Search Results (843)

Electrospinning (ES) can produce nonwoven fibrous mats with high surface area and interconnected porosity, making them attractive for biomedical and functional material applications. However, conventional ES often relies on volatile organic solvents, raising safety, environmental, and translational concerns. Fully aqueous (“green”) ES offers an appealing alternative, although many water-soluble polymers remain difficult to spin and may show limited stability under hydrated conditions. In this study, two fully aqueous binary systems, poly(vinylpyrrolidone)–sodium alginate (PVP–SA) and poly(vinylpyrrolidone)–riboflavin (PVP–RF), were investigated to decouple the roles of sodium alginate (SA) and riboflavin (RF) on solution behaviour, fibre formation, morphology, dry-state mechanical properties, and surface chemistry. Aqueous PVP solutions (20% w/v; molecular weight 1.3 MDa) were blended with SA (1–5 wt% relative to PVP) or RF (1–10 wt% relative to PVP). Electrical conductivity and rheological properties were evaluated prior to ES under controlled conditions, with simultaneous ultraviolet (UV) exposure at 344 nm during fibre collection. RF did not significantly alter conductivity (~0.74–0.75 µS·cm⁻¹), whereas SA increased conductivity up to 2.75 ± 0.03 µS·cm⁻¹ at 5 wt%. All formulations exhibited shear-thinning behaviour, while 10 wt% RF increased the zero-shear viscosity relative to neat PVP. Morphological analysis showed that low SA contents produced uniform fibres, whereas higher SA levels (4–5 wt%) led to bead defects and reduced fibre diameter (down to 85 ± 25 nm). Dry-state mechanical performance decreased with increasing SA content, while 10 wt% RF improved tensile strength and toughness, reaching an ultimate tensile strength of 5.21 ± 0.15 MPa and toughness of 40.51 ± 1.53 MJ·m⁻³. Fourier transform infrared spectroscopy (FTIR) and X-ray photoelectron spectroscopy (XPS) indicated subtle UV-driven redistribution of surface chemical states, consistent with mild photo-oxidative microstructural modification rather than extensive covalent network formation. Because the UV irradiance was not directly measured and wet-state stability was not assessed, the UV-related findings are interpreted as preliminary chemical evidence rather than confirmation of stabilized fibre mats. Overall, this work establishes a solvent-free aqueous ES platform in which ionic and photoactive additives can be used to tailor fibre morphology, dry-state mechanical behaviour, and surface characteristics without toxic reagents. Full article

The problem of bilevel decision-making under multi-expert uncertain information is addressed in this paper. Traditional fuzzy bilevel models are unable to accurately quantify expert consensus and capture evaluation hesitation. To overcome these limitations, a fully hesitant fuzzy bilevel linear programming model is proposed, in which all coefficients and decision variables are characterized by hesitant fuzzy numbers. By virtue of $(\alpha ,k)$-cuts, the original model is equivalently transformed into an interval-valued bilevel programming problem and further decomposed into best–best and worst–worst sub-models to derive the upper and lower bounds of optimal solutions. Under the Slater constraint qualification, Karush–Kuhn–Tucker (KKT) conditions are adopted to convert the two sub-models into single-level mathematical programs with complementarity constraints (MPCCs), thereby enabling efficient model solving. The proposed method is applied to the resource allocation problem in quantum communication networks. The numerical results demonstrate that the optimal solution interval converges to a unique core value as the membership-level $\alpha$ increases, while a larger consensus parameter k reduces the fuzzy support set without altering the core solution. Full article

All-in-one weather-degraded image restoration aims to restore clean images from diverse weather-degraded observations (such as rain, haze, and snow) using a unified model. However, this topic remains challenging due to its ill-posed nature and the scarcity of large-scale paired training data. This article develops a novel semi-supervised learning framework, termed Semi-Supervised Degradation-Aware Learning (S²DAL), to adjust the feature space to align with the unified parameter space for all-in-one adverse weather removal. Specifically, the proposed S²DAL consists of two backbone networks: a Degradation-guided Histogram Transformer (DHformer) for weather-degraded image restoration and a Degradation-guided Convolutional Neural Network (DCNN) for degradation generation. A key component, the Degradation-guided Histogram Transformer (DHT) block, is designed to effectively capture intrinsic image features while suppressing diverse degradation interference through channel shuffling modulation, dynamic-range histogram self-attention, and dual-scale gated feed forward. Furthermore, a Monte Carlo-based Expectation-Maximization (EM) algorithm is introduced to jointly optimize latent variables and network parameters under both labeled and unlabeled data. Extensive quantitative and qualitative results on synthetic and real-world datasets consistently demonstrate that the proposed S²DAL achieves superior restoration performance compared to multiple state-of-the-art fully supervised and semi-supervised approaches. Full article

