Network Hierarchy Research Articles

Breaking Spatial Constraints: A Dimensional Perspective-Based Analysis of the Eco-Efficiency of Cultivated Land Use and Its Spatial Association Network

Global urbanization has caused enormous challenges that seriously threaten ecological security and the food system. Thus, there is a need for finding an optimal solution for the eco-efficiency of cultivated land use (ECLU) that can promote the development of new-type urbanization, while ensuring the sustainable utilization of limited cultivated-land resources. The quantitative system of multi-scale ECLU used in existing studies is inadequate; it is necessary to establish a measurement system from the perspective of geographical spatial relationship that uses evaluation as a key basis for management. In this study, we considered the Changchun Metropolitan Area and a representative urban–rural transition area as the target regions and customized new ECLU evaluation systems for different scales. The super slack-based measure and gravity and social network analyses methods were applied to evaluate the ECLU and explore the structural characteristics of its spatial association network. The average ECLU value for the Changchun Metropolitan Area was 0.974; the results indicated that most of the study area was eco-efficient. The value of ECLU for the urban–rural transition area varied from 0.022 to 1.323; thus, the highly efficient cultivated land was mainly distributed around the urban built-up area. The spatial association network of ECLU revealed that the overall spatial correlations were relatively weak, with a significant “bipolar” division of ECLU; furthermore, the network hierarchy and stability needed improvement. Moreover, we noted distant attraction capacity and siphoning effects outside regional boundaries. In the Changchun Metropolitan Area, it manifested as a monocentric radiation, with Changchun City as the center. In the urban–rural transition area, the cultivated land in proximity to the newly built urban area was more likely to experience spatial spillover. These findings have important implications for strengthening land-use management and advancing sustainable agricultural development for new-type urbanization. Our study can be used by policymakers and stakeholders to design sustainable urban cities, while improving land-use management and optimizing resource use.

NPI-WGNN: A Weighted Graph Neural Network Leveraging Centrality Measures and High-Order Common Neighbor Similarity for Accurate ncRNA–Protein Interaction Prediction

Predicting ncRNA–protein interactions (NPIs) is essential for understanding regulatory roles in cellular processes and disease mechanisms, yet experimental methods are costly and time-consuming. In this study, we propose NPI-WGNN, a novel weighted graph neural network model designed to enhance NPI prediction by incorporating topological insights from graph structures. Our approach introduces a bipartite version of the high-order common neighbor (HOCN) similarity metric to assign edge weights in an ncRNA–protein network, refining node embeddings via weighted node2vec. We further enrich these embeddings with centrality measures, such as degree and Katz centralities, to capture network hierarchy and connectivity. To optimize prediction accuracy, we employ a hybrid GNN architecture that combines graph convolutional network (GCN), graph attention network (GAT), and GraphSAGE layers, each contributing unique advantages: GraphSAGE offers scalability, GCN provides a global structural perspective, and GAT applies dynamic neighbor weighting. An ablation study confirms the complementary strengths of these layers, showing that their integration improves predictive accuracy and robustness across varied graph complexities. Experimental results on three benchmark datasets demonstrate that NPI-WGNN outperforms state-of-the-art methods, achieving up to 96.1% accuracy, 97.5% sensitivity, and an F1-score of 0.96, positioning it as a robust and accurate framework for ncRNA–protein interaction prediction.

Addressing the urban congestion challenge based on traffic bottlenecks.

Historically, urban congestion and street life quality depended on city network hierarchies, shaped by land use and street layout. Yet navigation apps have shifted focus to travel time as the key route selection factor, challenging traditional urban structures. We review the development of an innovative approach to urban traffic management that leverages real-time data for the identification and analysis of traffic bottlenecks. This approach, combined with urban planning, aims to improve traffic flow and tackle modern urban challenges. It includes real-time bottleneck detection and cost, congestion analysis and designing a decentralized traffic management system that can serve planners. Based on complex system principles, it promises dynamic traffic optimization, merging urban planning with digital advancements. The research demonstrates the potential of different applications of the proposed methodologies to predict significant congestion from early bottleneck formation, offering urban planners a powerful toolset for reasserting their role in shaping the urban experience. This article posits that a nuanced understanding of traffic dynamics, coupled with advanced traffic management technologies, can restore the influence of urban planning in the digital era, fostering more liveable, equitable and efficient urban environments. This article is part of the theme issue 'Co-creating the future: participatory cities and digital governance'.

