Search Results (222)

Concept-cognitive learning reveals the principle of human cognition by simulating the brain’s process of learning and processing concepts. Nevertheless, for neighborhood similarity granules, the average information of objects regarding all attributes is not considered, which may lead to unbalanced acquisition of knowledge. On the other hand, there are some unnecessary concepts in the extension of fuzzy concepts, which results in poor classification learning. To tackle these challenges, we present a forgetting-based concept-cognitive learning model for classification in a fuzzy formal decision context. Firstly, the fuzzy concept space is established based on the the correlation coefficient matrix. Then, to delete unnecessary objects that are in the zone of proximal development, we construct the forgetting fuzzy concept space by selecting the concept corresponding to the maximum similarity. Subsequently, a forgetting-based fuzzy concept model (FCCLM) mechanism is proposed. In the end, experimental results on eight datasets validate the feasibility and efficiency of the proposed learning mechanism through classification performance assessment. Full article

Phishing attacks pose significant risks to security, drawing considerable attention from both security professionals and customers. Despite extensive research, the current phishing website detection mechanisms often fail to efficiently diagnose unknown attacks due to their poor performances in the feature selection stage. Many techniques suffer from overfitting when working with huge datasets. To address this issue, we propose a feature selection strategy based on a convolutional graph network, which utilizes a dataset containing both labels and features, along with hyperparameters for a Support Vector Machine (SVM) and a graph neural network (GNN). Our technique consists of three main stages: (1) preprocessing the data by dividing them into testing and training sets, (2) constructing a graph from pairwise feature distances using the Manhattan distance and adding self-loops to nodes, and (3) implementing a GraphSAGE model with node embeddings and training the GNN by updating the node embeddings through message passing from neighbors, calculating the hinge loss, applying the softmax function, and updating weights via backpropagation. Additionally, we compute the neighborhood random walk (NRW) distance using a random walk with restart to create an adjacency matrix that captures the node relationships. The node features are ranked based on gradient significance to select the top k features, and the SVM is trained using the selected features, with the hyperparameters tuned through cross-validation. We evaluated our model on a test set, calculating the performance metrics and validating the effectiveness of the PhishGNN dataset. Our model achieved a precision of 90.78%, an F1-score of 93.79%, a recall of 97%, and an accuracy of 93.53%, outperforming the existing techniques. Full article

Identifying correspondences of road segments in different road networks, namely road-network matching, is an essential task for road network-centric data processing such as data integration of road networks and data quality assessment of crowd-sourced road networks. Traditional road-network matching usually relies on feature engineering and parameter selection of the geometry and topology of road networks for similarity measurement, resulting in poor performance when dealing with dense and irregular road network structures. Recent development of graph neural networks (GNNs) has demonstrated unsupervised modeling power on road network data, which learn the embedded vector representation of road networks through spatial feature induction and topology-based neighbor aggregation. However, weighting spatial information on the node feature alone fails to give full play to the expressive power of GNNs. To this end, this paper proposes a Spatial Pattern-aware Graph EMbedding learning method for road-network matching, named SP-GEM, which explores the idea of spatially-explicit modeling by identifying spatial patterns in neighbor aggregation. Firstly, a road graph is constructed from the road network data, and geometric, topological features are extracted as node features of the road graph. Then, four spatial patterns, including grid, high branching degree, irregular grid, and circuitous, are modelled in a sector-based road neighborhood for road embedding. Finally, the similarity of road embedding is used to find data correspondences between road networks. We conduct an algorithmic accuracy test to verify the effectiveness of SP-GEM on OSM and Tele Atlas data. The algorithmic accuracy experiments show that SP-GEM improves the matching accuracy and recall by at least 6.7% and 10.2% among the baselines, with high matching success rate (>70%), and improves the matching accuracy and recall by at least 17.7% and 17.0%, compared to the baseline GNNs, without spatially-explicit modeling. Further embedding analysis also verifies the effectiveness of the induction of spatial patterns. This study not only provides an effective and practical algorithm for road-network matching, but also serves as a test bed in exploring the role of spatially-explicit modeling in GNN-based road network modeling. The experimental performances of SP-GEM illuminate the path to develop GeoEmbedding services for geospatial applications. Full article

