Search Results (623)

With the continuous advancement of polarization spectral sensing technology, multi-band polarization image fusion has emerged as a novel approach to image fusion. By integrating spectral and polarization information, this method overcomes the limitations of relying on a single information source and significantly improves overall image quality. To address this, this paper proposes a new polarization spectral fusion algorithm. First, feature matching is employed to achieve pixel-level spatial alignment of multi-band polarization images. Then, a fusion strategy based on multi-scale decomposition and singular value decomposition is adopted to preserve structural information and fine details. Subsequently, fractional-order processing and guided filtering are applied to enhance details and suppress noise. Finally, a progressive reconstruction from low to high scales is performed to ensure hierarchical consistency and information integrity throughout the fusion process. In addition, spectral information is utilized for color restoration, enabling the final image to achieve high spatial resolution while maintaining natural and rich color representation.Experimental results demonstrate that the proposed method effectively integrates features from different spectral bands and polarization information while preserving maximum similarity, leading to significant improvements in both image quality and detail representation. Full article

Remote sensing image (RSI) semantic segmentation is challenged by high inter-class spectral similarity, significant intra-class scale variation, and limited availability of labeled data. Although semi-supervised learning has reduced the dependency on large-scale annotations, existing approaches still suffer from degraded boundary precision and incomplete geometric structures in complex remote sensing scenes. To address these issues, this paper proposes a Multi-scale Consistency and Cross-Attention Teacher–Student Network (MSCA-TSN) for semi-supervised RSI semantic segmentation. Specifically, an Adaptive Multi-scale Uncertainty Consistency module (AMUC) is introduced to model feature reliability across hierarchical levels. By leveraging Monte Carlo Dropout to estimate feature uncertainty and employing adaptive weighting for multi-scale consistency learning, AMUC effectively suppresses unreliable supervision and improves segmentation robustness under significant scale variations. Furthermore, a Cross-Teacher–Student Cross-Attention Module (CCAM) is designed to enhance cross-network feature interaction. In CCAM, student features act as queries while teacher features serve as keys and values to construct cross-attention, enabling the student network to reconstruct more discriminative feature representations and reduce confusion among visually similar land-cover categories. Extensive experiments are conducted on the LoveDA and ISPRS Potsdam benchmarks under both 5% and 10% labeling ratios. On the LoveDA dataset, MSCA-TSN achieves mIoU scores of 51.05% and 52.41% under 5% and 10% labeled data, respectively, outperforming several state-of-the-art semi-supervised methods. On the ISPRS Potsdam dataset, the proposed method further reaches 75.35% and 76.34% mIoU under the same settings. Ablation and parameter sensitivity analyses further verify the effectiveness and robustness of the proposed AMUC and CCAM modules. Full article

Accurate brain tumor segmentation from magnetic resonance imaging (MRI) remains challenging due to heterogeneous tumor morphology, intensity variability, and multi-scale structural complexity. This study proposes a DeepLabV3+-based segmentation framework integrating a VGG19-UNet encoder, Atrous Spatial Pyramid Pooling (ASPP), and low-level feature refinement to simultaneously capture hierarchical semantics and boundary-sensitive spatial details. The architecture enhances receptive field coverage without additional downsampling while preserving fine-grained contour information during reconstruction. Extensive evaluation was conducted on the Figshare Brain Tumor Segmentation (FBTS) dataset and the BraTS 2021 and BraTS 2018 benchmarks, focusing on Whole Tumor segmentation across multiple MRI modalities and tumor grades. Under five-fold cross-validation, the proposed model achieved a mean Dice Similarity Coefficient of 0.9717 and Jaccard Index of 0.9456 on FBTS, with stable and competitive performance across FLAIR, T1, T2, and T1CE modalities in both HGG and LGG cases. Boundary-level analysis further confirmed controlled Hausdorff Distance and low Average Symmetric Surface Distance. Statistical validation and ablation analysis demonstrate consistent improvements over baseline U-Net configurations. The proposed framework provides a robust and computationally efficient solution for automated brain tumor segmentation across heterogeneous datasets. Full article

