Group distribution detection method based on Chebyshev filter

A Chebyshev and distribution detection technology, applied in the field of deep learning and complex network community discovery, can solve the problem of low computing efficiency, achieve the effect of improving efficiency and realizing network weight sharing

Pending Publication Date: 2019-10-08
桂林远望智能通信科技有限公司
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Traditional complex network community discovery methods n

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
  • Group distribution detection method based on Chebyshev filter
  • Group distribution detection method based on Chebyshev filter
  • Group distribution detection method based on Chebyshev filter

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] The group detection method based on the Chebyshev filter of the present invention will be further described below in conjunction with the accompanying drawings.

[0041] like figure 1 As shown, the present invention provides a group distribution detection method based on the Chebyshev filter.

[0042] For a complex social network formed by the college football league, the 115 college student teams participating in the competition were divided into 12 leagues, and 616 games were carried out. The specific process of group detection with the method of the present invention includes the following steps:

[0043] Step 1: Read complex network data, and abstract the complex network into a graph model, which includes nodes, edges, and adjacency weight matrix. The specific symbols are expressed as: G=(V, E, W), where V is The set of nodes represents the team, and E represents the set of nodes connecting edges, which means that two teams have played games. For each node v i ∈V,...

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 provides a group distribution detection method based on a Chebyshev filter, and the method mainly comprises the following steps: reading complex network data, and abstracting a complex network into a graph model; carrying out label initialization, that is, a unique label is marked for part of nodes and used for representing a group where the nodes are located, and other nodes are notmarked; inputting the initialized nodes into a Chebyshev filter, and extracting hidden layer features of the graph model; and mapping the extracted features to a marked node space for processing, andinputting an output value into a classifier, so that the nodes with the same label are the same group. A Chebyshev filter semi-supervised learning method is used for realizing group distribution detection, fewer parameters are used for discovering the group structure of the network, and the efficiency of complex network group distribution detection is improved.

Description

technical field [0001] The invention relates to the field of deep learning and complex network community discovery, in particular to a Chebyshev filter-based community distribution detection method. Background technique [0002] In recent years, deep learning has been widely used in speech recognition, image recognition, natural language processing and other fields, but there are few applications for complex networks such as social networks, telecommunication networks, protein interaction networks, and road networks. In the past two years, graph convolutional neural network technology has made new breakthroughs. This technology can process a large amount of network data, perform convolution operations on a network, and perform coarse-graining to achieve multi-layer signal processing. [0003] Traditional community discovery methods for complex networks need to set many parameters, and the calculation efficiency is low. This method uses a graph convolutional neural network t...

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): G06Q50/00G06N3/04G06N3/08
CPCG06Q50/01G06N3/08G06N3/045
Inventor 蔡晓东王萌
Owner 桂林远望智能通信科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap