An Improved Complex Network Community Detection Algorithm Based on K-Means

The air quality is directly related to people’s lives. This paper selects air quality data of Sichuan Province as the research object, and explores the inherent characteristics of air quality from the perspective of complex network theory. First, based on the complexity of network topology and nodes, a community detection algorithm which combines the clustering idea with principal component analysis (PCA) algorithm and self-organization competitive neural network (SOM) is designed (CSP). Compared with the classic community detection algorithm, the result proves that the CSP algorithm can accurately dig out a better community structure. Second, based on the strong correlation distance and strong correlation coefficient of the air quality network, the Sichuan Air Quality Complex Network (SCCN) was constructed. The SCCN is divided into five communities using the CSP algorithm. Combining the characteristics of each community and the Hurst coefficient, it is found that the air quality inside the community has long-term memory. Finally, based on the idea of time-dependent cross-correlation, this paper analyzes the cross-correlation of AQI time series of different stations in each community, constructs a directed air quality cross-correlation network combined with complex network theory, and locates the important pollution sources in each region of Sichuan Province according to the topological structure of the network. The work of this paper can provide the corresponding theoretical support and guidance for the current environmental pollution control.

Download Full-text

Community detection in complex network by network embedding and density clustering

Journal of Intelligent & Fuzzy Systems ◽

10.3233/jifs-202961 ◽

2021 ◽

pp. 1-12

Author(s):

JinFang Sheng ◽

Huaiyu Zuo ◽

Bin Wang ◽

Qiong Li

Keyword(s):

Complex Network ◽

Community Detection ◽

Dimensional Space ◽

Detection Algorithm ◽

Superior Performance ◽

Network Embedding ◽

Detection Algorithms ◽

Density Clustering ◽

Community Detection Algorithm ◽

Low Dimensional

In a complex network system, the structure of the network is an extremely important element for the analysis of the system, and the study of community detection algorithms is key to exploring the structure of the complex network. Traditional community detection algorithms would represent the network using an adjacency matrix based on observations, which may contain redundant information or noise that interferes with the detection results. In this paper, we propose a community detection algorithm based on density clustering. In order to improve the performance of density clustering, we consider an algorithmic framework for learning the continuous representation of network nodes in a low-dimensional space. The network structure is effectively preserved through network embedding, and density clustering is applied in the embedded low-dimensional space to compute the similarity of nodes in the network, which in turn reveals the implied structure in a given network. Experiments show that the algorithm has superior performance compared to other advanced community detection algorithms for real-world networks in multiple domains as well as synthetic networks, especially when the network data chaos is high.

Download Full-text

A Parallel Network Community Detection Algorithm Based on Distance Dynamics

Proceedings of the 2017 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining 2017 - ASONAM '17 ◽

10.1145/3110025.3110135 ◽

2017 ◽

Author(s):

Bin Wu ◽

Cuiyun Zhang ◽

Qian Guo

Keyword(s):

Community Detection ◽

Detection Algorithm ◽

Network Community ◽

Parallel Network ◽

Community Detection Algorithm

Download Full-text

Clustering Algorithm for Community Detection in Complex Network: A Comprehensive Review

Recent Advances in Computer Science and Communications ◽

10.2174/2213275912666190710183635 ◽

2020 ◽

Vol 13 (4) ◽

pp. 542-549

Author(s):

Smita Agrawal ◽

Atul Patel

Keyword(s):

Complex Network ◽

Community Detection ◽

Large Scale ◽

Clustering Algorithm ◽

Detection Algorithm ◽

Connected Subgraph ◽

Comprehensive Review ◽

Detection Algorithms ◽

Community Detection Algorithm ◽

Large Scale Networks

Many real-world social networks exist in the form of a complex network, which includes very large scale networks with structured or unstructured data and a set of graphs. This complex network is available in the form of brain graph, protein structure, food web, transportation system, World Wide Web, and these networks are sparsely connected, and most of the subgraphs are densely connected. Due to the scaling of large scale graphs, efficient way for graph generation, complexity, the dynamic nature of graphs, and community detection are challenging tasks. From large scale graph to find the densely connected subgraph from the complex network, various community detection algorithms using clustering techniques are discussed here. In this paper, we discussed the taxonomy of various community detection algorithms like Structural Clustering Algorithm for Networks (SCAN), Structural-Attribute based Cluster (SA-cluster), Community Detection based on Hierarchical Clustering (CDHC), etc. In this comprehensive review, we provide a classification of community detection algorithm based on their approach, dataset used for the existing algorithm for experimental study and measure to evaluate them. In the end, insights into the future scope and research opportunities for community detection are discussed.

Download Full-text