Network Data Research Articles

How Clinician-Scientists Access and Mobilise Social Capital and Thus Contribute to the Professional Development of Their Colleagues in Their Networks

ABSTRACT Clinician-scientists, physicians who conduct research, may fulfil a bridging role in networks of health care researchers and practitioners. Within clinician-scientists’ networks, knowledge sharing is thought to play a vital role in the continuing professional development of themselves and their colleagues. However, little is known about networks of clinician-scientists and how this impacts continuing professional development. Rooted in social capital theory, this study provides a mixed methods exploration of clinician-scientists’ networks. Ego-level social network data were collected via semi-structured interviews on professional interactions about evidence-based practice with 15 clinician-scientists in the area of general practice and elderly care. Quantitative analysis revealed that professional networks of clinician-scientists varied in size, composition, and frequency of interactions depending on appointed research time and experience. Less experienced clinician-scientists interacted most frequently with other clinician-scientists while experienced clinician-scientist experienced more sporadically with clinicians. Clinician-scientists with more research time interacted more frequently with scientists and had a slightly larger professional network than those with less research time. The thematic qualitative analysis revealed different decision-making processes of clinician-scientists on mobilising their social capital and connecting to others in the network: (1) deliberate decision about initiating connections; (2) reactive behaviour without a decision; (3) ad-hoc decision. Clinician-scientists exchange knowledge to enhance their own continuing professional development mainly but also contribute to the professional development of clinicians, scientists, and other clinician-scientists.

LEAF: A Lifestyle Approximation Framework Based on Analysis of Mobile Network Data in Smart Cities

The increasing use of mobile networks is an opportunity to collect and model users’ movement data for extracting knowledge about life and health while considering privacy leakage risk. This study aims to approximate the lifestyles of urban residents, employing statistical information derived from their movements among various Points of Interest (PoI). Our investigations comprehend a multidimensional analysis of key urban factors to provide insights into the population’s daily routines, preferences, and characteristics. To this end, we developed a framework called LEAF that models lifestyles by interpreting anonymized cell phone mobility data and integrating it with information from other sources, such as geographical layers of land use and sets of PoI. LEAF presents the information in a vector space model capable of responding to spatial queries about lifestyle. We also developed a consolidated lifestyle pattern framework to systematically identify and analyze the dominant activity patterns in different urban areas. To evaluate the effectiveness of the proposed framework, we tested it on movement data from individuals in a medium-sized city and compared the results with information collected through surveys. The RMSE of 5.167 between the proposed framework’s results and survey-based data indicates that the framework provides a reliable estimation of lifestyle patterns across diverse urban areas. Additionally, summarized patterns of criteria ordering were created, offering a concise and intuitive representation of lifestyles. The analysis revealed high consistency between the two methods in the derived patterns, underscoring the framework’s robustness and accuracy in modeling urban lifestyle dynamics.

Power flow distribution identification via machine learning algorithm and distributed resource clearing method

Abstract Under the background of dual carbon, a large number of distributed new energy sources are connected to the demand side, which leads to great risks in the operation of the power system. As an effective solution, distributed power transaction still has problems, such as high clearing time, unknown low-voltage distribution network structure, and resource scheduling ignoring user needs. Therefore, this paper proposes an optimal regulation method of demand-side resources based on distributed transactions. Based on the historical operation data of the distribution network, the eXtreme Gradient Boosting (XGBoost) algorithm is used to study the relationship between node injection power, node voltage, and node-side line power flow. It is also used to check the results of distributed transactions and design a market mechanism for rapid clearing and settlement of distributed transactions. The results of an example show that the identification of power flow distribution in a distribution network based on reinforcement learning can meet the security check requirements of distributed transaction results.

Factors associated with waitlist clinical deterioration among United States lung transplant recipients under the continuous distribution system

