Search Results (22,357)

Deep learning–based pansharpening methods for remote sensing have advanced rapidly in recent years. However, current methods still face three limitations that directly affect reconstruction quality. Content adaptivity is often implemented as an isolated step, which prevents effective interaction across scales and feature domains. Dynamic multi-scale mechanisms also remain constrained, since their scale selection is usually guided by global statistics and ignores regional heterogeneity. Moreover, frequency and spatial cues are commonly fused in a static manner, leading to an imbalance between global structural enhancement and local texture preservation. To address these issues, we design three complementary modules. We utilize the Adaptive Convolution Unit (ACU) to generate content-aware kernels through local feature clustering, thereby achieving fine-grained adaptation to diverse ground structures. We also develop the Multi-Scale Receptive Field Selection Unit (MSRFU), a module providing flexible scale modeling by selecting informative branches at varying receptive fields. Meanwhile, we incorporate the Frequency–Spatial Attention Unit (FSAU), designed to dynamically fuse spatial representations with frequency information. This effectively strengthens detail reconstruction while minimizing spectral distortion. Specifically, we propose the Hybrid Attention Fusion Network (HAFNet), which employs the Hybrid Attention-Driven Residual Block (HARB) as the fundamental utility to dynamically integrate the above three specialized components. This design enables dynamic content adaptivity, multi-scale responsiveness, and cross-domain feature fusion within a unified framework. Experiments on public benchmarks confirm the effectiveness of each component and demonstrate HAFNet’s state-of-the-art performance. Full article

The realization of efficient and durable earth-abundant electrocatalysts for alkaline hydrogen evolution reaction (HER) is critical for scalable hydrogen production, yet remains limited by insufficient intrinsic activity. Herein, we demonstrate a precursor-controlled hydrothermal strategy that enables precise morphology and surface-state regulation of spinel Co₂NiO₄ directly grown on nickel foam, allowing a clear correlation between catalyst architecture and HER performance. By replacing urea with hexamethylenetetramine, an ultrathin, highly interconnected two-dimensional nanosheet network (CNO-HT) is obtained, which promotes efficient electron transport, rapid electrolyte penetration, and maximized exposure of catalytically active sites. Structural and spectroscopic analyses confirm the formation of phase-pure cubic Co₂NiO₄ with enriched mixed-valence Ni and Co species, favoring enhanced redox activity. The CNO-HT catalyst exhibits a low overpotential (86 mV at 10 mA cm⁻²) and a smaller Tafel slope (103 mV dec⁻¹), significantly outperforming the urea-derived counterpart. Importantly, the catalyst maintains stable HER operation for 96 h at both 10 and 100 mA cm⁻², with post-stability electrochemical analyses confirming preserved kinetics and interfacial properties. This work establishes precursor-regulated nanosheet engineering as general and scalable strategy to unlock the intrinsic catalytic potential of spinel metal oxides, offering actionable design principles for next-generation non-noble electrocatalysts for alkaline hydrogen production. Full article

Accurate extraction of building vector contours from high-resolution remote sensing images is a fundamental task for urban mapping and geographic information systems. However, existing approaches often suffer from blurred boundaries and geometric distortions when dealing with buildings of complex shapes, limiting the accuracy and usability of the extracted building footprints. To address these challenges, this paper proposes a multi-level building contour refinement framework based on morphological perception. The proposed framework integrates a three-stage contour optimization strategy, including principal direction extraction, morphology-based contour reconstruction, and geometry-aware regularization, to progressively refine complex building contours under geometric constraints. In addition, a multi-dimensional contour complexity model and an adaptive threshold optimization network are introduced to dynamically adjust refinement parameters according to contour complexity. Experimental results on the WHU-Mix dataset demonstrate that the proposed method outperforms state-of-the-art approaches, achieving 87.52%, 77.43%, and 87.35% in boundary F1, vertex F1, and mIoU, respectively. These results indicate that the proposed framework provides an effective and robust solution for high-precision building vector contour extraction in complex remote sensing scenarios. Full article

