Search Results (1,516)

Seismic inversion is a key technique for quantitative characterization of subsurface elastic parameters and detailed reservoir description. However, due to the limited bandwidth of seismic signals and the strong heterogeneity of complex reservoirs, conventional inversion methods struggle to simultaneously achieve high vertical resolution and lateral continuity. To address these challenges, an intelligent elastic parameter inversion method based on kernel density estimation within a Bayesian framework is proposed. First, kernel density estimation is introduced to augment the training samples, thereby alleviating data scarcity. Second, a hybrid architecture integrating convolutional modules, Mamba, and cross-attention mechanisms is constructed to achieve collaborative modeling of local spatial features and long-range temporal dependencies. The cross-attention mechanism is further employed to adaptively weight and fuse multi-source features, thus enhancing the representation capability of the model. Subsequently, by designing a joint loss function, the strengths of deterministic inversion and data-driven approaches are effectively integrated, ensuring physical consistency while enhancing data adaptability, thereby improving the stability and accuracy of the inversion results. Furthermore, the neural network outputs are used as the initial model for Bayesian inversion to construct a probabilistic inversion framework for elastic parameter inversion. Finally, experimental results demonstrate that the proposed method improves the R² values of inversion results by more than 8.0% and 5.0% compared with conventional methods in thin interbedded models and real data experiments, respectively. Full article

In ceramic cup manufacturing, manual inspection is prone to missed detections and false positives, particularly for small surface defects. To address these challenges, this study presents an effective and efficient YOLOv11m-based detection framework, termed CEL-YOLOv11m, for precise identification of small-scale defects on ceramic surfaces. Specifically, a multi-scale convolution module (EMSC) is introduced to enhance the backbone feature extraction structure. By integrating convolution kernels of varying sizes, the module improves multi-scale feature representation, while grouped convolution is employed to reduce computational overhead. In the feature aggregation stage, a CRGseg-based structure is incorporated, and a refinement component (RCM) is designed to strengthen fine-grained information for small targets. Additionally, a cross-scale feature fusion strategy is applied to improve contextual representation across different resolutions. For the detection stage, a Layer-shared Detail-Enhanced Convolutional Detection Head (LSDECD) is adopted to improve fine-grained localization while improving computational efficiency through parameter sharing. Experiments conducted on a self-constructed ceramic defect dataset and the VisDrone2019 benchmark show that the proposed framework achieves competitive performance compared with representative methods. The model attains an mAP@50(%) of 54.8% with an inference speed of 89.9 FPS, providing a favorable trade-off between detection accuracy and computational efficiency while maintaining strong precision in small defect detection. Full article

Accurate prediction of reservoir production dynamics remains a key challenge in the oil and gas industry, especially for complex, high-dimensional time-series data. Conventional models fail to capture temporal dependencies, while existing hybrid models suffer from high parameter complexity and lack automated hyperparameter tuning, increasing training difficulty. To address these issues, this study proposes a novel hybrid model, TCN-LSTM-AVOA, combining a temporal convolutional network (TCN) with a long short-term memory network (LSTM) and incorporating the African Vulture Optimization Algorithm (AVOA) to enhance forecasting accuracy. The model not only captures complex temporal relationships and nonlinear features in reservoir data but also facilitates automated tuning of critical hyperparameters (e.g., the number of TCN kernels, LSTM units, batch size, and learning rate), which significantly enhances its robustness. Compared to eight benchmark models (back propagation neural network (BPNN), LSTM, convolutional neural network(CNN)-LSTM, TCN-LSTM, LSTM-AVOA, CNN-AVOA, TCN-AVOA), TCN-LSTM-AVOA achieves superior performance on a two-dimensional, three-phase heterogeneous reservoir, yielding a root mean square error (RMSE) of 7.0806, mean absolute error (MAE) of 3.4780, coefficient of determination (R²) of 0.9975, and mean absolute percentage error (MAPE) of 1.81%. This work demonstrates a more accurate and efficient methodology for reservoir production prediction, with significant potential for oilfield production optimization and resource management. Full article

