Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Improved density peak overlapping community discovery method based on rough set theory

A rough set theory and density peak technology, applied in the analysis and division of overlapping nodes, which can solve problems such as high complexity and inability to divide overlapping nodes.

Active Publication Date: 2019-11-08
SOUTHWEST JIAOTONG UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The community discovery method based on the density peak also has the problem of high complexity. Therefore, we study a data structure based on the network data set to improve the density peak algorithm and improve the efficiency of the density peak clustering algorithm for community discovery. At the same time, the overlapping More efficient identification and division of nodes is an urgent technical requirement for community discovery algorithms
However, the classic density peak clustering method cannot divide overlapping nodes

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Improved density peak overlapping community discovery method based on rough set theory
  • Improved density peak overlapping community discovery method based on rough set theory
  • Improved density peak overlapping community discovery method based on rough set theory

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] The specific implementation steps are as follows:

[0048] In order to efficiently divide large-scale networks, the present invention proposes a new method for the calculation of ρ and δ and the selection of the center point in the density peak clustering algorithm, and the steps are as follows:

[0049] Step 1: Enter the network is the adjacency matrix of the network. Each node in the computing network (v i ) local density (ρ i ), it is necessary to consider v i The number of neighbors|neib(v i )|, also consider v i The connection strength SN between neighbors i , and finally ρ i The size of |neib(v i )| and SN i Joint decision, the calculation formula is as follows:

[0050]

[0051]

[0052] Among them, A xy Corresponding to the value of the x and y position in the adjacency matrix, P(neib(v i )) means neib(v i ) constitutes the number of edges when a complete graph is formed;

[0053] Step 2: Calculate each node in the network (v i ) of the min...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses an improved density peak overlapping community discovery method based on a rough set theory. The improved density peak overlapping community discovery method comprises the following steps: firstly, calculating a local density attribute (rho) of each node in a network by adopting an improved node local density calculation method; secondly, adopting an improved efficient nodeminimum distance calculation strategy to calculate the minimum distance attribute (delta) of each node; aiming at the calculation of the distance between nodes, defining an ND-subspace distance measurement method, and providing a new community center point selection mode; and finally, performing community division on nodes in the network and performing iterative computation on overlapping nodes in the network on the density peak clustering. According to the improved density peak overlapping community discovery method, the problem of overlapping node division is effectively solved; an ND-subspace distance measurement method is defined for calculation of the distance between the nodes; a density peak clustering method is improved to divide the large-scale social network more efficiently; and the problem of overlapping community division of the large-scale social network can be effectively solved.

Description

technical field [0001] The invention relates to the field of data mining, in particular to the analysis and division of overlapping nodes in large-scale social networks. Background technique [0002] With the continuous development of network technology, social networking has become an important way for people to communicate and interact. Nowadays, there are many online social platforms, such as Facebook, YouTube, Twitter and so on. These platforms will generate a large amount of social network data, which contains deeper structural information. A community is a group composed of closely connected individuals in the network, and the community is the embodiment of the local characteristics of the network. Mining the community structure in the network can help people further explore the knowledge contained in the network. In recent years, many studies have shown that there may be overlapping regions between communities, which are the key to inter-community connections in ne...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06F16/9536G06K9/62G06Q50/00
CPCG06F16/9536G06Q50/01G06F18/2321
Inventor 陈红梅封云飞李天瑞桑彬彬王生武
Owner SOUTHWEST JIAOTONG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products