Convolutional neural networks uncover the dynamics of human visual memory representations over time.

The ability to accurately retrieve visual details of past events is a fundamental cognitive function relevant for daily life. While a visual stimulus contains an abundance of information, only some of it is later encoded into long-term memory representations. However, an ongoing challenge has been to isolate memory representations that integrate various visual features and uncover their dynamics over time. To address this question, we leveraged a novel combination of empirical and computational frameworks based on the hierarchal structure of convolutional neural networks and their correspondence to human visual processing. This enabled to reveal the contribution of different levels of visual representations to memory strength and their dynamics over time. Visual memory strength was measured with distractors selected based on their shared similarity to the target memory along low or high layers of the convolutional neural network hierarchy. The results show that visual working memory relies similarly on low and high-level visual representations. However, already after a few minutes and on to the next day, visual memory relies more strongly on high-level visual representations. These findings suggest that visual representations transform from a distributed to a stronger high-level conceptual representation, providing novel insights into the dynamics of visual memory over time.

Rényi entanglement entropy of a spin chain with generative neural networks.

We describe a method to estimate Rényi entanglement entropy of a spin system which is based on the replica trick and generative neural networks with explicit probability estimation. It can be extended to any spin system or lattice field theory. We demonstrate our method on a one-dimensional quantum Ising spin chain. As the generative model, we use a hierarchy of autoregressive networks, allowing us to simulate up to 32 spins. We calculate the second Rényi entropy and its derivative and cross-check our results with the numerical evaluation of entropy and results available in the literature.

Sex Differences in Hierarchical and Modular Organization of Functional Brain Networks: Insights from Hierarchical Entropy and Modularity Analysis.

Existing studies have demonstrated significant sex differences in the neural mechanisms of daily life and neuropsychiatric disorders. The hierarchical organization of the functional brain network is a critical feature for assessing these neural mechanisms. But the sex differences in hierarchical organization have not been fully investigated. Here, we explore whether the hierarchical structure of the brain network differs between females and males using resting-state fMRI data. We measure the hierarchical entropy and the maximum modularity of each individual, and identify a significant negative correlation between the complexity of hierarchy and modularity in brain networks. At the mean level, females show higher modularity, whereas males exhibit a more complex hierarchy. At the consensus level, we use a co-classification matrix to perform a detailed investigation of the differences in the hierarchical organization between sexes and observe that the female group and the male group exhibit different interaction patterns of brain regions in the dorsal attention network (DAN) and visual network (VIN). Our findings suggest that the brains of females and males employ different network topologies to carry out brain functions. In addition, the negative correlation between hierarchy and modularity implies a need to balance the complexity in the hierarchical organization of the brain network, which sheds light on future studies of brain functions.

From here to eternity: The rise and fall of global art worlds and the contemporary private museum

The process of converting a private collection into a public museum is often presented as a means of ensuring a collection’s future by transforming it into an enduring asset for future generations. This case study assesses contemporary collection models as well as entrepreneurial investor-collectors and their respective museum-building strategies by addressing two fundamental questions: (1) What is the role of the contemporary art collector and private museum and (2) How do their interactions with art markets challenge the established protocols and hierarchies of the global art network? It shall be argued that private collection museums often have a limited lifespan. Furthermore, the future of private collections and museums is often determined within the lifetimes of their creators. This can play out in one of four ways: first, collectors may offer artworks at high-profile auction houses; second, they may sell the art collection and close the museum or collector’s exhibition space; third, they may sell the museum or exhibition space. Alternatively, private collectors, along with their museums and art collections, can play an important role on the global stage. However, more rigorous planning is necessary for these collectors to distinguish themselves, expand the cultural landscape, and ensure their collections endure within or beyond their creators’ lifetime.

