Neighborhood Relations Research Articles

Handling Exponentially Growing Strategies in Spatial Cooperative Games: The Case of the European Union

This paper introduces a comprehensive cooperative game theory framework to measure the significance of location and neighborhood relations in conjunction with the magnitude of players/parties. The significances of these relations are measured over the EU geography. In this case, there are (i) the test of availability of a core solution that satisfies all associated parties/players; (ii) the measurement of players’/parties’ rational minimal and maximal return expectations from the grand coalition regarding their all individual and sub-group strategies and associated return rationalities; (iii) the determination of the critical players/parties in the grand coalition. The study’s main contributions are the provision of a methodology that identifies spatially/geographically critical players/parties and the design of an algorithm for handling exponentially growing strategies alongside increasing numbers of players/parties. In sum, a comprehensive cooperative game theory framework is introduced to measure the significance of location and neighborhood relations in conjunction with the magnitude of the players/parties. The case of the EU has revealed the union’s geographically critical countries, with Germany being found to be the most influential.

MGNR: A Multi-Granularity Neighbor Relationship and Its Application in KNN Classification and Clustering Methods.

In the real world, data distributions often exhibit multiple granularities. However, the majority of existing neighbor-based machine-learning methods rely on manually setting a single-granularity for neighbor relationships. These methods typically handle each data point using a single-granularity approach, which severely affects their accuracy and efficiency. This paper adopts a dual-pronged approach: it constructs a multi-granularity representation of the data using the granular-ball computing model, thereby boosting the algorithm's time efficiency. It leverages the multi-granularity representation of the data to create tailored, multi-granularity neighborhood relationships for different task scenarios, resulting in improved algorithmic accuracy. The experimental results convincingly demonstrate that the proposed multi-granularity neighbor relationship effectively enhances KNN classification and clustering methods.

U-Match: Exploring Hierarchy-Aware Local Context for Two-View Correspondence Learning.

Rejecting outlier correspondences is one of the critical steps for successful feature-based two-view geometry estimation, and contingent heavily upon local context exploration. Recent advances focus on devising elaborate local context extractors whereas typically adopting explicit neighborhood relationship modeling at a specific scale, which is intrinsically flawed and inflexible, because 1) severe outliers often populated in putative correspondences and 2) the uncertainty in the distribution of inliers and outliers make the network incapable of capturing adequate and reliable local context from such neighborhoods, therefore resulting in the failure of pose estimation. This prospective study proposes a novel network called U-Match that has the flexibility to enable implicit local context awareness at multiple levels, naturally circumventing the aforementioned issues that plague most existing studies. Specifically, to aggregate multi-level local context implicitly, a hierarchy-aware graph representation module is designed to flexibly encode and decode hierarchical features. Moreover, considering that global context always works collaboratively with local context, an orthogonal local-and-global information fusion module is presented to integrate complementary local and global context in a redundancy-free manner, thus yielding compact feature representations to facilitate correspondence learning. Thorough experimentation across relative pose estimation, homography estimation, visual localization, and point cloud registration affirms U-Match's remarkable capabilities.

Generalized relative neighborhood graph (GRNG) for similarity search

Generalized relative neighborhood graph (GRNG) for similarity search

Novel resampling algorithms with maximal cliques for class-imbalance problems

The imbalance issue significantly deteriorates the performance of classifiers. While researchers proposed resampling methods to address this problem, it often struggles with class overlap and small disjuncts, and focuses only on one-way relationships among instances. Most of these techniques emphasize neighbor relationships between pairs of instances while ignoring the global relationships within the dataset. To address this, we represented instances as nodes in a graph, with edges based on neighbor relationships. We constructed a neighbor graph of the dataset and identify its maximal clique. Using this concept, we proposed two resampling techniques: the Maximal Clique-based Oversampling (MCSO) and Undersampling (MCSU) methods. MCSO employs the maximal clique method to tackle the small disjunct problem, while MCSU addresses overlapping issues from a global perspective. We tested these methods using three base classifiers-CART, RF, and GBDT-on 35 public datasets. Our results showed that MCSO and MCSU outperform state-of-the-art methods in terms of AUC and G-mean. Additionally, the Friedman test and Nemenyi post-hoc test showed that our MCSO and MCSU are significantly better than other algorithms, demonstrating their superior performance.