BackgroundLung continuous distribution (CD), implemented on March 9, 2023, changed the calculation and relative importance of medical urgency and posttransplant survival in prioritizing candidates for transplant. We aimed to identify factors associated with waitlist clinical deterioration and change in expected posttransplant survival from listing to transplant in the current system. MethodsWe used Organ Procurement and Transplantation Network (OPTN) data to conduct a retrospective study of 2,395 adult, lung-only transplant recipients added to the waiting list and transplanted between March 09, 2023, and March 08, 2024. We used multivariable linear regression to identify factors associated with change in waitlist area under the curve (WLAUC) and posttransplant area under the curve (PTAUC), representing expected survival (in days) without and with transplant, respectively. ResultsIn multivariable analysis, longer waiting time (β=-1.3 per 7 days; p<0.001), male birth sex (β=-11; p=0.006), diagnosis group D (β=-27; p<0.001), and blood type O (β=-13; p<0.001) were associated with greater clinical deterioration from listing to transplant. Older (β=3.2 per 10-year increase in age; p=0.023) and taller (β=3.0 per 5 cm increase in height; p=0.003) recipients were less likely to clinically deteriorate from listing to transplant. Diagnosis group D (β=-4.7, p=0.032) and blood type O (β=-4.2, p=0.025) recipients had lower expected posttransplant survival at transplant compared to listing. ConclusionOur findings suggest the need to further investigate and address factors associated with waitlist clinical deterioration under CD. Future analysis of the effect of waitlist clinical deterioration on posttransplant outcomes under CD is needed.

Rapid deep learning prediction model using satellite imagery for radiation accident Announcement system in Serbia

Radioactivity environmental monitoring with the help of the Radiation Accident Announcement System (RAAS) established in the Republic of Serbia is of vital importance for rapid response in the event of intervention dose values being reached such as Operational Intervention levels (OILs). There are cases of impossibility of using a ground-based model in order to predict the transport and spread of radiation during a nuclear accident such as the one in the Fukushima Daiichi nuclear power plant 2011. Modern technology has made it possible to use machine learning models with remote sensing data in addition (or an alternative) to atmospheric models with ground data collection methods. Deep learning (DL) model was developed and trained on a satellite-based cloud fraction dataset to forecast diurnal cloud drift. By forecasting the movement of clouds that are potential carriers of radioactive materials, decision-makers can provide an adequate response with an Action Plan in the case of nuclear and radiation accidents and incidents. Designed Application Programming Interface (API) has been developed and integrated between the DL model and the RAAS. In this way, the monitoring, data sharing and exchange processes were automated in order to trigger the DL model when an OILs value of 1 μSv/h is reached. The hyperparameter optimization process of the DL model was done with grid search and Particle Swarm Optimization (PSO) to achieve maximum performance on the data in a reasonable amount of time. The evolution metrics to monitor and measure the performance of the DL model were cosine similarity (CS) and structural similarity (SS) with the best score of 0.78282 and 0.27063 for grid search, respectively, while 0.27065 and 0.78282 for PSO, respectively. It can be concluded that remote sensing imagery with DL model is an alternative approach against a ground-based forecasting system, and is able to predict in near real-time independently of ground network system and data.

Lymph node metastasis prediction from in-situ lung squamous cell carcinoma histopathology images using deep learning.

Lung squamous cell carcinoma (LUSC), a subtype of non-small cell lung cancer, represents a significant portion of lung cancer cases with distinct histologic patterns impacting prognosis and treatment. The current pathological assessment methods face limitations such as inter-observer variability, necessitating more reliable techniques. This study seeks to predict lymph node metastasis in LUSC using deep learning models applied to histopathology images of primary tumors, offering a more accurate and objective method for diagnosis and prognosis.Whole slide images (WSIs) from the Outdo-LUSC and TCGA-LUSC cohorts were used to train and validate deep-learning models. Multi-instance learning was applied, with patch-level predictions aggregated into WSI-level outcomes. The study employed the ResNet-18 network, transfer learning, and rigorous data preprocessing. To represent WSI features, innovative techniques like patch likelihood histogram (PLH) and bag of words (BoW) were used, followed by training of machine learning classifiers, including the ExtraTrees algorithm.The diagnostic model for lymph node metastasis showed strong performance, particularly using the ExtraTrees algorithm, as demonstrated by receiver operating characteristic (ROC) curves and Grad-CAM visualizations. The signature generated by the ExtraTrees algorithm, named LN_ISLUSCH (lymph node status-related in-situ lung squamous cell carcinoma histopathology), achieved an area under the curve (AUC) of 0.941 (95% CI: 0.926-0.955) in the training set and 0.788 (95% CI: 0.748-0.827) in the test set. Kaplan–Meier analyses confirmed that the LN_ISLUSCH model was a significant prognostic factor (p = 0.02).This study underscores the potential of artificial intelligence in enhancing diagnostic precision in pathology. The LN_ISLUSCH model stands out as a promising tool for predicting lymph node metastasis and prognosis in LUSC. Future studies should focus on larger and more diverse cohorts and explore the integration of additional omics data to further refine predictive accuracy and clinical utility.