A method for optimizing different geometric shields of D-T neutron generators by combining BP neural network and Analytic Hierarchy Process

In this paper, an optimization of shielding structures with different geometries is established for the D-T neutron generator system by combining Back Propagation (BP) neural network and Analytic Hierarchy Process (AHP). The D-T neutron generator (Model NG-9) used in the system was developed independently by Northeast Normal University. After investigating the rule of shielding performance among spherical, cylindrical and cubic geometries, the spherical shield is selected for BP neural network prediction to determine the total dose rate through it. Information about spherical multilayer-shielding structures and properties calculated by MCNP code is used to train the neural network. The predicted result serves as a parameter of the evaluation function, which provides a comprehensive assessment of the dose rate penetrated the shield, the shielding mass, and the shielding volume. Together with AHP, the weight factors are determined for all the optimization objectives to construct the evaluation function. By comparing its values, the optimal shielding structures for spherical, cylindrical and cubic materials are found. Against MCNP simulated values, the total dose rates’ errors of the optimal shielding structures for the sphere, cylinder, and cube are 1.72 %, -4.94 %, and -5.17 %, respectively. This result demonstrates that the combination of BP neural network and AHP is more effective in addressing multi-objective optimization problems related to the design of radiation shielding for various geometries.

New forest fire assessment model based on artificial neural network and analytic hierarchy process or fuzzy-analytic hierarchy process methodology for fire vulnerability map

Forest fires significantly disrupt global ecosystems. Many forecasting techniques predict fire activity and allocate prevention resources, but various factors are missing from the assessments, and multi-criteria decision approaches alone are insufficient. This work introduced a novel methodology combining artificial neural networks (ANN) with the analytical hierarchy process (AHP), fuzzy AHP multi-criteria methods, and spatial data to detect potential forest fire vulnerability areas using twenty variables. The results from AHP or fuzzy AHP, were processed using a multilayer perceptron with a backpropagation algorithm. The final ANN model has two objectives: first, to create a forest fire vulnerability with four classes (low, moderate, high, and very high), and second, to classify burned area sizes in regions highly or very highly vulnerable to fire. Evaluation metrics were also applied for validation. The fire model was tested using both literature review data and in situ observations. Comparative analysis showed that the burned area size model performed better than other machine learning methods, achieving an accuracy score of 89%. Meanwhile, the fire vulnerability model scored 82%. The study addresses the problem of prediction and provides an algorithm for classifying fire risk based on historical data in the Czech Republic, offering a master model for future forest management. Therefore, the ANN model, once trained, validated, and tested, does not require resetting and is effective for estimating forest fire vulnerability. Moreover, it produces results quickly, providing rapid insights into complex forest ecosystems, saving time and enhancing understanding for decision-makers.

The methods and tools of ensuring information security of networks

Currently, there is an increase in the number of information threats that lead to unstable operation of data networks. This is due to the mass use, the complication of the hierarchy of area networks, the increase in the heterogeneity of software tools, and the complication of the functionality of network services. In such cases, the development and improvement of methods for determining information security in data transmission networks has a great importance. The article discusses ways to increase the information security of the data network by increasing the reliability of detecting deviations in the operation of the main nodes of the data network and reducing the number of false starts when automating the detection of threats. Experimental verification and evaluation of the effectiveness of the methods were considered, it was shown that the developed methods allow skipping the anomaly of the first type and minimizing errors of the second type. The methods were implemented software in the form of a prototype access detection system (ADS).

EnNet: Enhanced Interactive Information Network with Zero-Order Optimization.

Interactive image segmentation extremely accelerates the generation of high-quality annotation image datasets, which are the pillars of the applications of deep learning. However, these methods suffer from the insignificance of interaction information and excessively high optimization costs, resulting in unexpected segmentation outcomes and increased computational burden. To address these issues, this paper focuses on interactive information mining from the network architecture and optimization procedure. In terms of network architecture, the issue mentioned above arises from two perspectives: the less representative feature of interactive regions in each layer and the interactive information weakened by the network hierarchy structure. Therefore, the paper proposes a network called EnNet. The network addresses the two aforementioned issues by employing attention mechanisms to integrate user interaction information across the entire image and incorporating interaction information twice in a design that progresses from coarse to fine. In terms of optimization, this paper proposes a method of using zero-order optimization during the first four iterations of training. This approach can reduce computational overhead with only a minimal reduction in accuracy. The experimental results on GrabCut, Berkeley, DAVIS, and SBD datasets validate the effectiveness of the proposed method, with our approach achieving an average NOC@90 that surpasses RITM by 0.35.

