflation delay or even deployment failure. To address these issues, this study develops a high-precision numerical simulation dummy model in which adaptive mesh generation techniques, combined with Euler–Lagrange bidirectional coupling based on a large eddy simulation, are employed to model the multiphase flow field during parachute descent. The key parameters are adjusted, and the numerical model is refined based on wind tunnel experiments and User-Defined Functions. The bidirectional validation of the experimental and simulated data reveals the mechanism of turbulent flow formation and its evolutionary patterns around the parachutist–parachute system for different lateral and descent velocities during the high-speed descent phase. A prediction model based on a multi-information fusion neural network algorithm is further established to address the challenge in special parachuting scenarios whereby vortices in the flow field around the parachutist prevent the parachute from opening. The model integrates the Haar wavelet to extract global low-frequency features that characterize the overall structure and trends, an energy valley optimization algorithm, a convolutional neural network, a bidirectional long short-term memory network, and a self-attention mechanism to achieve one-second-ahead turbulence prediction. With nine physical quantities as inputs and descent velocity as the output indicator, the model has a Root Mean Square Error of 0.085, a Mean Absolute Error of 0.051, and a Mean Absolute Percentage Error of 0.0021. Full article

To address the practical engineering challenges of limited fault samples for high-voltage circuit breaker spring operating mechanisms and the inability of single features to fully reflect equipment status, this paper proposes a small-sample fault diagnosis method based on multi-source feature fusion and Stacking ensemble learning. First, a multi-source sensing system containing MEMS (Micro-Electro-Mechanical System) pressure and travel, coil, and motor current was constructed to achieve comprehensive monitoring of the mechanical and electrical states of a 220 kV circuit breaker; in particular, the introduction of non-invasive MEMS sensors effectively solves the difficulty of capturing static spring fatigue characteristics inherent in traditional methods. Second, a high-dimensional feature space was constructed using Savitzky–Golay filtering and physical feature extraction techniques. To address the characteristics of small-sample data distribution, a two-layer Stacking ensemble learning model based on 5-fold cross-validation was designed. This model utilizes the SVM (Support Vector Machine), RF (Random Forest), and KNN (K-Nearest Neighbors) as base classifiers and Logistic Regression as the meta-learner, achieving an adaptive fusion of the advantages of heterogeneous algorithms. True-type experimental results show that the average diagnostic accuracy of this method under normal conditions and four typical fault conditions reaches 96.1%, which is superior to single base models (the RF was 94.2%). Feature importance analysis further confirms that closing and opening pressures are the most critical features for distinguishing mechanical faults. This study provides effective theoretical basis and technical support for condition-based maintenance of high-voltage circuit breakers under small-sample conditions. Full article

This study proposes a feature-level fusion method that integrates Differential Interferometric Synthetic Aperture Radar (D-InSAR) and Unmanned Aerial Vehicle photogrammetry (UAV-P) for monitoring mining-induced subsidence basin (MSB). The method begins by extracting key subsidence characteristics based on the patterns of coal-mining-related surface displacement; the centimeter-level subsidence boundary is determined from D-InSAR data, while the meter-scale deformation at the subsidence center is derived from UAV-P. These extracted features are then used to invert the parameters of the probability integral method (PIM). The subsidence basin predicted by the inverted parameters serves as a criterion to select the superior dataset between the D-InSAR and UAV-derived results. Finally, the selected subsidence data are fused to generate a composite subsidence map. The proposed method was applied to the 2S201 panel in the Wangjiata Coal Mine using eight Sentinel-1A images and two UAV surveys. The fusion results were evaluated for their regional and overall accuracy against 30 ground control points measured by total station and GPS. The results demonstrate that the fusion method not only accurately extracts large-scale deformations in the mining area, with a maximum subsidence of 2.5 m and a root mean square error (RMSE) of 0.277 m in the subsidence center area, but also precisely identifies the subsidence boundary region with an accuracy of 0.039 m. The fused subsidence basin exhibits an overall accuracy of 0.182 m, which represents a significant improvement of 83.6% and 27.8% over the results obtained using D-InSAR and UAV alone, respectively. This method effectively reconstructs the complete morphology of the mining-induced subsidence basin, confirming its feasibility for practical applications. Full article

