Search Results (616)

Geophysical forward modeling serves as a fundamental theoretical approach for characterizing subsurface structures and material properties, essentially involving the computation of gravity responses at surface or spatial observation points based on a predefined density distribution. With the rapid development of data-driven techniques such as deep learning in geophysical inversion, forward algorithms are facing increasing demands in terms of computational scale, observable types, and efficiency. To address these challenges, this study develops an efficient forward modeling method based on voxel discretization, the enabling rapid calculation of gravity anomalies and radial gravity gradients on multiple observational surfaces. Leveraging the parallel computing capabilities of graphics processing units (GPU), together with tensor acceleration, Compute Unified Device Architecture (CUDA) execution, and Just-in-time (JIT) compilation strategies, the method achieves high efficiency and automation in the forward computation process. Numerical experiments conducted on several typical theoretical models demonstrate the convergence and stability of the calculated results, indicating that the proposed method significantly reduces computation time while maintaining accuracy, thus being well-suited for large-scale 3D modeling and fast batch simulation tasks. This research can efficiently generate forward datasets with multi-view and multi-metric characteristics, providing solid data support and a scalable computational platform for deep-learning-based geophysical inversion studies. Full article

Background: Chest X-ray (CXR) is widely used for the assessment of thoracic diseases, yet automated multi-label interpretation remains challenging due to subtle visual patterns, overlapping anatomical structures, and frequent co-occurrence of abnormalities. While recent deep learning models have shown strong performance, limitations in interpretability, anatomical awareness, and robustness continue to hinder their clinical adoption. Methods: The proposed framework employs a hybrid ConvNeXtV2–Vision Transformer (ViT) architecture that combines convolutional feature extraction for capturing fine-grained local patterns with transformer-based global reasoning to model long-range contextual dependencies. The model is trained exclusively using image-level annotations. In addition to classification, three complementary post hoc components are integrated to enhance model trust and interpretability. A segmentation-aware Gradient-weighted class activation mapping (Grad-CAM) module leverages CheXmask lung and heart segmentations to highlight anatomically relevant regions and quantify predictive evidence inside and outside the lungs. An ontology-driven neuro-symbolic reasoning layer translates Grad-CAM activations into structured, rule-based explanations aligned with clinical concepts such as “basal effusion” and “enlarged cardiac silhouette”. Furthermore, a lightweight out-of-distribution (OOD) detection module based on confidence scores, energy scores, and Mahalanobis distance scores is employed to identify inputs that deviate from the training distribution. Results: On the VinBigData test set, the model achieved a macro-AUROC of 0.9525 and a Micro AUROC of 0.9777 when trained solely with image-level annotations. External evaluation further demonstrated strong generalisation, yielding macro-AUROC scores of 0.9106 on NIH ChestXray14 and 0.8487 on CheXpert (frontal views). Both Grad-CAM visualisations and ontology-based reasoning remained coherent on unseen data, while the OOD module successfully flagged non-thoracic images. Conclusions: Overall, the proposed approach demonstrates that hybrid convolutional neural network (CNN)–vision transformer (ViT) architectures, combined with anatomy-aware explainability and symbolic reasoning, can support automated chest X-ray diagnosis in a manner that is accurate, transparent, and safety-aware. Full article

Non-obstructive azoospermia (NOA) is a severe male infertility condition characterized by extremely low or absent sperm production. In microdissection testicular sperm extraction (Micro-TESE) procedures for NOA, embryologists must manually search through testicular tissue under a microscope for rare sperm, a process that can take 1.8–7.5 h and impose significant fatigue and burden. This paper presents an augmented reality (AR) microscope system with AI-based image analysis to accelerate sperm retrieval in Micro-TESE. The proposed system integrates a deep learning model (YOLOv5) for real-time sperm detection in microscope images, a multi-object tracker (DeepSORT) for continuous sperm tracking, and a velocity calculation module for sperm motility analysis. Detected sperm positions and motility metrics are overlaid in the microscope’s eyepiece view via a microdisplay, providing immediate visual guidance to the embryologist. In experiments on seminiferous tubule sample images, the YOLOv5 model achieved a precision of 0.81 and recall of 0.52, outperforming previous classical methods in accuracy and speed. The AR interface allowed an operator to find sperm faster, roughly doubling the sperm detection rate (66.9% vs. 30.8%). These results demonstrate that the AR microscope system can significantly aid embryologists by highlighting sperm in real time and potentially shorten Micro-TESE procedure times. This application of AR and AI in sperm retrieval shows promise for improving outcomes in assisted reproductive technology. Full article

