Search Results (847)

Graph anomaly detection aims at identifying rare, unusual entities in attributed networks with respect to their patterns or structures that deviate significantly from the majority within a graph. Over the years, extensive efforts in this field have been dedicated to the powerful capability of attributed networks to model real-world systems. Given the scarcity of labeled anomalies, current research primarily emphasizes model design via unsupervised learning. Graph autoencoders have been widely utilized for such purposes, leveraging the outstanding capabilities of Graph Neural Networks to model graph structured data. However, most existing graph autoencoder-based anomaly detectors do not exploit the nodes’ local subgraph information, limiting their ability to comprehensively understand the network for better representation learning. Moreover, these methods place greater emphasis on the attribute reconstruction process while neglecting the structure reconstruction aspect. This paper proposes an enhanced graph autoencoder framework for graph anomaly detection tasks that incorporates a subgraph extraction and aggregation preprocessing stage to utilize the nodes’ local topological information for enhanced embedding generation and to induce an additional node–subgraph view through model learning. A graph structure learning-based decoder is introduced as the structure decoder for better relationship learning. Finally, during the anomaly scoring stage, a node neighborhood selection technique is applied to enhance the detection performance. The effectiveness of the proposed framework is demonstrated through comprehensive experiments conducted on six commonly used real-world datasets. Full article

Landscape metrics are one of the main tools for studying changes in the landscape and the ecological structure of the territory. However, the calculation of some metrics yields significantly different values depending on the configuration of the “Cell neighborhood” (CN) used. This makes the comparison of different analysis results often impossible. In fact, although the metrics are defined in the same way for all software, the choice of a CN with four cells, which includes only the elements on the same row or column, or eight cells, which also includes the cells on the diagonal, changes their value. QGIS’ LecoS plugin uses the value eight while GRASS’ r.li module uses the value four and these values are not modifiable by users. A previous study has shown how the value of the CN used for the calculation of landscape metrics is rarely explicit in scientific publications and its value cannot always be deduced from the indication of the software used. The difference in value for the same metric depends on the CN configuration and on the compactness of the patches, which can be expressed through the Aggregation Index (AI), of the investigated landscape. The scope of this paper is to explore the possibility of deriving an analytical relationship between the Aggregation Index and the variation in the values of some landscape metrics as the CN varies. The numerical experiments carried out in this research demonstrate that it is possible to estimate the differences in landscape metrics evaluated with a four and eight CN configuration using polynomials only for few metrics and only for some intervals of AI values. This analysis combines different Free and Open Source Software (FOSS) systems: GRASS GIS for the creation of test maps and R landscapemetrics package for the calculation of landscape metrics and the successive statistical analysis. Full article

Unsupervised feature selection aims to characterize the cluster structure of original features and select the optimal subset without label guidance. However, existing methods overlook fuzzy information in the data, failing to model cluster structures between data effectively, and rely on squared error for data reconstruction, exacerbating noise impact. Therefore, a robust unsupervised feature selection algorithm based on fuzzy anchor graphs (FWFGFS) is proposed. To address the inaccuracies in neighbor assignments, a fuzzy anchor graph learning mechanism is designed. This mechanism models the association between nodes and clusters using fuzzy membership distributions, effectively capturing potential fuzzy neighborhood relationships between nodes and avoiding rigid assignments to specific clusters. This soft cluster assignment mechanism improves clustering accuracy and the robustness of the graph structure while maintaining low computational costs. Additionally, to mitigate the interference of noise in the feature selection process, an adaptive fuzzy weighting mechanism is presented. This mechanism assigns different weights to features based on their contribution to the error, thereby reducing errors caused by redundant features and noise. Orthogonal tri-factorization is applied to the low-dimensional representation matrix. This guarantees that each center represents only one class of features, resulting in more independent cluster centers. Experimental results on 12 public datasets show that FWFGFS improves the average clustering accuracy by 5.68% to 13.79% compared with the state-of-the-art methods. Full article