Deciphering spatial domains from spatially resolved transcriptomics through spatially regularized deep graph networks

BackgroundRecent advancements in spatially resolved transcriptomics (SRT) have opened up unprecedented opportunities to explore gene expression patterns within spatial contexts. Deciphering spatial domains is a critical task in spatial transcriptomic data analysis, aiding in the elucidation of tissue structural heterogeneity and biological functions. However, existing spatial domain detection methods ignore the consistency of expression patterns and spatial arrangements between spots, as well as the severe gene dropout phenomenon present in SRT data, resulting in suboptimal performance in identifying tissue spatial heterogeneity.ResultsIn this paper, we introduce a novel framework, spatially regularized deep graph networks (SR-DGN), which integrates gene expression profiles with spatial information to learn spatially-consistent and informative spot representations. Specifically, SR-DGN employs graph attention networks (GAT) to adaptively aggregate gene expression information from neighboring spots, considering local expression patterns between spots. In addition, the spatial regularization constraint ensures the consistency of neighborhood relationships between physical and embedded spaces in an end-to-end manner. SR-DGN also employs cross-entropy (CE) loss to model gene expression states, effectively mitigating the impact of noisy gene dropouts.ConclusionsExperimental results demonstrate that SR-DGN outperforms state-of-the-art methods in spatial domain identification across SRT data from different sequencing platforms. Moreover, SR-DGN is capable of recovering known microanatomical structures, yielding clearer low-dimensional visualizations and more accurate spatial trajectory inferences.

Two relocation strategies: Preserving erstwhile neighbourhood relationships in Shenzhen

Relocation, both within China and other countries, typically results in a decline in neighbourhood relationships, especially for people who do not move willingly. For migrants, preserving neighbourhood relationships is particularly important as they often rely on these connections as their fitting-in strategy within cities. However, little empirical research has unravelled how migrants navigate relocation under massive urban redevelopment contexts and preserve pre-existing neighbourhood relationships. This paper examines to what extent and in what ways relocation willingness influences pre-existing neighbourhood relationships by applying multiple mediation effect models to a questionnaire survey dataset collected in 2022–2023. The results reveal that migrants who are more willing to relocate tend to stay in touch with former neighbours post-relocation. Additionally, relocation strategies (i.e., moving with former neighbours and short-distance moving) are important pathways through which relocation willingness can have positive effects on preserving pre-existing neighbourhood relationships. Interview data further indicates that employing relocation strategies not only aids in preserving pre-existing neighbourhood relationships but also in establishing new ones in destination neighbourhoods. The results suggest that extended eviction notice periods and phased redevelopment approaches could provide migrants with the opportunity to implement relocation strategies mitigating adverse impacts of relocation and better adapt to new neighbourhoods.

The Impact of Built Environment in Shanghai Neighborhoods on the Physical and Mental Health of Elderly Residents: Validation of a Chain Mediation Model Using Deep Learning and Big Data Methods

As urban aging issues intensify, the impact of the built environment in urban neighborhoods on the physical and mental health of elderly residents has garnered increasing attention. Previous studies have demonstrated that the built environment is related to various health outcomes; however, most empirical research typically focuses on the objective physical environment, lacking measurements of subjective environmental perceptions. This study, using 24 neighborhoods in Shanghai as case studies, employed deep learning, big data methods, and surveys to collect 462 valid questionnaires from elderly residents. Structural equation modeling was applied to explore the relationship between the built environment and the physical and mental health of elderly residents, incorporating respondents’ subjective perceptions, physical activity, and neighborhood relationships as chain mediation effects. The results indicate that although there is no direct relationship between the built environment and the mental health of elderly residents, the built environment positively impacts mental health through enhancing subjective.