Accurate assessment of rice resistance to Sogatella furcifera (Horváth) is essential for breeding insect-resistant cultivars. Traditional assessment methods rely on manual scoring of damage severity, which is subjective and inefficient. To overcome these limitations, this study proposes an automated resistance evaluation approach based on multi-view 3D reconstruction and deep learning–based point cloud segmentation. Multi-view videos of rice materials with different resistance levels were collected over time and processed using Structure from Motion (SfM) and Multi-View Stereo (MVS) to reconstruct high-quality 3D point clouds. A well-annotated “3D Rice WBPH Damage” dataset comprising 174 samples (15 rice materials, three replicates each, 45 pots) was established, where each sample corresponds to a reconstructed 3D point cloud from a video sequence. A comparative study of various point cloud semantic segmentation models, including PointNet, PointNet++, ShellNet, and PointCNN, revealed that the PointNet++ (MSG) model, which employs a Multi-Scale Grouping strategy, demonstrated the best performance in segmenting complex damage symptoms. To further accurately quantify the severity of damage, an adaptive point cloud dimensionality reduction method was proposed, which effectively mitigates the interference of leaf shrinkage on damage assessment. Experimental results demonstrated a strong correlation (R² = 0.95) between automated and manual evaluations, achieving accuracies of 86.67% and 93.33% at the sample and material levels, respectively. This work provides an objective, efficient, and scalable solution for evaluating rice resistance to S. furcifera, offering promising applications in crop resistance breeding. Full article

In intelligent construction and BIM–Reality integration applications, high-quality, large-scale construction scene point cloud data with component-level semantic annotations constitute a fundamental basis for three-dimensional semantic understanding and automated analysis. However, point clouds acquired from real construction sites commonly suffer from high labeling costs, severe occlusion, and unstable data distributions. Existing public datasets remain insufficient in terms of scale, component coverage, and annotation consistency, limiting their suitability for data-driven approaches. To address these challenges, this paper constructs and releases a BIM-derived synthetic construction scene point cloud dataset, termed the Synthetic Point Cloud (SPC), targeting component-level point cloud semantic segmentation and related research tasks.The dataset is generated from publicly available BIM models through physics-based virtual LiDAR scanning, producing multi-view and multi-density three-dimensional point clouds while automatically inheriting component-level semantic labels from BIM without any manual intervention. The SPC dataset comprises 132 virtual scanning scenes, with an overall scale of approximately $8.75\times {10}^9$ points, covering typical construction components such as walls, columns, beams, and slabs. By systematically configuring scanning viewpoints, sampling densities, and occlusion conditions, the dataset introduces rich geometric and spatial distribution diversity. This paper presents a comprehensive description of the SPC data generation pipeline, semantic mapping strategy, virtual scanning configurations, and data organization scheme, followed by statistical analysis and technical validation in terms of point cloud scale evolution, spatial coverage characteristics, and component-wise semantic distributions. Furthermore, baseline experiments on component-level point cloud semantic segmentation are provided. The results demonstrate that models trained solely on the SPC dataset can achieve stable and engineering-meaningful component-level predictions on real construction point clouds, validating the dataset’s usability in virtual-to-real research scenarios. As a scalable and reproducible BIM-derived point cloud resource, the SPC dataset offers a unified data foundation and experimental support for research on construction scene point cloud semantic segmentation, virtual-to-real transfer learning, scan-to-BIM updating, and intelligent construction monitoring. Full article