Graph attention networks are pivotal for modeling non-Euclidean data, yet they face dual challenges: training oscillations induced by projection-based high-dimensional constraints and gradient anomalies due to poor adaptation to heterophilic structure. To address these issues, we propose LDC-GAT (Lyapunov-Stable Graph Attention Network with Dynamic Filtering and Constraint-Aware Optimization), which jointly optimizes both forward and backward propagation processes. In the forward path, we introduce Dynamic Residual Graph Filtering, which integrates a tunable self-loop coefficient to balance neighborhood aggregation and self-feature retention. This filtering mechanism, constrained by a lower bound on Dirichlet energy, improves multi-head attention via multi-scale fusion and mitigates overfitting. In the backward path, we design the Fro-FWNAdam, a gradient descent algorithm guided by a learning-rate-aware perceptron. An explicit Frobenius norm bound on weights is derived from Lyapunov theory to form the basis of the perceptron. This stability-aware optimizer is embedded within a Frank–Wolfe framework with Nesterov acceleration, yielding a projection-free constrained optimization strategy that stabilizes training dynamics. Experiments on six benchmark datasets show that LDC-GAT outperforms GAT by 10.54% in classification accuracy, which demonstrates strong robustness on heterophilic graphs. Full article

The literature shows greenspaces generally increase nearby property values, but in Riyadh, this relationship is complex and understudied. Existing studies lack sector-specific analyses across Riyadh’s neighborhoods, overlook the impact of the Green Riyadh Project launched in 2019, and fail to address negative externalities associated with large greenspaces in an arid, privacy-conscious context. Such paradoxical impact of larger greenspaces bordering major roads at the neighborhood edge, unexpectedly reduce property values by 2–4% due to petty crime, congestion, poor upkeep, and privacy concerns, contrasting with 10–18% premiums for properties abutting greenspaces with restricted access in affluent neighborhoods. Global studies typically report positive greenspace effects, so negative impacts in specific Riyadh sectors are surprising. This highlights the city’s unique arid, cultural, and urban dynamics in addressing this research gap. The research uses purposive quota sampling of Riyadh neighborhood greenspaces and a mixed-methods approach of quantitative hedonic pricing analysis combined with qualitative semi-structured interviews with real estate agents. Findings underscore the need for tailored urban planning (e.g., mitigating petty crime, overcrowding, poor maintenance). This suggests the importance of integrating green infrastructure into urban planning, not only for its ecological and social benefits but also for its tangible positive impact on property values. Poor greenspace upkeep and safety concerns can reduce price premiums of abutting properties. Full article

This study integrates socio-demographic factors and local sustainability indicators to assess their implications for public health and social vulnerability in the Henequén neighborhood of Cartagena, Colombia. This historically marginalized community, primarily composed of women and displaced families, faces chronic exposure to environmental contaminants due to its past as a municipal landfill. Poor housing conditions, overcrowding, and inadequate access to water and sanitation services exacerbate health risks. Additionally, low educational attainment and limited economic opportunities contribute to cycles of poverty and illicit activities, disproportionately affecting children’s development. Using a cross-sectional and correlational approach, the study identifies key variables, such as housing conditions, access to basic services, and marital status, that shape social vulnerability. The findings are analyzed in the context of the United Nations Sustainable Development Goals (SDGs), particularly SDG 3 (Good Health and Well-being), SDG 6 (Clean Water and Sanitation), and SDG 11 (Sustainable Cities and Communities). The study highlights critical gaps in sustainability efforts and provides a framework for assessing local progress toward achieving these global development objectives. Full article

Line feature matching is a crucial aspect of computer vision and image processing tasks, attracting significant research attention. Most line matching algorithms predominantly rely on local feature descriptors or deep learning modules, which often suffer from low robustness and poor generalization. In response, this paper presents a novel line feature matching approach grounded in point–line invariants through spatial invariant relationships. By leveraging a robust point feature matching algorithm, an initial set of point feature matches is acquired. Subsequently, the line feature supporting area is partitioned, and a constant ratio invariant is formulated based on the distances from point to line features within corresponding neighborhood domains. Additionally, a direction vector invariant is also introduced, jointly constructing a dual invariant for line matching. An initial matching matrix and line feature match pairs are derived using this dual invariant. Subsequent geometric constraints within line feature matches eliminate residual outliers. Comprehensive evaluations under diverse imaging conditions, along with comparisons to several state-of-the-art algorithms, demonstrate that our proposal achieved remarkable performance in terms of both accuracy and robustness. Our implementation code will be publicly released upon the acceptance of this paper. Full article

Environmental changes, which have led to frequent and severe climate-related disasters, profoundly affect individuals and communities in Louisiana that display already existing disparities in vulnerability. An increasing body of evidence documents the relationship between the effects of climate change and poor mental health. This underscores the importance of utilizing an environmental justice framework to assess and innovate strategies for addressing disasters’ unequal burden. As part of a broader Community-Based Participatory Research (CBPR) project on the effects of a community-based intervention to improve mental health resilience in communities affected by disasters and crises, we included 12 churches in a community asset mapping process to identify resources within their communities and discuss actions that could improve their neighborhoods and build additional support. We conducted deductive and inductive content analysis of asset maps and field notes from 32 small groups. We found the following: (1) the church was seen as a central asset; (2) key distinctions in how participants discussed their tangible and intangible resources according to their geography, and (3) the themes of charity, resource facilitation, connecting the most vulnerable, and absence of government support typified how groups discussed possibilities of action. Full article

