Convergence of a Belief Propagation Algorithm for Biological Networks
Joint Authors
Source
Discrete Dynamics in Nature and Society
Issue
Vol. 2019, Issue 2019 (31 Dec. 2019), pp.1-16, 16 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2019-07-24
Country of Publication
Egypt
No. of Pages
16
Main Subjects
Abstract EN
Constructing network models of biological systems is important for effective understanding and control of the biological systems.
For the construction of biological networks, a stochastic approach for link weights has been recently developed by using experimental data and belief propagation on a factor graph.
The link weights were variable nodes of the factor graph and determined from their marginal probability mass functions which were approximated by using an iterative scheme.
However, there is no convergence analysis of the iterative scheme.
In this paper, at first, we present a detailed explanation of the complicated multistep process step by step with a network of small size and artificial experimental data, and then we show a sufficient condition for the convergence of the iterative scheme.
Numerical examples are given to illustrate the whole process and to verify our result.
American Psychological Association (APA)
Choo, Sangmok& Kim, Young-Hee. 2019. Convergence of a Belief Propagation Algorithm for Biological Networks. Discrete Dynamics in Nature and Society،Vol. 2019, no. 2019, pp.1-16.
https://search.emarefa.net/detail/BIM-1146660
Modern Language Association (MLA)
Choo, Sangmok& Kim, Young-Hee. Convergence of a Belief Propagation Algorithm for Biological Networks. Discrete Dynamics in Nature and Society No. 2019 (2019), pp.1-16.
https://search.emarefa.net/detail/BIM-1146660
American Medical Association (AMA)
Choo, Sangmok& Kim, Young-Hee. Convergence of a Belief Propagation Algorithm for Biological Networks. Discrete Dynamics in Nature and Society. 2019. Vol. 2019, no. 2019, pp.1-16.
https://search.emarefa.net/detail/BIM-1146660
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-1146660