Recognition of Real-Time Video Activities Using Stacked Bi-GRU with Fusion-based Deep Architecture

Recognizing and understanding human activities in real-time videos is a challenging task due to the complex nature of video data and the need for efficient and accurate analysis. This research pioneers a breakthrough in video activity recognition by introducing a robust framework leveraging the power of a stacked Bidirectional Long Short-Term Memory (Bi-LSTM) and Gated Recurrent Unit (GRU) architecture, harmonized within a fusion-based deep model. The stacked Bi-LSTM-GRU model capitalizes on its dual recurrent architecture, capturing nuanced temporal dependencies within video sequences. The fusion-based deep architecture synergizes spatial and temporal features, enabling the model to discern intricate patterns in human activities. To further enhance the discriminative power of the model, we introduce a fusion module in the proposed deep architecture. The fusion module integrates multi-modal features extracted from different levels of the network hierarchy, allowing for a more comprehensive representation of video activities. We demonstrate the efficacy of our approach through rigorous experimentation on UCF50, UCF101, and HMDB51 datasets. In experiments on the UCF50 dataset, our model achieves an accuracy of 97.01% and 95.86% on training and validation sets respectively, showcasing its proficiency in discerning activities across a diverse range of scenarios. The evaluation extends to the UCF101 dataset, where the proposed approach achieves a competitive accuracy of 97.62% and 96.93% on training and validation sets, surpassing previous benchmarks by a margin of approx 1%. Further-more, on the challenging HMDB51 dataset, the model demonstrates a robust accuracy of 89.71%and 88.88% on training and validation sets, solidifying its efficacy in intricate action recognition tasks.

Disruption of network hierarchy pattern in bulimia nervosa reveals brain information integration disorder

The human brain works as a hierarchical organization that is a continuous axis spanning sensorimotor cortex to transmodal cortex (referring to cortex that integrates multimodal sensory information and participates in complex cognitive functions). Previous studies have demonstrated abnormalities in several specific networks that may account for their multiple behavioral deficits in patients with bulimia nervosa (BN), but whether and how the network hierarchical organization changes in BN remain unknown. This study aimed to investigate alterations of the hierarchy organization in BN network and their clinical relevance. Connectome gradient analyses were applied to depict the network hierarchy patterns of fifty-nine patients with BN and thirty-nine healthy controls (HCs). Then, we evaluated the network- and voxel-level gradient alterations of BN by comparing gradient values in each network and each voxel between patients with BN and HCs. Finally, the association between altered gradient values and clinical variables was explored. In the principal gradient, patients with BN exhibited reduced gradient values in dorsal attention network and increased gradient values in subcortical regions compared to HCs. In the secondary gradient, patients with BN showed decreased gradient values in ventral attention network and increased gradient values in limbic network. Regionally, the areas with altered principal or secondary gradient values in BN group were mainly located in transmodal networks, i.e., the default-mode and frontoparietal network. In BN group, the principal gradient values of right inferior frontal gyrus were negatively associated with external eating behavior. This study revealed the disordered network hierarchy patterns in patients with BN, which suggested a disturbance of brain information integration from attention network and subcortical regions to transmodal networks in these patients. These findings may provide insight into the neurobiological underpinnings of BN.

Community detection using Jaya optimization algorithm based on deep learning methods and KNN graph-based clustering