Background: Breast cancer disparities persist globally, with growing evidence implicating neighborhood and built environmental factors in disease outcomes. Methods: This study investigates the associations between neighborhood disadvantage, environmental exposures, and breast tumor characteristics and survival among 3041 stage I–III breast cancer patients treated at the University of Virginia Comprehensive Cancer Center (2014–2024). Neighborhood disadvantage was assessed via the Area Deprivation Index (ADI), while environmental exposures included PM2.5, green space (NDVI), and food indices (modified retail food environment index (mRFEI), retail food activity index (RFAI)). Multivariable regression and Cox models adjusted for demographic, socioeconomic, and clinical covariates were employed. Results: A higher ADI score was associated with aggressive tumor characteristics, including advanced stage (Odds Ratio (OR) = 1.06, 95% Confidence Interval (CI):1.01–1.11), poor differentiation (OR = 1.07, 1.01–1.15), ER-negative status (OR = 1.06, 1.01–1.12), and triple-negative breast cancer (TNBC) (OR = 1.08, 1.02–1.16), as well as younger diagnosis age (β = −0.22, −0.36 to −0.09). PM2.5 exposure was correlated with advanced tumor stage (OR = 1.24, 1.09–1.40 for stage III) but paradoxically predicted improved survival (Hazard Ratio (HR) = 0.71, 0.63–0.82). The food environment indices showed subtype-specific survival benefits: higher mRFEI and RFAI scores were linked to reduced mortality in ER-negative (HR = 0.45, 0.23–0.85 and HR = 0.61, 0.38–0.97) and TNBC (HR = 0.40, 0.18–0.90 and HR = 0.48, 0.26–0.87) patients. NDVI scores exhibited no significant associations. Conclusion: Our findings underscore the dual role of neighborhood disadvantage and the built environmental in breast cancer outcomes. While neighborhood disadvantage and PM2.5 exposure elevate tumor aggressiveness, survival disparities may be mediated by other factors. Improved food environments may enhance survival in aggressive subtypes, highlighting the need for integrated interventions addressing socioeconomic inequities, environmental risks, and nutritional support needs. Full article

Aiming at the problems of poor image quality of traditional cameras and serious noise interference of event cameras under complex lighting conditions in coal mines, an event denoising algorithm fusing spatio-temporal information and a method of denoising event target pose estimation is proposed. The denoising algorithm constructs a spherical spatio-temporal neighborhood to enhance the spatio-temporal denseness and continuity of valid events, and combines event density and curvature to achieve event stream denoising. The attitude estimation framework adopts the noise reduction event and global optimal perspective-n-line (OPNL) methods to obtain the initial target attitude, and then establishes the event line correlation model through the robust estimation, and achieves the attitude tracking by minimizing the event line distance. The experimental results show that compared with the existing methods, the noise reduction algorithm proposed in this paper has a noise reduction rate of more than 99.26% on purely noisy data, and the event structure ratio (ESR) is improved by 47% and 5% on DVSNoise20 dataset and coal mine data, respectively. The maximum absolute trajectory error of the localization method is 2.365 cm, and the mean square error is reduced by 2.263% compared with the unfiltered event localization method. Full article

Point cloud completion reconstructs incomplete, sparse inputs into complete 3D shapes. However, in the current 3D completion task, it is difficult to effectively extract the local details of an incomplete one, resulting in poor restoration of local details and low accuracy of the completed point clouds. To address this problem, this paper proposes a multi-scale point cloud completion method based on local neighborhood dynamic fusion (LNDF: adaptive aggregation of multi-scale local features through dynamic range and weight adjustment). Firstly, the farthest point sampling (FPS) strategy is applied to the original incomplete and defective point clouds for down-sampling to obtain three types of point clouds at different scales. When extracting features from point clouds of different scales, the local neighborhood aggregation of key points is dynamically adjusted, and the Transformer architecture is integrated to further enhance the correlation of local feature extraction information. Secondly, by combining the method of generating point clouds layer by layer in a pyramid-like manner, the local details of the point clouds are gradually enriched from coarse to fine to achieve point cloud completion. Finally, when designing the decoder, inspired by the concept of generative adversarial networks (GANs), an attention discriminator designed in series with a feature extraction layer and an attention layer is added to further optimize the completion performance of the network. Experimental results show that LNDM-Net reduces the average Chamfer Distance (CD) by 5.78% on PCN and 4.54% on ShapeNet compared to SOTA. The visualization of completion results demonstrates the superior performance of our method in both point cloud completion accuracy and local detail preservation. When handling diverse samples and incomplete point clouds in real-world 3D scenarios from the KITTI dataset, the approach exhibits enhanced generalization capability and completion fidelity. Full article

