Search Results (1,700)

Due to the inherent limitations of both hyperspectral and multispectral imagery, balancing high spatial resolution with high spectral fidelity has become one of the fundamental challenges in remote sensing image processing. A prevailing strategy is to fuse these two types of data to reconstruct images that jointly preserve their respective advantages. However, existing reconstruction approaches still suffer from complex coupling between spatial and spectral information, and limited feature extraction capabilities. To address these issues, this study proposes PMSwinNet (Pyramid Multi-scale Swin Transformer Network), a novel architecture that integrates pyramid-based feature enhancement with Transformer mechanisms. The PMSwinNet incorporates multi-scale pyramid feature fusion and window-based self-attention. Through a progressive multi-stage design and three complementary components—feature extraction and reconstruction modules—the Transformer branch leverages window partitioning and shifting operations to capture long-range spatial dependencies and local contextual cues, while the pyramid features extract both global and local information across multiple spatial scales. In addition, a high-frequency branch is introduced, which employs lightweight convolutions to enhance edges, textures, and other high-frequency details, effectively suppressing blurring and artifacts during reconstruction. Experimental evaluations on multiple public hyperspectral datasets demonstrate that the PMSwinNet outperforms state-of-the-art methods, particularly in terms of detail preservation, spectral distortion suppression, and robustness. Full article

Skin cancer represents a significant public health challenge, necessitating early detection and timely treatment for optimal management. Timely and accurate evaluation of skin lesions is crucial, as delays can lead to more severe outcomes. However, identifying skin lesions accurately can be challenging due to differences in color, shape, and the various types of imaging equipment used for diagnosis. While recent studies have demonstrated the potential of ensemble convolutional neural networks (CNNs) for early diagnosis of skin disorders, these models are often too large and inefficient for processing contextual information. Although lightweight networks like MobileNetV3 and EfficientNet have been developed to reduce parameters and enable deep neural networks on mobile devices, their performance is limited by inadequate feature representation depth. To mitigate these limitations, we propose a new hybrid attention dual-stream deep learning model for skin lesion detection. Our model uses one training process to preprocess the images and splits the task into two branches. Each branch extracts different features using multi-stage and multi-branch attention techniques, improving the model’s ability to detect skin lesions accurately. The first branch processes the original image using a convolutional layer integrated with three novel attention modules: Enhanced Separable Depthwise Convolution (SCAttn), stage attention, and branch attention. The second branch utilizes Contrast Limited Adaptive Histogram Equalization (CLAHE) to enhance the input image, improving local contrast and revealing finer details. The integration of CLAHE with SCAttn modules leverages enhanced local contrast to capture more nuanced features while maintaining computational efficiency. A classification module receives the concatenated hierarchical characteristics that were taken from both branches. Utilizing the PAD2020 and ISIC 2019 datasets, we assessed the proposed model and obtained an accuracy rate of 98.59% for PAD2020, surpassing the state-of-the-art performance by 2%, and stable performance accuracy for the ISIC 2019 dataset. This illustrates how well the model can integrate several attention mechanisms and feature enhancement methods, providing a reliable and effective means of detecting skin cancer. Full article

Against the backdrop of expanding digital dissemination and experiential transformation in cultural heritage, visitors’ visual attention and symbolic choices increasingly shape heritage cognition and value transmission. Taking the Yellow Crane Tower as a case study, this research constructs a cultural symbol recognition dataset based on visitor-shared social media images and develops an enhanced ResNet-50 model for multi-label analysis. By integrating attention mechanisms and regularisation strategies, the model improves its capacity to capture complex cultural imagery, achieving a macro F1 score of 72.70% and a micro F1 score of 81.05% on the test set, indicating strong generalisation performance. The results reveal a significant imbalance in visual preferences: landmark symbols centred on the main architectural structure dominate at 32.95%, whereas culturally informative elements such as signage, cultural products, and interpretive facilities each account for less than 5%. Tag co-occurrence analysis further identifies three image production patterns: commemorative presentation, contextual documentation, and detail-oriented cultural photography reflecting different levels of heritage perception. Rather than directly proposing prescriptive strategies, the findings provide an empirical basis for informing future interventions aimed at shifting from landmark-focused viewing to deeper cultural perception. In this way, the study contributes to heritage display optimisation and research on visitor visual behaviour. Full article