Purpose In this paper, community identification has been considered as the most critical task of social network analysis. The purpose of this paper is to organize the nodes of a given network graph into distinct clusters or known communities. These clusters will therefore form the different communities available within the social network graph. Design/methodology/approach To date, numerous methods have been developed to detect communities in social networks through graph clustering techniques. The k-means algorithm stands out as one of the most well-known graph clustering algorithms, celebrated for its straightforward implementation and rapid processing. However, it has a serious drawback because it is insensitive to initial conditions and always settles on local optima rather than finding the global optimum. More recently, clustering algorithms that use a reciprocal KNN (k-nearest neighbors) graph have been used for data clustering. It skillfully overcomes many major shortcomings of k-means algorithms, especially about the selection of the initial centers of clusters. However, it does face its own challenge: sensitivity to the choice of the neighborhood size parameter k, which is crucial for selecting the nearest neighbors during the clustering process. In this design, the Jaya optimization method is used to select the K parameter in the KNN method. Findings The experiment on real-world network data results show that the proposed approach significantly improves the accuracy of methods in community detection in social networks. On the other hand, it seems to offer some potential for discovering a more refined hierarchy in social networks and thus becomes a useful tool in the analysis of social networks. Originality/value This paper introduces an enhancement to the KNN graph-based clustering method by proposing a local average vector method for selecting the optimal neighborhood size parameter k. Furthermore, it presents an improved Jaya algorithm with KNN graph-based clustering for more effective community detection in social network graphs.

Fitness-based growth of directed networks with hierarchy

Abstract Growing attention has been brought to the fact that many real directed networks exhibit hierarchy and directionality as measured through techniques like Trophic Analysis and non-normality. We propose a simple growing network model where the probability of connecting to a node is defined by a preferential attachment mechanism based on degree and the difference in fitness between nodes. 
In particular, we show how mechanisms such as degree-based preferential attachment and node fitness interactions can lead to the emergence of the spectrum of hierarchy and directionality observed in real networks. In this work, we study various features of this model relating to network hierarchy, as measured by Trophic Analysis. This includes (I) how preferential attachment can lead to network hierarchy, (II) how scale-free degree distributions and network hierarchy can coexist, (III) the correlation between node fitness and trophic level, (IV) how the fitness parameters can predict trophic incoherence and how the trophic level difference distribution compares to the fitness difference distribution, (V) the relationship between trophic level and degree imbalance and the unique role of nodes at the ends of the fitness hierarchy and (VI) how fitness interactions and degree-based preferential attachment can interplay to generate networks of varying coherence and degree distribution. We also provide an example of the intuition this work enables in the analysis of a real historical network. This work provides insight into simple mechanisms which can give rise to hierarchy in directed networks and quantifies the usefulness and limitations of using Trophic Analysis as an analysis tool for real networks.

Multiplicities and fluidity in the networked relationships of migrant academics in Britain

AbstractIncreasing internationalization and marketization of higher education, global research collaboration, and staff mobility place academics' networking practices at the centre of higher education systems. Migrant academics are conceptualized with different network types including personal, local and transnational family and friendship networks. However, this research aims to understand the boundaries between different types of participants' networked relationships. The data of this paper comes from a larger research project on transnational family relationships of migrant academics conducted between 2018 and 2022. Life story interviews with 45 migrant academics from 27 different national backgrounds working at British universities were conducted. Additionally, sociogram maps are used as embedded in qualitative interviews. Migration background (as European or non‐European countries); gender; age; the length of the stay in the UK; academic position/contract type; annual income level and marital/relationship status were considered while forming the sample. The findings reveal that network forms and structures do not determine the resources and benefits of relationships; rather, individuals' actions over a time period and the meanings they attribute shape the positions of an alter (other actors that the focal person have connection with) within the personal network structure. As such, actions and meanings regarding those actions can bring one forward or backward in the personal network hierarchy. The boundaries regarding the content of these networks are usually blurred in relation to time, relationality and human agency attributing specific sets of meanings to certain relationships. The findings of this research translate into specific contributions to the discussions in migration and social network research. That is, research findings emphasized that different types of networks shaping participants' lives and migratory experiences are far from being stable and fixed, rather, they are characterized by being transmissive and dynamic. It is revealed that none of the network categories are homogenous, stable and fixed in terms of the content of the relationships. This adds to Emirbayer and Goodwin's (1994) discussions around the ‘form’ and the ‘content’ of networks. This paper underscores the significance of the historical settings, dynamism and the content of each relationship in understanding individual networks.