A protocol for trustworthy EEG decoding with neural networks

Deep learning solutions have rapidly emerged for EEG decoding, achieving state-of-the-art performance on a variety of decoding tasks. Despite their high performance, existing solutions do not fully address the challenge posed by the introduction of many hyperparameters, defining data pre-processing, network architecture, network training, and data augmentation. Automatic hyperparameter search is rarely performed and limited to network-related hyperparameters. Moreover, pipelines are highly sensitive to performance fluctuations due to random initialization, hindering their reliability. Here, we design a comprehensive protocol for EEG decoding that explores the hyperparameters characterizing the entire pipeline and that includes multi-seed initialization for providing robust performance estimates. Our protocol is validated on 9 datasets about motor imagery, P300, SSVEP, including 204 participants and 26 recording sessions, and on different deep learning models. We accompany our protocol with extensive experiments on the main aspects influencing it, such as the number of participants used for hyperparameter search, the split into sequential simpler searches (multi-step search), the use of informed vs. non-informed search algorithms, and the number of random seeds for obtaining stable performance. The best protocol included 2-step hyperparameter search via an informed search algorithm, with the final training and evaluation performed using 10 random initializations. The optimal trade-off between performance and computational time was achieved by using a subset of 3-5 participants for hyperparameter search. Our protocol consistently outperformed baseline state-of-the-art pipelines, widely across datasets and models, and could represent a standard approach for neuroscientists for decoding EEG in a trustworthy and reliable way.

Context-Aware Adaptive Encryption: Integrating Sensitive Data Detection and Network intrusion detection for Dynamic Data Security and Encryption

In today's digital landscape, ensuring the security of sensitive data and protecting against network intrusions are critical challenges. This research project develops and evaluates a novel context-aware adaptive encryption system that integrates sensitive data detection, network intrusion detection, and dynamic encryption techniques to enhance data security. The proposed system employs deep learning models to identify sensitive information and machine learning algorithms to monitor network activity for potential intrusions. Upon detecting sensitive data or a security threat, the system automatically applies encryption with adjustable strength based on the context, increasing protection in high-risk situations. This approach minimizes unnecessary overhead in low-risk scenarios while maintaining robust security measures. Through simulations using real-world data, the system's effectiveness in accurately detecting sensitive information and network intrusions, as well as its capability to adapt encryption dynamically, is evaluated. The results demonstrate the potential of combining machine learning with adaptive security measures to create a responsive and efficient data protection system.

Big geo-data unveils influencing factors on customer flow dynamics within urban commercial districts

Commercial districts, as the epicenters of urban commerce and economic activity, largely reflect an area’s prosperity through their customer flow. However, previous research, which often relied on statistical and survey data, has typically not captured the full scope of customer flow dynamics throughout urban commercial districts and has not adequately measured the specific impacts of business district locations and their surrounding communities on customer flow. To bridge these gaps, this study utilizes multidimensional big geo-data resources, including mobile phone signaling data, Points of Interest (POI) data, and transportation network data, to uncover the underlying factors that influence customer flow within urban commercial districts. The findings suggest that several factors—the size of the commercial district, the diversity of business formats, the convenience of parking, the working and residential population in surrounding communities, and the proximity to urban centers—significantly influence the customer flow. Consumers show a preference for larger-scale, centrally-located commercial districts that offer convenient parking options, while a homogenized and uncharacteristic business format may reduce a commercial district’s appeal. Furthermore, the study reveals that industrial parks and mixed-use complexes within the 15-minute living circle surrounding the commercial district have a stronger attraction to customer flow than residential neighborhoods do. The insights from this research not only guide the strategic placement of new commercial centers but also provide a robust framework for enhancing the layout of urban commercial spaces and for the revitalization and advancement of established commercial districts.

Network community detection via neural embeddings

Recent advances in machine learning research have produced powerful neural graph embedding methods, which learn useful, low-dimensional vector representations of network data. These neural methods for graph embedding excel in graph machine learning tasks and are now widely adopted. However, how and why these methods work—particularly how network structure gets encoded in the embedding—remain largely unexplained. Here, we show that node2vec—shallow, linear neural network—encodes communities into separable clusters better than random partitioning down to the information-theoretic detectability limit for the stochastic block models. We show that this is due to the equivalence between the embedding learned by node2vec and the spectral embedding via the eigenvectors of the symmetric normalized Laplacian matrix. Numerical simulations demonstrate that node2vec is capable of learning communities on sparse graphs generated by the stochastic blockmodel, as well as on sparse degree-heterogeneous networks. Our results highlight the features of graph neural networks that enable them to separate communities in the embedding space.

