Search Results (104)

Purpose: Luggage X-rays suffer from low contrast, material overlap, and noise; dual-energy imaging reduces ambiguity but creates colour biases that impair segmentation. This study aimed to (1) employ connotative fusion by embedding realistic detonator patches into real X-rays to simulate threats and enhance unattended detection without requiring ground-truth labels; (2) thoroughly evaluate fusion techniques in terms of balancing image quality, information content, contrast, and the preservation of meaningful features. Methods: A total of 1000 X-ray luggage images and 150 detonator images were used for fusion experiments based on deep learning, transform-based, and feature-driven methods. The proposed approach does not need ground truth supervision. Deep learning fusion techniques, including VGG, FusionNet, and AttentionFuse, enable the dynamic selection and combination of features from multiple input images. The transform-based fusion methods convert input images into different domains using mathematical transforms to enhance fine structures. The Nonsubsampled Contourlet Transform (NSCT), Curvelet Transform, and Laplacian Pyramid (LP) are employed. Feature-driven image fusion methods combine meaningful representations for easier interpretation. Singular Value Decomposition (SVD), Principal Component Analysis (PCA), Random Forest (RF), and Local Binary Pattern (LBP) are used to capture and compare texture details across source images. Entropy (EN), Standard Deviation (SD), and Average Gradient (AG) assess factors such as spatial resolution, contrast preservation, and information retention and are used to evaluate the performance of the analysed methods. Results: The results highlight the strengths and limitations of the evaluated techniques, demonstrating their effectiveness in producing sharpened fused X-ray images with clearly emphasized targets and enhanced structural details. Conclusions: The Laplacian Pyramid fusion method emerges as the most versatile choice for applications demanding a balanced trade-off. This is evidenced by its overall multi-criteria balance, supported by a composite (geometric mean) score on normalised metrics. It consistently achieves high performance across all evaluated metrics, making it reliable for detecting concealed threats under diverse imaging conditions. Full article

This paper investigates the bipartite synchronization problem for cooperation–competition neural networks (CCNNs) under asynchronous sampling control. First, using signed graph theory to characterize the interrelationships between cooperation and competition, a mathematical model for cooperative–competitive neural networks is established. To formulate the error systems of such networks, a Laplacian matrix with zero row sum is derived through coordinate transformation techniques. Considering network complexity and deception attack impacts, an asynchronous sampling-based secure control scheme is designed while preserving performance guarantees. By relaxing positive definiteness constraints, a class of looped functionals is introduced. State norm estimations are utilized to derive criteria for achieving bipartite synchronization. The feedback gain matrices of the asynchronous sampling controller are obtained by solving linear matrix inequalities. Finally, numerical simulations validate the effectiveness of the proposed method. Full article

The airborne Synthetic Aperture Radar (SAR) has the advantages of high-precision real-time observation of wave height variations and portability in the high frequency band, such as the Ku band. In view of the Four Fast Fourier Transform (4-FFT) algorithm, combined with a Gaussian operator, a Laplacian of Gaussian (LoG) Phase Unwrapping (PU) expression was derived. Then, an Adaptive LoG (ALoG) algorithm was proposed based on adaptive variance, further optimizing the algorithm through iteration. Building the models of Kelvin wake on the sea surface and height to phase, the interferometric phase of wave height can be simulated. These PU algorithms were qualitatively and quantitatively evaluated. The Principal Component Analysis (PCA) scores of the ALoG iteration (ALoGI) algorithm are the best under the tested noise levels of the simulation. Through a simulation experiment, it has been proven that the superiority of the ALoGI algorithm in high spatial resolution inversion for the sea-ship surface height of the Kelvin wake, with good stability and noise resistance. Full article

