Search Results (3,377)

Warm-season precipitation over Sichuan, China, is jointly modulated by complex terrain, monsoon water vapor transport, and local convective activities, leading to significant spatiotemporal heterogeneity. However, radar observations over mountainous areas are frequently impaired by terrain blockage, beam shielding, and insufficient network coverage, which cause missing data and spatial discontinuity, thereby restricting the accurate monitoring of precipitation systems. To alleviate these problems, this study develops an Efficient Multi-Scale Attention (EMA) U-Net model integrated with Digital Elevation Model (DEM) information, termed EMA-U-Net-DEM, to retrieve radar composite reflectivity by utilizing multi-channel observations from the Fengyun-4A (FY-4A) Advanced Geostationary Radiation Imager (AGRI). In the experiments, FY-4A AGRI multi-spectral measurements were used as model inputs, while radar composite reflectivity products from the Severe Weather Automatic Nowcasting (SWAN) system were applied as reference labels. The modeling and validation were carried out using warm-season (June–August) datasets over Sichuan Province. The results indicate that the proposed EMA-U-Net-DEM exhibits better performance than the traditional U-Net and several typical attention-based benchmark models. Quantitatively, the model achieves a root mean square error (RMSE) of 6.728 dBZ, a mean absolute error (MAE) of 4.788 dBZ, a coefficient of determination $R^2$ of 0.656, a peak signal-to-noise ratio (PSNR) of 25.243 dB, and a structural similarity index measure (SSIM) of 0.793. Categorical verification further reveals that the model yields the highest critical success indices (CSI) of 0.850, 0.560, and 0.364 in the reflectivity ranges of 0–25 dBZ, 25–45 dBZ, and 45–70 dBZ, respectively, demonstrating its superior ability in characterizing weak precipitation backgrounds, moderate precipitation structures, and intense convective cores. The performance enhancements are mainly attributed to the strengthened multi-scale feature extraction by the EMA module and the effective topographic constraints introduced by DEM data. This study confirms that the fusion of FY-4A multi-spectral observations and topographic information can effectively improve radar composite reflectivity retrieval over complex terrain, providing a feasible solution for precipitation monitoring, quantitative precipitation estimation, and severe weather nowcasting in mountainous regions with limited radar coverage. Full article

This study proposes a multi-source perceptual information fusion method to improve the accuracy and stability of dairy cow behavior monitoring. Existing machine vision approaches are often affected by lighting conditions, occlusion, and complex cowshed environments, while single wearable inertial measurement unit (IMU) devices may confuse similar behaviors such as eating, ruminating, standing, and lying. To address these limitations, a wireless collar was developed to synchronously collect nine-axis IMU data and ultra-wideband (UWB) ranging data in real time. Combined with manual behavioral observations, a dataset covering seven behaviors—eating, ruminating, standing, lying, drinking, sleeping, and lateral trunk contact—was constructed. By integrating neck-motion features extracted from the IMU data with spatial-distance features obtained from the UWB data, an IMU–UWB dual-branch fusion model was developed to automatically classify dairy cow behaviors. The results indicate that the proposed method can effectively reduce confusion among similar behaviors and improve the recognition of behaviors with limited samples. This approach enables more comprehensive assessment of dairy cows’ daily activities and health status, providing technical support for health monitoring, early disease warning, and intelligent dairy farm management. Full article

Multimodal medical image fusion combines anatomical and functional information from different imaging modalities. However, existing methods often struggle to preserve fine anatomical structures while incorporating complementary functional information. To address this problem, we propose TAPGFusion, an anatomy-aware multimodal medical image fusion network. It employs a Multi-Scale Encoder to capture fine local details and broad anatomical structures through parallel convolutions with different receptive fields. A Detail-Enhanced Attention Block further refines the extracted features through channel, spatial, and pixel attention. In addition, a Physiological Prior-Guided Attention Block dynamically balances anatomical and functional features using MRI-conditioned prior information and edge constraints. The main contribution of TAPGFusion is a unified framework that jointly addresses multi-scale feature representation, fine-grained feature selection, and spatially adaptive anatomical–functional fusion. Extensive experiments on three public medical imaging datasets demonstrate the effectiveness and robustness of the proposed method. TAPGFusion achieves CC values above 0.83 and SSIM values above 0.78 on the CT–MRI, PET–MRI, and SPECT–MRI fusion tasks. These results indicate that the proposed method effectively preserves anatomical structures while integrating complementary functional information. Full article