The objective of this work is to investigate the $\mathbb{T}=(s,t)$-deformed free convolution ${⊞}_{\mathbb{T}}$ for $s>0$ and $t\in \mathbb{R}$ and to clarify its structural and asymptotic properties within the framework of Cauchy–Stieltjes kernel (CSK) families. The methodology is based on the analysis of the associated variance functions (VFs), which provide an effective analytic tool for describing deformation mechanisms, invariance properties, and convolution structures. In particular, we derive an explicit formula for the VF of convolution powers and exploit this representation to develop approximation procedures for distributions in CSK families generated by the $(s,t)$-deformed free Gaussian and free Poisson laws. We also establish several limit theorems describing the asymptotic behavior of the deformation. These findings highlight intrinsic symmetry and scaling properties and reveal connections with free additive, Boolean additive, and free multiplicative convolutions, thereby placing the $(s,t)$-deformation within a unified probabilistic framework governed by transformation, invariance, and structural regularity. Full article

Cranial reconstruction is a critical task in computer-assisted surgery, requiring both high geometric accuracy and computational efficiency for patient-specific implant design. While recent deep learning approaches, particularly 3D UNet-based models, have demonstrated promising performance, most studies primarily focus on architectural modifications, with limited attention to the systematic impact of data preparation and training strategies on reconstruction quality. In this study, we present a comprehensive data-centric investigation of key factors influencing the performance of a baseline 3D UNet for cranial defect reconstruction. Specifically, we analyze the effects of data preprocessing (denoising), dataset organization (ordered versus randomized training), defect morphology diversity, convolutional kernel size, and loss function design under controlled experimental conditions. Experiments were conducted on 250 complete skulls (NRRD format) from the MUG500+ dataset, with synthetically generated defects across multiple anatomical regions. From these volumes, a total of 3750 training samples were generated, including: (i) 1250 noisy samples with diverse defect morphologies, (ii) 1250 denoised samples with ellipsoidal defects, and (iii) 1250 denoised samples with multiple defect types. The results demonstrate that data-centric and training-related factors have a substantial impact on model performance, in several cases exceeding the influence of architectural design. In particular, denoising significantly improves boundary stability and reduces geometric error, while incorporating diverse defect morphologies enhances generalization to unseen shapes. Additionally, ordered training contributes to more stable convergence, and an optimal kernel size of (3 × 3 × 3) achieves the best trade-off between accuracy and computational efficiency. A hybrid Dice and boundary loss further improves boundary precision compared to conventional Dice loss. The optimized configuration achieves a Dice Similarity Coefficient of 0.94 and a Hausdorff Distance of 3.8 mm, with an average inference time of 0.004 s per case. These results demonstrate that data-centric optimization can be as influential as, or even more impactful than, architectural design in cranial defect reconstruction. The findings provide practical and reproducible guidelines for developing efficient, robust, and clinically applicable deep learning-based systems for patient-specific cranial implant design. Full article

Accurate prediction of the Remaining Useful Life (RUL) of special gas cylinders is critical for industrial safety management. However, the nonlinear, strongly coupled degradation behaviors of these cylinders, combined with non-stationary and high-noise monitoring data, limit the performance of single deep learning models. Traditional hyperparameter tuning and signal processing methods often fail to meet the required prediction accuracy. To address these challenges, this study proposes a hybrid SSA–PSO–ResNet–LSTM–Attention framework for RUL prediction of special gas cylinders. The framework first applies Singular Spectrum Analysis (SSA) to decompose and reconstruct the 12-dimensional multi-source sensor signals, effectively suppressing noise while extracting core degradation trends. Subsequently, a ResNet–LSTM–Attention collaborative model is constructed, where ResNet ensures stable spatial feature propagation, LSTM captures long- and short-term temporal dependencies, and a multi-head attention mechanism emphasizes critical time steps associated with abrupt degradation. Furthermore, a Particle Swarm Optimization (PSO) algorithm is employed to globally optimize key hyperparameters, including the number of convolutional kernels, LSTM hidden units, and learning rate, mitigating the subjectivity of manual tuning. Experimental validation is conducted on 1000 real monitoring samples from 100 composite material gas cylinders, with a cylinder ID-based 7:1:2 train–validation–test split and stratified sampling covering four operating conditions. PSO optimizes hyperparameters using the validation set RMSE as the fitness function, and the test set is exclusively used for final performance evaluation. All results are reported as the mean ± standard deviation from grouped 5-fold cross-validation on the cylinder-wise partition. The proposed model achieves a test RMSE of 71.55, MAE of 50.63, and R² of 0.9584, representing a 34.2% and 30.2% reduction in RMSE and MAE, respectively, compared with the second-best CNN-LSTM model, and significantly outperforming SVR, MLP, and other benchmark models. Ablation studies confirm the positive synergistic effect of each component, with the removal of either the attention mechanism or the ResNet module causing substantial performance degradation. By employing physically calibrated RUL labels and a balanced multi-condition dataset, the proposed framework achieves high predictive accuracy and good potential for industrial application, providing an effective solution for RUL prediction of special gas cylinders and similar high-pressure vessels, with potential applications in intelligent maintenance of complex industrial equipment. Full article