The heart’s performance relies on its contractile and rhythmic properties, which are modulated not only by extrinsic autonomic inputs but also by the intrinsic cardiac nervous system (ICNS), a distributed network of intracardiac ganglia and neurons that integrates local sensory, autonomic, and inflammatory signals. Growing evidence indicates that cardiac fibrosis and neuronal remodeling are intertwined processes within this network. This review synthesizes current knowledge on molecular, structural, and functional remodeling of the ICNS to drive neurofibrosis, autonomic imbalance, and arrhythmogenesis. We outline ICNS anatomy and neurochemical diversity, then summarize core fibrotic mechanisms, fibroblast activation, extracellular matrix dynamics, and inflammatory signaling, and map these onto intracardiac ganglia. Across diabetes, myocardial infarction, heart failure, and neuroinflammatory states, shared pathways (e.g., IL-6/STAT3, TGF-β/SMAD, PI3K/AKT, MAPK/ERK, oxidative stress) suppress neuronal excitability, promote neuron–glia–fibroblast coupling, and culminate in neurofibrotic remodeling. We integrate functional data linking these changes to autonomic dysregulation and arrhythmia vulnerability. Future priorities involve constructing detailed human ICNS atlases and applying single-cell and spatial multi-omics to better characterize intracardiac neurons, their circuitry, and their interactions with fibroblasts and immune cells. These insights will be essential to inform targeted neuromodulation and anti-fibrotic interventions. The ICNS is a dynamic regulatory hub whose cells and circuits participate directly in cardiac fibrosis and electrical instability. Recognizing neurofibrosis as a companion process to myocardial fibrosis reframes therapeutic strategy toward preserving both neural and myocardial integrity. Full article

Accurate estimation of the state of charge (SOC) of lithium-ion batteries is critical for assessing the safety and remaining range of electric vehicles. However, due to the complex and variable operating environment of batteries and their highly nonlinear internal mechanisms, achieving high-precision SOC prediction remains a central challenge in current research. To this end, this paper proposes a nonlinear Hammerstein model based on the Hippopotamus Optimization Algorithm (HO) to optimize the backpropagation neural network, thereby enhancing the accuracy of SOC prediction. The HO-BP-Hammerstein model optimizes the BP neural network architecture using the Hippopotamus Algorithm and conducts SOC prediction accuracy tests on real-world data. Experimental results demonstrate the superiority of the proposed method through comparative accuracy analysis of various SOC prediction approaches under different operating conditions, confirming its significant engineering application value. Full article

Image-Based Visual Servoing (IBVS) systems often suffer from instability due to measurement noise, modeling errors, and external disturbances. To address these issues, this study proposes a Visual Predictive Control framework integrating Radial Basis Function (RBF) and Extended Kalman Filter (EKF) coupled state-disturbance estimation and task-oriented K-means clustering. First, a feedback linearization Model Predictive Control (MPC) law is designed to handle system nonlinearities and physical constraints. Second, a coupled estimation mechanism is established where the EKF suppresses noise while the RBF network learns lumped disturbances. Crucially, to optimize network efficiency, a task-oriented K-means clustering method is introduced to select RBF centers based on the nominal IBVS path. Lyapunov analysis confirms the Uniformly Ultimately Bounded (UUB) stability. Simulation results demonstrate that the proposed method significantly reduces estimation errors and improves tracking accuracy compared to traditional schemes. Ultimately, this approach enhances the robustness and engineering practicality of robotic visual servoing through the deep coordination of control and estimation. Full article

Inflammatory and immune-mediated skin diseases are increasingly recognized as disorders in which genetic susceptibility is shaped and sustained by environmentally responsive regulatory programs. Psoriasis, atopic dermatitis (AD), vitiligo, systemic sclerosis (SSc), lupus erythematosus (LE), and lichen planus (LP) are clinically distinct, yet they share chronic or relapsing inflammation, tissue remodeling, and limited durability of many current therapies. Because genetic variation alone cannot fully explain disease onset, flare dynamics, heterogeneity in severity, or lesion recurrence, epigenetic mechanisms have emerged as a plausible link between environmental exposures and stable disease phenotypes in skin. Epigenetic regulation, including DNA methylation, histone modifications, and non-coding RNA networks, controls cell-type-specific transcription without altering the DNA sequence and may contribute to persistent inflammatory states and disease memory despite clinical improvement. The current review synthesizes primary preclinical and translational evidence on epigenetic-targeted therapeutic strategies across these conditions, focusing on interventions that modulate DNA methylation, histone acetylation and deacetylation, histone methylation, chromatin-associated regulatory proteins, and RNA-based approaches. We compare the maturity of therapeutic development across diseases, noting that research and intervention studies are concentrated in psoriasis and AD, whereas evidence for vitiligo, SSc, LE, and LP remains more limited and often derived from systemic or non-cutaneous models. Finally, we outline key gaps that currently restrict clinical translation and discuss why bridging them is essential for determining whether epigenetic modulation can move beyond proof-of-concept toward durable and clinically actionable interventions in inflammatory skin disease. Full article