Timely and accurate termite detection is essential for effective termite control. To address the challenges posed by the small size of termite individuals and the susceptibility of target features to background texture interference under complex backgrounds, this study proposes ESD-YOLO, a fine-grained feature-enhanced object detection model. Using YOLO11n as the baseline, ESD-YOLO redesigns the feature extraction, deep feature aggregation, and multi-scale feature fusion stages to improve the representation of small-scale termite targets under complex backgrounds. Specifically, the Efficient Multi-scale Attention (EMA) mechanism is incorporated into the C3k2 module to enhance feature discriminability between termite individuals and the background. A Spatial Pyramid Pooling-Fast with Dual Global Pooling (SPPF-DGP) module is employed to supplement deep features with global contextual information and salient response information. In addition, the DySample dynamic upsampling module is introduced to improve spatial alignment during multi-scale feature fusion and enhance boundary representation for small targets. Experimental results show that ESD-YOLO achieves Precision, Recall, mAP@0.5, and mAP@0.5:0.95 values of 95.39%, 96.33%, 97.85%, and 65.92%, respectively, with 2.67 M parameters and 6.68 G FLOPs. Compared with Faster R-CNN, RetinaNet, RT-DETR, and several YOLO-series models, ESD-YOLO demonstrates strong small-target detection and localization performance under the controlled complex-background conditions established in this study, providing a methodological reference for automated termite detection in practical settings. Full article

Low-altitude UAV aerial imagery often has complex backgrounds with densely distributed small objects, posing challenges to accurate small-object detection. To address these problems, we propose a spatial–frequency response aware synergistic network for small-object detection in low-altitude UAV aerial imagery. A Frequency-Response-Aware Enhancement Module (FRAEM) is designed to effectively extract discriminative features. The module employs a deterministic stage-aware filtering strategy: Scharr-based edge-sensitive filtering is used in the shallow stage, whereas Gaussian smoothing is used in deeper stages, enabling complementary enhancement of hierarchical representations. A Detail Feature Fusion module (DFFusion) is then developed to improve the efficiency of multi-scale feature fusion. The existing Content-Aware Reassembly of Features (CARAFE) operator is employed for content-aware upsampling and feature alignment, after which DFFusion uses learnable scalar weighting to integrate high-resolution detail information with low-resolution contextual information. A Lightweight Adaptive Decoupled Head (LADH) is also designed to reduce complexity. LADH asymmetrically allocates computational capacity across the prediction tasks: the confidence branch retains stronger spatial processing, whereas the classification and regression branches use lightweight projections; depthwise separable convolution serves as an efficiency-oriented implementation choice. Experiments on the VisDrone2019 and DOTA-v2.0 datasets demonstrate that the proposed method can achieve balance between detection performance and model complexity over mainstream detection methods. Ablation experiments also prove the effectiveness of the proposed components. Full article

Hyperspectral anomaly detection aims to find abnormal targets without prior information. However, the high dimensionality of hyperspectral data, complicated spatial structures, and varying object scales make it challenging to jointly utilize spectral and spatial information. Therefore, anomalies may be confused with background regions. A Balanced Spectral–Spatial Cross-Fusion Network (BSCF-Net) is proposed for hyperspectral anomaly detection. The network uses a multi-branch encoder, where spatial branches capture features with different receptive fields and spectral branches extract spectral patterns through one-dimensional convolutions and channel attention. The Bidirectional Spectral–Spatial Cross-Attention (BSCA) mechanism enables information exchange between spectral and spatial features. The Multi-Scale Gated Refiner (MSGR) module is used to refine the fused features. With an autoencoder reconstruction framework, BSCF-Net identifies anomalies according to reconstruction errors and reduces background interference. Experimental results on five public hyperspectral datasets demonstrate the effectiveness of BSCF-Net, achieving competitive AUC performance under diverse background conditions. Full article

Medical image resolution plays a crucial role in early disease detection and fine-structure observation. Super-resolution reconstruction technology can restore low-resolution images to high-resolution versions, thereby assisting physicians in making accurate diagnoses. To address challenges in medical image super-resolution reconstruction, including insufficient global information acquisition, excessive network complexity, and suboptimal loss function adaptation for medical imaging data, this paper proposes an image super-resolution reconstruction algorithm named IDCASR-MMF based on improved dilated convolution and multi-module fusion. First, multi-dilation-rate dilated convolution is introduced to expand the receptive field and integrated with a spatial attention mechanism to dynamically calibrate high-frequency features after feature extraction. Subsequently, the Squeeze-and-Excitation module is fused with dilated convolution as a channel attention mechanism to streamline the network architecture. Finally, a weighted fusion strategy combining adversarial loss and MSE loss is adopted, where the dynamic adjustment of weighting coefficients balances pixel-level structural accuracy and high-frequency detail authenticity, achieving synergistic optimization of objective precision and subjective quality for medical images. To validate the effectiveness of the proposed algorithm, IDCASR-MMF is compared with 11 state-of-the-art methods across five datasets (Set5, Set14, BSD100, Urban100, and Bone FD). Experimental results demonstrate that the proposed algorithm achieves superior PSNR and SSIM values on multiple datasets, confirming that IDCASR-MMF can effectively reconstruct high-resolution medical images from low-resolution inputs. Full article

Boundary-layer atmospheric stability, wind-shear variability, and thermodynamic forcing are all important factors for the initiation, intensification, and transport of dust storms. But there is limited knowledge of the quantitative evaluation of bulk-layer atmospheric stability and the relation between wind-driven dust dynamics and atmospheric stability in arid and semi-arid regions. In this research, a hybrid AI–meteorology framework, HyMet-Fusion, is presented that combines visual information derived from satellite observations with physics-based indicators of atmospheric stability to evaluate atmospheric stability during dust storm events over Iraq. The proposed framework is based on the use of deep features extracted from the satellite imagery through a frozen EfficientNetB0 backbone, combined with indicators derived from the ERA5 pressure level data for the atmosphere, such as the Bulk Richardson Number (Bulk Ri), the Wind Shear (WS) and the Dry Air Index (DAI). The two branches were merged using a late fusion (0.75 physics/0.25 image) and each hour was classified into three atmospheric stability conditions: Relatively Stable, Moderately Unstable and Unstable. The overall hourly accuracy using a Leave-One-Event-Out (LOEO) cross-validation scheme, where each dust event was used for independent testing and no dust event was used for training, was 72.4%, with 81.2% accuracy for the dominant stability state and 92.2% correct assessment of the unstable condition time for the severe dust events. Inaccuracies were mainly (66%) in the conservative direction (more instability). Unstable atmospheric conditions were also found to be associated with all severe dust storms and coincided with higher wind shear, lower Bulk Ri values and higher thermodynamic variability. Moderate and light dust events were primarily associated with transitional and relatively stable atmospheric conditions, and differed between the various regions, primarily in Kirkuk and Nasiriyah. Correlation analysis showed that wind shear had the highest correlation with atmospheric instability (r = 0.92), followed by DAI (r = 0.90) and Bulk Ri (r = −0.75). In addition, the wind shear also increased significantly from light to severe dust events at all stations investigated, showing that wind shear is a critical factor for turbulent mixing, vertical momentum exchange and dust uplift processes. The results suggest wind shear is the leading dynamics mechanism for bulk-layer instability in Iraqi dust storms. The findings highlight the complementary benefit of using physics-based atmospheric indicators embedded with deep learning satellite image analysis. The HyMet-Fusion system can be used as a transferable method for observing wind-driven instability of the atmosphere and related dust hazards, which could be employed in boundary-layer meteorology, air-quality forecasting, aviation safety and environmental risk assessment in arid and semi-arid areas. Full article

Multi-modal 3D object detection is an important task in autonomous driving systems, where cameras and LiDAR provide complementary semantic and geometric information. Most existing BEV fusion methods are designed based on the Cartesian representation space, which does not fully match the sensing geometry of camera and LiDAR. This generally leads to redundant computation in distant regions. To address this issue, GARF, a geometry-aware polar BEV framework, is presented for multi-modal 3D object detection. GARF organizes camera and LiDAR features in a unified polar BEV space, which can represent spatial resolution more compactly. For the camera branch, the uncertainty-guided transformation of the polar view is designed to improve the reliability of depth estimation. Then, the generated polar BEV feature is further refined to attenuate radial noise and angular discontinuity. For the LiDAR branch, the polar-aware sparse feature extraction and distortion correction modules are designed to deal with the anisotropic structure and geometric distortion caused by polar voxelization. For multi-modal fusion, the region-aware cross-modal fusion strategy and polar detection head with anisotropic Gaussian center response map are developed, which achieve effective feature interaction and consistent geometry supervision. The experimental results on nuScenes show that GARF achieves 71.8% mAP and 73.7% NDS, improving the baseline by 3.3% mAP and 2.3% NDS. Meanwhile, the inference speed increases from 7.1 FPS to 8.9 FPS, and the consumption of GPU memory decreases from 41,114 MiB to 33,346 MiB. Full article