Safe low-altitude flight requires precise perception of obstacles like widespread transmission towers. Traditional inspection is often costly and inefficient. While satellite remote sensing enables automated detection, transmission towers exhibit small scales, slender structures, and random orientations, causing feature loss and receptive field mismatch. This study constructs HRS-PTD, a multi-source, multi-resolution satellite optical dataset, and analyzes target morphology. We then propose an optimized composite YOLO model using a streamlined three-stage baseline with C3k2 and SPPF modules. To enhance small object feature reconstruction, CARAFE is integrated into the upsampling path for content-aware dynamic kernels. Furthermore, a direction-aware C_DCA module, incorporating deformable convolutions, utilizes multi-directional strip branches and adaptive attention to improve slender target representation. Ablation experiments show the model achieves 92.28% mAP, with precision and recall increasing by 1.53 and 12.12 percentage points over the baseline. Comparative experiments against representative classical detectors further demonstrate that the proposed model achieves superior overall performance in both detection accuracy and inference efficiency. Tests on Google Earth and Gaofen-7 imagery yield 88% and 76% accuracy, confirming real-world feasibility. Full article

The automated inspection of aluminum profile surface defects, which heavily relies on data acquired by machine vision sensors, is a critical task in industrial quality control. Addressing the current challenges of intense background texture interference and the difficulty in detecting defects with extreme aspect ratios on aluminum profiles, this research puts forward a complete end-to-end defect detection algorithm named WMC-DFINE (WIFA-MKSS-CSFF-DFINE) based on the DFINE framework. First, a Wavelet-Integrated Frequency Attention (WIFA) module is introduced, which utilizes a discrete wavelet transform to decouple features into the frequency domain, thereby dynamically suppressing high-frequency background noise and enhancing defect edge responses. Second, a Cross-Scale Feature Fusion (CSFF) module based on dual-channel pooling is designed to ensure the continuity of defect features, thereby resolving the semantic misalignment issue in traditional fusion. Third, a Multi-Kernel Strip Shuffle (MKSS) module is incorporated, utilizing decomposed convolution kernels to capture the geometric features of slender scratches. Finally, a knowledge distillation strategy is employed to transfer structured knowledge from a complex teacher model to a lightweight student model. Experiments on the Tianchi aluminum defect dataset demonstrate that WMC-DFINE achieves a mAP of 82.1%, which surpasses algorithms including YOLOv12, RT-DETR, and the baseline model DFINE. Furthermore, the distilled student model, WMC-DFINE-distill, improves the mAP by 3.2% compared to DFINE, reduces parameter count by 47%, and achieves an inference speed of 59.75 FPS on the experimental equipment. The proposed method effectively resolves the problem of balancing background suppression and defect detail feature preservation, offering a practical and efficient scheme for real-time industrial defect inspection. Full article

Early mild cognitive impairment (EMCI) is the earliest intervenable stage of Alzheimer’s disease (AD). Although graph neural networks (GNNs) have begun to exploit brain network topology, traditional fMRI-based diagnostic methods often neglect these structural patterns by relying on vectorized features. Furthermore, existing GNNs frequently disregard inter-regional functional heterogeneity and group-level discriminative patterns, leading to limited accuracy and biomarker interpretability. To address these challenges, we propose HF-BrainGNN, an end-to-end hierarchical graph learning framework for EMCI identification. Our method introduces a functional affinity region convolution (FAR-Conv) layer to learn region-adaptive kernels, a Differential Focus Pooling (DF-Pool) module to identify disease-salient brain regions by maximizing inter-group distinctiveness, and a hierarchical integration classifier (HIC) to fuse multi-level graph representations. The framework is optimized using classification, focus separation, and consistency regularization losses. Experiments on the ADNI dataset (104 EMCI, 114 Cognitively Normal) show that HF-BrainGNN achieves 86.78% accuracy, outperforming the best baseline (Hi-GCN) by 4.64%. Furthermore, the automatically identified regions, such as the bilateral hippocampus and default mode network hubs, align with established EMCI biomarkers. Ultimately, HF-BrainGNN provides an efficient, interpretable artificial intelligence tool for precise brain network characterization and early AD intervention. Full article