This paper addresses the trajectory tracking control problem of underactuated ships in ocean engineering, which faces the dual challenges of tracking error time–performance regulation and robustness design due to the system’s underactuated characteristics, model uncertainties, and external disturbances. Aiming to address the issues of traditional finite-time control (convergence time dependent on initial states) and fixed-time control (control chattering and parameter conservativeness), this paper proposes a predefined-time adaptive control framework that integrates an event-triggered mechanism and neural networks. By constructing a Lyapunov function with time-varying weights and designing non-periodic dynamically updated dual triggering conditions, the convergence process of tracking errors is strictly constrained within a user-prespecified time window without relying on initial states or introducing non-smooth terms. An adaptive approximator based on radial basis function neural networks (RBF-NNs) is employed to compensate for unknown nonlinear dynamics and external disturbances in real-time. Combined with the event-triggered mechanism, it dynamically adjusts the update instances of control inputs, ensuring prespecified tracking accuracy while significantly reducing computational resource consumption. Theoretical analysis shows that all signals in the closed-loop system are uniformly ultimately bounded, tracking errors converge to a neighborhood of the origin within the predefined-time, and the update frequency of control inputs exhibits a linear relationship with the predefined-time, avoiding Zeno behavior. Simulation results verify the effectiveness of the proposed method in complex marine environments. Compared with traditional control strategies, it achieves more accurate trajectory tracking, faster response, and a substantial reduction in control input update frequency, providing an efficient solution for the engineering implementation of embedded control systems in unmanned ships. Full article

Hazelnut (Corylus avellana L.) is a significant global agricultural product due to its high economic and nutritional worth. The traditional methods used to measure the hazelnut kernel percentage for quality assessment are often time-consuming, expensive, and prone to human errors. Inaccurate measurements can adversely impact the market value, shelf life, and industrial applications of hazelnuts. This research introduces a novel system for calculating hazelnut kernel percentage utilizing a non-destructive X-ray imaging technique along with deep learning methods to assess hazelnut quality more efficiently and reliably. An image dataset of hazelnut kernels has been developed using X-ray technology, and defective areas are identified employing YOLOv7 architecture. Additionally, a novel bounding box regression technique called DCIoU and an algorithm for Neighborhood Relationship have been introduced to enhance object detection capabilities and to improve the selection of the target box with greater precision, respectively. The performance of these proposed methods has been evaluated using both the created hazelnut dataset and the COCO-128 dataset. The results indicate that the system can serve as a valuable tool for measuring hazelnut kernel percentages by accurately identifying defects in hazelnuts. 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

The structure and interpersonal interactions of traditional residential communities have also been impacted and recreated as a result of the fast development of urban space and related communities. This study explores the interrelationship between neighborhood social cohesion and the life satisfaction of urban adult residents through the mediating effect of place attachment. A comprehensive theoretical model was constructed to analyze the action mechanism among these variables. Data were collected through an online questionnaire platform (n = 301), and structural equation modeling (PLS-SEM) was employed for analysis. The findings revealed a significant positive relationship between neighborhood social cohesion and residents’ place attachment. Place attachment appeared to play a mediating role between neighborhood social cohesion and life satisfaction, in which place dependence was also a potential effective mediator between the three dimensions of neighborhood social cohesion (neighborliness, sense of community, and neighborhood attractiveness) and life satisfaction. The results suggest that enhancing community cohesion may contribute to urban adult residents’ well-being by strengthening their functional dependence on the community. Full article

This paper builds on place theory and the psycho-social approach to the study of perceived residential environmental quality to examine the relationship between environmental perceptions and residential action in the neighborhood. An exploratory study on (N = 185) Italian respondents assessed the role of perceived residential environmental quality (i.e., perceived quality of green areas and perceived maintenance levels within the neighborhood), awareness of neighborhood environmental problems, neighborhood descriptive norms, and place attachment (attachment to the neighborhood) as predictors of self-reported individual residential engagement (engagement in improving the environmental quality of the neighborhood). Likert-type measures of the corresponding constructs were included in a structured questionnaire and used to carry out an online survey. Findings showed problem awareness and descriptive norms to directly predict residential engagement. Problem awareness mediated the relationship between perceived maintenance levels and residential engagement. Place attachment was directly predicted by perceived residential quality (quality of green areas), but did not show an independent predictive power vis-à-vis residential engagement. Results suggest new possible research avenues for modelling the individual commitment to improve the environmental quality of one’s own residential architectural and green environment. Full article

Heterogeneous information network (HIN) embedding transforms multi-type nodes into low-dimensional vectors to preserve structural and semantic information for downstream tasks. However, it struggles with multiplex networks where nodes connect via diverse semantic paths (metapaths). Information fusion mainly improves the quality of node embedding by fully exploiting the structure and hidden information within the network. Current metapath-based methods ignore information from intermediate nodes along paths, depend on manually defined metapaths, and overlook implicit relationships between nodes sharing similar attributes. Our objective is to develop an adaptive framework that overcomes limitations in existing metapath-based embedding (incomplete information aggregation, manual path dependency, and ignorance of latent semantics) to learn more discriminative embeddings. We propose an adaptive multi-hop neighbor information fusion model for heterogeneous network embedding (ANHNE), which: (1) autonomously extracts composite metapaths (weighted combinations of relations) via a multipath aggregation matrix to mine hierarchical semantics of varying lengths for task-specific scenarios; (2) projects heterogeneous nodes into a unified space and employs hierarchical attention to selectively fuse neighborhood features across metapath hierarchies; and (3) enhances semantics by identifying potential node correlations via cosine similarity to construct implicit connections, enriching network structure with latent information. Extensive experimental results on multiple datasets show that ANHNE achieves more precise embeddings than comparable baseline models. Full article

