Search Results (1,589)

The governance of land use carbon emissions is pivotal to achieving the goals of carbon peak and carbon neutrality. Rural revitalization significantly shapes the spatiotemporal patterns and evolutionary dynamics of land use carbon emissions, yet this relationship has received inadequate attention in existing literature. This study employs a combination of decoupling models, the Boston Matrix, spatial analysis, and interpretable machine learning models to conduct an empirical analysis of 124 regions in western China. The findings reveal diversified spatiotemporal evolution trends in rural revitalization land use carbon emissions. The decoupling relationship between rural revitalization and carbon emissions demonstrates a polarized nature, with over half of the assessed regions experiencing negative decoupling effects. The role of impact factors in decoupling relationships is characterized by a mixed nature, hierarchical intensity, nonlinear pathways, spatial heterogeneity and autocorrelation. The pathways of factor effects display nonlinear forms such as wave-like, inverted U-shaped, and U-shaped patterns, with the nature and intensity of effects dynamically shifting between “threshold mutations” and “inflection reversals” as factors evolve. The spatiotemporal evolution patterns, decoupling relationships, and SHAP values all exhibit significant spatial autocorrelation and form “spatial clusters” of various shapes. The decoupling of rural revitalization and carbon emissions in western China constitutes a complex systemic endeavor, necessitating comprehensive analysis from multiple dimensions—encompassing spatiotemporal evolution patterns, decoupling relationship, nonlinear mechanisms, and spatial effects—followed by the formulation of differentiated and precision-targeted governance strategies. Full article

The growing demand for sustainable and high-performance materials has positioned cellulose as a key biopolymer for next-generation functional systems. Beyond its traditional use, cellulose undergoes a qualitative transformation at the nanoscale, where increased surface area, interfacial dominance, and tunable chemistry enable functions unattainable in bulk form. This review provides a critical and integrative analysis of functionalization strategies governing the transition from structural modification to application-specific performance in cellulose and nanocellulose-based materials. A unified structure–property–function–process (SPFP) framework is introduced to systematically connect modification approaches with resulting structural features, physicochemical properties, and functional outcomes. Chemical, physical, and surface/interface modification strategies are comparatively evaluated with respect to their efficiency, scalability, and environmental trade-offs. Rather than cataloguing methods, the review emphasizes cross-domain synthesis and identifies key limitations, including high energy demand, reagent consumption, structural instability, and challenges in large-scale implementation. Particular attention is given to applications in biomedicine, environmental remediation, and energy technologies, where performance is governed by surface reactivity, accessibility, and hierarchical organization. The analysis highlights that no single modification strategy is universally optimal, and that effective material design requires balancing performance, sustainability, and process feasibility. By integrating conceptual frameworks, comparative analysis, and emerging design principles, this review provides a forward-looking perspective on the development of cellulose-based functional materials, supporting their transition from laboratory-scale demonstrations to application-ready technologies. Full article

Accurate farmland boundary mapping from high-resolution aerial imagery is vital for precision agriculture, yet existing methods struggle with complex geospatial boundaries and texture degradation in fragmented plots. To address irreversible detail loss under downsampling, difficulty in capturing both sharp boundaries and large-scale textures, and weak boundary supervision without extra annotations, we propose PaintingFormer, an enhanced UNet-based segmentation framework. It introduces three targeted innovations: an original feature retention module (OFRM) that injects raw RGB images into the deepest decoder layer to recover lost details; a dual attention–MLP design combining FeaAttention (full-resolution global attention with linear complexity) and TWLK-MLP (cascaded 3 × 3, 5 × 5, and 7 × 7 depthwise separable kernels within an MLP) to capture multi-scale spatial patterns; and a deep edge loss from the encoder’s bottleneck that enforces boundary constraints without manual edge labels. PaintingFormer surpasses mainstream methods, achieving 84.5% mIoU and 91.5% F1 on Vaihingen, 87.3% mIoU on Potsdam, 53.7% on LoveDA, and 84.2% on our private dataset. This work offers an effective solution for fine-grained farmland segmentation, improving boundary accuracy and texture preservation. Full article