Extended connectivity in graphs can be analyzed through k-path Laplacian matrices, which permit the capture of long-range interactions in various real-world networked systems such as social, transportation, and multi-agent networks. In this work, we present several alternative methods based on machine learning methods (LSTM, xLSTM, Transformer, XGBoost, and ConvLSTM) to predict the final consensus value based on directed networks (Erdös–Renyi, Watts–Strogatz, and Barabási–Albert) and on the initial state. We highlight how different k-hop interactions affect the performance of the tested methods. This framework opens new avenues for analyzing multi-scale diffusion processes in large-scale, complex networks. Full article

Underwater remote sensing image enhancement is complicated by low illumination, color bias, and blurriness, affecting deep-sea monitoring and marine resource development. This study compares a multi-scale fusion-enhanced physical model and deep learning algorithms to optimize intelligent processing. The physical model, based on the Jaffe–McGlamery model, integrates multi-scale histogram equalization, wavelength compensation, and Laplacian sharpening, using cluster analysis to target enhancements. It performs well in shallow, stable waters (turbidity < 20 NTU, depth < 10 m, PSNR = 12.2) but struggles in complex environments (turbidity > 30 NTU). Deep learning models, including water-net, UWCNN, UWCycleGAN, and U-shape Transformer, excel in dynamic conditions, achieving UIQM = 0.24, though requiring GPU support for real-time use. Evaluated on the UIEB dataset (890 images), the physical model suits specific scenarios, while deep learning adapts better to variable underwater settings. These findings offer a theoretical and technical basis for underwater image enhancement and support sustainable marine resource use. Full article

Traditional object detection methods for meat duck counting suffer from high manual costs, low image quality, and varying object sizes. To address these issues, this paper proposes FE-P Net, an image enhancement-based parallel density estimation network that integrates CNNs with Transformer models. FE-P Net employs a Laplacian pyramid to extract multi-scale features, effectively reducing the impact of low-resolution images on detection accuracy. Its parallel architecture combines convolutional operations with attention mechanisms, enabling the model to capture both global semantics and local details, thus enhancing its adaptability across diverse density scenarios. The Reconstructed Convolution Module is a crucial component that helps distinguish targets from backgrounds, significantly improving feature extraction accuracy. Validated on a meat duck counting dataset in breeding environments, FE-P Net achieved 96.46% accuracy in large-scale settings, demonstrating state-of-the-art performance. The model shows robustness across various densities, providing valuable insights for poultry counting methods in agricultural contexts. Full article

In this paper, we focus on the multiplicity of positive solutions for a singular tempered fractional initial-boundary value problem with a p-Laplacian operator and a changing-sign perturbation term. By introducing a truncation function and combing with the properties of the solution of isomorphic linear equations, we transform the changing-sign tempered fractional initial-boundary value problem into a positive problem, and then the existence results of multiple positive solutions are established by the fixed point theorem in a cone. It is worth noting that the changing-sign perturbation term only satisfies the weaker Carathèodory conditions, which implies that the perturbation term ℏ can be allowed to have an infinite number of singular points; moreover, the value of the changing-sign perturbation term can tend to negative infinity in some singular points. Full article

This study introduces a novel one-dimensional Fractional Time–Space Stochastic Advection–Diffusion Equation that revolutionizes the modeling of moisture transport within atmospheric boundary layers adjacent to oceanic surfaces. By synthesizing fractional calculus, advective transport mechanisms, and pink noise stochasticity, the proposed model captures the intricate interplay between temporal memory effects, non-local turbulent diffusion, and the correlated-fluctuations characteristic of complex ocean–atmosphere interactions. The framework employs the Caputo fractional derivative to represent temporal persistence and the fractional Laplacian to model non-local turbulent diffusion, and incorporates a stochastic term with a $1/f$ power spectral density to simulate environmental variability. An efficient numerical solution methodology is derived utilizing complementary Fourier and Laplace transforms, which elegantly converts spatial fractional operators into algebraic expressions and yields closed-form solutions via Mittag–Leffler functions. This method’s application to a benchmark coastal domain demonstrates that stronger advection significantly increases the spatial extent of conditions exceeding fog formation thresholds, revealing advection’s critical role in moisture transport dynamics. Numerical simulations demonstrate the model’s capacity to reproduce both anomalous diffusion phenomena and realistic stochastic variability, while convergence analysis confirms the numerical scheme’s robustness against varying noise intensities. This integrated fractional stochastic framework substantially advances atmospheric moisture modeling capabilities, with direct applications to meteorological forecasting, coastal climate assessment, and environmental engineering. Full article