Object detection in remote sensing imagery plays an irreplaceable role in critical fields such as military reconnaissance and disaster monitoring. However, when dealing with minute targets characterised by an extremely low pixel proportion, a lack of textural information, and severe background interference, existing algorithms still face the challenge of balancing detection accuracy with computational efficiency. To address this, this paper proposes a lightweight frequency-domain-aware end-to-end detection model, LE-DETR, based on an improved version of RT-DETR. Firstly, a Lightweight Feature Extraction Module (LFEM) is designed. Through a heterogeneous dual-path architecture and reparameterisation techniques, it significantly reduces computational complexity whilst enhancing the capture of fine-grained spatial features. Secondly, an Efficient Spatio-Frequency Fusion Module (ESFFM) is introduced. This utilises a multi-head self-attention mechanism to construct a global view whilst combining the Fourier transform to reconstruct target features from a frequency-domain perspective, thereby effectively suppressing background noise and enhancing the target’s edge signals. Finally, we propose the Efficient Frequency-Aware Fusion Feature Pyramid Network (EFAM-FPN), which utilises SPD Conv to mitigate the loss of key features during downsampling and introduces a frequency-domain attention mechanism to suppress complex background noise, thereby improving the model’s detection accuracy for extremely small objects. The experimental results show that, whilst reducing the number of parameters by 41.7% compared to the baseline model, LE-DETR achieved improvements of 2.6%, 1.7% and 2.4%, respectively, in the mAP50 metric across the three mainstream remote sensing datasets—VisDrone2019, NWPU VHR-10 and DIOR. This demonstrates an effective balance between detection accuracy and inference efficiency, fully validating its robustness and practical value in complex remote sensing application scenarios. Full article

Atherosclerosis (AS) is the primary underlying cause of cardiovascular and cerebrovascular diseases. The occurrence and development of AS are closely related to lipid deposition, chronic inflammation, phenotypic modulation of vascular smooth muscle cells (VSMCs), and extracellular matrix (ECM) remodeling. Numerous studies indicate that low-density lipoprotein receptor-associated protein 1 (LRP1), as a multifunctional receptor, contributes to vascular homeostasis in AS and vascular remodeling by regulating lipid handling, inflammatory responses, transforming growth factor beta (TGFβ) signaling, and platelet-derived growth factor receptor beta (PDGFRβ) trafficking. Rather than treating the LRP1-TGFβ-PDGFRβ relationship as a fully established linear pathway, this review distinguishes demonstrated mechanisms from inferred cross-talk and proposes an integrated, cell- and stage-dependent regulatory model. This article systematically elaborates on the structure and function of LRP1; LRP1-mediated regulation of TGFβ and PDGFRβ in AS and vascular remodeling; the possible relationship among LRP1, TGFβ, and PDGFRβ; and cell-specific effects in VSMCs, macrophages, endothelial cells, and pericytes. Meanwhile, this article summarizes potential translational strategies such as lipid-lowering, anti-inflammatory therapy, PDGFRβ inhibitor repositioning, TGFβ pathway modulation, biomarker-based stratification, and LRP1-targeted delivery. A deeper understanding of the cell-specificity and stage-dependence of the LRP1-TGFβ-PDGFRβ signaling network may help elucidate the progression mechanism of AS and provide new ideas for risk stratification and precise intervention. Full article

Probabilistic risk assessment of complex offshore oil and gas systems is often challenged by scarce statistical data and multiple uncertainties. Traditional point-value probability and standard Bayesian networks cannot fully represent and propagate these uncertainties, which may mislead high-risk security decision-making. To address this issue, this paper proposes a new hybrid risk assessment framework that combines interval-valued T-spherical fuzzy sets (IVTSFS) with credal networks (CN). First, IVTSFS is used to quantify the subjective risk perception of multiple experts, effectively capturing hesitancy, fuzziness, and group disagreement. An improved probability mapping mechanism is introduced to align linguistic evaluations with objective failure frequency spaces, thereby avoiding systemic transformation biases. Subsequently, the interval conditional probability table is constructed using the imprecise leakage noise-OR model, which alleviates the problem of parameter dimension explosion in complex causal structure and explicitly retains the parameter uncertainty. The 2U algorithm is then applied to perform accurate interval inference in CN. The feasibility and comparative advantages of the method are illustrated in the actual case of the single-point mooring system. The results clearly output the upper and lower bounds of the system failure risk, and identify the key vulnerable nodes through diagnostic reasoning and sensitivity analysis. This study has theoretical contributions in fuzzy decision-making and uncertainty modeling. By unifying advanced fuzzy cognitive quantification and imprecise probability propagation, it provides a structured uncertainty representation tool for expert-informed risk screening under data scarcity. Full article