Self-healing materials have attracted increasing attention as a strategy to enhance durability, extend service life, and reduce maintenance in advanced material systems. Among these, cellulose-based self-healing materials represent a sophisticated intersection between sustainable macromolecular chemistry and adaptive materials science. This review provides a synthesis of recent advancements in the field, systematically categorizing materials derived from cellulose raw materials. We evaluate the fundamental chemical strategies employed to achieve autonomous repair, distinguishing between extrinsic mechanisms—utilizing cellulose-based micro/nano-capsules to sequester healing agents—and intrinsic mechanisms governed by dynamic covalent chemistry (Schiff-base, boronic ester, Diels–Alder) and supramolecular interactions (hydrogen bonding, metal–ligand coordination, and host–guest assemblies). The analysis highlights how cellulose’s hierarchical structure and abundant surface functionality are leveraged to overcome the traditional trade-off between mechanical toughness and healing efficiency. Particular emphasis is placed on the transition from simple structural hydrogels to sophisticated multifunctional systems. These include ultra-stretchable strain and pressure sensors for e-skin applications, biocompatible and injectable matrices for chronic wound management and stem cell delivery, and advanced anti-freezing eutectogels for performance in extreme environments. Furthermore, we explore the integration of cellulose into traditional sectors, such as self-healing concrete utilizing microbe-induced calcification and smart, eco-friendly coatings for corrosion protection. Finally, we discuss critical challenges, including environmental stability, scalability, and the development of standardized evaluation protocols, providing a roadmap for the next generation of bio-derived, sustainable and intelligent materials. Full article

Accurate identification of weak nodes is a prerequisite for online security assessment, preventive control, and resilience enhancement in modern power systems. However, conventional single-layer graph-learning models mainly emphasize local neighborhood aggregation and are insufficient for characterizing vulnerability propagation from equipment-level disturbance to regional congestion and system-level transfer constraints. This paper proposes a mechanism-aware hierarchical graph-learning framework for weak-node identification in complex interconnected power grids. We emphasize that attention, fusion, and gating operations are standard neural-network mechanisms and are not claimed as new generic deep-learning blocks. The contribution of this paper is the power-system-specific formulation: constructing an electrically meaningful local-supernode hierarchy, defining reproducible mechanism-based node and branch-vulnerability proxies, and interpreting weak-node rankings through node–line–corridor coupling evidence. In the validated implementation, a local graph convolutional encoder and a supernode/global graph convolutional encoder generate 32-dimensional local embeddings and 16-dimensional global embeddings, which are concatenated and decoded by a 48 → 24 → 1 multilayer perceptron to obtain node vulnerability scores. Experiments are conducted on reproducible IEEE benchmark data generated from pandapower standard systems, with representative comparisons on the IEEE 57-bus, 145-bus, and 300-bus systems and a detailed structural interpretation on the IEEE 145-bus case. The present results validate the ability of the implemented local–global hierarchical model to reproduce the proposed mechanism-based vulnerability proxy on representative small- and medium-scale benchmarks. Full article

Background/Objectives: Light training tasks are widely used in athletic training, yet the cognitive processes that underlie performance on these tasks remain poorly understood. Method: In this study, we investigated whether exogenous attentional orienting and visual search abilities could explain individual differences in performance on SpeedPad, a Virtual Reality light training task, in participants who engage in physical exercise and in controls. Results: Our results showed that participants engaging in physical exercise outperformed those who did not in SpeedPad sessions that required fast reactions to targets with or without distractors. Furthermore, hierarchical regression analyses revealed that engagement in physical exercise accounted for a significant amount of variance in SpeedPad performance. In addition, both the cueing benefit from an exogenous orienting task and the intercept of a visual search task with feature search trials accounted for unique variance in SpeedPad performance. Conclusions: Overall, the current findings suggest that performance in light training tasks such as SpeedPad depends on both physical/physiological and cognitive factors, especially those related to different types of attention. Full article

While Vision Transformers (ViTs) have achieved state-of-the-art (SOTA) results in visual recognition, their scalability remains fundamentally constrained by the quadratic complexity of global self-attention. To address this, we present a linear complexity attention design employing dual-stream information propagation to enhance representational efficiency and structured feature aggregation. Our proposed $D{S}^2$ attention acts as a versatile replacement for standard attention in various SOTA designs, such as Tokens-to-Token (T2T) and FasterViT. In our design, half of the attention heads perform left-to-right segmented information propagation in a Perceiver-style manner, while the remaining half of the heads perform right-to-left propagation. This bidirectional structured attention enables efficient long-range dependency modeling without the overhead of full global attention. To improve classification performance, we introduce a segment-level classification strategy in which each segment is associated with a summary token. The final prediction is produced via cross-attention between image tokens and these summary tokens, enabling hierarchical semantic comprehension. Extensive experiments demonstrate that the proposed attention design achieves on average 0.3% higher accuracy on the ImageNet-1K dataset, while offering improved information flow and higher efficiency across SOTA Vision Transformer designs. Full article