In this study, we develop a class of multivariate HHC-type operators generated by adjustable half-hyperbolic tangent activation functions and a symmetrized kernel structure. The analysis is carried out within the classical framework of positive linear operators (PLOs), which allows a deeper investigation of their approximation behavior. By means of the modulus of continuity, we obtain quantitative convergence estimates toward the identity operator together with explicit bounds for the approximation error. The proposed construction is developed in a multivariate setting, where both simultaneous approximation with respect to several variables and iterated applications of the operators are examined. It is shown that the convergence properties remain stable under iteration, which further strengthens the analytical framework. The proposed operators also preserve important structural features of the approximated functions, including convexity and differentiability, and therefore provide a mathematically controlled approach to multivariate approximation. In contrast to earlier univariate HHC-type studies, the present work introduces a symmetry-enhanced multivariate operator structure together with explicit multivariate error analysis and a broader comparative numerical investigation. The numerical study, supported by Python 3.13 computations, combines regression-based error metrics with graphical analysis in order to illustrate convergence and compare the behavior of the classical, Kantorovich-type, and quadrature-type forms of the operators. Overall, the results contribute to the theory of convolution-type PLOs and provide a meticulous approximation framework with potential relevance to computational mathematics and learning-oriented operator design. Full article

Steel surface defects in manufacturing are typically tiny, low-contrast, and boundary-ambiguous, especially under complex textures (e.g., rolling marks, crazing), poor illumination, and high noise. These characteristics cause frequent missed detections and localization errors, particularly for defects with large-scale variations. Existing detectors, including YOLOv11, lack sufficient local spatial modeling for deformed or blurred boundaries and suffer from limited cross-scale feature interaction, leading to suboptimal performance on industrial benchmarks. To overcome these limitations, we propose YOLOv11-LLR—a YOLOv11-based framework that jointly enhances multi-scale feature modeling and inference efficiency. YOLOv11-LLR synergistically integrates three modules: Deformable Large Kernel Attention (DLKA) for adaptive local spatial perception, Lightweight Group-wise Attention (LWGA) for cross-scale interaction, and Re-parameterized Convolution (RepConv) for deployment-friendly speed. We evaluate on two representative datasets: NEU-DET (six defect types on hot-rolled steel strips) and GC10-DET (ten defect types with higher background complexity). Compared to baseline YOLOv11, YOLOv11-LLR achieves +3.5% mAP@0.5 (80.2%→83.7%) and +2.4% mAP@0.5:0.95 (48.7%→51.1%) on NEU-DET, and larger gains of +9.8% (61.0%→70.8%) and +3.4% (33.4%→36.8%) on the more challenging GC10-DET. These results demonstrate that YOLOv11-LLR provides an effective, robust, and industrially deployable solution for steel surface defect detection under complex textures, noise, and multi-scale variations. Full article

Accurate ultra-short-term forecasting of photovoltaic (PV) power is critical for maintaining grid stability and facilitating renewable energy integration. Although convolutional neural networks have demonstrated strong performance in computer vision, their effectiveness in time-series forecasting remains insufficiently validated. This study systematically evaluates a ConvNeXt–LSTM hybrid model for 15 min-resolution, 16-step-ahead (4 h) PV power forecasting. The results indicate that the proposed model outperforms the baseline LSTM, achieving reductions of 6.6% in MAE and 5.8% in RMSE, with statistical significance confirmed by the Wilcoxon signed-rank test (p < 0.05). However, the performance gains are highly dependent on architectural design, exhibiting sensitivity to kernel size and channel width, and showing diminishing returns under excessive scaling. These findings suggest a structural mismatch between vision-oriented convolutional inductive biases and temporal sequence characteristics. Furthermore, analyses of loss functions and feature degradation demonstrate consistent model ranking and enhanced robustness under reduced feature conditions. Overall, this study delineates the applicability boundaries of modern vision backbones in PV forecasting and provides practical guidance for model selection. Full article

