Search Results (30)

Identifying village functional differentiation within rural territorial systems is essential for differentiated rural revitalization and place-based governance. However, existing approaches still lack effective analytical pathways for translating complex rural territorial relations and sparse planning labels into fine-grained measures of rural functional intensity. To address these gaps, this study develops a Few-Shot Hierarchical Graph Representation Learning (FH-GRL) framework. By integrating a Hierarchical Graph Infomax (HGI) model to capture cross-scale village–township–city relational dependencies and an Evidential Deep Learning (EDL) mechanism to map high-dimensional representations into class-specific evidence and Global Percentile Ranks (GPR), the framework supports fine-grained classification and continuous grading of rural functions. Empirical analysis in Pingdingshan City yields three main findings. First, within the present case study, FH-GRL shows more stable performance than traditional flat clustering and local graph models in identifying complex rural functions under limited labeled samples. Second, hierarchical context serves as a spatial calibration mechanism, reducing locally generated noise and improving the identification of village functional differentiation under spatial heterogeneity. Third, rural functional differentiation reflects the combined effects of place-based conditions and potential flow-related interaction conditions. In particular, Center villages show differentiated trajectories between endogenous production or service centers in agricultural plains and exogenous service centers along urban development axes. Overall, this study provides a planning-oriented quantitative framework for diagnosing rural functional differentiation under label scarcity and spatial heterogeneity. The GPR-based outputs can support the identification of high-intensity functional carriers, transitional villages, and general reserve areas, thereby providing diagnostic evidence for differentiated governance and tiered resource allocation. Rather than replacing formal planning judgment, the framework offers geospatially informed support for classified rural governance and more evidence-informed territorial planning. Full article

To address the limitations of the traditional Teaching–Learning-Based Optimization (TLBO) algorithm when solving high-dimensional, multimodal, strongly nonlinear, and constrained global optimization problems—such as single search direction, inefficient population information exchange, insufficient local exploitation capability, susceptibility to premature convergence, and low solution accuracy—this paper proposes a multi-strategy collaborative enhanced Teaching–Learning-Based Optimization algorithm (CSTLBO). While retaining the fundamental two-phase framework of the original TLBO, namely the teacher phase and learner phase, three novel strategies are sequentially incorporated: a Collaborative Differential Guidance (CDG) strategy to enrich global search directions, an Elite-Guided Collaborative Interaction (EGCI) strategy to enhance efficient transmission of high-quality population information, and a Quadratic Interpolation Local Refinement (QILR) strategy to improve fine-grained exploitation in promising regions. Together, these strategies enable an adaptive trade-off between broad search capability and refined local optimization. The effectiveness of CSTLBO is systematically assessed using the CEC2017 and CEC2022 benchmark suites, with comparative analyses conducted against multiple advanced algorithms and the baseline TLBO method. Experimental results demonstrate that CSTLBO exhibits significant superiority in terms of convergence speed, solution accuracy, robustness, and statistical performance, particularly in the 100-dimensional CEC2017 benchmark problems and the WSN deployment problem, while maintaining competitive performance on the 10- and 20-dimensional CEC2022 benchmarks. The superiority of CSTLBO is further validated through the Wilcoxon rank-sum test and Friedman mean rank test. Furthermore, the proposed algorithm is applied to the coverage deployment optimization problem in Wireless Sensor Networks (WSNs), a typical high-dimensional engineering problem involving multiple conflicting deployment indicators, which is formulated as a weighted single-objective optimization problem in this study. The results show that CSTLBO achieves a coverage rate of up to 95.71% with a fitness value as low as 0.1344, outperforming the compared algorithms in overall performance. Owing to its simple structure, low computational complexity, and strong generalization capability, CSTLBO provides an efficient and reliable solution for complex global optimization problems and practical engineering applications. Full article