The Different Aspects of the Housing Quality of Older Adults: Which Criteria Should Be Prioritized?

ABSTRACT Various studies have identified that older adults’ assessment of their housing quality differs from that deemed as good-quality housing by housing professionals. This has prompted the need to advance academic discourse beyond simply reporting high levels of satisfaction in older adult’s housing surveys. This study attempts to achieve this by using empirical data gathered through a mixed quantitative and qualitative research approach conducted with older adults in Slovenia. While the quantitative survey revealed generally high levels of satisfaction, the qualitative face-to-face interviews revealed numerous deficiencies, irrespective of whether older adults tended to express satisfaction with their dwellings. Therefore, our findings suggest that attributes such as ownership, period of residence, and neighborhood relations are far more important in determining housing satisfaction. Thus, we conclude that policies and programs for modifying housing for older adults must be based on a deeper understanding of their specific needs. During the policy formulation process and the implementation of specific housing improvement programs, emphasis should be placed on the social-historical aspects related to the lifestyle of each specific older adult.

A Sustainable urban renovation assessment model (SURAM) for enhancing elderly-friendly environments

The rapid increase in the aging population has raised significant concerns about the living conditions and well-being of elderly residents in old communities. This study addresses these concerns by proposing a Sustainable Urban Renovation Assessment Model (SURAM) specifically designed to enhance elderly-friendly environments in Chongqing City. The model encompasses multiple dimensions, including the comfort of public facilities, service safety and convenience, medical travel services, infrastructure security, life service convenience, neighbor relations, ambulance aid accessibility, commercial service facilities, privacy protection, elderly care facilities and service supply, and medical and health facilities. By employing factor analysis, the study reduces the dimensionality of the 49 indicator factors, allowing for a more focused and comprehensive evaluation of the effectiveness of aging-friendly renovation efforts. The main factors identified in the proposed model include community infrastructure security, elderly comfort of community public facilities, completeness and convenience of surrounding living services, and security and convenience of elderly care services. The results reveal that the age-appropriate comfort of public facilities plays a significant role in achieving successful aging-appropriate renovation outcomes. The findings demonstrate that by addressing specific needs such as safety, accessibility, and convenience, communities can significantly improve the quality of life for elderly residents. Moreover, the application of SURAM provides actionable insights for policymakers, urban planners, and community stakeholders, guiding them in implementing targeted initiatives for sustainable and inclusive urban development.

Integrated Knowledge Graph and Drug Molecular Graph Fusion via Adversarial Networks for Drug-Drug Interaction Prediction.

The Co-administration of multiple drugs can enhance the efficacy of disease treatment by reducing drug resistance and side effects. However, it also raises the risk of adverse drug interactions, presenting a challenging problem in healthcare. Various approaches have been developed to predict drug-drug interactions (DDIs) by leveraging both knowledge graphs and drug attribute information. While these methods have shown promise, they often fail to effectively capture correlations between biomedical information in the knowledge graph and drug properties. This work introduces a novel end-to-end DDI predictor framework based on generative adversarial networks. This framework utilizes a message-passing neural network to capture molecular structure information while employing the knowledge-aware graph attention network to capture the representation of drugs in the knowledge graph through considering the importance of different multihop neighbor nodes and relationships. The dual generative adversarial networks employ two generators and two discriminators in knowledge graph embedding and molecular topology embedding for adversarial training to capture the interrelations and complementary knowledge between molecular structure information and semantic information from the knowledge graph. comprehensive experiments have demonstrated that the proposed method outperforms state-of-the-art algorithms in binary classification, with improvements of 1.0% in accuracy, 0.45% in area under the receiver operating characteristic curve (AUC), 0.24% in area under the precision-recall curve (AUPR), and 0.98% in F1 score. Furthermore, for multiclass classification tasks, improvements were observed across various evaluation metrics, including 0.9% in accuracy, 0.25% in macro precision, 0.2% in macro recall, and 0.28% in macro F1. Additionally, ablation studies were conducted to showcase the effectiveness and robustness of our method in DDI prediction tasks.