Image semantic segmentation is essential in autonomous driving, medical imaging, and remote sensing. While convolutional neural networks (CNNs) excel at local feature extraction and spatial structure modeling, their limited receptive fields restrict the capture of long-range dependencies and global semantic consistency. Transformers provide strong global modeling through self-attention but often lack local inductive bias and show weaker generalization on small datasets. To address these limitations, this paper proposes a Multi-Scale Context-aware Network (MSC-Net) for image semantic segmentation. Under an encoder–decoder framework, MSC-Net combines a convolutional backbone with a Multi-Scale Self-Attention module to integrate the complementary strengths of CNNs and attention mechanisms. The backbone extracts local texture and structural information and can adopt architectures such as MobileNet, Xception, DRN, and ResNet, while the attention module captures long-range dependencies and multi-scale contextual information. This design improves cross-layer feature collaboration, multi-scale feature fusion, and boundary quality while maintaining computational efficiency. Experimental results show that MSC-Net achieves 38.8% mIoU and 98.4% ACC under comparable computational settings. Compared with SegFormer and DeepLabV3+, the model improves mIoU by approximately +3.0 and +3.3 percentage points, respectively, while reducing FLOPs and parameter size. Full article

As the cornerstone of contemporary electronics, the quality of electronic substrates—including Printed Circuit Boards (PCBs) and Ceramic Package Substrates (CPSs)—is intrinsic to product reliability. However, automated inspection is currently impeded by two persistent obstacles: the drastic multi-scale variation in defects and the acute class imbalance within defect datasets. Conventional deep learning approaches often fail to reconcile these challenges simultaneously, leading to suboptimal recognition of rare defect categories. To bridge this gap, we propose Multi-scale Partial Vision Transformer—Simple, Parameter-free Attention Module (MulPViT-SimAM), a robust framework designed for class-imbalanced electronic substrate defect detection. Our method features a novel multi-scale backbone (MulPViT) that synergizes partial convolutions with hierarchical attention mechanisms, facilitating the efficient extraction of both fine-grained local textures and global contextual dependencies. Additionally, we embed the Simple, Parameter-free Attention Module (SimAM) into the feature fusion stage to adaptively highlight defect-specific features while dampening background noise. To further mitigate data imbalance, we utilize the Equalized Focal Loss (EFL) function, which employs a category-specific modulating factor to dynamically equilibrate the learning focus across different classes. Comprehensive benchmarking reveals state-of-the-art performance, achieving mAP@0.5 scores of 95.7% on the standard PKU-MARKET-PCB dataset and 54.2% on the highly challenging CPS2D-AD dataset. Significantly, our approach effectively mitigates class imbalance, narrowing the performance deviation of rare categories to just 4.3% on the PKU-Market-PCB dataset and 1.4% on the CPS2D-AD dataset, compared to 11.8% and 7.5% in baseline models. These findings position MulPViT-SimAM as a viable and efficient solution for industrial quality control. Full article

The security of financial messaging systems is critical to maintaining trust in digital financial platforms. Despite advances in cryptography, many contemporary systems remain vulnerable to channel-based and cryptographic threats, including eavesdropping, interception, tampering, and unauthorized access. Hybrid cryptographic models that combine asymmetric encryption for secure key exchange with symmetric encryption for efficient data protection have emerged as effective approaches for strengthening confidentiality, integrity, and authenticity in financial message communications. This study presents a scoping review of literature published between 2015 and 2025, mapping research on user vulnerabilities in financial messaging systems and examining the role of hybrid cryptographic models in mitigating these risks. Guided by the PRISMA-ScR reporting standards, 615 articles were identified across nine scholarly databases. Forty-four studies met the inclusion criteria after systematic screening. The findings reveal a growing emphasis on hybrid encryption strategies, particularly RSA–AES and ECC–AES combinations, due to their balance of security strength and computational efficiency. However, significant gaps persist in empirical validation, real-world deployment, and user-centred security design, especially in mobile-first and resource-constrained environments. Existing research largely prioritizes theoretical performance and algorithmic efficiency, with limited attention to practical integration, usability, and operational constraints. This review highlights the need for holistic security frameworks that integrate cryptographic robustness with usability, regulatory compliance, and contextual deployment considerations. It provides a structured foundation for future research focused on developing scalable, user-centric, and resilient security solutions for financial messaging systems. Full article