Accurate identification of key nodes in complex networks is vital for optimizing system robustness and controlling information spread. Existing centrality metrics struggle to balance the continuous extraction of global topological features with the fine-grained perception of local structures, while traditional heuristic algorithms also face severe resolution limitations. To address these issues, this paper proposes a node importance evaluation method based on fractional-order topological propagation and local information entropy (FSEC). This method overcomes the limitations of discrete integer-order propagation inherent in traditional graph walks. It constructs a continuous fractional-order topological propagation operator within the spectral graph theory framework. This enables the smooth projection of node degree features into the global topological space, thereby yielding high-order global impact factors. Furthermore, an information theory mechanism is introduced to quantify the probability distribution of a node’s information contribution within its local neighborhood. The local structural information entropy is then calculated to reflect the node’s asymmetric control over micro-level information flow. Deliberate attack simulations were conducted on nine real-world networks and three types of artificial network models. The results show that the proposed FSEC algorithm significantly outperforms baseline algorithms like Autoencoder and Graph Neural Network (AGNN), Degree Centrality, k-shell, PageRank, and Mixed Degree Decomposition (MDD) in degrading the largest connected component (LCC) and global network efficiency (NE). The proposed method also achieves the minimum Area Under the Curve (AUC) values globally. Its monotonicity is slightly lower than that of AGNN but superior to all other baseline algorithms. In addition, SIR simulations further confirm the effectiveness of the FSEC method. This approach successfully resolves the ranking tie problem among nodes in the same topological layer. Full article

The widespread deployment of unmanned aerial vehicles (UAVs) in remote sensing has highlighted the necessity for robust object detection methods in UAV imagery. However, high-altitude UAV imagery suffers from severe background clutter that obscures target discriminability and extreme scale variations that degrade fine-grained features. To address these challenges, we propose CSSA-YOLO, a clutter-suppressed and scale-aware detection framework built upon YOLOv9. Specifically, we project dense spatial features into a low-rank token space via a Semantic Bottleneck Module (SBM). This projection acts as an information bottleneck, suppressing the background clutter while robustly retaining critical target semantic and structural priors. Furthermore, we develop a Scale-Aware Complete-IoU (SA-CIoU) loss to tackle gradient attenuation for small objects. By analytically integrating a scale-aware modulation factor with a dynamic alignment mechanism into localization optimization, SA-CIoU shifts the optimization priority to the precise localization of small and hard-to-detect instances. Extensive experiments on the VisDrone2019 benchmark demonstrate the superiority of our approach, with CSSA-YOLO achieving an mAP@0.5 of 46.0% and an mAP@0.5:0.95 of 28.4%, yielding an absolute 1.4% improvement over the YOLOv9 baseline. Furthermore, when integrated with a P2-enhanced YOLOv9 architecture, our method achieves a remarkable mAP@0.5 of 49.5%. Notably, evaluations across diverse scenarios, including the infrared (IR) thermal HIT-UAV benchmark and PCB defect detection datasets, further demonstrate the generalizability and robustness of our framework. Full article

Personality assessment serves as a key building block in intelligent information systems that enable human-centered modeling. Unlike cognitive tests, personality assessments rely primarily on self-reports and are therefore susceptible to faking. Forced-choice (FC) formats partially mitigate this problem, yet socially desirable responding remains a systematic source of bias. Traditional approaches rely on expert-annotated social desirability (SD) ratings to construct FC item blocks and infer respondents’ personality traits from block-level rankings. This rating procedure is labor-intensive and coarse-grained. Furthermore, existing methods neglect the non-linear SD interactions between respondents and items, which act as structured adversarial noise that hinders the recovery of true latent traits. To address these challenges, we propose the Social Desirability-aware Forced-Choice Diagnosis (SDFCD) approach. Our approach adopts a knowledge-guided learning paradigm by leveraging large language models (LLMs) to distill fine-grained, continuous SD ratings, thereby replacing sparse expert ratings. We then introduce a decoupled neural interaction module that jointly represents latent personality traits and SD tendencies, enabling the modeling of respondent–item SD interactions. Experiments on real assessment data demonstrate that our method significantly outperforms baseline FC models in personality trait diagnostic performance and model interpretability. This study highlights the potential of LLMs for automated, fine-grained SD quantification and offers a scalable path toward more trustworthy personality assessment. Full article