Research on Gating Fusion Algorithm for Power Grid Survey Data Based on Enhanced Mamba Spatial Neighborhood Relationship.

In power grid surveying, it is often necessary to fuse panchromatic and multispectral imagery for the design of power lines. Despite the abundance of deep learning networks for fusing these images, the results often suffer from spectral information loss or structural blurring. This study introduces a fusion model specifically tailored for power grid surveying that significantly enhances the representation of spatial-spectral features in remote sensing images. The model comprises three main modules: a TransforRS-Mamba module that integrates the sequence processing capabilities of the Mamba model with the attention mechanism of the Transformer to effectively merge spatial and spectral features; an improved spatial proximity-aware attention mechanism (SPPAM) that utilizes a spatial constraint matrix to greatly enhance the recognition of complex object relationships; and an optimized spatial proximity-constrained gated fusion module (SPCGF) that integrates spatial proximity constraints with residual connections to boost the recognition accuracy of key object features. To validate the effectiveness of the proposed method, extensive comparative and ablation experiments were conducted on GF-2 satellite images and the QuickBird (QB) dataset. Both qualitative and quantitative analyses indicate that our method outperforms 11 existing methods in terms of fusion effectiveness, particularly in reducing spectral distortion and spatial detail loss. However, the model's generalization performance across different data sources and environmental conditions has yet to be evaluated. Future research will explore the integration of various satellite datasets and assess the model's performance in diverse environmental contexts.

Domesticating Property: Moral Economies of Post‐Socialist Homeownership Through Rental and Neighbour Relations

This article analyses property relations in post‐socialism through the analytical lens of housing studies and moral economy, specifically in the context of rental and neighbour relations in urban apartment buildings. It draws on 50 in‐depth residential biographies of residents of St. Petersburg, Russia, collected between 2017 and 2021. The interviews represent a diversity of tenures, as well as direct and indirect voices of homeowners and non‐owners. The article begins by introducing the socio‐historical context of the privatisation and commodification of housing in post‐socialist Russia. Then, based on the stories of the origin of property and the intensity of attachment to it, I analyse owners’ homemaking through daily interactions with other owners and non‐owners who act as their tenants and neighbours. Focusing on privatised, mortgaged, and inherited residential property, I identify three trajectories of complex relationships between owners and non‐owners in urban buildings and modes of homemaking, at the intersection of monetary and non‐monetary relations and imaginaries of counterparts. I argue that despite everyday interactions in the housing market and in apartment blocks, both the owners of privatised Soviet property and new owner‐occupiers tend to avoid the total commercialisation of the home and to challenge the dominance of homeownership as the only socially sanctioned tenure.

Cross-modal independent matching network for image-text retrieval

Image-text retrieval serves as a bridge connecting vision and language. Mainstream modal cross matching methods can effectively perform cross-modal interactions with high theoretical performance. However, there is a deficiency in efficiency. Modal independent matching methods exhibit superior efficiency but lack in performance. Therefore, achieving a balance between matching efficiency and performance becomes a challenge in the field of image-text retrieval. In this paper, we propose a new Cross-modal Independent Matching Network (CIMN) for image-text retrieval. Specifically, we first use the proposed Feature Relationship Reasoning (FRR) to infer neighborhood and potential relations of modal features. Then, we introduce Graph Pooling (GP) based on graph convolutional networks to perform modal global semantic aggregation. Finally, we introduce the Gravitation Loss (GL) by incorporating sample mass into the learning process. This loss can correct the matching relationship between and within each modality, avoiding the problem of equal treatment of all samples in the traditional triplet loss. Extensive experiments on Flickr30K and MSCOCO datasets demonstrate the superiority of the proposed method. It achieves a good balance between matching efficiency and performance, surpasses other similar independent matching methods in performance, and can obtain retrieval accuracy comparable to some mainstream cross matching methods with an order of magnitude lower inference time.