Background/Objectives: Single-parent families represent a growing and particularly vulnerable family structure within community and primary health care contexts. These families often experience cumulative burdens related to caregiving overload, socioeconomic constraints, social isolation, and fragmented support networks, which directly affect health and well-being. This integrative review aimed to synthesize and critically analyse direct and conceptually transferable evidence relevant to Family Health Nursing interventions supporting single-parent families in community and primary health care contexts, identify existing knowledge gaps, and inform the development of a relational empowerment model. Methods: An integrative literature review was conducted following PRISMA 2020 guidelines. A comprehensive search was performed across three electronic databases (PubMed, CINAHL, and Scopus) covering publications from 2020 to 2025. Inclusion criteria comprised peer-reviewed empirical studies and reviews addressing nursing or health interventions relevant to single-parent families in community or primary health care contexts. Data were extracted and synthesized thematically, with attention to theoretical frameworks, intervention characteristics, and reported outcomes. Results: Twenty-nine studies met the inclusion criteria. The synthesis revealed four main thematic domains: (1) caregiving burden and psychosocial vulnerability, (2) access to and coordination of community-based resources, (3) nurse–family relational processes, and (4) empowerment-oriented nursing interventions. Theoretical underpinnings frequently included family systems perspectives, the Calgary Family Assessment and Intervention Models, and empowerment-oriented frameworks. Conclusions: Nursing interventions for single-parent families in community health settings should prioritise relational empowerment approaches that acknowledge family diversity, contextual vulnerability, and dynamic caregiving demands. The proposed relational empowerment model offers a practice-informed framework to guide Family Health Nursing interventions, education, and policy development, supporting more responsive and equitable care for single-parent families. Full article

Accurate vessel speed prediction is essential for maritime traffic supervision, navigational safety, and intelligent coastal management. However, due to the nonlinear, time-varying, and context-dependent characteristics of vessel motion in nearshore waters, conventional single-model approaches often fail to provide sufficiently accurate forecasts. To address this issue, this study proposes a hybrid deep learning framework for Automatic Identification System (AIS)-based nearshore vessel speed prediction and risk warning, integrating a temporal convolutional network (TCN), an attention mechanism, and a bidirectional long short-term memory network (BiLSTM) into a unified architecture. The core novelty of this framework is its task-oriented sequential design, in which TCN extracts local temporal patterns and multi-scale sequence features from historical AIS observations, the attention mechanism adaptively emphasizes informative representations, and BiLSTM models bidirectional contextual dependencies in vessel motion sequences; on this basis, a speed-risk warning process is constructed by combining the predicted speed with electronic-fence threshold constraints. Experiments conducted on real AIS data from coastal waters show that the proposed method obtains lower mean absolute error (MAE), mean squared error (MSE), and root mean square error (RMSE) as well as a higher coefficient of determination (R²) than several benchmark models. The results illustrate that the proposed framework effectively improves vessel speed prediction accuracy within the studied coastal area and provides practical support for proactive maritime supervision and nearshore safety management. Full article

Phosphorus is an essential and finite resource critical for global food production, yet its inefficient use and discharge from wastewater systems contribute to eutrophication and resource depletion. The transition from conventional wastewater treatment plants to water resource recovery facilities has intensified interest in technologies that enable phosphorus recovery within a circular economy framework. This review provides a critical and up-to-date synthesis of phosphorus recovery strategies from wastewater, with primary emphasis on struvite (MgNH₄PO₄·6H₂O) crystallization as one of the most mature and practically implemented recovery routes. The occurrence and chemical forms of phosphorus in wastewater streams are discussed alongside conventional approaches, such as enhanced biological phosphorus removal and chemical precipitation, in order to position struvite recovery within the broader phosphorus management landscape. In addition to struvite crystallization, selected competing and complementary recovery pathways, including electrochemical systems, biochar-assisted processes, and sludge ash recovery, are discussed to compare technological maturity, recovery potential, and practical applicability. Particular attention is given to reactor configurations, full-scale applications, and commercial technologies to assess operational reliability, recovery performance, and fertilizer product quality. Life-cycle assessment results and regulatory developments are also discussed to contextualize sustainability claims, technology selection, and market integration. The review identifies key technical and economic challenges, particularly regarding magnesium supply, competing ions, wastewater matrix effects, and the feasibility of mainstream application. Overall, controlled sidestream struvite crystallization appears to offer the most favorable balance between recovery efficiency, operational reliability, and fertilizer product quality under suitable plant conditions. Full article