As recent Multi-Layer Perceptron (MLP) mixer models have achieved state-of-the-art performance in time series forecasting, modeling each MLP-mixer as a separate expert within a mixture is expected to extend the representational capacity of the model, allowing each expert to be activated in response to time-varying inputs. However, extending MLP-mixers into a Mixture-of-Experts (MoE) architecture introduces a significant increase in the number of trainable parameters, rendering the model more challenging to train. To mitigate this problem, we propose a method that composes a fully trainable global expert and multiple non-trainable local experts. Specifically, our approach clones the weights of the global expert into the local experts and then modifies their weight distributions using moment learning, a recently proposed unconventional method for training neural networks. Concretely, each local expert is produced by applying moment-based transformations to a shared copy of the global expert’s weights, so that expert specialization is obtained without independently training the additional experts. Experimental results using a lightweight Time Series Mixer (TSMixer) architecture demonstrate that our method achieves performance competitive with fully trainable MoE counterparts, without introducing a significant increase in trainable parameters. Across multiple benchmark settings, the proposed model attains forecasting accuracy on par with, and in several cases favorable to, a fully trainable multi-expert baseline while adding only a small fraction of the extra trainable parameters that such a baseline requires, and this efficiency is further corroborated by measurements of memory footprint as well as an effect-size-based assessment of the observed differences. Full article

Medical image registration integrates information from different types of medical images to support and improve clinical diagnosis. Existing image registration approaches are mainly classified into two categories: model-driven methods and data driven methods. Model-driven methods can achieve high registration accuracy but suffer from low computational efficiency and long processing time. In contrast, data-driven methods stand out for their high efficiency, which gives them great practical value. Taking this advantage as the core basis, this paper proposes a simple unsupervised deep learning framework embedded with a multi-scale strategy. The overall network consists of two core modules: an Affine Transformation Network (AT-Net) and a multi-scale Deformable Transformation Network (DT-Net). The multi-scale design adopted in the DT-Net enables image registration at different feature scales, which effectively improves the overall registration accuracy. In addition, a dual consistency constraint is introduced into the framework to further enhance the model robustness. The entire network realizes end-to-end medical image registration. We verified the performance of the proposed method on a public dataset, with mutual information (MI) adopted as the evaluation metric. The experimental results show that our registration algorithm outperforms several mainstream methods, including Symmetric Image Normalization (SyN), VoxelMorph (VM), the coarse-to-fine deformable transformation framework for unsupervised multi-contrast MR image registration with dual consistency constraint (C-F-I-R), TransMorph and DiffuseMorph. The comparative experiments fully demonstrate that combining the multi-scale strategy with deep learning techniques is an effective solution for medical image registration tasks. Full article

Vertebral compression fractures (VCFs) are one of the most common spinal disorders encountered clinically. Untimely diagnosis or inaccurate classification often leads to prolonged pain and functional impairment in patients. To enhance diagnostic accuracy and efficiency, this study addressed the high cost and limited applicability of computed tomography (CT) and magnetic resonance imaging (MRI) examinations by leveraging the universality and convenience of X-ray imaging. We proposed a multi-stage deep learning-based method for identifying vertebral compression fractures. The method first employs Discrete Wavelet Transform-YOLOv5 (DWT-YOLOv5) for preliminary vertebral region localization, followed by Polarized Self-Attention-UNet (PSA-UNet) for precise segmentation. Finally, a ResNet50 network incorporating a Convolutional Block Attention Module (CBAM) performs graded classification, categorizing vertebrae into four types: Non-fracture, Mild fracture, Moderate fracture, and Severe fracture. The experimental results demonstrate that the proposed method achieved average accuracy, precision, recall, specificity, and F1-score of 83.7%, 88.1%, 86.2%, 97.7%, and 87.2%, respectively. The proposed method fully leverages the cost-effectiveness and convenience of X-ray imaging, providing clinicians with an efficient and economical auxiliary diagnostic tool. It enables rapid and accurate identification of vertebral compression fractures in emergency and initial screening scenarios. Full article