To address the challenge of bearing load monitoring in elastically supported marine shafting systems, a multi-data fusion-based prediction model is constructed. In view of the small-sample nature of measured bearing load data, transfer learning is adopted to migrate the physical relationships embedded in finite element simulations to the measurement domain. A limited number of actual samples are used to correct the simulation data, forming a high-fidelity hybrid training set. The system—supported by air-spring isolators mounted on the raft—is divided into multiple sub-regions according to their spatial layout, establishing local mappings from air-spring pressure variations to bearing load increments to reduce model complexity. On this basis, a Stacking ensemble learning framework is further incorporated into the prediction model to integrate multi-source information such as air-spring pressure and raft strain, thereby enriching the model’s information acquisition and improving prediction accuracy. Experimental results show that the proposed transfer learning-based multi-sub-region bearing load prediction model performs significantly better than the full-parameter input model. Furthermore, the strain-enhanced Stacking-based multi-data fusion bearing load prediction model improves the characterization of shafting features and reduces the maximum prediction error. The proposed multi-data fusion modeling strategy offers a viable approach for condition monitoring and intelligent maintenance of marine shafting systems. Full article

Power-equipment fault detection is challenging in real-world inspections due to subtle defect cues and cluttered backgrounds. This paper proposes an improved YOLOv12-based framework for multi-class power defect detection. We introduce a Prior-Guided Region Attention (PG-RA) module and design a Lightweight Residual Efficient Layer Aggregation Network (LR-RELAN). In addition, we develop a Dual-Spectrum Adaptive Fusion Loss (DSAF Loss) function to jointly improve classification confidence and bounding box regression consistency, enabling more robust learning under complex scenes. To support defect-oriented visual analytics and system interpretability, the framework further constructs Region of Interest (ROI) pseudo point clouds from detection outputs and compares two denoising strategies, Statistical Outlier Removal (SOR) and Radius Outlier Removal (ROR). A Python-based graphical prototype integrates image import, defect detection, ROI pseudo point cloud construction, denoising, 3D visualization, and result archiving into a unified workflow. Experimental results demonstrate that the proposed method improves detection accuracy and robustness while maintaining real-time performance, and the ROI pseudo point cloud module provides an intuitive auxiliary view for defect-structure inspection in practical applications. Full article

Three-dimensional visual grounding is a core technology that identifies specific objects within complex 3D scenes based on natural language instructions, enhancing human–machine interactions in robotics and augmented reality domains. Traditional approaches have focused on supervised learning, which relies on annotated data; however, zero-shot methodologies are emerging due to the high costs of data construction and limitations in generalization. SeeGround achieves state-of-the-art performance by integrating 2D rendered images and spatial text descriptions. Nevertheless, SeeGround exhibits vulnerabilities in clearly discerning relative depth relationships owing to its implicit depth representations in 2D views. This study proposes the relational depth text (RDT) technique to overcome these limitations, utilizing a Monocular Depth Estimation model to extract depth maps from rendered 2D images and applying the K-Nearest Neighbors algorithm to convert inter-object relative depth relations into natural language descriptions, thereby incorporating them into Vision–Language Model (VLM) prompts. This method distinguishes itself by augmenting spatial reasoning capabilities while preserving SeeGround’s existing pipeline, demonstrating a 3.54% improvement in the Acc@0.25 metric on the Nr3D dataset in a 7B VLM environment that is approximately 10.3 times lighter than the original model, along with a 6.74% increase in Unique cases on the ScanRefer dataset, albeit with a 1.70% decline in Multiple cases. The proposed technique enhances the robustness of grounding through viewpoint anchoring and candidate discrimination in complex query scenarios, and is expected to improve efficiency in practical applications through future multi-view fusion and conditional execution optimizations. Full article

Collaborative sensing between low-altitude remote sensing and ground-based mobile mapping lays the theoretical foundation for multi-platform 3D data fusion. However, point clouds collected from Airborne Laser Scanners (ALSs) remain scarce due to high acquisition and annotation costs. In contrast, while autonomous driving datasets are more accessible, dense annotation remains a significant bottleneck. To address this, we propose Ground to Altitude (GTA), a weakly supervised domain generalization (DG) framework. GTA leverages sparse autonomous driving data to learn robust representations, enabling reliable segmentation on airborne point clouds under zero-label conditions. Specifically, we tackle cross-platform discrepancies through progressive domain-aware augmentation (PDA) and cross-scale semantic alignment (CSA). For PDA, we design a distance-guided dynamic upsampling strategy to approximate airborne point density and a cross-view augmentation scheme to model viewpoint variations. For CSA, we impose cross-domain feature consistency and contrastive regularization to enhance robustness against perturbations. A progressive training pipeline is further employed to maximize the utility of limited annotations and abundant unlabeled data. Our study reveals the limitations of existing DG methods in cross-platform scenarios. Extensive experiments demonstrate that GTA achieves state-of-the-art (SOTA) performance. Notably, under the challenging 0.1% supervision setting, our method achieves a 6.36% improvement in mIoU over the baseline on the SemanticKITTI → DALES benchmark, demonstrating significant gains across diverse categories beyond just structural objects. Full article