Social determinants of health, blood pressure classification, and incident stroke in community-dwelling adults: a prospective cohort study

Abstract Objective To determine whether the association of blood pressure (BP) categories, defined by the 2017 American College of Cardiology (ACC)/American Heart Association (AHA) BP guideline, with stroke differ among Chinese adults with low or high burden of unfavorable social determinants of health (SDOH). Design and Methods: Analyses were conducted in the prospective sub-cohort of the China Patient-Centered Evaluative Assessment of Cardiac Events Million Persons Project, started in 1, July 2017 and followed stroke events until 31, June 2023. Participants were divided into groups with low and high burden of unfavorable SDOH, which consisted of educational attainment, economic stability, health care access, social support, and neighborhood relationship. Within each group, participants were categorized as having normal BP (systolic BP [SBP] <120 mm Hg and diastolic BP [DBP] <80 mm Hg), elevated BP (SBP 120-129 mm Hg and DBP <80 mm Hg), stage 1 hypertension (SBP 130-139 mm Hg or DBP 80-89 mm Hg), and stage 2 hypertension (SBP ≥140 mm Hg or DBP ≥90mm Hg). The association between BP categories and stroke risk were examined within each SDOH group, separately, using multivariable-adjusted Cox proportional hazards models. Results Of the 96,686 adults included in this study (mean [SD] age, 53.8 [10.1] years; 59,080 [61.1%] women), 64,823 (67.0%) were categorized as having high burden of unfavorable SDOH. Over a median follow-up of 5.0 years, 4,673 (4.8%) incident stroke events occurred. In the group of low burden of SDOH, hazard ratios (95% CI) for stroke events for elevated BP, stage 1 hypertension, and stage 2 hypertension vs normal BP were 1.09 (0.86-1.37), 1.14 (0.94-1.37), and 1.59 (1.33-1.90), respectively. In the group of high burden of SDOH, hazard ratios for stroke events for elevated BP, stage 1 hypertension, and stage 2 hypertension vs normal BP were 1.20 (1.04-1.38), 1.45 (1.29-1.62), and 1.71 (1.53-1.91), respectively. Results were similar after excluding those taking antihypertensive medications. Conclusion Lower BP categories were closely associated with increased risk of stroke in the context of high burden of SDOH. Early counseling and surveillance of high BP should be emphasized within socioeconomically disadvantaged populations.

Facial Expression Recognition-You Only Look Once-Neighborhood Coordinate Attention Mamba: Facial Expression Detection and Classification Based on Neighbor and Coordinates Attention Mechanism.

In studying the joint object detection and classification problem for facial expression recognition (FER) deploying the YOLOX framework, we introduce a novel feature extractor, called neighborhood coordinate attention Mamba (NCAMamba) to substitute for the original feature extractor in the Feature Pyramid Network (FPN). NCAMamba combines the background information reduction capabilities of Mamba, the local neighborhood relationship understanding of neighborhood attention, and the directional relationship understanding of coordinate attention. The resulting FER-YOLO-NCAMamba model, when applied to two unaligned FER benchmark datasets, RAF-DB and SFEW, obtains significantly improved mean average precision (mAP) scores when compared with those obtained by other state-of-the-art methods. Moreover, in ablation studies, it is found that the NCA module is relatively more important than the Visual State Space (VSS), a version of using Mamba for image processing, and in visualization studies using the grad-CAM method, it reveals that regions around the nose tip are critical to recognizing the expression; if it is too large, it may lead to erroneous prediction, while a small focused region would lead to correct recognition; this may explain why FER of unaligned faces is such a challenging problem.