Research on BP neural network model-based data mining technique in KOL identification

Abstract. Accompanied by the development of artificial intelligence industry, to play the data value of web crawler technology has been the focus of research in the field of computer network and data science, and the data mining technology based on artificial neural network intelligent algorithm is widely used. In view of this, this paper takes the BP neural network data mining technology, which has excellent nonlinear mapping capability, parallel processing capability and fault tolerance and is widely used, as the basis, and integrates the methods and ideas of data mining into the mining of data laws in the field of KOL identification of key opinion leaders, with a view to finding valuable intrinsic laws and relationships between the mining of web crawler technology and the identification of KOL features. The research content of this paper mainly includes two aspects of research work, the design of high-performance data mining technology and the actual work in the field of KOL recognition. On the one hand, this paper comprehensively describes the basic theory and methods of data mining, and focuses on the in-depth analysis and elaboration of BP neural network-based data mining technology on the basis of understanding and analyzing a variety of data mining technologies. On the other hand, this paper aims to solve the problem of bias in the prediction of traditional KOL model and design the experimental method of KOL recognition by BP neural network algorithm.

Using Social Network Analysis to Identify Influential Community Organizations

BackgroundWe used a social network approach to identify influential community organizations within integrated public health networks in three regions in Texas, US: Houston/Harris County, Cameron County, and Northeast Texas. The study aimed to understand how network structures influence organizational performance in COVID-19 response. MethodsIn collaboration with community partners in each region, we administered a snowball sampling network data collection. Initial seed sets for the regions of 23, 25, and 55 organizations identified other organizations that then responded to the survey, which expanded the sets to 268, 145, and 138, respectively. Principal component analysis (PCA) identified key network structures—centrality and brokerage—and we introduced two network-based performance measures: Fulfillment Rate (FR), which measures securing needed resources, and Provision Rate (PR), which measures providing resources to others. We tested hypotheses to examine the associations between these network structures and organizational performance. FindingsCentrality consistently emerged as a predictor of organizational performance across all three regions. Community organizations that are more centrally positioned, rather than broker organizations, play a critical role in meeting resource needs and providing services to other organizations. Centrally positioned organizations conducted more COVID-19 tests, whereas brokers administered fewer vaccines. InterpretationsThis study suggests that public health interventions should prioritize central organizations for resource allocation and distribution. Our network-based performance metrics offer new avenues for evaluating organizational effectiveness in networked public health systems, with broader applicability to future crises and public health planning.

A cross-sectional geospatial analysis of access to cesarean delivery in Uganda by facility functionality

Introduction: There is minimal data on spatial access to surgical maternal care in Uganda. We aimed to determine geospatial access to facilities performing cesarean delivery in Uganda at differing facility functional levels. Methods: We defined three levels of facility functionality: level 1 – functional by designation, i.e., health system level; level 2 – performed at least one cesarean delivery in the past year; and level 3 – performed at least 20 cesarean deliveries in the past year. We mapped facilities in ArcGIS Pro using GPS coordinates, calculated Manhattan distances, and using transportation network data, identified the area indicating 30-minute, 1-hour, and 2-hour geographic walking and driving access to facilities. The population estimate raster was overlain with drive time analysis areas to calculate the total population catchment within each travel time. Results: Of 6937 total facilities, 339 (4.9%) met level 1 functionality, 287 (4.1%) met level 2 functionality, and 241 (3.5%) met level 3 functionality. The percentages of women within 30-minute, 1-hour, and 2-hour walking times from level 1 facilities were 9.7%, 19.8%, and 34.8%, respectively. These percentages decreased to 9.2%, 19%, and 33% for level 2 functionality and 8.1%, 17.4%, and 30.5% for level 3 functionality, respectively. Access varied regionally, with the poorest access in the Northern region (20% within 2 hours walking) compared to the Central region (55.2% within 2 hours walking). Conclusion: We demonstrate a substantial proportion of the Ugandan population does not have timely access to cesarean delivery, with substantial subnational variation. This inequity in access to surgical obstetric care is vital information that can assist policymakers in achieving universal maternal health access.