Slime moulds (Eumycetozoa) are closely associated with forest structure, moisture and the availability of microhabitats, which together make them promising candidates for bioindication. This study synthesised an integrated, georeferenced resource from Central and Eastern Europe to assess how forest habitat, management intensity, and elevation structure assemblages, and to identify indicator taxa suited to monitoring. Analyses in R (RStudio, version 4.5.2) combined effort-controlled diversity comparisons, models of record intensity, habitat-stratified elevation responses, constrained ordination, and indicator testing at species and higher ranks. The resulting corpus encompassed 624 species from 16 countries and eight consolidated forest habitat classes, enabling quantification of joint assemblage responses to habitat, management intensity, and elevation under effort-controlled sampling, and facilitating the identification of indicator sets that are robust to uneven sampling. At the order and genus levels, Physarales, Trichiales, and Stemonitidales, together with genera such as Trichia, Meriderma, and Polyschismium, exhibited the clearest and most transferable indicator behaviour, while species including Trichia varia, Fuligo septica, and Meriderma carestiae emerged as promising candidates for fine-grained bioindication along habitat and elevation gradients. Habitat exerted clearer contrasts than management; elevation effects were strongly habitat specific, and a compact set of taxa showed stable, interpretable indicator behaviour across gradients. These indicator assemblages, together with an appraisal of cross-country generalisation, provide an operational basis for elevation-aware, habitat-structured bioindication with slime moulds in European forests. Taken together, these results indicate that slime mould assemblages have the potential to complement existing forest bioindication systems, both by tracking broad forest habitat types along management and elevation gradients and by providing indirect information on less conspicuous attributes such as stand naturalness and the availability of dead wood, although such applications remain at a proof-of-concept stage and will require further targeted evaluation before operational deployment. Full article

To address the issues of uneven population initialization, insufficient individual information interaction, and passive boundary handling in the standard Golden Jackal Optimization (GJO) algorithm, while improving the accuracy and efficiency of multilevel thresholding in artistic image segmentation, this paper proposes an improved Golden Jackal Optimization algorithm (MGJO) and applies it to this task. MGJO introduces a high-quality point set for population initialization, ensuring a more uniform distribution of initial individuals in the search space and better adaptation to the complex grayscale characteristics of artistic images. A dual crossover strategy, integrating horizontal and vertical information exchange, is designed to enhance individual information sharing and fine-grained dimensional search, catering to the segmentation needs of artistic image textures and color layers. Furthermore, a global-optimum-based boundary handling mechanism is constructed to prevent information loss when boundaries are exceeded, thereby preserving the boundary details of artistic images. The performance of MGJO was evaluated on the CEC2017 (dim = 30, 100) and CEC2022 (dim = 10, 20) benchmark suites against seven algorithms, including GWO and IWOA. Population diversity analysis, exploration–exploitation balance assessment, Wilcoxon rank-sum tests, and Friedman mean-rank tests all demonstrate that MGJO significantly outperforms the comparison algorithms in optimization accuracy, stability, and statistical reliability. In multilevel thresholding for artistic image segmentation, using Otsu’s between-class variance as the objective function, MGJO achieves higher fitness values (approaching Otsu’s optimal values) across various artistic images with complex textures and colors, as well as benchmark images such as Baboon, Camera, and Lena, in 4-, 6-, 8-, and 10-level thresholding tasks. The resulting segmented images exhibit superior peak signal-to-noise ratio (PSNR), structural similarity (SSIM), and feature similarity (FSIM) compared to other algorithms, more precisely preserving brushstroke details and color layers. Friedman average rankings consistently place MGJO in the lead. These experimental results indicate that MGJO effectively overcomes the performance limitations of the standard GJO, demonstrating excellent performance in both numerical optimization and multilevel thresholding artistic image segmentation. It provides an efficient solution for high-dimensional complex optimization problems and practical demands in artistic image processing. Full article