In this study, we investigate the residential stability and mobility patterns of Black single mothers compared to White single mothers. Using data from the Panel Study of Income Dynamics from 1970 to 2015, linked to the U.S. Census for contextual characteristics, our multilevel linear probability models reveal substantial racial disparities. Black single mothers have a lower probability of remaining in non-poor neighborhoods rather than migrating to poor neighborhoods relative to White single mothers. Conversely, Black single mothers possess a higher probability of remaining in poor neighborhoods instead of moving to non-poor ones in relation to White single mothers. When economic resources are allowed to vary between Black and White single mothers, even higher-income Black single mothers cannot convert these resources into remaining in or migrating to non-poor neighborhoods at the same rate as White single mothers. Full article

Intensifying heat from warming climates regularly concentrates in urban areas lacking green infrastructure in the form of green space, vegetation, and ample tree canopy cover. Nature-based interventions in older U.S. city cores can help minimize the urban heat island effect, yet neighborhoods targeted for cooling interventions may remain outside the decisional processes through which change affects their communities. This translational research seeks to address health disparities originating from the absence of neighborhood-level vegetation in core urban areas, with a focus on tree canopy cover to mitigate human susceptibility to extreme heat exposure. The development of LiDAR-based imagery enables communities to visualize the proposed greening over time and across seasons of actual neighborhood streets, thus becoming an effective communications tool in community-engaged research. These tools serve as an example of how visualization strategies can initiate unbiased discussion of proposed interventions, serve as an educational vehicle around the health impacts of climate change, and invite distributional and participatory equity for residents of low-income, nature-poor neighborhoods. Full article

Urban green space can effectively optimize the urban landscape and environment and provide residents with space for daily leisure and recreational activities. In order to realize the green development of Macau, this paper takes the Macau Special Administrative Region (SAR) as an example, uses the green open space occupancy rate (GOSOR) to measure the level of green open space in Macau, and researches the planning positioning of Macau City’s green development, the layout mode of urban public open space, and the integration and optimization of the space in Largo of high-density neighborhoods, so as to explore the planning paradigm of Macau’s green development. In addition, the research data show that the per capita green area of Macau Peninsula is on the low side and extremely unbalanced, and there is a disconnection between some of the large-scale green patches on Macau Outlying Island; therefore, this paper proposes that the planning layout mode of “green veins connecting green patches” is suitable for Macau Peninsula and that the planning layout mode of “greenways embedded in jade” is suitable for Macau Outlying Island. On the other hand, in order to improve the problem of poor living conditions in the high-density city of Macau, the study proposes to make use of the unutilized Macau Largo space and carry out the optimization and transformation of the Largo space from “gray to green”, so as to release a large amount of green open space and enhance the GOSOR value of the high-density street area of Macau Peninsula. Full article

Population aging and urbanization are two of the most significant social transformations of the 21st century. Against the backdrop of rapid aging in China, developing age-friendly community environments, particularly through the renovation of legacy residential communities, not only supports active and healthy aging but also promotes equity and sustainable development. This study focuses on residential communities built in the 1980s in Hangzhou, exploring strategies for the age-friendly renovation of outdoor public spaces. The residential communities that flourished during the construction boom of the 1980s are now confronting a dual challenge: aging populations and deteriorating facilities. However, existing renovation efforts often pay insufficient attention to the comprehensive age-friendly transformation of outdoor public spaces within these neighborhoods. Following a structured research framework encompassing investigation, evaluation, design, and discussion, this study first analyzes linear grid layouts and usage patterns of these communities. Then, the research team uses post-occupancy evaluation (POE) to assess the age-friendliness of outdoor public spaces. Semi-structured interviews with elderly residents identify key concerns and establish a preliminary evaluation framework, while a Likert-scale questionnaire quantifies the satisfaction with age-friendly features across four communities. The assessment reveals that key age-friendliness issues, including poor traffic safety, dispersed activity spaces, and insufficiently adapted facilities, are closely linked to the linear usage patterns within the spatial framework of the grid layouts. Based on the findings, the study develops tiered renovation goals, renovation principles and implemented an age-friendly design in the Hemu Community. The strengths, weaknesses, and feasibility of the renovation plan are discussed, while three recommendations are made to ensure successful implementation. The study is intended to provide a valuable reference for advancing age-friendly residential renewal efforts in Hangzhou and contributing to the broader objective of sustainable, inclusive city development. Full article