By enhancing transient fidelity before geometric inversion, this work revisits the classical LCT-based non line-of-sight (NLOS)imaging paradigm and establishes a unified Bayesian sparse-enhancement framework for reconstructing hidden objects under photon-starved and hardware-limited conditions. We introduce sparse Bayesian learning (SBL) as a dedicated front-end transient restoration module, leveraging adaptive sparsity modeling to suppress background fluctuations while preserving physically consistent multipath returns. This lightweight and geometry-agnostic design enables seamless integration into existing LCT processing pipelines, granting the framework strong compatibility with diverse acquisition configurations. Comprehensive simulations and experiments on complex reflective targets demonstrate significant improvements in spatial resolution, boundary sharpness, and robustness to IRF-induced temporal blurring compared with traditional LCT and f-k migration methods. The results validate that transient quality remains a critical bottleneck in practical NLOS deployment, and addressing it via probabilistic sparsity inference offers a scalable and computationally affordable pathway toward stable, high-fidelity NLOS reconstruction. This study provides an effective signal-domain enhancement solution that strengthens the practicality of NLOS imaging in real-world environments, paving the way for future extensions toward dynamic scenes, multi-view fusion, and high-throughput computational sensing. Full article

Wearable multi-modal body fluid monitoring enables continuous, non-invasive, and context-aware assessment of human physiology. By integrating biochemical and physical information across multiple modalities, wearable systems overcome the limitations of single-marker sensing and provide a more holistic view of dynamic health states. This review offers a system-level overview of recent advances in multi-modal body fluid monitoring, structured into three hierarchical dimensions. We first examine sensing-combination strategies such as multi-marker analysis within single fluids, coupling biochemical signals with bioelectrical, mechanical, or thermal parameters, and emerging multi-fluid acquisition to improve analytical accuracy and physiological relevance. Next, we discuss platform-integration mechanisms based on biochemical, physical, and hybrid sensing principles, along with monolithic and modular architectures enabled by flexible electronics, microfluidics, microneedles, and smart textiles. Finally, the data-processing patterns are analyzed, involving cross-modal calibration, machine learning inference, and multi-level data fusion to enhance data reliability and support personalized and predictive healthcare. Beyond summarizing technical advances, this review establishes a comprehensive framework that moves beyond isolated signal acquisition or simple metric aggregation toward holistic physiological interpretation. It guides the development of next-generation wearable multi-modal body fluid monitoring systems that overcome the challenges of high integration, miniaturization, and personalized medical applications. Full article

Solar irradiance is one of the main factors affecting the output of photovoltaic power stations. The cloud distribution above the photovoltaic power station can determine the strength of the absorbed solar irradiance. Cloud estimation is another important factor affecting the output of photovoltaic power stations. Ground-based cloud automation observation is an important means to achieve cloud estimation and cloud distribution. Ground-based cloud image segmentation is an important component of ground-based cloud image automation observation. Most of the previous ground-based cloud image segmentation methods rely on convolutional neural networks (CNNs) and lack modeling of long-distance dependencies. In view of the rich fine-grained attributes in ground-based cloud images, this paper proposes a new Transformer architecture for ground-based cloud image fine-grained segmentation based on deep learning technology. The model consists of an encoder–decoder. In order to further mine the fine-grained features of the image, the BiFormer Block is used to replace the original Transformer; in order to reduce the model parameters, the MLP is used to replace the original bottleneck layer; and for the local features of the ground-based cloud, a multi-scale dual-attention (MSDA) block is used to integrate in the jump connection, so that the model can further extract local features and global features. The model is analyzed from both quantitative and qualitative aspects. Our model achieves the best segmentation accuracy, with mIoU reaching 65.18%. The ablation experiment results prove the contribution of key components to segmentation accuracy. Full article