This study systematically benchmarks the performance of four single soft magnetic powders—water-atomized Fe–Si–Cr (FeSiCr), silica-coated reduced iron powder (RIP), silica-coated carbonyl iron powder (CIP), and phosphate-coated CIP (CIP-P)—to establish quantitative relationships between powder attributes, deformation substructure, and high-frequency loss for molded power inductors (100 kHz–1 MHz). We prepared toroidal compacts at 200 MPa and characterized them by initial permeability (μ_i), core-loss (P_cv(f)), partitioning (P_cv(f) = K_hf + K_ef², K_h, $K_{\mathrm{e}}$: hysteresis and eddy-current loss coefficients), and EBSD (electron backscatter diffraction)-derived microstrain metrics (Kernel Average Misorientation, KAM; low-/high-angle grain-boundary fractions). Corrosion robustness was assessed using a 5 wt% NaCl, 35 °C, 24 h salt-spray protocol. Our findings reveal that FeSiCr achieves the highest μ_i across the frequency band, despite its lowest compaction density. This is attributed to its coarse particle size (D₅₀ ≈ 18 µm) and the resulting lower intragranular pinning. The loss spectra are dominated by hysteresis over this frequency range, with FeSiCr exhibiting the largest K_h, while the fine, silica-insulated Fe powders (RIP/CIP) most effectively suppress K_e. EBSD analysis shows that the high coercivity and hysteresis loss in CIP (and, to a lesser extent, RIP) are correlated with dense, deformation-induced subgrain networks, as evidenced by higher mean KAM and a lower low-angle grain boundary fraction. In contrast, FeSiCr exhibits the lowest KAM, with strain confined primarily to particle contact regions. Corrosion testing ranked durability as FeSiCr ≳ CIP ≈ RIP ≫ CIP-P, which is consistent with the Cr-rich passivation of FeSiCr and the superior barrier properties of the SiO₂ shells compared to low-dose phosphate. At 15 A, inductance retention ranks CIP (67.9%) > RIP (55.7%) > CIP-P (48.8%) > FeSiCr (33.2%), tracking a rise in effective anisotropy and—for FeSiCr—lower M_s that precipitate earlier roll-off. Collectively, these results provide a microstructure-informed selection map for single-powder formulations. We demonstrate that particle size and shell chemistry are the primary factors governing eddy currents (K_e), while the KAM-indexed substructure dictates hysteresis loss (K_h) and DC-bias superposition characteristics. This framework enables rational trade-offs between magnetic permeability, core loss, and environmental durability. Full article

Background: Current fMRI (functional magnetic resonance imaging)-driven brain information decoding for visual image reconstruction techniques faces issues such as poor structural fidelity, inadequate model generalization, and unnatural visual image reconstruction in complex scenarios. Methods: To address these challenges, this study proposes a Dynamic Confidence Bayesian Adaptive Network (DCBAN). In this network model, deep nested Singular Value Decomposition is introduced to embed low-rank constraints into the deep learning model layers for fine-grained feature extraction, thus improving structural fidelity. The proposed Bayesian Adaptive Fractional Ridge Regression module, based on singular value space, dynamically adjusts the regularization parameters, significantly enhancing the decoder’s generalization ability under complex stimulus conditions. The constructed Dynamic Confidence Adaptive Diffusion Model module incorporates a confidence network and time decay strategy, dynamically adjusting the semantic injection strength during the generation phase, further enhancing the details and naturalness of the generated images. Results: The proposed DCBAN method is applied to the NSD, outperforming state-of-the-art methods by 8.41%, 0.6%, and 4.8% in PixCorr (0.361), Incep (96.0%), and CLIP (97.8%), respectively, achieving the current best performance in both structural and semantic fMRI visual image reconstruction. Conclusions: The DCBAN proposed in this thesis offers a novel solution for reconstructing visual images from fMRI signals, significantly enhancing the robustness and generative quality of the reconstructed images. Full article