Red tide events pose substantial threats to marine ecosystems, aquaculture, and coastal public health. Timely and accurate delineation of red tide extent from satellite imagery is therefore essential for operational monitoring and early warning. However, existing deep learning-based semantic segmentation methods generally treat multispectral bands as homogeneous inputs and do not fully exploit the domain knowledge embodied in spectral indices commonly used in traditional remote sensing analysis. To address this limitation, this study proposes a spectral-index-guided network (SIG-Net) that explicitly incorporates spectral-index priors into deep feature extraction through a dual-branch architecture. SIG-Net comprises three components: a spectral encoder based on a Mix Vision Transformer (MiT-B2) that learns spatial-spectral representations from the original Sentinel-2 bands; a lightweight CNN-based index encoder that extracts discriminative features from four spectral indices, namely the red-green index (RGI), blue-green index (BGI), normalized difference vegetation index (NDVI), and the normalized difference Noctiluca index (NDNI) proposed in this study; and a spectral-index-guided fusion (SIGF) module that adaptively integrates multi-scale features from the two branches using spatial-reduction cross-attention and a gated fusion mechanism. Experiments on a Sentinel-2 red tide dataset show that SIG-Net outperforms single-branch baselines, including U-Net, DeepLabV3+, and SegFormer, as well as naive multi-source fusion strategies. Ablation studies further confirm the contributions of the SIGF module, the gating mechanism, and the proposed NDNI to performance improvements. The proposed method provides an effective framework for integrating domain knowledge with deep learning for red tide remote sensing monitoring. Full article

Accurate, non-invasive body weight estimation is essential for management and performance monitoring in beef cattle systems, yet conventional scales and manual measurements require animal handling, infrastructure, and labor. This study presents an integrated pipeline that segments cattle from overhead depth images and predicts body weight from extracted image features. The approach uses a Light Attention Encoder–Decoder (LAED) segmentation model combining depthwise separable convolutions, Gaussian Context Transformer (GCT) attention, a multi-scale dilated bottleneck, and dual heads for region and boundary prediction. Depth videos were collected using an overhead Intel RealSense D435 RGB-D camera from 60 beef heifers. To reduce animal-level leakage, leave-one-animal-out cross-validation was used for segmentation. LAED + GCT achieved 96.91% Dice (95% confidence interval (CI): 96.56–97.21%) and 94.22% IoU (95% CI: 93.58–94.77%), while operating at 33.08 frames per second. For weight prediction, biometric traits and deep features were evaluated using random forest, support vector regression, and fully connected neural networks. The best primary-metric body-weight model used biometric traits with support vector regression, achieving MAPE = 6.75%, pooled $R^2$ = 0.68, MAE = 23.92 kg, and RMSE = 31.79 kg. Among FCNN models trained independently within each cattle-level fold, the best result used ResNet50 features and achieved MAPE = 7.76%, a pooled $R^2$ = 0.56, an MAE = 27.60 kg, and an RMSE = 37.07 kg. The mean signed prediction bias for the biometric-SVR model was −1.04 kg, using predicted minus observed body weight, with a bootstrap 95% confidence interval of −9.63 to 7.41 kg. These results support the promise of overhead depth imaging for non-invasive cattle body segmentation and weight estimation, while larger external validation remains necessary. Full article

Emotion recognition through electroencephalogram (EEG) signals is crucial for brain–computer interfaces (BCIs), yet existing methods often struggle with heterogeneous feature fusion and capturing long-range temporal dependencies. To address these challenges, we propose MAF-TransNet, a novel unified spatiotemporal framework. Specifically, parallel Fully Connected Neural Network (FCNN) modules first non-linearly align heterogeneous differential entropy (DE) and power spectral density (PSD) features. Subsequently, an Adaptive Channel-wise Feature Encoder (ACFE) recalibrates spatial–spectral responses to highlight emotion-relevant cortical activations. Finally, a Transformer encoder dynamically models the global temporal evolution of emotional states. Evaluated on the SEED-IV and DEAP datasets, MAF-TransNet achieves superior subject-dependent (SD) accuracies of 88.80% and 96.58%, respectively, alongside robust subject-independent (SI) performance. Furthermore, Granger causality analysis reveals distinct emotion-dependent prefrontal asymmetry, while t-SNE visualizations confirm the formation of a highly discriminative, linearly separable feature manifold. Ultimately, MAF-TransNet effectively unifies local spatial–spectral extraction with global temporal modeling, providing an accurate and robust approach, while offering preliminary insights into the spatiotemporal dynamics of emotion for future affective BCI applications. Full article