Aspect-Based Sentiment Analysis explores sentiment trends related to specific opinion aspects and holds significant commercial potential for monitoring brand reputation, understanding customer satisfaction, and personalizing recommendations. However, traditional methods rely exclusively on textual input and often struggle when the target aspect is not mentioned in the sentence. Multimodal Aspect-Based Sentiment Analysis addresses this limitation by incorporating both textual and visual modalities to enable more comprehensive sentiment understanding. Despite advancements in deep learning and transformer-based architectures, existing models often suffer from suboptimal modality fusion and weak aspect grounding, limiting their classification accuracy. To overcome these challenges, we propose an Attention-Driven Feature Fusion (ADFF) approach based on a three-stage hierarchical attention mechanism. First, it only fuses text and image embeddings. Second, it incorporates aspect-level features. Third, a multi-head attention layer further enhances cross-modal dependencies. The resulting representation is passed to a Long Short-Term Memory (LSTM) classifier for sentiment polarity prediction. We evaluate our model on three benchmark datasets, namely Twitter-2015, Twitter-2017, and MASAD. The experimental results demonstrate that the proposed model substantially outperforms state-of-the-art multimodal and unimodal baselines, improves both accuracy and F1-score, achieving 82.55% accuracy and 81.05% F1-score on Twitter-2015, 77.07% accuracy and 77.15% F1-score on Twitter-2017, and up to 99.67% accuracy and F1-score in the Plant domain of MASAD, where we observe consistent improvements across all seven domains. These results highlight the effectiveness and scalability of the hierarchical attention-based fusion strategy for real-world aspect-based sentiment analysis tasks. Full article

Currently, dual-functional composites that simultaneously provide structural support and energy storage capabilities have garnered significant attention. However, the challenge of balancing mechanical strength and energy storage performance remains a limiting factor for their application. Herein, a novel N-doped reduced graphene oxide/nano-sulfur@porous SiC (N-rGO/S@porous SiC) composite material was successfully prepared by in situ embedding N-rGO supported with nano-sulfur into a 3D-printed porous SiC scaffold via a hydrothermal synthesis approach. The hierarchical porous structure composed of SiC and N-rGO facilitates mass transport of the liquid electrolyte. Benefiting from the high strength of SiC, the novel material achieves a compressive strength of 93.5 MPa. Benefiting from the synergistic effect of the N-rGO/S composite and the high ionic conductivity of the liquid electrolyte, the electrode material delivers superior electrochemical energy storage performance, achieving a specific capacitance of 800.7 mF/cm² at a current density of 1 mA/cm², together with remarkable rate capability and good cycling stability. To our knowledge, this composite exhibits a high level of integrated properties. More importantly, the strategy of integrating porous, high-strength supports with high-performance electrode materials opens new avenues for the synthesis of structure-energy-storage dual-functional composites. Full article

Digital camera sensors are designed to capture a wide range of incident illuminants, enabling the creation of high-quality images. However, these sensors lack the capability to differentiate between the color of the source illuminant and the actual color (or original color) of the object being captured. For this reason, the computational color constancy (CCC) was introduced and has been developed over decades. The CCC is an approach to modeling the color perception of the human visual system (HVS) by ensuring accurate object color determination under varying source illuminant conditions. At the core of human visual perception (HVP)-based CCC is attaining higher accuracy in scene illuminant estimation. The emergence of deep convolutional neural networks (DCNNs) was a recent innovation in accurate illuminant estimation, fundamentally transforming the CCC research landscape. Nevertheless, accurate illuminant estimation still remains a huge challenge for both traditional and state-of-the-art (SOTA) approaches. To further advance precision in illuminant estimation, this article presents a novel learning-based illumination color cast estimation approach to HVP-based CCC. Most importantly, the proposed approach is intended to integrate informative features into both channel and spatial regions while preserving long-term dependency feature information with the use of dense skip connections. To achieve these objectives, the proposed Dense Dual Connection Aggregated Transform Network (DDCATNet) architecture is designed to comprise several modules: shallow feature extraction, channel-wise and spatial feature-based Dense Dual Connection (DDC), fusion of the dense channel-wise attention (CA) and spatial attention (SA) branches through a gate mechanism (GM) unit, and aggregate transform. It is worth noting that both the CA blocks and the SA blocks in the DDC module are characterized by dense and cascading connections, meant to preserve long-term feature information and modulate different-level feature information at both global and local scales. The densely connected CA branch (DCA) and the densely connected SA branch (DSA) are also highly effective in securing high-contribution information while suppressing redundant data. The GM unit is integrated at the back of the DDC module, fusing the two DCA and DSA branches to ensure the adaptive merging of useful hierarchical feature information and the extraction of more valuable feature information. As a result, the proposed DDCATNet architecture significantly enhanced precision in illuminant estimation, thereby improving performance. In rigorous experiments on a wide range of datasets, the proposed DDCATNet approach outperformed its SOTA counterparts, validating the efficacy and generalization capabilities, as well as robust camera-invariance, across diverse, single- and multi-illuminant datasets and model architectures. Full article