The quality of underwater imagery is inherently degraded by light absorption and scattering, a challenge that severely limits its application in critical domains such as marine robotics and archeology. While existing enhancement methods, including recent hybrid models, attempt to address this, they often struggle to restore fine-grained details without introducing visual artifacts. To overcome this limitation, this work introduces a novel hybrid U-Net-Transformer (UTR) architecture that synergizes local feature extraction with global context modeling. The core innovation is a Recurrent Multi-Scale Feature Modulation (R-MSFM) mechanism, which, unlike prior recurrent refinement techniques, employs a gated modulation strategy across multiple feature scales within the decoder to iteratively refine textural and structural details with high fidelity. This approach effectively preserves spatial information during upsampling. Extensive experiments demonstrate the superiority of the proposed method. On the EUVP dataset, UTR achieves a PSNR of 28.347 dB, a significant gain of +3.947 dB over the state-of-the-art UWFormer. Moreover, it attains a top-ranking UIQM score of 3.059 on the UIEB dataset, underscoring its robustness. The results confirm that UTR provides a computationally efficient and highly effective solution for underwater image enhancement. Full article

High-precision semantic segmentation of remote sensing imagery is crucial in geospatial analysis. It plays an immeasurable role in fields such as urban governance, environmental monitoring, and natural resource management. However, when confronted with complex objects (such as winding roads and dispersed buildings), existing semantic segmentation methods still suffer from inadequate target recognition capabilities and multi-scale representation issues. This paper proposes a neural network model, LMVMamba (LoRA Multi-scale Vision Mamba), for semantic segmentation of remote sensing images. This model integrates the advantages of convolutional neural networks (CNNs), Transformers, and state-space models (Mamba) with a multi-scale feature fusion strategy. It simultaneously captures global contextual information and fine-grained local features. Specifically, in the encoder stage, the ResT Transformer serves as the backbone network, employing a LoRA fine-tuning strategy to effectively enhance model accuracy by training only the introduced low-rank matrix pairs. The extracted features are then passed to the decoder, where a U-shaped Mamba decoder is designed. In this stage, a Multi-Scale Post-processing Block (MPB) is introduced, consisting of depthwise separable convolutions and residual concatenation. This block effectively extracts multi-scale features and enhances local detail extraction after the VSS block. Additionally, a Local Enhancement and Fusion Attention Module (LAS) is added at the end of each decoder block. LAS integrates the SimAM attention mechanism, further enhancing the model’s multi-scale feature fusion capability and local detail segmentation capability. Through extensive comparative experiments, it was found that LMVMamba achieves superior performance on the OpenEarthMap dataset (mIoU 52.3%, OA 69.8%, mF1: 68.0%) and LoveDA (mIoU 67.9%, OA 80.3%, mF1: 80.5%) datasets. Ablation experiments validated the effectiveness of each module. The final results indicate that this model is highly suitable for high-precision land-cover classification tasks in remote sensing imagery. LMVMamba provides an effective solution for precise semantic segmentation of high-resolution remote sensing imagery. Full article

With the growing demand for multilingual financial information, cross-lingual financial sentiment recognition faces significant challenges, including semantic misalignment, ambiguous sentiment expression, and insufficient transferability. To address these issues, a unified multilingual recognition framework is proposed, integrating semantic contrastive learning with a language-adaptive modulation mechanism. This approach is built upon the XLM-R multilingual model and employs a semantic contrastive module to enhance cross-lingual semantic consistency. In addition, a language modulation module based on low-rank parameter injection is introduced to improve the model’s sensitivity to fine-grained emotional features in low-resource languages such as Chinese and French. Experiments were conducted on a constructed trilingual financial sentiment dataset encompassing English, Chinese, and French. The results demonstrate that the proposed model significantly outperforms existing methods in cross-lingual sentiment recognition tasks. Specifically, in the English-to-French transfer setting, the model achieved 73.6% in accuracy, 69.8% in F1-Macro, 72.4% in F1-Weighted, and a cross-lingual generalization score of 0.654. Further improvements were observed under multilingual joint training, reaching 77.3%, 73.6%, 76.1%, and 0.696, respectively. In overall comparisons, the proposed model attained the highest performance across cross-lingual scenarios, with 75.8% in accuracy, 72.3% in F1-Macro, and 74.7% in F1-Weighted, surpassing strong baselines such as XLM-R+SimCSE and LaBSE. These results highlight the model’s superior capability in semantic alignment and generalization across languages. The proposed framework demonstrates strong applicability and promising potential in multilingual financial sentiment analysis, public opinion monitoring, and multilingual risk modeling. Full article