Punch-through accidents pose a significant risk during the positioning of jack-up rigs. To mitigate this hazard, accurate prediction of the peak penetration resistance of spudcan foundations is essential for developing safe operational plans. Advances in artificial intelligence have spurred the widespread application of machine learning (ML) to geotechnical engineering. To evaluate the prediction effect of different algorithm frameworks on the peak resistance of spudcans, this study evaluates the feasibility of ML and multi-view learning (MVL) methods using existing centrifuge test data. Six ML models—Random Forest, Support Vector Machine (with Gauss, second-degree, and third-degree polynomial kernels), Multiple Linear Regression, and Neural Networks—alongside a Ridge Regression-based MVL method are employed. The performance of these models is rigorously assessed through training and testing across various working conditions. The results indicate that well-trained ML and MVL models achieve accurate predictions for both sand-over-clay and three-layer clay strata. For the sand-over-clay stratum, the mean relative error (MRE) across the 58-case dataset is approximately 15%. The Neural Network and MVL method demonstrate the highest accuracy. This study provides a viable and effective empirical solution for predicting spudcan peak resistance and offers practical guidance for algorithm selection in different stratigraphic conditions, ultimately supporting enhanced safety planning for jack-up rig operations. Full article

Wind power forecasting is critical to renewable energy generation, as accurate predictions are essential for the efficient and reliable operation of power systems. However, wind power output is inherently unstable and is strongly affected by meteorological factors such as wind speed, wind direction, and atmospheric pressure. Weather conditions and wind power data are recorded by sensors installed in wind turbines, which may be damaged or malfunction during extreme or sudden weather events. Such failures can lead to inaccurate, incomplete, or missing data, thereby degrading data quality and, consequently, forecasting performance. To address these challenges, we propose a method that integrates a pre-trained large-scale language model (LLM) with the spatiotemporal characteristics of wind power networks, aiming to capture both meteorological variability and the complexity of wind farm terrain. Specifically, we design a spatiotemporal graph neural network based on multi-view maps as an encoder. The resulting embedded spatiotemporal map sequences are aligned with textual representations, concatenated with prompt embeddings, and then fed into a frozen LLM to predict future wind turbine power generation sequences. In addition, to mitigate anomalies and missing values caused by sensor malfunctions, we introduce a novel frequency-domain learning-based interpolation method that enhances data correlations and effectively reconstructs missing observations. Experiments conducted on real-world wind power datasets demonstrate that the proposed approach outperforms state-of-the-art methods, achieving root mean square errors of 17.776 kW and 50.029 kW for 24-h and 48-h forecasts, respectively. These results indicate substantial improvements in both accuracy and robustness, highlighting the strong practical potential of the proposed method for wind power forecasting in the renewable energy industry. Full article

Intrusion detection in Internet of Things (IoT) environments is challenged by high-dimensional traffic, heterogeneous attack behaviors, and severe class imbalance. To address these issues, this paper proposes EHFOA-ID, an intrusion detection framework driven by an Enhanced HawkFish Optimization Algorithm integrated with a hybrid deep ensemble. The proposed optimizer jointly performs feature selection and hyperparameter tuning using adaptive exploration–exploitation balancing, Lévy flight-based global searching, and diversity-preserving reinitialization, enabling efficient navigation of complex IoT feature spaces. The optimized features are processed through a multi-view ensemble that captures spatial correlations, temporal dependencies, and global contextual relationships, whose outputs are fused via a meta-learner to improve decision reliability. This unified optimization–learning pipeline reduces feature redundancy, enhances generalization, and improves robustness against diverse intrusion patterns. Experimental evaluation on benchmark IoT datasets shows that EHFOA-ID achieves detection accuracies exceeding 99% on UNSW-NB15 and 98% on SECOM, with macro-F1 scores above 0.97 and false-alarm rates reduced to below 2%, consistently outperforming state-of-the-art intrusion detection approaches. Full article