A FIELD STUDY ON SOCIAL CAPITAL, CULTURE OF LIVING TOGETHER AND NEIGHBORHOOD RELATIONS

Turkey, which is the intersection of Europe, Asia and Africa, has been the main route of migration throughout human history. Forced migrants coming to Turkey have low-skilled labor and mostly consist of farmers engaged in agriculture in rural areas. Turkey settles migrants migrating from nearby geography in districts where agricultural production is carried out in rural areas and can employ these migrants in agricultural production. When the host community trusts the migrants, they can treat them warmly, neighborly relations begin and a culture of living together that is beneficial for both parties is formed. This study aimed to investigate on-site the contribution of social capital to the neighborhood relations and the culture of living together process established by Meskhetian Turks settled in Üzümlü District of Erzincan Province since 2016 with the residents of Üzümlü District. In line with this objective, a survey was conducted with 269 Meskhetian Turks migrating from the Russian Federation. In the analyses conducted with Structural Equation Modeling, it was determined that Meskhetian Turks developed very good neighborhood relations with the people of Üzümlü District of Erzincan Province and created a culture of living together. While the Bonding Social Capital contributed positively to this process, the Bridging Social Capital had a negative effect. The study approaches the issue of migration within the scope of “microeconomic migration theories”. The economic needs and desires of individuals are taken as basis.

Catalysts of connection. The role of digital information and communication technology in fostering neighbourhood social cohesion: A systematic review of empirical findings

Neighbourhood social cohesion is associated with a range of beneficial outcomes for residents. However, it is commonly hypothesised that neighbourhood relations face potential disruptions from digital information and communication technologies (DICT) as they are assumed to alter traditional community structures previously grounded in physical proximity. We systematically review 52 empirical studies on the relationship between DICT and neighbourhood social cohesion to determine in what ways DICT hinder or promote neighbourhood social cohesion. We found that DICT promote social cohesion by catalysing local social capital, but not for everyone and not in every neighbourhood. We propose the theoretical concept of ‘catalysts of connection’ to explain how technological affordances and online content interact with collective and individual social capital to develop various domains of social cohesion. Based on these results and our theoretical concept, we conclude that DICT exacerbate socio-spatial inequality in cities as neighbourhoods with low social capital are less likely to reap the benefits of the digital age. We provide paths for future investigations on the intersection of urban research and media and communication studies.

A simulation data-driven semi-supervised framework based on MK-KNN graph and ESSGAT for bearing fault diagnosis

Current supervised intelligent fault diagnosis relies on abundant labeled data. However, collecting and labeling data are typically both expensive and time-consuming. Fault diagnosis with unlabeled data remains a significant challenge. To address this issue, a simulation data-driven semi-supervised framework based on multi-kernel K-nearest neighbor (MK-KNN) and edge self-supervised graph attention network (ESSGAT) is proposed. The novel MK-KNN establishes the neighborhood relationships between simulation data and real data. The developed multi-kernel function mitigates the risks of overfitting and underfitting, thereby enhancing the robustness of the simulation-real graphs. The designed ESSGAT employs two forms of self-supervised attention to predict the presence of edges, increasing the weights of crucial neighboring nodes in the MK-KNN graph. The performance of the proposed method is evaluated using a public bearing dataset and a self-constructed dataset of high-speed train axle box bearings. The results show that the proposed method achieves better diagnostic performance compared with other state-of-the-art graph construction methods and graph convolutional networks.

Resilient cooperative platoon control for leader-following uncertain vehicular systems subject to cyber-physical attacks

This paper develops a resilient cooperative platoon control protocol for vehicle following systems under unreliable switching communication networks with cyber composite attacks, which includes actuator and sensors attacks, as well as denial of service (DoS) attacks. In this framework, to achieve leader-following platoon task, a novel resilient distributed adaptive control algorithm is designed by exploiting relative neighborhood information. First, a switching resilient turning mechanism with controller parameter updating laws is introduced into platoon controller architecture, which can compensate sensor and actuator attacks. Second, a topology-dependent analysis shows that cooperative leader-following platoon objective is achieved under some sufficient conditions, then the robust stability of the closed-loop coordination tracking error system is built. Finally, the simulation studies on a platoon of autonomous vehicles are provided to testify the design.