A sense of school belonging predicts NEET outcomes for adolescents. However, young people from marginalized groups often have a lower sense of school belonging than their majority peers. Emerging understandings of belonging as a complex, agentic process shaped by multiple relational, contextual, cultural and structural factors have posed problems for real-world applications of belonging. NEET young people tend to be viewed through a lens of risk factors, with a lack of research accounting for their experiences and feelings. While recent research recognizes the intersectional effects of disadvantage, or ‘compound disadvantage’, on NEET outcomes for young people from certain social groups, there is a lack of viable alternatives for educators and policymakers to account for these differential experiences of belonging in order to be able to respond to them. Connected Belonging is a relational and identity-building approach to enhancing young people’s wellbeing through supporting their connectedness and sense of self across the eight social domains of their lives. This paper outlines the development and validation of a young people’s survey, which enables education professionals to attend to and respond to the differing belonging experiences of diverse groups, operationalizing an intersectional lens on school belonging. After introducing the views of young people about systemic priorities to better support their engagement in education, training or work (EET), gathered through a youth voice event as part of a parallel research project, the paper outlines the process of developing, piloting and validating the tool. We argue that this survey tool has the potential to support improved attention to the views and experiences of diverse young people in a systematic, regular fashion. Furthermore, it offers potential for the evaluation of supportive actions grounded in youth voice. Full article

Ship classification in optical remote sensing requires balancing discriminative representation and model efficiency. Standard convolutional neural network (CNN) bottlenecks rely on local spatial kernels and may emphasize high-frequency texture cues, while stronger backbones increase parameter cost. We propose a frequency-aware lightweight bottleneck (FALB) that couples enhanced wavelet convolution (WTsConv) and contextual anchor attention (CAA) in a cascaded design. WTsConv adopts Sym4 wavelets and a learnable symmetric fusion weight between spatial and wavelet-reconstructed features to improve frequency-aware feature mixing. CAA is then applied to the refined features for contextual aggregation. Integrated into ResNet-50 bottlenecks, FALB is evaluated on FGSCM-52 and achieves 97.88% top-1 accuracy with 17.78 M parameters, compared with 96.92% and 25.56 M for the ResNet-50 baseline, surpassing ResNet-50 by 0.96% and outperforming compared general-purpose baselines while reducing parameters by 30.4%. Under this experimental setting, FALB improves the observed accuracy–parameter trade-off for remote sensing ship classification. Full article

Rapid and reliable tea classification is valuable for routine product screening, yet conventional sensory or physicochemical methods are subjective or time-consuming. Electronic nose (E-nose) sensing provides a fast alternative, but performance often degrades under domain shifts caused by different tea types, commercial categories, or acquisition conditions. This study proposes MGDA-Net, a multi-granularity domain adversarial network for cross-domain tea classification using E-nose time-series signals. MGDA-Net learns local temporal dynamics via a CNN branch and global contextual dependencies via a self-attention branch, and fuses them through an adaptive gating module. A branch-level adversarial alignment strategy is introduced to reduce source–target discrepancy at both local and global feature levels. A three-stage training procedure, consisting of source pretraining, adversarial alignment, and target fine-tuning, enables knowledge transfer from a labeled green tea source-domain to two target tasks. Experiments on oolong tea commercial-category classification (6 classes) and jasmine tea retail price-level classification (8 classes) show that MGDA-Net achieves mean accuracies of 99.31 ± 0.69% and 99.38 ± 0.51% over 10 independent runs, substantially outperforming all compared baseline methods. Ablation studies, feature-space analyses, and label-efficiency experiments further confirm the contribution of each component and show that MGDA-Net maintains mean accuracies above 87% when only 40% of the target-domain labels are used for fine-tuning. These findings suggest that MGDA-Net is a promising approach for cross-domain tea classification using E-nose data. Full article