Shoreline change detection from remote sensing imagery remains challenging in environments subject to water level fluctuations, as remotely sensed shoreline positions reflect instantaneous hydrodynamic states rather than true geomorphic change. In the Great Lakes, seasonal and short-term water level variations can produce apparent shoreline shifts unrelated to sediment dynamics. Reliable calibration with bathymetry and water level data can mitigate this effect, but such data are often unavailable or difficult to obtain for many coastal and lacustrine systems worldwide. To address this limitation, we proposed a morphology-based framework that quantifies geometric change between successive shoreline curves using a discrete Fréchet distance, a modified Euclidean distance and a Union distance metric. Rather than relying solely on cross-shore displacements, the approach leverages shape similarity to differentiate water-level-driven shifts from true morphological change. We evaluated the framework across three spatial scales (100 m, 500 m, and 1000 m) along 125 km of southwestern Lake Michigan coastline using 2010 and 2020 aerial imagery, benchmarking against water-level-calibrated DSAS erosion hotspots. The Fréchet distance improved monotonically with scale, achieving strong agreement at 1000 m (F1 = 0.84, Spearman $\rho$ = 0.79) but limited reliability at 100 m. While individual morphology-based metrics appeared competitive with or inferior to uncalibrated DSAS at each scale, the union of both distances substantially outperformed uncalibrated DSAS at management-relevant scales (F1 of 0.64 vs. 0.50 at 500 m and 0.79 vs. 0.42 at 1000 m), reflecting the complementary nature of shape-based and displacement-based detection. The Patient Rule Induction Method (PRIM) further identified gentle nearshore slopes and moderate separation from engineered structures as the geomorphic conditions under which the morphology-based and calibrated erosion indicators converged most closely (in-box F1 = 0.92 at 1000 m and 0.72 at 500 m). These results suggest that the proposed framework, particularly the complementary union of both metrics, provides a practical, calibration-free alternative for multiscale shoreline change screening in lacustrine and microtidal, data-limited environments, while local-scale applications still benefit from explicit water-level correction. Full article

The accurate and rapid prediction of hazard gas dispersion fields in urban environments is essential for guiding emergency sensor deployment and enabling real-time risk assessment. However, the computational cost associated with Computational Fluid Dynamics (CFD) simulations hinders their use as real-time forward models, while simplified Gaussian plume models lack the fidelity to resolve building obstruction effects. This study proposes a morphology-guided conditional Generative Adversarial Network (cGAN) framework designed to achieve real-time gas dispersion field modeling in urban environments with complex building configurations. The urban area is discretized into 50 × 50 m grid cells, each characterized by six morphological parameters describing building geometry. K-means clustering categorizes these cells into distinct morphological types. High-fidelity dispersion datasets are then generated for each type using Lattice Boltzmann Method (LBM) simulations. Each sample encodes building geometry, release location, wind speed, and time as multi-channel input images, with the corresponding gas dispersion concentration field is recorded as the output. Two cGAN architectures, Image-to-Image Translation (Pix2Pix) and its high-resolution variant (Pix2PixHD), are employed to learn the mapping from input features to dispersion fields. Model performance is evaluated using four complementary metrics: Fraction within a Factor of Two (FAC2) for prediction accuracy, Normalized Root Mean Square Error (NRMSE) for precision, Fractional Bias (FB) for systematic error, and Structural Similarity Index (SSIM) for spatial pattern fidelity. A case study is conducted across a 1176 km² urban district in China. The results demonstrate that under varying wind speeds (0.5–1.5 m/s) and temporal scales (5–60 s), and across five morphological categories, the Pix2PixHD-based model achieves 92.5% prediction accuracy and reproduces 97.6% of the spatial patterns. The proposed framework accelerates computation by approximately 18,000 times compared to traditional CFD, reducing inference time to under 0.1 s per scenario. This sub-second capability enables real-time concentration field estimation for emergency management, and provides a physically informed, computationally feasible forward model that can potentially support sensor-based gas source localization and detection network planning in complex urban environments. Full article