Aiming at the dual dilemma in high-resolution cropland change detection, where CNNs are constrained by limited local receptive fields and Transformers suffer from heavy computational costs, we propose LiteScan-Net, a lightweight and robust network architecture incorporating scanning principles from state-space modeling. The network innovatively introduces the Multi-Directional Global Scanning (MDGS) mechanism as an efficient engineering surrogate, which simulates the selective scanning process using large-kernel 1D convolutions. This achieves global context modeling with linear complexity while avoiding the hardware limitations imposed by recurrent computations. Based on this mechanism, a three-stage collaborative architecture is constructed: the Coordinate-Aware Feature Purification (CAFP) module is designed to mitigate shallow phenological noise via coordinate sensitivity; the Context Difference Verification (CDV) module aims to alleviate pseudo-changes caused by registration errors through global alignment; and the State-Space Guided Refinement (SSGR) module promotes the generation of change masks with precise boundaries and compact interiors. To verify the model generalization, we construct a Massive Specialized Cropland Change Detection dataset named MSCC, which exhibits significant cross-scale characteristics. Experimental results demonstrate that LiteScan-Net achieves state-of-the-art (SOTA) performance across the CLCD, Hi-CNA, and MSCC datasets, with F1-scores of 79.43%, 84.82%, and 89.62%, respectively. With a low computational cost of only 1.78 GFLOPs and a real-time inference speed of 37.9 FPS, LiteScan-Net demonstrates high potential for future deployment on resource-constrained edge devices. Full article

Object detection in unmanned aerial vehicle (UAV) remote sensing imagery remains a formidable challenge due to the diminutive scale of targets, complex background clutter, and extreme variability in target morphology. Standard convolutional neural networks typically suffer from irreversible fine-grained information loss during downsampling, as strided operations discard critical spatial details essential for the localization of tiny objects. To address these issues, we propose RFE-YOLO, a lightweight receptive field-enhanced network specifically tailored for high-precision small object detection in UAV scenarios. First, the Cross-Scale Receptive Field Enhancement (CSRE) module is designed to mitigate intrinsic information loss by integrating space-to-depth convolution (SPD-Conv), which preserves spatial details by migrating them into the channel dimension. This module further employs an energy-based adaptive weight generation mechanism to distinguish target signals from environmental noise. Second, this paper proposes the C3k2-Dynamic Inception Mixer Block (C3k2-DIMB), which adaptively captures anisotropic features—such as slender vehicles—via dynamic kernel weighting and multi-shape inception kernels. Third, the Shuffled Upsampling for Resolution Enhancement (SURE) module is introduced to maintain spatial fidelity during resolution recovery, utilizing a channel shuffle mechanism to overcome information isolation. Finally, the Multi-feature Fusion Module (MFM) replaces conventional static concatenation with a dynamic softmax-based competition mechanism, effectively bridging the semantic gap between multi-level features while suppressing background distractors. Experimental results on the VisDrone dataset demonstrate that RFE-YOLO significantly enhances the representation capability for small objects. Specifically, the proposed model achieves a state-of-the-art $mA{P}_{50}$ of 42.70%, representing a substantial 9.3% improvement over the baseline YOLO11n. Furthermore, our architecture maintains an exceptionally lightweight profile with only 1.91 M parameters, demonstrating that high-precision detection can be achieved through structural intelligence rather than excessive parameter scaling. This makes RFE-YOLO highly suitable for real-time inference on edge-deployed UAV platforms. Full article

In drone aerial photography applications, small object detection is crucial. For instance, it enables locating missing individuals on the ground during search-and-rescue operations, identifying distant vehicles in traffic monitoring, and detecting early-stage pest infestations in agricultural fields. However, aerial images present a unique challenge: due to the high flight altitude of drones, targets occupy only a minimal pixel area. Combined with complex backgrounds and sparse features, small objects are easily obscured by surrounding environments. To address these issues, this paper proposes the EFPN-YOLO model based on YOLOv12n. First, we introduce the Feature-Sharing Convolution (FSConv) module, which extracts multi-scale features with low parameter requirements through shared convolution kernels and multi-scale sparse sampling. Second, by integrating deformable convolutions with a dual-channel attention mechanism, we develop the Enhanced Dual-Dimensional Calibration (EDDC) module, significantly improving spatial feature modeling capabilities and feature enhancement effectiveness. Finally, we construct the RC-FPN architecture, employing a bidirectional fusion structure and diagonal cross-layer skip connections to minimize information loss. Meanwhile, the Bottleneck structure in the C3K2 module is replaced with the RepViTBlock to construct the C3k2_RVB module, which enhances the multi-scale feature expression ability through a two-stage design of spatial and channel mixing. On the VisDrone2019 dataset, the model’s mAP50 improved from 33.9% to 40.7%; on the TinyPerson dataset, it rose from 13.9% to 19.2%; and on the NVIDIA Jetson Orin Nano 8 GB superplatform, the model achieved a frame rate (FPS) of 15. Experiments demonstrate that EFPN-YOLO excels in small object detection and holds significant practical value. Full article