Hydraulic systems are pivotal components in safety-critical aerospace and industrial applications, making reliable health monitoring essential. However, traditional data-driven diagnosis methods typically rely on static graph structures that fail to capture evolving sensor correlations during different fault modes. Furthermore, existing grid-based models often struggle to extract multi-resolution features and maintain performance under data-limited conditions. To address these challenges, this paper proposes a novel Dynamic Multi-Scale Graph Neural Network (DMS-GNN) for hydraulic system fault diagnosis. The framework integrates a hierarchical multi-scale feature extraction module to capture diverse fault signatures across different frequency bands. Crucially, a self-attention-based dynamic graph learner is introduced to adaptively infer latent sensor topologies end-to-end, eliminating the reliance on predefined physical connections. Experimental validation on a dedicated electro-hydraulic test bench demonstrates that the proposed DMS-GNN achieves a superior diagnostic accuracy of 98.47%, outperforming state-of-the-art baselines such as GraphSAGE, Static GCN, and GAT. The result confirms the efficacy of combining multi-scale temporal learning with dynamic spatial reasoning for robust multi-sensor fusion diagnosis. Full article

The purpose of this paper is to analyze the media visibility of investments implemented in Wrocław, with a particular focus on the democratization of urban processes through the Wrocław Participatory Budget (WPB) and to study the public perception of these projects within the local information landscape. The paper presents an integrated analytical methodology combining geospatial data from the Spatial Information System of Wrocław (SIP) with textual data from the full corpus of local news articles from Wrocław. A hybrid data processing pipeline was used, including filtering of articles about Wrocław, geoparsing of location names, matching articles to investments using classic Term Frequency-Inverse Document Frequency (TF-IDF) models and embedding in language models such as HerBERT, and sentiment analysis using the XLM-T model. The results reveal strong imbalances in the visibility of WPB projects, that almost 90% of investments were not mentioned even once in the media. Temporal sentiment analysis indicated differences between categories of WPB projects. The results confirm the existence of “media deserts” and “islands of attention,” which leads to information exclusion for specific local communities and marginalized groups. This translates into asymmetry in residents’ knowledge of the real scope of the WPB program. The paper emphasizes the importance of Geographic Information System (GIS) fusion methods with natural language processing models (NLP) for urban research, and identifies directions for further analysis, including accompanying problems and limitations in the present day. Full article

Local Climate Zone (LCZ) classification provides a standardized framework for characterizing urban morphology and its climatic implications. However, most existing remote sensing-based LCZ mapping methods rely on pixel-level classification and multispectral data alone, which limits their ability to capture urban scene heterogeneity and to distinguish structurally similar LCZ classes. In this paper, we propose LCZ-HMSSNet, a deep learning framework for scene-level LCZ classification that integrates PRISMA hyperspectral images with Sentinel-2 multispectral data. The proposed approach exploits both the spectral richness of hyperspectral data and the spatial context provided by multispectral observations, and incorporates a spatial–spectral feature separation mechanism to enhance the discriminability of the fused representations. Experiments conducted across six representative European cities evaluate the proposed method from multiple perspectives, including comparisons with different classification models, data contribution analysis, and structural ablation studies. The results demonstrate that the proposed method consistently outperforms MSI-only and existing LCZ classification approaches, achieving an overall accuracy (OA) of 0.988 and a Kappa of 0.985. In addition, the small-sample experiments indicate the robustness and potential of the proposed model, providing a practical reference for future LCZ mapping in data-scarce scenarios. Full article