Obtaining multiple MRI contrasts for each patient prolongs scan acquisition time, increases healthcare costs, and may not always be feasible due to patient specific constraints. Deep learning-based MRI contrast synthesis offers a potential solution, yet most existing approaches are evaluated on preprocessed public benchmarks that do not reflect real-world clinical variability. In this study, we propose a fusion U-Net transformer framework for bidirectional T1-weighted ↔ T2-weighted brain MRI synthesis trained and evaluated exclusively on retrospectively acquired clinical data. The proposed architecture integrates multiscale convolutional feature extraction with axial attention mechanisms and a transformer bottleneck for efficient global context modeling. A fusion refinement block is incorporated to mitigate skip connection artifacts. An adversarial training strategy with the least squares GAN objective and a hybrid loss combining L1 reconstruction and structural similarity (SSIM) is employed to promote both pixel-level accuracy and perceptual fidelity. The model is evaluated using SSIM and PSNR metrics alongside qualitative expert assessment conducted by two board-certified radiologists. For both synthesis directions, the framework achieves competitive quantitative performance against baseline models under the challenging conditions of clinical data. Expert evaluation confirms high anatomical fidelity and clinically acceptable image quality across both synthesis directions. These results indicate that the proposed framework represents a promising approach for multi-contrast MRI synthesis in clinically heterogeneous data environments. Full article

Under maize–soybean rotation systems, weeds and crops at the seedling stage in dryland fields exhibit high similarity in morphological structure, scale distribution, and spatial arrangement. In addition, complex illumination conditions, occlusion, and background interference further complicate accurate weed discrimination. To address these challenges, this study proposes an improved YOLOv11n-based weed detection method for seedling-stage crops under dryland rotation conditions, aiming to enhance detection accuracy and robustness in UAV-acquired field images. Three key improvements were introduced to enhance model performance: (1) the incorporation of Dynamic Convolution (DynamicConv) to adaptively strengthen feature representation for weeds with varying morphologies and scales in low-altitude remote sensing imagery; (2) the design of a SlimNeck lightweight feature fusion architecture to improve multi-scale feature propagation efficiency while reducing computational cost; (3) the cascaded group attention mechanism (CGA) is integrated into the C2PSA module, thereby improving discrimination capability under complex background conditions. These results represent consistent improvements over baseline models, including YOLOv5, YOLOv6, YOLOv8, YOLOv11, and YOLOv12. Specifically, detection performance for broadleaf weeds and Poaceae weeds reached mAP@0.5 values of 87.2% and 73.9%, respectively. Overall, the proposed method demonstrates superior detection accuracy and stability for seedling-stage weed identification under rotation conditions, providing reliable technical support for variable-rate herbicide application and precision field management. Full article

Power system blackouts represent typical manifestations of instability in complex systems, whose evolution often exhibits non-stationarity, long-range correlations, and nonlinear scaling behavior. Most reliability assessment methods widely used in engineering practice are built on the core assumptions of event independence and light-tailed distribution, which will inevitably lead to systematic underestimation of extreme tail risks when blackouts actually present long-range memory and power-law heavy-tailed characteristics. Based on long-cycle historical blackout records of China’s power grid spanning 1981–2025, this paper develops an integrated framework combining Self-Organized Criticality (SOC) theory, Hurst exponent analysis, symbolic time-series methods, and Multifractal Detrended Fluctuation Analysis (MFDFA). This study systematically characterizes the evolution law and inherent dependence structure of blackout events from four dimensions: statistical scaling, temporal correlation, nonlinear structure, and multi-scale fractal spectrum. The results show that both the load-loss magnitudes and inter-event intervals of blackouts follow strict power-law distributions, with the system exhibiting scaling behavior consistent with SOC theory. The blackout event sequence presents significant long-range positive correlation and self-similarity, confirming a persistent long-term memory effect in the system evolution. Symbolic analysis further reveals the nonlinear fluctuation patterns and burst clustering behavior of the blackout process, reflecting the intermittency and complexity of blackout risks. MFDFA results verify that the blackout sequence has a broad-spectrum multifractal structure across different temporal scales, and Monte Carlo shuffle tests demonstrate that this multifractality mainly arises from intrinsic long-range temporal correlations, rather than being driven solely by heavy-tailed distribution. This study confirms that blackouts in China’s power grid are not random independent events, but present fractal statistical characteristics consistent with the self-organized critical mechanism. The findings provide a novel fractal perspective and quantitative framework for the statistical characterization, operational security assessment, and multi-scale early-warning modeling of blackout risks in China’s large-scale power systems. Full article