A Provably Secure and Lightweight Two-Factor Authentication Protocol for Wireless Sensor Network

Wireless Sensor Networks (WSNs) are rapidly being integrated into various fields, significantly impacting and facilitating many aspects of human life. However, the increasingly prominent security issues associated with WSNs have become a significant challenge. This paper provides an in-depth analysis of the security challenges faced by WSNs in resource constrained and open communication environments. As a key component of the Internet of Things (IoT), a WSN can perceive, collect and transmit physical environmental data in real-time, and is widely used in military, medical, agricultural and other fields. However, the insecurity of communication channels and unauthorized user access pose severe threats to network security and data integrity. To address these challenges, this paper proposes a provably secure two-factor authentication protocol. This protocol utilizes a Chebyshev chaotic map and a two-factor authentication mechanism, which not only enhances security in WSNs but also improves authentication efficiency. The protocol is validated through security proof and performance experiments, demonstrating excellent security, functionality and efficiency. This provides strong support for secure and efficient communication in WSNs across various application scenarios.

Optimizing IOT Network Performance: A Study on Low-Power Wide-Area Network (LPWAN) Technologies for Smart City Applications

Abstract: This research explores with a specific focus on smart city applications, how to optimise the execution of Web of Things (IoT) networks by utilising breakthroughs in Low-Powered Wide Area Networks (LPWAN). As IoT devices proliferate and generate vast amounts of data, having a competent network becomes essential, especially when dealing with low device thickness and limited power availability. This analysis provides a detailed energy consumption model tailored to LoRaWAN, based on a deeper understanding of its functional components in Internet of Things scenarios. The review uses MATLAB for replication and looks at two clear scenarios: the standard allocation of spreading factors without optimisation and an improved method that uses particle swarm optimisation (PSO) for dynamic spreading factor work. The results show that the network energy consumption dropped significantly, from 6.3997×10^ (- 17) Joules to 2.5230×10^(- 17) Joules, along with increased throughput, decreased parcel misfortune, and decreased idleness. Through a detailed analysis of several parameters, such as network density and data transfer efficiency, this study demonstrates the feasibility of the suggested optimisation model in terms of improving battery efficiency and overall network performance. Finally, the findings demonstrate how efficient LPWAN systems may provide robust and useful IoT environments, which are essential for the successful implementation of smart city initiatives.

축제 산업생태계 네트워크 구조 분석 : 명예 문화관광축제를 중심으로

The demand for the industrialization of festivals has become increasingly prominent both academically and in policy discussions. Approaching festivals from an industrial perspective is regarded as a key strategy for improving supply chain efficiency and expanding the festival business ecosystem. The demand for the industrialization of festivals is increasingly strong, both academically and in policy discussions. This study aims to analyze the structural characteristics (connectivity and cohesion) and positional characteristics (influence) of South Korea's festival industry through social network analysis, grounded in industry ecosystem theory. The research utilizes 595 expenditure data points from four major cultural tourism festivals in Korea. The data were preprocessed in Excel, using pivot tables to identify relationships between attributes. After data cleaning, the dataset was divided into node and edge files, which were analyzed using Gephi 0.10, an open-source Java-based software optimized for large-scale network analysis. This multidimensional approach was critical in visualizing and optimizing the network data. The findings reveal that Korea’s festival business ecosystem displays characteristics of early-stage industrialization, characterized by low network density and limited two-way interactions between actors. While cohesive clusters within the network show diversity, the influence of major networks remains low, highlighting the need for focused efforts to strengthen them. In terms of positional characteristics, festival organizations, venue construction industries, and content development companies were identified as influential actors. Academically, this study contributes to the empirical identification of the network structure within the festival business ecosystem, providing foundational data for understanding its dynamic changes. Practically, it offers policy recommendations, including fostering key actors to enhance cohesion and expanding opportunities for inter-company collaboration to further develop the ecosystem.

Recommendations for sharing network data and materials

Abstract One of the goals of open science is to promote the transparency and accessibility of research. Sharing data and materials used in network research is critical to these goals. In this paper, we present recommendations for whether, what, when, and where network data and materials should be shared. We recommend that network data and materials should be shared, but access to or use of shared data and materials may be restricted if necessary to avoid harm or comply with regulations. Researchers should share the network data and materials necessary to reproduce reported results via a publicly accessible repository when an associated manuscript is published. To ensure the adoption of these recommendations, network journals should require sharing, and network associations and academic institutions should reward sharing.

Network determinants of relationship influence on HIV prevention decision-making among people in the social networks of women who have experienced incarceration in the US.

