In this paper, we make a significant step toward designing a scalable community detection algorithm using hypergraph modularity function. The main obstacle with adjusting the initial stage of the classical Louvain alg...
详细信息
ISBN:
(数字)9783031322969
ISBN:
(纸本)9783031322952;9783031322969
In this paper, we make a significant step toward designing a scalable community detection algorithm using hypergraph modularity function. The main obstacle with adjusting the initial stage of the classical Louvain algorithm is dealt via carefully adjusted linear combination of the graph modularity function of the corresponding two-section graph and the desired hypergraph modularity function. It remains to properly tune the algorithm and design a mechanism to adjust the weights in the modularity function (in an unsupervised way), depending on how often nodes in one community share hyperedges with nodes from other communities. It will be done in the journal version of this paper.
In recent years, a significant number of distributed small-capacity energy storage (ES) systems have been integrated into power grids to support grid frequency regulation. However, the challenges associated with high-...
详细信息
In recent years, a significant number of distributed small-capacity energy storage (ES) systems have been integrated into power grids to support grid frequency regulation. However, the challenges associated with high-dimensional control and synergistic operation alongside conventional generators remain unsolved. In this paper, a partitioning-based control approach is developed for the participation of widespread distributed ES systems on frequency control in power systems. The approach comprises a network partitioning method and a two-layer frequency control scheme. The partitioning method utilizes a community detection algorithm in which the weights between the buses are calculated based on the electrical distances. After partitioning the buses into different groups, an optimization-based frequency control system with two layers is established to aggregate and dis-aggregate the inertia and droop coefficients so that frequency regulation and economical operation can be achieved. The effectiveness of the proposed method is demonstrated through numerical simulations on an IEEE 39-bus system. The results confirm the successful elimination of frequency deviations and low operating cost of the proposed approach.
To understand psychological data, it is crucial to examine the structure and dimensions of variables. In this study, we examined alternative estimation algorithms to the conventional GLASSO-based exploratory graph ana...
详细信息
To understand psychological data, it is crucial to examine the structure and dimensions of variables. In this study, we examined alternative estimation algorithms to the conventional GLASSO-based exploratory graph analysis (EGA) in network psychometric models to assess the dimensionality structure of the data. The study applied Bayesian conjugate or Jeffreys' priors to estimate the graphical structure and then used the Louvain community detection algorithm to partition and identify groups of nodes, which allowed the detection of the multi- and unidimensional factor structures. Monte Carlo simulations suggested that the two alternative Bayesian estimation algorithms had comparable or better performance when compared with the GLASSO-based EGA and conventional parallel analysis (PA). When estimating the multidimensional factor structure, the analytically based method (i.e., ***) showed the best balance between accuracy and mean biased/absolute errors, with the highest accuracy tied with EGA but with the smallest errors. The sampling-based approach (***) yielded higher accuracy and smaller errors than PA;lower accuracy but also lower errors than EGA. Techniques from the two algorithms had more stable performance than EGA and PA across different data conditions. When estimating the unidimensional structure, the PA technique performed the best, followed closely by EGA, and then *** and ***. Furthermore, the study explored four full Bayesian techniques to assess dimensionality in network psychometrics. The results demonstrated superior performance when using Bayesian hypothesis testing or deriving posterior samples of graph structures under small sample sizes. The study recommends using the *** technique as an alternative tool for assessing dimensionality and advocates for the usefulness of the *** method as a valuable alternate technique. The findings also indicated encouraging results for extending the regulariz
Massive disaster-related data and model methods are available in different stages of natural disaster emergency management;however, they often lack the representation of the significance of crucial information. In add...
详细信息
Massive disaster-related data and model methods are available in different stages of natural disaster emergency management;however, they often lack the representation of the significance of crucial information. In addition, traditional methods are difficult to automate and fine-match, resulting in greater difficulty in intelligent applications. To address this problem, interconnected knowledge arranged in a knowledge graph and a community discovery algorithm were used to match disaster data with the appropriate method under a unified description framework. Based on the knowledge graph constructed by ontology mapping, this study aimed to represent and store the complex entities and relationships among disaster-related information. The node importance analysis and community discovery algorithm were used to analyze the community structure of important nodes, and a typical rainstorm flood disaster risk assessment emergency service scenario was taken as an example for experimental verification. The results showed that the constructed knowledge graph of natural disaster emergency services can support the formal expression of semantic correlation between disaster scenarios, model methods, and disaster data. The community discovery method performed well in overlapping community module degrees. The method proposed in this study can be used to formalize the representation and storage of massive heterogeneous data and conduct fine matching after quantitative analysis of the importance of model methods and data required for risk assessment of emergency service scenarios. Furthermore, the proposed method can provide theoretical support for improving the scientificity, accuracy, and interpretability of risk assessment decision management and promoting knowledge-driven intelligent emergency information service capabilities.
community detection algorithms are essential tools that allow us to discover organizational principles in net-works. Today, in most cases, social networks are modeled as a multi-relational network. So far, despite the...
详细信息
community detection algorithms are essential tools that allow us to discover organizational principles in net-works. Today, in most cases, social networks are modeled as a multi-relational network. So far, despite the introduction of community detection algorithms specific to multi-relational networks, very few of these algo-rithms have been able to find overlapping communities in a multi-relational directional network. In this paper, we present OCMRN (Overlapping Communities in Multi-Relational Networks), an overlapping communitydetection method in multi-relational directional networks. A semi-supervised method is used in the training phase of this algorithm which allows determining the importance of each layer to shape communities. The proposed method is evaluated on nine real and eight synthetic datasets and is compared with different algo-rithms. Well-known evaluation criteria are used to compare overlapping and non-overlapping communities resulting from various algorithms. The high accuracy of the results obtained from the proposed model suggests this algorithm can be used with high confidence for communitydetection of multi-relational directional net-works to find overlapping communities.