Maritime vessel detection in nearshore waters is a fundamental capability for artificial intelligence (AI)-enabled maritime transportation systems, including coastal monitoring, traffic management, and digital maritime services. Although attention mechanisms are widely incorporated into YOLO-based detectors, their relative effectiveness in marine environments under strictly controlled experimental conditions remains insufficiently clarified. This study presents a systematic comparison of Coordinate Attention (CA), Convolutional Block Attention Module (CBAM), and CLIP-based semantic fusion within a unified YOLOv8n framework for binary discrimination between ships and fishing boats in cluttered coastal imagery. All model variants were trained under identical data partitions and optimization settings to isolate architectural effects. The experimental results show that CA achieves the highest localization robustness (mAP@0.5:0.95 = 0.6127) and substantially improves precision (+7.13% over baseline), while CBAM provides the most balanced performance with the highest F1-score. In contrast, CLIP-based semantic fusion consistently degrades detection reliability, indicating limitations of global vision–language representations in small-scale maritime datasets. Precision–Recall and F1 analyses further reveal architecture-specific confidence calibration behaviors relevant to deployment-sensitive maritime applications. The findings provide practical guidance for selecting attention mechanisms in AI-driven maritime perception systems and support reliable AI integration in marine science and engineering applications. Full article

With the increasing adoption of intelligent inspection systems for substation equipment, massive amounts of data are being generated. To address the challenge of balancing detection accuracy and lightweight deployment in current object detection models, this paper proposes YOLOv10-SPD (Substation Power Defect), a high-precision yet lightweight improved model tailored for substation defect detection. Compared to existing methods, the proposed model introduces multiple innovations in structural design and module fusion. (1) A Feature Modulation Module is proposed to significantly enhance the model’s ability to perceive and model defect details. (2) A hybrid module integrating structural information and channel attention is designed to efficiently reconstruct and represent feature maps. (3) A Multi-Scale Context Modeling Module is developed, leveraging shared convolutional kernels to achieve compact expression of multi-scale semantic information. (4) An Efficient Detection Head adopts a hierarchical semantic fusion strategy, further improving recognition accuracy for small and multi-scale targets. (5) A Weight-Magnitude-Based Hierarchical Pruning Strategy is introduced to compress model size and boost inference efficiency while maintaining accuracy. Experiments on a public substation defect dataset demonstrate that the proposed method achieves 94.11% mAP@0.5, outperforming the baseline YOLOv10n by 5.14%, while reducing model parameters by 76.09% and computational costs by 38.82%. The model achieves higher detection accuracy with lower computational overhead, effectively meeting the requirements for efficient and accurate substation defect detection, demonstrating strong practical applicability. Full article

In order to address the challenges of limited accuracy in identifying non-meteorological clutter and the spatial overlap between meteorological and non-meteorological echoes in cloud radar observations under complex weather conditions, in this study, we propose a quality-control method for cloud-radar data, which integrates machine learning with neighborhood filtering, This quality-control method first uses the Light Gradient Boosting Machine (LightGBM) to initially identify clutter, then employs a customized neighborhood filtering module to optimize and eliminate residual isolated clutter. This two-stage framework combines the strengths of accurate machine-learning-based classification and physically motivated filtering optimization, enabling reliable discrimination between meteorological and non-meteorological echoes. Based on multi-region, long-term and multi-model radar baseline observations, which cover typical complex weather types such as snow, fog, rain, low clouds and dust, the refined manual labeling of meteorological and non-meteorological echoes is carried out, combined with multi-source ground observation data such as surface observations, temperature and humidity. Based on this, a feature training dataset for machine learning is constructed, which contains over 20 million samples. A multi-index evaluation system—including echo classification accuracy and non-meteorological clutter rejection rate—is used to quantitatively assess the quality-control performance of the method in different weather scenarios. The results indicate that the proposed method demonstrates stable performance in typical complex weather scenarios, with comprehensive scores of 90.73 (snow), 94.23 (rain), 96.49 (low clouds), 91.10 (fog) and 95.79 (dust) on a 100-point scale. Through typical case studies and statistical data analysis, the proposed algorithm achieves better quality-control scores in comparison with the Random Forest and single LightGBM algorithms. It provides a new technical approach for cloud-radar data quality control and also offers a theoretical basis for the feature selection of machine-learning-based quality-control models, further enhancing the application value of cloud-radar data in refined meteorological observations. Full article