Amman’s rapid population growth and sprawling urbanization have resulted in car-centric, fragmented neighborhoods that lack social cohesion and are vulnerable to the impacts of climate change. This study reframes walkability as a climate adaptation strategy, demonstrating how pedestrian-oriented spatial planning can reduce vehicle emissions, mitigate urban heat island effects, and enhance the resilience of green infrastructure in peri-urban contexts. Using Deir Ghbar, a rapidly developing marginal area on Amman’s western edge, as a case study, we combine objective walkability metrics (street connectivity and residential and retail density) with GIS-based spatial regression analysis to examine relationships with residents’ sense of community. Employing a quantitative, correlational research design, we assess walkability using a composite objective walkability index, calculated from the land-use mix, street connectivity, retail density, and residential density. Our results reveal that higher residential density and improved street connectivity significantly strengthen social cohesion, whereas low-density zones reinforce spatial and socioeconomic disparities. Furthermore, the findings highlight the potential of targeted green infrastructure interventions, such as continuous street tree canopies and permeable pavements, to enhance pedestrian comfort and urban ecological functions. By visualizing spatial patterns and correlating built-environment attributes with community outcomes, this research provides actionable insights for policymakers and urban planners. These strategies contribute directly to several Sustainable Development Goals (SDGs), particularly SDG 11 (Sustainable Cities and Communities) and SDG 13 (Climate Action), by fostering more inclusive, connected, and climate-resilient neighborhoods. Deir Ghbar emerges as a model for scalable, GIS-driven spatial planning in rural and marginal peri-urban areas throughout Jordan and similar regions facing accelerated urban transitions. By correlating walkability metrics with community outcomes, this study operationalizes SDGs 11 and 13, offering a replicable framework for climate-resilient urban planning in arid regions. Full article

Recently, a network based on selective state space models (SSMs), Mamba, has emerged as a research focus in hyperspectral image (HSI) classification due to its linear computational complexity and strong long-range dependency modeling capability. Originally designed for 1D causal sequence modeling, Mamba is challenging for HSI tasks that require simultaneous awareness of spatial and spectral structures. Current Mamba-based HSI classification methods typically convert spatial structures into 1D sequences and employ various scanning patterns to capture spatial dependencies. However, these approaches inevitably disrupt spatial structures, leading to ineffective modeling of complex spatial relationships and increased computational costs due to elongated scanning paths. Moreover, the lack of neighborhood spectral information utilization fails to mitigate the impact of spatial variability on classification performance. To address these limitations, we propose a novel model, Dual-Aware Discriminative Fusion Mamba (DADFMamba), which is simultaneously aware of spatial-spectral structures and adaptively integrates discriminative features. Specifically, we design a Spatial-Structure-Aware Fusion Module (SSAFM) to directly establish spatial neighborhood connectivity in the state space, preserving structural integrity. Then, we introduce a Spectral-Neighbor-Group Fusion Module (SNGFM). It enhances target spectral features by leveraging neighborhood spectral information before partitioning them into multiple spectral groups to explore relations across these groups. Finally, we introduce a Feature Fusion Discriminator (FFD) to discriminate the importance of spatial and spectral features, enabling adaptive feature fusion. Extensive experiments on four benchmark HSI datasets demonstrate that DADFMamba outperforms state-of-the-art deep learning models in classification accuracy while maintaining low computational costs and parameter efficiency. Notably, it achieves superior performance with only 30 training samples per class, highlighting its data efficiency. Our study reveals the great potential of Mamba in HSI classification and provides valuable insights for future research. Full article

