Research of Hierarchical Random Graph Model based on maximum likelihood estimation

With the extensive application of the network structure, the complexity of the network becomes higher and higher. According to the features of the complex network's structure, the Hierarchical Random Graph Model (HRGM) based on Hierarchical clustering method, establishes and expresses the hiera...

Full description

Saved in:
Bibliographic Details
Published in:RISTI : Revista Ibérica de Sistemas e Tecnologias de Informação no. 17B; p. 359
Main Authors: Shaoyan, Sun, Fengnan, Sun
Format: Journal Article
Language:English
Portuguese
Published: Lousada AISTI (Iberian Association for Information Systems and Technologies) 30.03.2016
Associação Ibérica de Sistemas e Tecnologias de Informacao
Subjects:
Analysis
Distribution (Probability theory)
Social networks
ISSN:1646-9895
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:With the extensive application of the network structure, the complexity of the network becomes higher and higher. According to the features of the complex network's structure, the Hierarchical Random Graph Model (HRGM) based on Hierarchical clustering method, establishes and expresses the hierarchical structure of the network, and uses the cumulative number of weights to evaluate the organizational structure of the network and to measure the importance of nodes. The principle of maximum likelihood estimation is applied in this model, which can obtain a sample set of relevant probability density functions of the parameters, and suits the HRGM absolutely. Moreover, practical researches agree well with its fine accuracy when maximum likelihood algorithm of the HRGM deals with the networks with hierarchical structure. In this paper, this new method of applying the HRGM to the brain network link prediction has achieved good results, and may have certain reference value to the exploration of the brain network link research. Keywords: Hierarchical random graph; network structure; binary tree; cumulative number of weights; maximum likelihood estimation algorithm
Bibliography:SourceType-Scholarly Journals-1
ObjectType-General Information-1
content type line 14
ISSN:1646-9895
DOI:10.17013/risti.17B.359-369