Reliable operating-state recognition of gas pressure regulators is essential for pressure stability, operational safety, and supply continuity in urban natural gas distribution networks. However, SCADA pressure–flow signals from regulating stations are often affected by non-stationary noise, impulsive disturbances, limited fault-state samples, and short-window temporal fluctuations, which reduce the reliability of data-driven recognition. To address these issues, this study proposes K²-TLNet, a noise-state-guided fault-state recognition framework for gas pressure regulation processes. The framework integrates adaptive Kalman filtering, training-only KMeans-SMOTE, parallel temporal convolutional network–long short-term memory feature extraction, and a Noise-Aware Gated Fusion mechanism. Adaptive Kalman filtering is used to generate denoised pressure–flow sequences and extract innovation-residual-based noise descriptors. These descriptors guide the fusion module to adaptively balance local transient features from the temporal convolutional network and contextual temporal features from long short-term memory. A field-SCADA-background-based semi-synthetic dataset was constructed using real operating records and mechanism-informed fault-state emulation rules. Experimental results demonstrate that K²-TLNet achieves 98.50% accuracy and 98.20% Macro-F1, while maintaining strong robustness under Gaussian and impulsive noise disturbances. Full article

Background: Major depressive disorder (MDD) affects 332 million people worldwide, yet diagnosis remains reliant on subjective clinical interviews with substantial inter-rater variability. Objective neuroimaging model-attributed regions offer a path toward precision psychiatry, but existing computational approaches often lack clinical interpretability. Methods: We propose HDGNN-Mamba2, a Mamba-based spatiotemporal heterogeneous dynamic graph neural network. A hybrid Mamba2-GNN block with cross-attention fusion is developed to capture individual spatiotemporal contextual features and identify model-attributed regions. A heterogeneous global graph block with dynamic edge updating is constructed, integrating individual brain features with non-imaging phenotypic information (sex, age, education) to extract embeddings through inter-individual relationship modeling. Heterogeneous Graph Supervised Contrastive Learning is integrated to enhance discriminative capacity. Results: Evaluated on 533 subjects from the REST-meta-MDD dataset, HDGNN-Mamba2 achieved 83.88% accuracy, 86.52% sensitivity, and 80.85% specificity in ten-fold cross-validation. The identified model-attributed regions include the anterior cingulate cortex, parahippocampal gyrus, and thalamus. Conclusions: HDGNN-Mamba2 demonstrates competitive performance as an algorithmic framework for MDD classification, offering complementary architectural advantages in spatiotemporal fusion and interpretable region identification. Full article

Early identification of COVID-19 patients requiring intensive care is critical for improving treatment prioritization, supporting clinical decision-making, and managing limited hospital resources. While structured electronic health record (EHR) data provide important physiological information, chest computed tomography (CT) imaging contains additional indicators related to disease severity. This study presents a multimodal clinical decision support framework for a multimodal risk prediction framework for severe COVID-19 outcomes using structured emergency clinical features and patient-level CT imaging from the COVID Data for Shared Learning (CDSL) dataset. After multimodal cohort construction, 784 patients with both structured clinical records and CT imaging were included in the analysis. Three predictive settings were evaluated: EHR-only prediction using Gradient Boosting, CT-only prediction using ResNet50-based feature extraction with Logistic Regression, and multimodal prediction using weighted late fusion. The experimental results indicate that the CT-based model surpassed the clinical baseline, yielding an F1-score of 0.42 and an ROC-AUC of 0.772, whereas the EHR-only model achieved scores of 0.30 and 0.715, respectively. Overall, the multimodal fusion framework achieved the strongest results among the approaches tested, reaching an F1-score of 0.47 and an ROC-AUC of 0.782. Taken together, these findings indicate that, although CT imaging alone carries meaningful predictive power for evaluating ICU risk, combining it with clinical data leads to predictions that are more reliable and robust. The proposed framework offers a practical and interpretable foundation for multimodal clinical decision support and demonstrates the potential of combining structured clinical data with medical imaging for intelligent critical care applications. Full article

Benefiting from information complementarity, the fusion of hyperspectral imagery (HSI) and light detection and ranging (LiDAR) data for land cover classification has attracted significant attention in the remote sensing community. However, due to modality imbalance and information redundancy, effectively extracting and integrating complementary knowledge from HSI and LiDAR data remains a major challenge. To address the aforementioned issues, a class semantic prototype guided fusion network (CSPGFNet) is proposed to realize efficient and accurate classification by task-relevant feature mining, fusion, and interaction. Specifically, feature extraction sub-networks with multi-scale and multi-type convolutional structures are designed for each modality to mitigate semantic imbalance caused by inherent dimensional discrepancies. Moreover, a feature fusion-interaction module based on cross-attention mechanism is designed to fuse and interact task-relevant spatial–spectral and elevation information from modalities with class semantic prototype (CSP) as the bridge. Furthermore, a composite loss that incorporates multi-factor constraints is optimized to ensure information complementarity, semantic consistency and task relevance of the whole network. Experimental evaluations on three benchmark datasets demonstrate the effectiveness of the proposed method. Full article

Coal–rock cutting state recognition is essential for adaptive cutting and intelligent speed regulation in shearers. To address the limited representational capability of individual signals, the confusion between adjacent gangue-bearing cutting conditions, and the domain discrepancy between simulation and experimental data, a vibration–current multimodal fusion method based on CORRECT-Net is proposed. First, an EDEM–RecurDyn–MATLAB/Simulink co-simulation system was developed to generate cutting records for four coal–rock states. After screening for physical equivalence and label conflicts, 158 valid records were retained and grouped into 150 physical-condition groups, which were partitioned at the group level into training, validation, and test sets. Subsequently, SincNet was employed to extract frequency-band-constrained features, a Transformer was used to model long-range temporal dependencies, and a residual importance-guided GATv2 module was introduced to perform cross-modal fusion of vibration-impact and current-load features. On 2500 test windows, CORRECT-Net achieved an accuracy of 96.20% ± 0.11%, a macro-F1 score of 95.14% ± 0.21%, and a hazardous-condition miss rate of 0.58% ± 0.13%. Compared with the multimodal 1D-CNN, TCN, and Bi-LSTM models, CORRECT-Net improved the accuracy by 8.80, 4.00, and 2.08 percentage points, respectively. In the progressive ablation study, the accuracy increased from 87.40% ± 0.26% to 96.20% ± 0.11%, while the macro-F1 score increased from 84.57% ± 0.34% to 95.14% ± 0.21%. Under Gaussian noise with a standard deviation of 0.05, the model retained an accuracy of 92.76% ± 0.24%. When the vibration and current modalities were separately unavailable, the corresponding accuracies were 86.56% ± 0.37% and 92.44% ± 0.25%, respectively. A five-fold simulation-to-experiment transfer evaluation was further conducted at the independent-run level using five experimental records per class. Without adaptation using experimental samples, the model achieved an accuracy of 91.33% ± 5.19%. When 20% and 50% of the experimental windows were used for adaptation, the accuracy increased to 96.33% ± 0.75% and 98.67% ± 1.39%, respectively. These results demonstrate that CORRECT-Net effectively integrates mechanical vibration responses and motor-load information and, under the present simulation and experimental conditions, achieves high recognition accuracy, a low hazardous-condition miss rate, and effective adaptability to the experimental domain. Full article

Underground cables are critical infrastructure for electrical power and communication transmission, and their reliable operation is of paramount importance to urban public safety. Although Distributed Acoustic Sensing (DAS) enables wide-range, continuous, and real-time monitoring, traditional DAS signal processing methods suffer from poor intrusion discrimination and weak anti-interference capability. To address these limitations, we propose a dual-branch network based on multi-domain feature fusion, integrating a Multilayer Perceptron, a Long Short-Term Memory network (LSTM), and an attention mechanism. Vibration signals corresponding to four representative high-risk intrusion events were acquired through controlled field experiments, and a standardized, category-balanced dataset was constructed accordingly. Time-domain, frequency-domain and joint time-frequency features were extracted and mapped through a time-frequency weighting transformation to form one branch of the network, while the parallel branch employed an LSTM to capture long-range temporal dependencies. A multi-head attention mechanism enables deep adaptive fusion of two types of modal information and overcomes the limitations of conventional simple feature concatenation. Comparative experiments against KNN, 1D-CNN and LSTM baselines demonstrate that the proposed model achieves a test accuracy of 98.89%, outperforming all reference methods. Ablation studies further validate the necessity and effectiveness of each constituent module within the proposed architecture. The results indicate that this approach provides reliable support for DAS-based online monitoring of power cables against external damage. Full article