In underwater detection tasks involving bleached corals, band disease corals, and white pox disease corals, several challenges persist, including high morphological variability, difficulty in identifying small pathological regions, interference from complex underwater environments, and constraints imposed by underwater hardware. To address these issues, a lightweight underwater diseased coral target detection method, termed CD-YOLO, is proposed. Specifically, (1) a lightweight network named CDShuffleNet is constructed to replace the YOLO11 backbone, aiming to reduce model complexity while preserving detection performance; (2) a SPDConv downsampling convolution module is introduced to reduce the loss of fine-grained coral detail information during the downsampling process; and (3) attention mechanisms are incorporated through an engineering-oriented integration of EMA into the C2PSA module and the adoption of SENetV2, in order to enhance the representation of color and shape features of pathological regions and suppress interference from complex underwater environments. Experimental results demonstrate that the proposed improvements yield consistent gains in both model lightweighting and detection performance under the adopted evaluation settings. Specifically, the number of parameters, computational cost, and model size are reduced by 20.6%, 21.9%, and 18.9%, respectively, while mAP increases by 4.3 percentage points. Comparative experiments further show that the proposed method achieves a markedly higher mAP than several other state-of-the-art models. In addition, experiments conducted on the BHD Coral dataset provide preliminary evidence of cross-dataset adaptability of the proposed model. Overall, this study presents a task-oriented and application-driven improvement, demonstrating that the effective integration of lightweight components can achieve a favorable balance between model efficiency and detection performance in underwater diseased coral detection tasks. Full article

Understanding the intimate interactions between plants and their microbiota at the cellular level is essential for unlocking the full potential of plant holobionts in agricultural systems. Traditional bulk and microbial community-level sequencing approaches reveal broad community patterns but fail to resolve how distinct plant cell types interact with or regulate microbial colonization, as well as the diverse antagonistic and synergistic interactions and responses existing between various microbial populations. Recent advances in single-cell and spatial multi-omics have transformed our understanding of plant cell identities as well as gene regulatory programs and their dynamic regulation in response to environmental stresses and plant development. In this review, we highlight the single-cell discoveries that uncover the plant cell-type-specific microbial perception, immune activation, and symbiotic differentiation, particularly in roots, nodules, and leaves. We further discuss how integrating transcriptomic, epigenomic, and spatial data can reconstruct multilayered interaction networks that connect plant cell-type-specific regulatory states with microbial spatial niches and inter-kingdom signaling (e.g., ligand–receptor and metabolite exchange), providing a foundation for developing new strategies to engineer crop–microbiome interactions to support sustainable agriculture. We conclude by outlining key methodological challenges and future research priorities that point toward building a fully integrated cellular interactome of the plant holobiont. Full article

Non-line-of-sight (NLOS) propagation remains a major obstacle to high-accuracy ultra-wideband (UWB) indoor positioning. To address this issue, this study investigates solutions from two complementary perspectives: NLOS identification and error mitigation. First, an NLOS signal classification model is proposed based on multidimensional statistics of the channel impulse response (CIR). The model incorporates an attention mechanism and an improved snake optimization (ISO) algorithm, achieving significantly enhanced classification accuracy and robustness. For error mitigation, a UKF–BiLSTM dual-directional mutual calibration framework is proposed to dynamically compensate for NLOS errors. The framework embeds the constant turn rate and velocity (CTRV) motion model within an unscented Kalman filter (UKF) to enhance trajectory modeling. It establishes a bidirectional correction loop with a bidirectional long short-term memory (BiLSTM) network. Through the synergy of physical constraints and data-driven learning, the framework adaptively suppresses NLOS errors. Experimental results show that the proposed framework achieves state-of-the-art–comparable performance with improved model efficiency in complex indoor UWB positioning scenarios. Full article

The endocannabinoid system is a ubiquitous neuromodulatory network that links internal physiological state to neural circuit function across the brain. While its roles in memory, reward, pain, and motor control are well established, its contribution to olfactory processing has only recently gained attention. This review synthesizes the current knowledge on the anatomical, cellular, and functional interactions between the endocannabinoid system and the olfactory pathway, from the olfactory epithelium and main olfactory bulb to higher order cortical targets. We highlight how endocannabinoid signaling, primarily via cannabinoid receptor type 1 (CB1), shapes synaptic transmission within olfactory bulb microcircuits, modulates centrifugal feedback, and adjusts sensory gain in a state-dependent manner, particularly in relation to hunger, feeding behavior, stress, and reward. In addition, we review evidence that the endocannabinoid system regulates olfactory neurodevelopment and adult neurogenesis by influencing neural stem cell proliferation, migration, and integration into existing circuits. Emerging links between endocannabinoid signaling, olfactory dysfunction, neuropsychiatric disease, metabolic disorders, and neurodegeneration underscore the translational relevance of this system. We also discuss methodological challenges inherent to studying endocannabinoid signaling and outline future directions, including circuit-specific targeting and intranasal delivery strategies. Together, these findings position the olfactory system as a powerful and accessible model for understanding how endocannabinoids couple internal state to perception and behavior, with important implications for therapeutic development. Full article