The synergistic integration of Hyperspectral Imaging (HSI) and Light Detection and Ranging (LiDAR) data has become a pivotal strategy in remote sensing for precise land-cover classification. However, existing multimodal deep learning frameworks frequently suffer from intrinsic limitations, including rigid feature extraction protocols, underutilization of LiDAR-derived textural information, and asymmetric fusion mechanisms that fail to balance the contribution of spectral and elevation features effectively. To address these challenges, this paper proposes a novel framework named DGC-BCAF, which integrates Dynamic Group Convolution and Bidirectional Guided Cross-Attention Fusion to achieve adaptive feature representation and robust cross-modal interaction. First, a Dynamic Group Convolution (DGConv) module embedded within a ResNet18 backbone is designed to function as the central spatial context extractor. Unlike traditional group convolution, this module learns a dynamic relationship matrix to automatically group input channels, thereby facilitating flexible and context-aware feature representation that adapts to complex spatial distributions. Second, to overcome the insufficient exploitation of elevation data, we introduce a dedicated LiDAR texture encoding branch. This branch innovatively fuses Gray-Level Co-occurrence Matrix (GLCM) statistical features with multi-scale convolutional representations, capturing both geometric height information and fine-grained surface textural details that are critical for distinguishing objects with similar elevations. Finally, central to our architecture is the Bidirectional Cross-Attention Fusion (BCAF) module. Unlike standard unidirectional fusion approaches, BCAF employs a LiDAR geometry to guide the selection of salient spectral bands, while simultaneously utilizing spectral signatures to emphasize informative LiDAR channels. This mutual guidance ensures a balanced contribution from both modalities. Extensive experiments conducted on three benchmark datasets—Houston 2013, Trento, and MUUFL—demonstrate that DGC-BCAF consistently outperforms state-of-the-art methods in terms of overall accuracy, average accuracy, and Kappa coefficient. The results confirm that the proposed adaptive grouping and bidirectional guidance strategies significantly improve classification performance, particularly in distinguishing spectrally similar materials and delineating complex urban structures. Full article

Microwave imaging is emerging as an alternative to conventional medical diagnostic techniques. Traditional analytical and numerical methods fail to adequately address these fundamental challenges: they often rely on strict linear approximations or simplified physical models, leading to low reconstruction accuracy, poor robustness, and limited generalization ability in complex clinical scenarios. As a result, they cannot meet the high-precision requirements of practical stroke microwave imaging. To further improve the accuracy of microwave imaging algorithms in recognizing stroke regions and solving the backscattering problem, this study employs a combination of methods with deep learning. It presents the Multi-Scale Attention Network (MSA-Net) for microwave imaging. The network is based on the EGE-UNet network structure with improved multi-axis Hadamard attention, incorporating null-space pyramid pooling and introducing a deep supervisory mechanism to improve the network performance further. To combine microwave imaging with deep learning, firstly, a large amount of microwave data need to be simulated with HFSS, in which the simulation model is a human brain stroke model constructed by an HFSS simulation system. Secondly, the microwave data obtained from the simulation are converted into a tensor format. Then, the tensor data are input into the MSA-Net neural network, which generates a binary mask image that can be used to detect the size and location of the stroke. This study also prompts the model to converge faster by sparsifying the microwave data to improve training efficiency. The method has been tested using simulation data, and based on the comparison experiments with other networks, MSA-Net is more accurate in detecting the location and the bleed size. The experimental results show that the proposed method is superior for stroke imaging. The experimental results show that the proposed model achieves a 1.08 improvement in peak signal-to-noise ratio and a 0.017 reduction in learned perceptual image block similarity, fully validating the effectiveness of the structural optimization strategy proposed in this paper. Full article