Many cisgender women in the US who have experienced incarceration are at substantial risk for HIV acquisition after they return to the community. Various network interventions have been leveraged for HIV prevention in this population. The objective of this study was to identify network and relationship determinants of influence on HIV prevention decisions, including PrEP. We conducted interviews with a network mapping exercise with participants recruited from the social and sexual networks of women who had experienced incarceration. Participants enumerated important individuals in their lives from the past six months and provided demographic and relationship data as well as whether each relationship influenced their HIV prevention decisions. We abstracted network data from the interview transcripts and described the data set using descriptive statistics and network density graphs. To measure associations between characteristics at each level and whether a relationship was considered influential regarding PrEP decision-making, we use multiple logistic regression with random intercepts for each respondent. We interviewed 32 participants, average age 33.5 years (SD = 8.98), majority female (n = 28, 87.5%), white (n = 23, 71.8%), heterosexual/straight (n = 25, 78.1%), and with a personal history of incarceration (n = 29, 90%). They reported 253 relationships (119 family, 116 friend, 18 sexual relationships). Most adult network members had used drugs or alcohol (n = 182, 80.9%), and of those, 30.8% had used them with the participant (n = 53). The mean network size was 7 (SD = 4) and network density was 52.2%. In the full model, significant positive predictors of an influential relationship included participant non-heterosexual identity (OR 27.8), older average age in the network (OR 3.9 per standard deviation), and being a current or prior sexual partner (OR 10.1). Significant negative predictors included relationships with individuals who use or had used drugs (OR 0.28), longer average relationship duration in the network (OR 0.09) and being in a network with at least one sexual partner (OR 0.2). There are significant positive and negative determinants of relationship influence related to PrEP at individual-, dyad-, relationship-, and network-levels. These support using nuanced network approaches to behavior change that respect and leverage the diversity of relationships that comprise the social networks of women who have experienced incarceration.

Multi-layer graph attention neural networks for accurate drug-target interaction mapping

In the crucial process of drug discovery and repurposing, precise prediction of drug-target interactions (DTIs) is paramount. This study introduces a novel DTI prediction approach—Multi-Layer Graph Attention Neural Network (MLGANN), through a groundbreaking computational framework that effectively harnesses multi-source information to enhance prediction accuracy. MLGANN not only strides forward in constructing a multi-layer DTI network by capturing both direct interactions between drugs and targets as well as their multi-level information but also amalgamates Graph Convolutional Networks (GCN) with a self-attention mechanism to comprehensively integrate diverse data sources. This method exhibited significant performance surpassing existing approaches in comparative experiments, underscoring its immense potential in elevating the efficiency and accuracy of DTI predictions. More importantly, this study accentuates the significance of considering multi-source data information and network heterogeneity in the drug discovery process, offering new perspectives and tools for future pharmaceutical research.

Urban Land Use Classification Model Fusing Multimodal Deep Features

Urban land use classification plays a significant role in urban studies and provides key guidance for urban development. However, existing methods predominantly rely on either raster structure deep features through convolutional neural networks (CNNs) or topological structure deep features through graph neural networks (GNNs), making it challenging to comprehensively capture the rich semantic information in remote sensing images. To address this limitation, we propose a novel urban land use classification model by integrating both raster and topological structure deep features to enhance the accuracy and robustness of the classification model. First, we divide the urban area into block units based on road network data and further subdivide these units using the fractal network evolution algorithm (FNEA). Next, the K-nearest neighbors (KNN) graph construction method with adaptive fusion coefficients is employed to generate both global and local graphs of the blocks and sub-units. The spectral features and subgraph features are then constructed, and a graph convolutional network (GCN) is utilized to extract the node relational features from both the global and local graphs, forming the topological structure deep features while aggregating local features into global ones. Subsequently, VGG-16 (Visual Geometry Group 16) is used to extract the image convolutional features of the block units, obtaining the raster structure deep features. Finally, the transformer is used to fuse both topological and raster structure deep features, and land use classification is completed using the softmax function. Experiments were conducted using high-resolution Google images and Open Street Map (OSM) data, with study areas on the third ring road of Shenyang and the fourth ring road of Chengdu. The results demonstrate that the proposed method improves the overall accuracy and Kappa coefficient by 9.32% and 0.17, respectively, compared to single deep learning models. Incorporating subgraph structure features further enhances the overall accuracy and Kappa by 1.13% and 0.1. The adaptive KNN graph construction method achieves accuracy comparable to that of the empirical threshold method. This study enables accurate large-scale urban land use classification with reduced manual intervention, improving urban planning efficiency. The experimental results verify the effectiveness of the proposed method, particularly in terms of classification accuracy and feature representation completeness.