Land Cover Classification of Remote Sensing Imagery with Hybrid Two-Layer Attention Network Architecture

In remote sensing image processing, when categorizing images from multiple remote sensing data sources, the deepening of the network hierarchy is prone to the problems of feature dispersion, as well as the loss of semantic information. In order to solve this problem, this paper proposes to integrate a parallel network architecture HDAM-Net algorithm with a hybrid dual attention mechanism Hybrid dual attention mechanism for forest land cover change. Firstly, we propose a fusion MCA + SAM (MS) attention mechanism to improve VIT network, which can capture the correlation information between features; secondly, we propose a multilayer residual cascade convolution (MSCRC) network model using Double Cross-Attention Module (DCAM) attention mechanism, which is able to efficiently utilize the spatial dependency between multiscale encoder features: the spatial dependency between multiscale encoder features. Finally, the dual-channel parallel architecture is utilized to solve the structural differences and realize the enhancement of forestry image classification differentiation and effective monitoring of forest cover changes. In order to compare the performance of HDAM-Net, mountain urban forest types are classified based on multiple remote sensing data sources, and the performance of the model is evaluated. The experimental results show that the overall accuracy of the algorithm proposed in this paper is 99.42%, while the Transformer (ViT) is 96.92%, which indicates that the proposed classifier is able to accurately determine the cover type.The HDAM-Net model emphasizes the effectiveness in terms of accurately classifying the land, as well as the forest types by using multiple remote sensing data sources for predicting the future trend of the forest ecosystem. In addition, the land utilization rate and land cover change can clearly show the forest cover change and support the data to predict the future trend of the forest ecosystem so that the forest resource survey can effectively monitor deforestation and evaluate forest restoration projects.

Methodological proposal for measuring economic efficiency in regional transportation networks

This article seeks to improve the understanding and efficiency of transportation within and between metropolitan areas. Efficient transportation infrastructure and services are essential for achieving sustainable development, fostering economic growth, and minimizing environmental impacts. In metropolitan regions, where urbanization and population growth are concentrated, the significance of transportation efficiency becomes even more critical. To address this issue, the study proposes a methodology that combines graph theory and centrality measures to analyze regional hierarchies and their influence on transportation efficiency. By representing the regional road network, cities, and toll plazas as a graph with attributes linked to quantitative data of urban economies, this approach provides a concise and replicable method for examining network hierarchy in urban economies.

WBi-YOLOSF: improved feature pyramid network for aquatic real-time target detection under the artificial rabbits optimization

As the pillar industry of coastal areas, aquaculture needs artificial intelligence technology to promote economic development. To realize the automation of the aquaculture industry, this paper proposes a new underwater object detection network: WBi-YOLOSF. It realizes the automatic classification and detection of aquatic products, improves the production efficiency of the aquaculture industry, and promotes its economic development. This paper creates an image dataset containing 15 aquatic products to lay the data foundation for model training. In the data preprocessing part, an underwater image enhancement algorithm is proposed to improve the quality of the data set effectively. Aiming at the problem of high false detection rate and missed detection rate of underwater dense small targets, a new data enhancement method was proposed to improve the training set’s data quality comprehensively. Inspired by the weighted bidirectional feature pyramid network, this paper proposes a new feature extraction network: AU-BiFPN, which solves the gradient problem caused by the network hierarchy’s deepening on enhancing the network’s multi-scale feature fusion. The AU-BiFPN network structure is embedded into the YOLO series network framework, significantly improving the basic network’s feature extraction and feature fusion ability and dramatically improving the prediction accuracy without affecting the network inference speed. Here, the swarm intelligence algorithm is introduced to optimize the model hyperparameters, accelerating the convergence speed of model training and significantly reducing the computational cost. At the same time, the model’s accuracy is improved by a cliff. In addition, the Funnel Activation is introduced in the network’s backbone, and the simple, parameter-free attention module is integrated, effectively improving the accuracy and speed of the model prediction. Ablation and comparison experiments show the effectiveness and superiority of the proposed model. Verified by the mean average precision and frame rate evaluation indicators, the experimental results of the WBi-YOLOSF target detection network can reach 0.982 and 203 frames per second, which are 1.4% and five frames per second higher than the network with the second score. In summary, this method can quickly and accurately identify aquatic products, realize real-time target detection of aquatic products, and lay the foundation for developing an aquaculture automation system.

A Study on the Mechanism of Network Hierarchy on Collaborative Innovation of Enterprises

A Study on the Mechanism of Network Hierarchy on Collaborative Innovation of Enterprises