To address the limitations of existing knowledge graph-based recommendation algorithms, including insufficient utilization of semantic information and inadequate modeling of user behavior motivations, we propose SKGRec, a novel recommendation model that integrates knowledge graph and semantic features. The model constructs a semantic interaction graph (USIG) of user behaviors and employs a self-attention mechanism and a ranked optimization loss function to mine user interactions in fine-grained semantic associations. A relationship-aware aggregation module is designed to dynamically integrate higher-order relational features in the knowledge graph through the attention scoring function. In addition, a multi-hop relational path inference mechanism is introduced to capture long-distance dependencies to improve the depth of user interest modeling. Experiments on the Amazon-Book and Last-FM datasets show that SKGRec significantly outperforms several state-of-the-art recommendation algorithms on the Recall@20 and NDCG@20 metrics. Comparison experiments validate the effectiveness of semantic analysis of user behavior and multi-hop path inference, while cold-start experiments further confirm the robustness of the model in sparse-data scenarios. This study provides a new optimization approach for knowledge graph and semantic-driven recommendation systems, enabling more accurate capture of user preferences and alleviating the problem of noise interference. Full article

Re-identification (ReID) has been widely applied in person and vehicle recognition tasks. This study extends its application to a novel domain: insect (silkworm) recognition. However, unlike person or vehicle ReID, silkworm ReID presents unique challenges, such as the high similarity between individuals, arbitrary poses, and significant background noise. To address these challenges, we propose a multi-view network for silkworm ReID, called WormNet, which is built upon an innovative strategy termed extraction purification extraction interaction. Specifically, we introduce a multi-order feature extraction module that captures a wide range of fine-grained features by utilizing convolutional kernels of varying sizes and parallel cardinality, effectively mitigating issues of high individual similarity and diverse poses. Next, a feature mask module (FMM) is employed to purify the features in the spatial domain, thereby reducing the impact of background interference. To further enhance the data representation capabilities of the network, we propose a channel interaction module (CIM), which combines an efficient channel attention network with global response normalization (GRN) in parallel to recalibrate features, enabling the network to learn crucial information at both the local and global scales. Additionally, we introduce a new silkworm ReID dataset for network training and evaluation. The experimental results demonstrate that WormNet achieves an mAP value of 54.8% and a rank-1 value of 91.4% on the dataset, surpassing both state-of-the-art and related networks. This study offers a valuable reference for ReID in insects and other organisms. Full article

Unsupervised sentence embedding, vital for numerous NLP tasks, struggles with the inherent asymmetry of semantic relationships within contrastive learning (CL). This paper proposes Label Smoothing-based Ranking Negative Sampling (LS-RNS), a novel framework that directly tackles the semantic asymmetry between anchor and negative samples in CL. LS-RNS utilizes a Large Language Model (LLM) to assess fine-grained asymmetric similarity scores between sentences, constructing a ranking-aware negative sampling strategy combined with adaptive label smoothing. This design encourages the model to learn more effectively from informative negatives that are semantically closer to the anchor, leading to asymmetry-aware sentence embeddings. Experiments on standard Semantic Textual Similarity (STS) benchmarks (STS12–STS16, STS-B, SICK-R) show that LS-RNS achieves state-of-the-art performance. We adopt Spearman’s rank correlation coefficient as the primary evaluation metric for semantic similarity tasks, and we use classification accuracy for downstream and transfer tasks. LS-RNS achieves 79.87 on STS tasks with BERT-base (vs. 76.25 for SimCSE, +3.62) and 80.41 with RoBERTa-base (vs. 79.18 for DiffCSE). On transfer tasks, it attains 88.82 (BERT) and 87.68 (RoBERTa), consistently outperforming PromptBERT and SNCSE. On STL-10, LS-RNS improves SimCLR top-one accuracy from 79.50% to 80.52% with ResNet-18 and from 68.91% to 72.19% with VGG-16, even enabling a shallow ResNet-18 to surpass a deeper ResNet-34 baseline. These results confirm the modality-agnostic effectiveness of LS-RNS and its potential to redefine contrastive learning objectives by modeling semantic asymmetry, rather than relying solely on encoder depth or pre-training objectives. Full article