Small object detection in UAV imagery presents challenges due to factors such as minute scale, indistinct features, and severe background clutter, which constrain the recognition performance of end-to-end models like RT-DETR. To enhance detection accuracy for small-scale objects, this paper proposes MSA-DETR, a Multi-scale Spatial Attention-enhanced detection model based on RT-DETR (Res18). Three specific structural improvements are introduced. First, a PercepConv module is designed to capture comprehensive multi-scale information through 1 × 1, 3 × 3, and 5 × 5 convolutions, as well as dilated convolutions. This module integrates a lightweight channel attention mechanism to adaptively emphasize regions containing small objects. Second, the SODAttention module is introduced to jointly model local spatial details and global contextual information, thereby enhancing the discriminative capability in key regions and significantly suppressing interference from complex backgrounds. Finally, a dedicated small object detection layer is added to the detection head, incorporating shallow fine-grained features to compensate for the semantic limitations of deep layers concerning small targets. Experimental results demonstrate that the proposed MSA-DETR achieves significant performance gains on the VisDrone2019 dataset, increasing mAP@50 from 47.5% to 52.2% and mAP@50–95 from 29.3% to 33.2%. Moreover, the proposed model outperforms the baseline by an absolute margin of 1.9% on the small-object-specific metric APs, achieving 20.3%. These results validate the effectiveness of the proposed method for small object detection in UAV scenarios. Full article

Accurate forecasting of wind and photovoltaic power remains challenging due to the strong nonlinearity, nonstationarity, and seasonal heterogeneity of renewable generation series. To address this issue, this study proposes a hybrid forecasting framework integrating time–frequency joint analysis (TFAA), temporal convolutional networks (TCN), long short-term memory (LSTM), and multi-head self-attention (MHSA). Wavelet transform is used to extract frequency-domain representations, which are jointly encoded with the original time-domain sequence through a dual-branch architecture and adaptively fused. The fused features are then processed by a TCN-LSTM backbone to capture both long-range dependencies and short-term dynamics, while MHSA is introduced to enhance global contextual modeling. Experiments on wind-farm and photovoltaic datasets from China, together with external validation on the NREL WIND Toolkit and the GEFCom2014 Solar benchmark, show that the proposed model achieves the best overall seasonal performance and maintains competitive improvements on public benchmarks. Additional ablation studies, repeated-run statistical validation, persistence-based skill-score analysis, prediction-interval evaluation, ramp-event assessment, meteorological-driver enrichment, permutation-based driver attribution, regime-conditioned error diagnostics, and transferability evidence analysis further confirm the effectiveness, robustness, physical consistency, and practical applicability of the proposed framework. The results indicate that the proposed model provides a reliable and operationally relevant solution for short-term wind and photovoltaic power forecasting. These findings further support sustainable renewable-energy integration, smart-grid dispatch, and low-carbon power-system operation. Full article

Age-related macular degeneration (AMD) remains the leading cause of irreversible central vision loss in the elderly. Increasing attention has been directed toward lipid metabolism as a potential contributor to disease onset and progression. The overlap between AMD and atherosclerosis—particularly regarding lipid accumulation, endothelial dysfunction, and chronic inflammation—has prompted interest in lipid-lowering therapies. This narrative review synthesizes the clinical evidence published between 2020 and 2025 on the potential role of statins and fenofibrate in AMD risk modification and disease progression. A structured literature search was conducted in PubMed, Scopus, and Web of Science using combined MeSH and free-text terms related to lipid-lowering agents and AMD. Human studies evaluating clinical incidence or progression outcomes were considered alongside contextual evidence from prior evidence syntheses. Overall, findings remain heterogeneous. Most studies did not demonstrate a consistent association between statin therapy and AMD incidence or progression in unselected populations. However, selected reports suggested a potential delay in dry AMD onset or slower disease progression among patients receiving prolonged or higher-intensity statin treatment. Evidence regarding fenofibrate was more limited and heterogeneous, with only a tentative protective signal observed in adherent users, particularly for non-exudative AMD. The current literature does not support lipid-lowering therapy as a universal preventive strategy for AMD. Nonetheless, subgroup-specific benefits cannot be excluded, especially in early disease stages or metabolically high-risk populations. Further well-designed prospective and randomized studies are needed to clarify therapeutic relevance and identify the patients who are most likely to benefit. Full article