Indoor radon constitutes a public health issue in various regions across the United States as the second leading cause of lung cancer following tobacco smoke. The U.S. Environmental Protection Agency advises radon mitigation interventions for residential buildings with indoor radon concentrations exceeding the threshold level of 4 pCi/L. Despite considerable research assessing the technical effectiveness of radon mitigation systems, there remains a gap in understanding their broader influence on occupant behavior and preferences in residential design. This study aims to investigate the impact of residing in radon-mitigated homes within the Commonwealth of Kentucky—an area known for elevated radon concentrations—on occupants’ preferences regarding healthy home design attributes. The objectives of this research are twofold: firstly to determine if living in radon-mitigated homes enhances occupant awareness and consequently influences their preferences toward health-related home attributes and secondly to quantitatively evaluate and compare the relative significance homeowners assign to health-related attributes such as indoor air quality, thermal comfort, and water quality relative to conventional attributes including home size, architectural style, and neighborhood quality. The overarching purpose is to explore the potential role radon mitigation initiatives may play in motivating occupants towards healthier home construction and renovation practices. Using choice-based conjoint (CBC) analysis, this paper compares preferences reported by homeowners from radon-mitigated homes against those from non-mitigated homes. While the findings suggest a relationship between radon mitigation and increased preference for indoor air quality, the cross-sectional design limits causal interpretation, and the possibility of reverse causation—where health-conscious individuals are more likely to seek mitigation—must be considered. The results provide novel insights into how radon mitigation efforts might effectively influence occupant priorities towards integrating healthier design elements in residential environments. Full article

Urban commercial districts, with their unique characteristics, serve as a reflection of broader urban development patterns. However, only a handful of studies have harnessed point-of-interest (POI) data to model the intricate relationship between retail commercial space types and other factors. This paper endeavors to bridge this gap, focusing on the influence of urban development factors on retail commerce districts through the lens of POI data. Our exploration underscores how commercial zones impact the density of residential neighborhoods and the coherence of pedestrian pathways. To facilitate our investigation, we propose an ensemble clustering technique for identifying and outlining urban commercial areas, including Kernel Density Analysis (KDE), Density-based Spatial Clustering of Applications with Noise (DBSCAN), Geographically Weighted Regression (GWR). Our research uses the city of Manchester as a case study, unearthing the relationship between commercial retail catchment areas and a range of factors (retail commercial space types, land use function, walking coverage). These include land use function, walking coverage, and green park within the specified areas. As we explore the multiple impacts of different urban development factors on retail commerce models, we hope this study acts as a springboard for further exploration of the untapped potential of POI data in urban business development and planning. Full article

Crack detection in complex pavement scenarios remains challenging due to the sparse small-target features and computational inefficiency of existing methods. To address these limitations, this study proposes an enhanced architecture based on Mask2Former. The framework integrates two key innovations. A Local Perception Module (LPM) reconstructs geometric topological relationships through a Sequence-Space Dynamic Transformation Mechanism (DS2M), enhancing neighborhood feature extraction via depthwise separable convolutions. Simultaneously, an Auxiliary Convolutional Layer (ACL) combines lightweight residual convolutions with shallow high-resolution features, preserving critical edge details through channel attention weighting. Experimental evaluations demonstrate the model’s superior performance, achieving improvements of 3.2% in mIoU and 2.7% in mAcc compared to baseline methods, while maintaining computational efficiency with only 12.8 GFLOPs. These results validate the effectiveness of geometric relationship modeling and hierarchical feature fusion for pavement crack detection, suggesting practical potential for infrastructure maintenance systems. The proposed approach balances precision and efficiency, offering a viable solution for real-world applications with complex crack patterns and hardware constraints. Full article

Most health studies use cross-sectional data to examine neighborhood context because of the difficulty of collecting and analyzing longitudinal data; this prevents an examination of historical trends that may influence health outcomes. Using the Neighborhood Change Database, we categorized longitudinal (1990–2010) poverty and White concentration trajectories (long-term low, long-term moderate, long-term high, increasing, or decreasing) for Texas census tracts and linked them to tract-level health-related characteristics (social determinants of health [SDOH] in 2010, health risk and preventive behaviors [HRPB] in 2017, and health status/outcomes [HSO] in 2017) from multiple sources (N = 2961 tracts). We conducted univariate and bivariate descriptive analyses, followed by linear regressions adjusted for population density. SDOH, HRPB, and HSO measures varied widely across census tracts. Both poverty and White concentration trajectories were strongly and consistently associated with a wide range of SDOH. Long-term high-poverty and low-White tracts showed the greatest disadvantages, while long-term low-poverty and high-White tracts had the most advantages. Neighborhoods undergoing changes in poverty or White concentrations, either increasing or decreasing, had less advantageous SDOH compared with long-term low-poverty or long-term high-White neighborhoods. While associations between poverty, White concentration trajectories, and SDOH were consistent, those with HRPB and HSO were less so. Understanding impact of the relationships between longitudinal neighborhood poverty and racial/ethnic composition on health can benefit stakeholders designing policy proposals and intervention strategies. Full article