A new high-order hybrid method integrating neural networks and corrected finite differences is developed for solving elliptic equations with irregular interfaces and discontinuous solutions. Standard fourth-order finite difference discretization becomes invalid near such interfaces due to the discontinuities and requires corrections based on Cartesian derivative jumps. In traditional numerical methods, such as the augmented matched interface and boundary (AMIB) method, these derivative jumps can be reconstructed via additional approximations and are solved together with the unknown solution in an iterative procedure. Nontrivial developments have been carried out in the AMIB method in treating sharply curved interfaces, which, however, may not work for interfaces with geometric singularities. In this work, machine learning techniques are utilized to directly predict these Cartesian derivative jumps without involving the unknown solution. To this end, physics-informed neural networks (PINNs) are trained to satisfy the jump conditions for both closed and open interfaces with possible geometric singularities. The predicted Cartesian derivative jumps can then be integrated in the corrected finite differences. The resulting discrete Laplacian can be efficiently solved by fast Poisson solvers, such as fast Fourier transform (FFT) and geometric multigrid methods, over a rectangular domain with Dirichlet boundary conditions. This hybrid method is both easy to implement and efficient. Numerical experiments in two and three dimensions demonstrate that the method achieves fourth-order accuracy for the solution and its derivatives. Full article

In this work, we establish the existence of at least one solution for a p-Laplacian Langevin differential equation involving the $\psi$-Hilfer fractional derivative with antiperiodic boundary conditions. More precisely, we transform the studied problem into a Hammerstein integral equation, and after that, we use the Schafer fixed point theorem to prove the existence of at least one solution. Two examples are provided to validate the main result. Full article

X-ray computed tomography (CT) is vital for medical diagnostics, but frequent radiation exposure raises concerns, driving the adoption of low-dose CT (LDCT) to mitigate risks. However, LDCT often introduces noise, compromising diagnostic accuracy. This paper proposes a pure vision transformer (PViT) for LDCT denoising, enhanced with a gradient–Laplacian attention module (GLAM) to improve edge preservation and fine structural detail reconstruction. The model’s robustness was validated across five diverse datasets (piglet, head, abdomen, chest, thoracic), demonstrating consistent performance in preserving anatomical structures. Extensive ablation studies on attention configurations and loss functions further substantiated the contributions of each module. Quantitative evaluation using PSNR and SSIM, alongside radiologist assessment, confirmed significant noise suppression and sharper anatomical boundaries, particularly in regions with fine details such as organ interfaces and bone structures. Additionally, in benchmark comparisons against state-of-the-art LDCT models (RED-CNN, TED-Net, DSC-GAN, DRL-EMP) and traditional methods (BM3D), the model exhibited lower parameter and stable training performance. These findings highlight the model’s robustness, efficiency, and clinical applicability, making it a promising solution for improving LDCT image quality while maintaining computational efficiency. Full article