Automatic emotion recognition based on EEG has been a key research frontier in recent years, involving the direct extraction of emotional states from brain dynamics. However, existing deep learning approaches often treat EEG either as a sequence or as a static spatial map, thereby failing to jointly capture the temporal evolution and spatial dependencies underlying emotional responses. To address this limitation, we propose an Interpretable Residual Spatio-Temporal Graph Attention Network (IRSTGANet) that integrates temporal convolutional encoding with residual graph-attention blocks. The temporal module enhances short-term EEG dynamics, while the graph-attention layers learn adaptive node connectivity relationships and preserve contextual information through residual links. Evaluated on the DEAP and SEED datasets, the proposed model achieved exceptional performance on valence and arousal, as well as four-class and nine-class classification on the DEAP dataset and on the three-class SEED dataset, exceeding state-of-the-art methods. These results demonstrate that combining temporal enhancement with residual graph attention yields both improved recognition performance and interpretable insights into emotion-related neural connectivity. Full article

Monitoring the concentration of Total Volatile Fatty Acids (TVFA (M)) is critical for ensuring the stability and efficiency of the Anaerobic Digestion (AD) process although conventional laboratory methods are often time-consuming and hinder real-time control. This study develops soft sensors based on machine learning techniques to predict TVFA (M) levels using readily available parameters such as pH, pCO₂, and Total Ammoniacal Nitrogen (TAN). A primary contribution of this work is the comprehensive benchmarking of the proposed approach against current State-of-the-Art (SOTA) deep learning and machine learning models including XGBoost, Random Forest, TorchMLP, and the advanced RealTabPFN-v2.5. Experimental results demonstrate that the RealTabPFN-v2.5 model outperforms other modern algorithms by achieving the highest accuracy with an R² of 0.889 and the lowest error rate with an RMSE of 0.0079. SHAP (SHapley Additive exPlanations) analysis was employed to interpret the model’s predictions, identifying pH as the most influential factor in TVFA (M) prediction and confirming that the model’s decision-making process aligns with established biological principles. These findings highlight the significant potential of integrating SOTA machine learning models into intelligent monitoring systems for the automation and optimization of biogas production processes. Full article

The foundation of an automatic sign language training (ASLT) system lies in word-level sign language recognition (WSLR), which refers to the translation of captured sign language signals into sign words. However, two key issues need to be addressed in this field: (1) the number of sign words in all public sign language datasets is too small, and the words do not match real-world scenarios, and (2) only single-view sign videos are typically provided, which makes solving the problem of hand occlusion difficult. In this work, we design an efficient algorithm for WSLR which is trained on our recently released NationalCSL-DP dataset. The algorithm first performs frame-level alignment of dual-view sign videos. A two-stage deep neural network is then employed to extract the spatiotemporal features of the signers, including hand motions and body gestures. Furthermore, a front-view guided early fusion (FvGEF) strategy is proposed for effective fusion of features from different views. Extensive experiments were carried out to evaluate the algorithm. The results show that the proposed algorithm significantly outperformed existing dual-view sign language recognition algorithms. Compared with several state-of-the-art methods, the proposed algorithm achieves Top-1 accuracy on the NationalCSL6707 dataset that is 10.29 and 11.38 higher than MViT and CNN + Transformer, respectively. Full article

Background/Objectives: The variable accuracy of middle ear disease diagnosis based on oto-endoscopy underscores the need for improved decision support. Although convolutional Neural Networks (CNNs) are currently a mainstay of computer-aided diagnosis (CAD), their constraints in global feature integration persist. We therefore systematically benchmarked state-of-the-art CNNs and Transformers to establish a performance baseline. Beyond this benchmark, our primary contribution is the development of a probability-guided Top-K clinical decision framework that balances high accuracy with complete case coverage for practical deployment. Methods: Using a multicenter dataset of 6361 images (five categories), we implemented a two-stage validation strategy (fixed-split followed by 5-fold cross-validation). A comprehensive comparison was performed among leading CNNs and Transformer variants assessed by accuracy and Macro-F1 score. Results: The Swin Transformer model demonstrated superior performance, achieving an accuracy of 95.53% and a Macro-F1 score of 93.37%. It exhibited exceptional stability (95.61% ± 0.38% in cross-validation) and inherent robustness to class imbalance. A probability-guided Top-2 decision framework was developed, achieving 93.25% accuracy with 100% case coverage. Conclusions: This rigorous benchmark established Swin Transformer as the most effective architecture. Consequently, this study delivers not only a performance benchmark but also a clinically actionable decision-support framework, thereby facilitating the deployment of AI-assisted diagnosis for chronic middle ear conditions in specialist otology. Full article