As many deep neural network models become deeper and more complex, processing devices with stronger computing performance and communication capability are required. Following this trend, the dependence on multichip ma...
详细信息
As many deep neural network models become deeper and more complex, processing devices with stronger computing performance and communication capability are required. Following this trend, the dependence on multichip many-core systems that have high parallelism and reasonable transmission costs is on the rise. In this work, in order to improve routing performance of the system, such as routing runtime and power consumption, we propose a reinforcement learning (RL)based core placement optimization approach, considering application constraints, such as deadlock caused by multicast paths. We leverage the capability of deep RL from indirect supervision as a direct nonlinear optimizer, and the parameters of the policy network are updated by proximal policy optimization. We treat the routing topology as a network graph, so we utilize a graph convolutional network to embed the features into the policy network. One step size environment is designed, so all cores are placed simultaneously. To handle large dimensional action space, we use continuous values matching with the number of cores as the output of the policy network and discretize them again for obtaining the new placement. For multichip system mapping, we developed a community detection algorithm. We use several datasets of multilayer perceptron and convolutional neural networks to evaluate our agent. We compare the optimal results obtained by our agent with other baselines under different multicast conditions. Our approach achieves a significant reduction of routing runtime, communication cost, and average traffic load, along with deadlock-free performance for inner chip data transmission. The traffic of interchip routing is also significantly reduced after integrating the community detection algorithm to our agent.
The deluge of attacks on IT infrastructure has necessitated the understanding of cybersecurity vulnerabilities for mitigation. A two-step novel model is developed to harness the time-stamped data to analyze the vulner...
详细信息
ISBN:
(纸本)9798350319415
The deluge of attacks on IT infrastructure has necessitated the understanding of cybersecurity vulnerabilities for mitigation. A two-step novel model is developed to harness the time-stamped data to analyze the vulnerability trends. In the first step of the model, a text network is created from the vulnerability report. A software is constructed that analyzes vulnerabilities by leveraging natural language processing and network theory. The network theoretic study provides details of the complex relationships between vulnerabilities. The visualizations from the tool provide information for security researchers for an in-depth study of vulnerabilities.
A central theme of network analysis, these days, is the detection of community structure as it offers a coarse-grained view of the network at hand. A more interesting and challenging task in network analysis involves ...
详细信息
A central theme of network analysis, these days, is the detection of community structure as it offers a coarse-grained view of the network at hand. A more interesting and challenging task in network analysis involves the detection of overlapping community structure due to its wide-spread applications in synthesising and interpreting the data arising from social, biological and other diverse fields. Certain real-world networks possess a large number of nodes whose memberships are spread through multiple groups. This phenomenon called community structure with pervasive overlaps has been addressed partially by the development of a few well-known algorithms. In this paper, we presented an algorithm called Interaction Coefficient-based Local communitydetection (IC-LCD) that not only uncovers the community structures with pervasive overlaps but do so efficiently. The algorithm extracted communities through a local expansion strategy which underlie the notion of interaction coefficient. We evaluated the performance of IC-LCD on different parameters such as speed, accuracy and stability on a number of synthetic and real-world networks, and compared the results with well-known baseline algorithms, namely DEMON, OSLOM, SLPA and COPRA. The results give a clear indication that IC-LCD gives competitive performance with the chosen baseline algorithms in uncovering the community structures with pervasive overlaps. The time complexity of IC-LCD is O(nc(max)), where n is the number of nodes, and c(max) is the maximum size of a community detected in a network.
While the majority of methods for communitydetection produce disjoint communities of nodes, most real-world networks naturally involve overlapping communities. In this paper, a scalable method for the detection of ov...
详细信息
While the majority of methods for communitydetection produce disjoint communities of nodes, most real-world networks naturally involve overlapping communities. In this paper, a scalable method for the detection of overlapping communities in large networks is proposed. The method is based on an extension of the notion of normalized cut to cope with overlapping communities. A spectral clustering algorithm is formulated to solve the related cut minimization problem. When available, the algorithm may take into account prior information about the likelihood for each node to belong to several communities. This information can either be extracted from the available metadata or from node centrality measures. We also introduce a hierarchical version of the algorithm to automatically detect the number of communities. In addition, a new benchmark model extending the stochastic blockmodel for graphs with overlapping communities is formulated. Our experiments show that the proposed spectral method outperforms the state-of-the-art algorithms in terms of computational complexity and accuracy on our benchmark graph model and on five real-world networks, including a lexical network and large-scale social networks. The scalability of the proposed algorithm is also demonstrated on large synthetic graphs with millions of nodes and edges.
community over the social media is the group of globally distributed end users having similar attitude towards a particular topic or product. community detection algorithm is used to identify the social atoms that are...
详细信息
community over the social media is the group of globally distributed end users having similar attitude towards a particular topic or product. community detection algorithm is used to identify the social atoms that are more densely interconnected relatively to the rest over the social media platform. Recently researchers focused on group-based algorithm and member-based algorithm for communitydetection over social media. This paper presents comprehensive overview of communitydetection technique based on recent research and subsequently explores graphical prospective of social media mining and social theory (Balance theory, status theory, correlation theory) over communitydetection. Along with that this paper presents a comparative analysis of three different state of art community detection algorithm available on I-Graph package on python i.e. walk trap, edge betweenness and fast greedy over six different social media data set. That yield intersecting facts about the capabilities and deficiency of community analysis methods.
暂无评论