Medical image analysis is critical for diagnosing and planning treatments, particularly in addressing heart disease, a leading cause of mortality worldwide. Precise segmentation of the left atrium, a key structure in cardiac imaging, is essential for detecting conditions such as atrial fibrillation, heart failure, and stroke. However, its complex anatomy, subtle boundaries, and inter-patient variations make accurate segmentation challenging for traditional methods. Recent advancements in deep learning, especially semantic segmentation, have shown promise in addressing these limitations by enabling detailed, pixel-wise classification. This study proposes a novel segmentation framework Adaptive Multiscale U-Net (AMU-Net) combining Convolutional Neural Networks (CNNs) and transformer-based encoder–decoder architectures. The framework introduces a Contextual Dynamic Encoder (CDE) for extracting multi-scale features and capturing long-range dependencies. An Adaptive Feature Decoder Block (AFDB), leveraging an Adaptive Feature Attention Block (AFAB) improves boundary delineation. Additionally, a Spectral Synthesis Fusion Head (SFFH) synthesizes spectral and spatial features, enhancing segmentation performance in low-contrast regions. To ensure robustness, data augmentation techniques such as rotation, scaling, and flipping are applied. Laplacian approximation is employed for uncertainty estimation, enabling interpretability and identifying regions of low confidence. Our proposed model achieves a Dice score of 93.35, a Precision of 94.12, and a Recall of 92.78, outperforming existing methods. Full article

The combinatorial fusion cascade provides a surprisingly simple and complete explanation for the origin of the genetic code based on competing protocodes. Although its molecular basis is only beginning to be uncovered, it represents a natural pattern of information generation from initial signals and has potential applications in designing more-efficient neural networks. By utilizing the properties of the combinatorial fusion cascade, we demonstrate its embedding into deep neural networks with sequential fully connected layers using the dynamic matrix method and compare the resulting modifications. We observe that the Fiedler Laplacian eigenvector of a combinatorial cascade neural network does not reflect the cascade architecture. Instead, eigenvectors associated with the cascade structure exhibit higher Laplacian eigenvalues and are distributed widely across the network. We analyze a text classification model consisting of two sequential transformer layers with an embedded cascade architecture. The cascade shows a significant influence on the classifier’s performance, particularly when trained on a reduced dataset (approximately 3% of the original). The properties of the combinatorial fusion cascade are further examined for their application in training neural networks without relying on traditional error backpropagation. Full article

The increasing integration of autonomous driving systems into modern vehicles heightens the significance of Image Quality Assessment (IQA), as it pertains directly to vehicular safety. In this context, the development of metrics that can emulate the Human Visual System (HVS) in assessing image quality assumes critical importance. Given that blur is often the primary aberration in images captured by aging or deteriorating camera sensors, this study introduces a No-Reference (NR) IQA model termed BREMOLA (Blind/Referenceless Model via Moving Spectrum and Laplacian Filter). This model is designed to sensitively respond to varying degrees of blur in images. BREMOLA employs the Fourier transform to quantify the decline in image sharpness associated with increased blur. Subsequently, deviations in the Fourier spectrum arising from factors such as nighttime lighting or the presence of various objects are normalized using the Laplacian filter. Experimental application of the BREMOLA model demonstrates its capability to differentiate between images processed with a 3 × 3 average filter and their unprocessed counterparts. Additionally, the model effectively mitigates the variance introduced in the Fourier spectrum due to variables like nighttime conditions, object count, and environmental factors. Thus, BREMOLA presents a robust approach to IQA in the specific context of autonomous driving systems. Full article

Accurate 6D object pose estimation is critical for autonomous docking. To address the inefficiencies and inaccuracies associated with maximal cliques-based pose estimation methods, we propose a fast 6D pose estimation algorithm that integrates feature space and space compatibility constraints. The algorithm reduces the graph size by employing Laplacian filtering to resample high-frequency signal nodes. Then, the truncated Chamfer distance derived from fusion features and spatial compatibility constraints is used to evaluate the accuracy of candidate pose alignment between source and reference point clouds, and the optimal pose transformation matrix is selected for 6D pose estimation. Finally, a point-to-plane ICP algorithm is applied to refine the 6D pose estimation for autonomous docking. Experimental results demonstrate that the proposed algorithm achieves recall rates of 94.5%, 62.2%, and 99.1% on the 3DMatch, 3DLoMatch, and KITTI datasets, respectively. On the autonomous docking dataset, the algorithm yields rotation and localization errors of 0.96° and 5.82 cm, respectively, outperforming existing methods and validating the effectiveness of our approach. Full article