To address the problem of road crack detection in low-quality pavement images, existing semantic segmentation methods still have shortcomings such as missed crack detection and inaccurate localization due to weak crack boundaries, low contrast, and complex pavement texture. To address these limitations, this study proposes a crack segmentation model based on feature integration and a triple attention mechanism. The model uses DeepLabv3+ as the backbone network and introduces the proposed three-dimensional interactive attention module after feature extraction. The attention module enhances the extraction of key features related to the spatial location and morphological details of cracks, thereby improving the ability of crack location. A hierarchical feature integration branch is introduced in the cross-layer connection, and a dimension-aware selective fusion module is used to enhance the saliency of small cracks in complex backgrounds. In addition, the proposed multi-group dilation feature fusion module is introduced to improve the multi-scale modeling of small and slender cracks and reduce background interference. The experimental results on Crack500 and GAPS384 datasets show that the proposed model achieves better overall segmentation performance than the comparison model, especially in reducing the missed detection of weak, small, and discontinuous cracks in low-quality pavement images. Complexity analysis further shows that the proposed model maintains practical inference efficiency rather than relying on too large a model size. These results show that the proposed method provides an effective solution for low-quality road crack segmentation, but it still needs to be further verified in actual detection scenarios. Full article

Background/Objectives: Epiretinal membrane (ERM) is a common vitreoretinal disorder characterized by fibrocellular proliferation on the inner retinal surface, often leading to progressive visual impairment. Accurate grading of ERM severity using optical coherence tomography (OCT) is critical for treatment planning and surgical decision-making; however, manual grading is labor-intensive and subjective. This study aims to develop an automated and reliable deep learning-based method for ERM severity classification. Methods: We propose DenseViT-OCT, a hybrid deep learning model that integrates dense convolutional neural networks (CNN) and vision transformers (ViT). The model introduces three key modules: Multi-Scale Dense Feature Aggregation (MDFA) for capturing hierarchical features across multiple spatial scales, Adaptive Feature Calibration (AFC) for enhancing feature discrimination through channel and spatial attention, and Cross-Attention Feature Fusion (CAFF) for enabling bidirectional interaction between convolutional and transformer representations. The model was trained and evaluated on 2195 OCT B-scan images obtained from 397 patients. Results: DenseViT-OCT achieved an overall accuracy of 94.76% on the internal four-class test set, outperforming 19 benchmark models, including ConvNeXt, EfficientNet, ViT, and Swin Transformers. The model demonstrated balanced performance with a macro-averaged precision of 93.76%, recall of 93.22%, F1-score of 93.47%, Cohen’s kappa of 92.62%, and macro-Area Under the Curve (AUC) of 98.95%. Ablation experiments confirmed the contribution of the proposed MDFA, AFC, CAFF, and deep supervision components, with the full model consistently outperforming reduced variants and standalone DenseNet121 and ViT-B/16 backbones. In repeated experiments across five random seeds, DenseViT-OCT also achieved the best mean accuracy (0.9399 ± 0.0052). External validation on the public multicenter OCTDL dataset, performed as binary ERM-versus-normal classification because of label availability, yielded 90.76% accuracy and 97.61% AUC, indicating promising generalization beyond the development cohort. Conclusions: DenseViT-OCT provides a robust framework for automated ERM severity classification from OCT B-scans. The combination of local CNN features, global transformer context, and dedicated fusion modules improves classification performance and yields clinically meaningful error patterns. Although further stage-wise multicenter validation, volumetric OCT analysis, and prospective clinical assessment are required, the proposed method shows promise as a research-oriented decision-support framework for B-scan-level ERM assessment. Full article