Accurate measurement of robotic pose is indispensable for large-scale precision manufacturing and robotic calibration, particularly because traditional robotic kinematic models often fall short owing to environmental disturbances and structural uncertainties. Laser tracker systems offer high-precision, large-volume measurement capabilities and are therefore appealing as external references for robot pose estimation; however, their practical efficacy is heavily reliant on optical tracking stability, sensor noise levels, and system robustness. This paper introduces a laser tracker-based framework for measuring robot pose, which integrates PSD-based optical spot sensing, multi-sensor fusion, and simulation-based system analysis. A prototype PSD sensing subsystem has been developed utilizing analog signal conditioning, high-speed A/D sampling, and FPGA-based centroid computation. Bench experiments validate the linearity, geometric sensitivity, and robustness of the PSD sensing chain under controlled spot translations and various ambient illumination conditions. Results demonstrate that the PSD response is nearly linear within a ±0.9 mm spot displacement and that the implementation of an interference optical filter significantly enhances measurement repeatability under background light. At the system level, a comprehensive simulation framework is established wherein PSD measurements are fused with inertial and encoder data via an extended Kalman filter. The simulations explore the effects of process noise tuning, time synchronization, systematic error sources, and control strategies on pose estimation accuracy. Ranging-related effects and error-compensation mechanisms are analyzed within the context of modeling and simulation, providing insights into the interferometric ranging principle underlying the complete laser tracker system. The validation of the prototype alongside simulation results demonstrates that PSD-based optical tracking, combined with multi-sensor fusion and layered error compensation, can effectively improve robustness and positional accuracy. The proposed framework offers valuable guidance for the development and phased validation of laser tracker-oriented robot pose measurement systems in complex industrial environments. Full article

Accurate acquisition of low-observable targets with a minimal radar cross-section (RCS) poses a significant challenge for multi-source remote sensing systems, such as integrated radar–electro-optical (REO) platforms, particularly in complex electromagnetic environments characterized by strong noise interference and a high false-alarm rate. Conventional methods, which often treat data association and fusion from heterogeneous sensors as separate, offline processes, struggle with the dynamic uncertainties and real-time decision requirements of such scenarios. To address these limitations, this paper proposes a novel Evidence–Reinforcement Learning-based Decision and Control (ERL-DC) framework. It operates through a closed-loop architecture consisting of three core modules: A static assessment model for initial target prioritization, a Dempster–Shafer (D–S) evidence-based multi-source data decision generator for dynamic information fusion and uncertainty-aware target selection, and a Deep Reinforcement Learning (DRL) controller for noise-robust sensor steering. A high-fidelity simulation environment was developed to model the multi-source data stream, encompassing radar detection with clutter and false targets, as well as the physical constraints of the electro-optical (EO) servo system. Based on the averaged results from multiple Monte Carlo simulations, the proposed ERL-DC framework reduced the Average Decision Time (ADT) from 7.51 s to 4.53 s, corresponding to an absolute reduction of 2.98 s when compared to the conventional method integrating threshold logic with Model Predictive Control (MPC). Furthermore, the Net Discrimination Accuracy (NDA), derived from the statistical outcomes across all the simulation runs, exhibited an absolute increase of 37.8 percentage points, rising from 57.8% to 95.6%. These results indicate that ERL-DC achieves a more favorable trade-off in terms of scheduling efficiency, decision robustness, and resource utilization. The primary contribution is an intelligent, closed-loop architecture that tightly couples high-level evidential reasoning for multi-source data fusion with low-level adaptive control. Within the simulated environment characterized by clutter, false targets, and angular measurement noise, ERL-DC demonstrates improved target discrimination accuracy and decision efficiency compared to conventional methods. Future work will focus on online parameter adaptation and validation on physical platforms. Full article