Hyperspectral imagery (HSI) offers rich spectral signatures and fine-grained spatial structures for remote sensing, but practical HSI classification is often constrained by scarce labels and complex geometric disturbances, including translation, rotation, scaling, and shear. Existing deep models are typically developed under Euclidean assumptions and rely on data-hungry training pipelines, which makes them brittle in the few-shot regime. To address this challenge, we propose EMNet, a Lie-group-based Equivariant Manifold Network for few-shot HSI classification that explicitly encodes geometric invariance and improves discriminative accuracy. EMNet couples an SE(2)-based Equivariance-Guided Module (EGM) to enforce equivariance to translations and rotations with an affine Lie-group-based Characteristic Filtering Convolution (CFC) that models scaling and shearing on the feature manifold while adaptively suppressing redundant responses. Extensive experiments on WHU-Hi-HongHu, Houston2013, and Indian Pines demonstrate state-of-the-art performance with competitive complexity, achieving OAs of 95.77% (50 samples/class), 97.37% (50 samples/class), and 96.09% (5% labeled samples), respectively, and yielding up to +3.34% OA, +6.01% AA, and +4.14% Kappa over the strong DGPF-RENet baseline. Under a stricter 25-samples-per-class protocol with 10 repeated random hold-out splits, EMNet consistently improves the mean accuracy while exhibiting lower variance, indicating better stability to sampling uncertainty. On the city-scale Xiongan New Area dataset with extreme long-tail imbalance (1580 × 3750 pixels, 256 bands, and 5.925 M labeled pixels), EMNet further boosts OA from 85.89% to 93.77% under the 1% labeled-sample protocol, highlighting robust generalization for large-area mapping. Beyond point estimates, we report mean ± SD/SE across repeated splits and provide rigorous statistical validation by computing Yule’s Q statistic for class-wise behavior similarity, performing the Friedman test with Nemenyi post hoc comparisons for multi-method ranking significance, and presenting 95% confidence intervals together with Cohen’s d effect sizes to quantify practical improvement. Full article

Bone marrow cell classification and nucleus segmentation in microscopic images are fundamental tasks for computer-aided diagnosis of lymphocytic leukemia. However, bone marrow cells from different subtypes exhibit high morphological similarity, and structural information is often constrained under optical microscopic imaging, posing challenges for stable and effective feature representation. To address this issue, we propose MTLL (Multitask Model on Lymphocytic Leukemia), a novel multitask approach that performs cell classification and nucleus segmentation within a unified network to exploit their complementary information. The model constructs a hybrid backbone for shared feature representation based on a CNN-Transformer architecture, in which Fuse-MBConv modules are tightly integrated with multilayer multi-scale transformers to enable deep fusion of local texture and global semantic information. For the segmentation branch, we design an AM (Atrous Multilayer Perceptron) decoder that combines atrous spatial pyramid pooling with multilayer perceptrons to fuse multi-scale information and accurately delineate nucleus boundaries. The classification branch incorporates prior knowledge of cell nuclei structures to capture subtle variations in cellular morphology and texture, thereby enhancing the model’s ability to distinguish between leukemia subtypes. Experimental results demonstrate that the MTLL model significantly outperforms existing advanced single-task and multi-task models in both lymphocytic leukemia classification and cell nucleus segmentation. These results validate the effectiveness of the multi-task feature-sharing strategy for lymphocytic leukemia diagnosis using bone marrow microscopic images. Full article