Semantic segmentation of large-scale airborne point clouds traditionally relies on labor-intensive 3D manual annotations. While recent zero-shot methods attempt to alleviate this burden by distilling knowledge from 2D Vision–Language Models (VLMs) via 2D-to-3D projection, they suffer from performance degradation in complex urban environments. Specifically, lacking 3D geometric awareness, 2D VLMs frequently exhibit “semantic bleeding”, where large-scale background categories (e.g., ground) erroneously submerge small-scale targets (e.g., vehicles and street elements). To address this issue, we propose a geometry-constrained pseudo-label generation and purification framework. Our approach tackles the problem through a dual-branch design: extracting open-vocabulary semantics via SAM3-based multi-view projection while simultaneously deriving sharp, class-agnostic instances using SAM2 on Gamma-transformed elevation maps. By introducing a geometric–semantic consistency module, we evaluate the internal semantic purity and external spatial homogeneity of these instances, detecting and filtering out semantic misclassifications. The purified pseudo-labels are then used to supervise a 3D sparse convolutional network via a Masked Cross-Entropy Loss. Experiments on the H3D and Turin3D datasets demonstrate that our method recovers small-scale targets that are prone to being submerged, outperforming existing zero-shot baselines by improving mIoU from 52.15% to 63.45% on H3D and from 29.52% to 58.51% on Turin3D, thereby narrowing the performance gap with fully-supervised approaches. Full article

The operational health state of motor bearings is critical to the operational safety of harbor portal slewing cranes. However, in harsh industrial environments with strong noise and time-varying rotational speeds, existing bearing fault diagnosis methods still suffer from the problems of incomplete fault feature extraction from single-sensor signals and the excessively large size of multi-source fusion models, which makes them unable to adapt to edge deployment. To address these issues, this paper proposes a Multi-source Feature Fusion Lightweight Network (MTFL-Net) integrated with targeted structured channel pruning. First, vibration and current signals are preprocessed via differentiated time-frequency transformation and converted into 2D time-frequency images, to fully preserve transient impact and spectral fault features. Second, a multi-branch feature extraction architecture embedded with residual connections, multi-scale convolution and channel attention gating is designed, to alleviate feature degradation and adaptively enhance fault-sensitive features. Third, targeted structured channel pruning is performed on the feature extraction branches, to remove redundant channels while retaining the multi-source fusion logic and core feature extraction structure. Experiments on two public bearing datasets show that the original model achieves 99% diagnostic accuracy, and the pruned model still maintains an accuracy of 95%. The results demonstrate that MTFL-Net can significantly reduce model size and computational cost while retaining high diagnostic precision. Full article

Magnesium-based hydrides remain among the most intensively studied solid-state hydrogen storage materials because they combine high theoretical hydrogen capacity, elemental abundance, and relatively low cost. Yet their practical behavior often varies far more strongly than nominal composition alone would suggest. Materials described under similar chemical labels may show markedly different activation profiles, sorption kinetics, reversible capacities, and cycling responses, even when they appear compositionally comparable. This Perspective argues that such discrepancies are best understood by recognizing that Mg-based hydrogen storage materials are not fully defined by composition, catalyst identity, and equilibrium thermodynamics alone. Instead, they react from historically written states produced by synthesis, activation, and cycling. These histories generate hidden state variables, including defects, residual strain, metastable structural motifs, interfacial topology, and catalyst transformation states, that reshape the operative hydrogen sorption pathway. The discussion therefore moves from a conventional composition-centered view toward a pathway-centered interpretation of reactivity. First, it examines how hidden state variables are written into Mg-based materials through processing, activation, and repeated use. It then shows how metastability serves as the structural bridge that allows these variables to persist into the reaction window. On that basis, the article argues that hydrogen sorption in Mg-based hydrides is fundamentally pathway-dependent, with history influencing hydrogen entry, transport-network selection, interfacial route construction, and pathway evolution during cycling. This perspective also provides a more coherent explanation for the long-standing reproducibility problem in the field, which is reinterpreted here as a pathway-mismatch problem arising from comparisons among historically different reactive states. Finally, a metadata-aware, pathway-aware, and boundary-aware design framework is proposed as a more realistic basis for cumulative materials development. From this viewpoint, the future of Mg-based solid-state hydrogen storage depends not only on better compositions, but on better-defined, better-constructed, and better-preserved reactive pathways under clearly specified internal and external constraints. Full article