User behavior anomaly detection plays a vital role in network security for identifying malicious access and abnormal activities in high-dimensional internet user behavior data. Although Transformer architectures have been widely adopted in anomaly detection tasks, and their integration with Variational Autoencoders (VAEs) has often been used to further improve detection accuracy, existing integration methods have failed to effectively balance global feature dependency modeling and generative data distribution learning. This results in limited capability in identifying complex anomalous patterns. To address this issue, this paper proposes DF-TransVAE, a novel deeply integrated framework that advances the integration of a Transformer and a VAE for supervised anomaly detection. The framework first fuses global contextual representations from the Transformer encoder with original input features, then maps the fused representation into the latent space via the VAE encoder. A cross-attention mechanism is introduced as the core of deep integration, enabling dynamic, bidirectional interaction between the fused features and latent variables to enhance information fusion. Lastly, a fully connected classifier equipped with residual connections outputs anomaly probabilities for supervised binary classification. Experimental results on two public datasets demonstrate that the proposed framework achieves better performance than existing deep learning methods in terms of accuracy, precision, recall, and F1-score, particularly in detecting complex anomalous patterns. Our results indicate that the deep integration mechanism we propose effectively addresses the limitations of conventional Transformer–VAE combinations. Full article

In recent years, deep learning-based vulnerability detection has drawn wide attention for its data-driven ability to analyze code semantics and learn vulnerability patterns without predefined models. However, data distribution differences across projects limit model generalization. Transfer learning provides a solution, yet most studies ignore expert-designed metrics. This paper proposes Decpvd, a data-driven cross-project software vulnerability detection method based on a dual-feature stacking ensemble. It builds an adaptive and transferable model using only code and vulnerability label data from source and target projects. It extracts code semantic features via Gated Graph Neural Networks, incorporates expert metrics from tools, performs cross-domain data-driven modeling with TrAdaBoost, and adaptively fuses the two features through stacking, overcoming fixed-weight fusion limitations. Experiments on six cross-project groups from three real datasets (FFmpeg, LibTIFF, LibPNG) show that Decpvd achieves an average AUC of 0.814, significantly outperforming mainstream baselines. Full article

Under practical operating conditions, intelligent fault diagnosis of permanent magnet synchronous motors (PMSMs) is often hindered by the shortage of effective fault samples. To address this issue, this paper proposes a twin-data-driven transfer learning-based diagnostic method for PMSM inter-turn short-circuit faults. First, a finite element model of the motor is established in Ansys to generate inter-turn short-circuit twin data, thereby enriching the source-domain samples. Second, continuous wavelet transform (CWT) is employed to convert stator current signals into multi-scale time–frequency feature maps, which are then fed into a feature extraction network constructed by integrating a residual network (ResNet) into an efficient channel attention mechanism (ECA) to achieve effective fusion of local and global time–frequency features. Finally, a joint loss function combining multi-kernel maximum mean discrepancy (MK-MMD) and a domain-adversarial neural network (DANN) is introduced to align feature distributions and perform adversarial optimization, enhancing cross-domain invariance and improving fault recognition capability. Experimental results demonstrate that the proposed REDM method achieves higher diagnostic accuracy and robustness than several existing intelligent fault diagnosis approaches. Full article

Assessing human embryo quality is a critical step in in vitro fertilization (IVF), yet traditional manual grading remains subjective and physically limited by the shallow depth-of-field in conventional microscopy. This study develops a novel “soft optical sensor” architecture that transforms standard optical microscopy into an automated, high-precision instrument for embryo quality assessment. The proposed system integrates two key computational innovations: (1) a multi-focal image fusion module that reconstructs lost morphological details from Z-stack focal planes, effectively creating a 3D-aware representation from 2D inputs; and (2) a retrieval-augmented generation (RAG) framework coupled with a Swin Transformer to provide both high-accuracy classification and explainable clinical rationales. Validated on a large-scale clinical dataset of 102,308 images (prior to augmentation), the system achieves a diagnostic accuracy of 94.11%. This performance surpasses standard single-plane analysis methods by 9.43%, demonstrating the critical importance of fusing multi-focal data. Furthermore, the RAG module successfully grounds model predictions in standard ESHRE consensus guidelines, generating natural language explanations. The results demonstrate that this soft sensor approach significantly reduces inter-observer variability and offers a robust tool for standardized morphological assessment, though prospective validation against live birth outcomes remains essential for clinical adoption. Full article