We study the predictability and cross-market structural similarity of Brent, WTI, and Dubai crude oil futures by means of a wavelet-based Sharma–Mittal energy entropy measure. The proposed framework combines multiresolution wavelet decomposition with a parametric generalised entropy, allowing the characterisation of informational complexity across scales and entropic parameters. We show that predictability is jointly scale- and parameter-dependent. Despite this dependence, the resulting wavelet entropy surfaces exhibit a high degree of geometric similarity across the three benchmarks. A discrepancy analysis further indicates that cross-market differences are localised in restricted regions of the parameter space, whereas intermediate scales are associated with maximal entropy values. Outside such regions, the entropy surfaces converge. Overall, the results provide evidence of a common multi-scale entropic structure underlying crude oil benchmarks, with regional effects affecting predictability without altering the global structural properties. These findings are consistent with the hypothesis of strong informational integration in global oil markets. Full article

Fluid mechanics in disordered structures gives rise to rich multiscale dynamics through the interplay of topology, symmetry breaking, and fluid–structure interactions. Heterogeneous networks encode mechanical responses, regulate flow organization, and shape energy dissipation, enabling memory effects and emergent collective behaviors across both natural and engineered systems. These principles operate across vast scales: from seamounts with characteristic scales of $L\approx {10}^3\mathrm{m}$ and Froude numbers $Fr\approx {10}^{-2}–{10}^{-1}$ generating deep-ocean turbulent mixing, to marine tidal turbines operating at Reynolds numbers $Re\approx {10}^7–{10}^8$ and Euler numbers $Eu\approx {10}^{-1}–{10}^0$, where inertial forces dominate flow dynamics. Although the dominant physical forces may vary across scales—for example, planetary rotation and stratification in large-scale oceanic flows versus viscous or interfacial effects in microscale systems—the comparison of dimensionless parameters provides a useful framework for discussing similarities in flow organization and scaling behavior. Empirical observations, network-based descriptions, and multiscale simulations collectively demonstrate how topological features constrain symmetry, organize transport pathways, and support predictive reconstruction and inverse design. These principles underpin applications ranging from engineered systems that exploit broken symmetries to rectify chaotic transport, to biological architectures where flows mediate information transfer, locomotion, and structural self-organization. In this Review, we synthesize recent advances to propose a unifying physical paradigm: fluid flows actively interact with disorder, reorganize dissipation, and convert structural asymmetry into functional mechanical performance across scales. Full article

Continuous representations in brain navigation system are manifested as spatially structured patterns of population activity, such as a single-peaked bump moving along a ring manifold in head-direction system and hexagonal lattice patterns underlying spatial representation in grid-cell systems. These phenomena are commonly modelled within the framework of continuous attractor networks (neural dynamical field), yet the mechanisms by which activation-function nonlinearities interact with connectivity structure to determine pattern selection and dynamics remain incompletely understood. This paper separately analyses the interactions between non-resonant and resonant modes using a multiscale unfolding approach. We show that, when the critical modes satisfy a resonance condition, the quadratic nonlinearity of the activation function induces a three-mode coupling that fundamentally alters the structure of the amplitude equations and becomes the dominant mechanism governing spatial pattern selection. Building on this analysis, we introduce a weak asymmetric component in the connectivity and analytically derive the resulting pattern drift velocity, which is subsequently confirmed by numerical simulations. Finally, we apply these dynamical mechanisms to input-driven scenarios, illustrating that similar dynamical mechanisms can account for activity-bump tracking in head-direction models and lattice translations in grid-cell models. Overall, this work provides an analytically tractable framework for studying pattern dynamics in neural field models relevant to spatial representations, and may inform biomimetic approaches to spatial representation and navigation. Full article