Accurate identification of arable land, as the foundation of the high-standard farmland construction, impacts the crop layout, accurate management of water and fertilizers, and intelligent control. Due to the 10-m resolution limitation of Sentinel-2 imagery, there is feature overlap within individual pixels of the satellite imagery. This leads to fragmented semantic features during farmland identification, and adjacent plots often appear unclear and intertwined. To address these issues, a Hierarchical Agricultural Segmentation Network (HASNet) was proposed. Built upon the classic encoder-decoder structure, this HASNet model incorporates an expanded feature enhancer (DFE) module to recover weak features and reconstruct cropland features (e.g., edges and shapes) that are obscured by mixed pixels. It also introduces a lightweight strip spatial attention (LSSA) mechanism to capture long-range features unique to farmland. Furthermore, it used a pyramid decoding module (PDM) to refine cropland parcel boundaries. Taking a farm in Xinjiang Uygur Autonomous Region, a semantic segmentation dataset of cultivated land was constructed based on Sentinel-2 imagery. Through accuracy comparisons, visualizations, and inferences, HASNet achieved an MIoU of 88.52% and a Kappa coefficient of 87.82%, outperforming mainstream models such as Unetformer and MPFUnet. Ablation experiments confirmed the effectiveness of the DFE, LSSA, and PDM modules in feature capture and edge refinement. The large-scale image sliding inference experiment prevented the seam effect and demonstrated its practicality. In summary, HASNet provides low-cost technical and theoretical support for the intelligent monitoring of high-standard farmland. Full article

Background/Objectives: Multiple instance learning (MIL) is widely used for automated classification of epithelial ovarian cancer subtypes from whole slide images (WSIs), but the relative contributions of feature extractor, aggregation strategy, and classification framework (flat vs. hierarchical) choices remain unclear under severe class imbalance. Methods: We evaluated 36 configurations on 510 WSIs from the UBC-OCEAN dataset using stratified five-fold cross-validation, comparing three pathology foundation models (Phikon-v2, CTransPath, UNI), six aggregators (mean/max pooling, ABMIL, CLAM-SB, DSMIL, DTP-TransMIL), and two classification strategies. Pathologist-annotated WSIs assessed attention map interpretability. Results: Feature extractor selection contributed substantially more variance than aggregator choice. Cascade balanced accuracy ranged from 0.538 (Phikon-v2) to 0.925 (UNI); CTransPath (~32 K pretraining WSIs) reached 0.870, exceeding Phikon-v2 (~58 K WSIs) and approaching UNI (~100 K+ WSIs), indicating that pretraining objective and architecture contribute as substantially as scale. The hierarchical cascade consistently improved high-grade serous carcinoma (HGSC) recall across all six evaluated configurations (+0.073 to +0.530), detecting 206 of 217 cases (0.949) with UNI max pooling. Quantitative spatial alignment analysis confirmed that both stronger feature extractors—CTransPath and UNI—generated significantly more spatially structured attention distributions than Phikon-v2 (paired Wilcoxon, p = 0.008 and p = 0.032, respectively). Conclusions: Feature extractor choice contributed more variance than aggregator selection, with the largest gap between Phikon-v2 and stronger extractors. Hierarchical cascades consistently improved HGSC recall across all configurations. Full article

Crop leaf disease segmentation in complex natural environments remains challenging because lesion regions often exhibit substantial scale variation, blurred boundaries, and severe background interference. To address these issues, this study proposes a Multi-Scale Feature Rectification Network (MFR-Net) for crop leaf disease segmentation. The proposed network adopts an EfficientNetV2-S-based encoder to extract hierarchical features, incorporates a hybrid attention mechanism to enhance lesion-sensitive spatial and channel representations, introduces a Cross-Window Atrous Spatial Pyramid Pooling (CWASPP) module to strengthen multi-scale contextual modeling, and employs a Feature Rectification Module (FRM) in the decoder to alleviate semantic inconsistency during cross-level feature fusion. Experiments on a Kaggle-derived benchmark constructed from the unaugmented data folder of the public Leaf Disease Segmentation Dataset, containing 588 diseased-leaf images and 588 corresponding binary lesion masks, showed that MFR-Net achieved the highest mIoU of 74.27% and the highest Recall of 87.61% among the compared methods, and maintained competitive Dice performance (84.25%) with 25.10 M parameters and 37.55 G FLOPs. Ablation results further confirmed the effectiveness of the proposed design, with CWASPP providing the most notable individual contribution. Additional experiments were conducted on an independent Apple Leaf Dataset comprising 3197 image–mask pairs, collected under mixed controlled and natural field-like imaging conditions. The results showed competitive performance under a different data distribution, and robustness evaluation further verified stable performance under severe noise, blur, darkness, and contrast variation. All experiments were implemented in PyTorch 2.11.0 (CUDA 12.8) on a workstation equipped with an NVIDIA GeForce RTX 4060 Ti GPU (8 GB). These results indicate that MFR-Net provides an effective and robust solution for crop leaf disease segmentation in complex agricultural scenarios. Full article