|
Activity Number:
|
318
- Statistical and Network Modeling in Defense and National Security
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Wednesday, August 5, 2020 : 10:00 AM to 2:00 PM
|
|
Sponsor:
|
Section on Statistics in Defense and National Security
|
|
Abstract #311029
|
|
|
Title:
|
Mixed Network Model for Network Characterization and Simulation
|
|
Author(s):
|
Fairul Mohd-Zaid* and Christine M Schubert Kabban and Richard Deckro and Wright Shamp
|
|
Companies:
|
Air Force Research Lab and Air Force Institute of Technology and Air Force Institute of Technology and Florida State University
|
|
Keywords:
|
Network Characterization;
Network Simulation;
Bootstrap;
Scale-Free Networks
|
|
Abstract:
|
A method for 1) characterizing small networks via a Binomial-Pareto maximum-likelihood approach on the degree distribution and 2) simulating the characterized network using a mixed Barabási-Albert (BA) and Erdös-Rényi (ER) graph are proposed. The BA portion of the network is characterized using simple hypothesis tests based on the Pareto distribution, and the ER portion is characterized through parameter estimation of a doubly truncated binomial distribution. Application on selected real world networks suggests that although real world networks are not completely scale-free as shown in literature, some networks may be characterized as a mixture of BA and ER graphs. The characterized networks were then simulated using an algorithm that combines both BA and ER network generators. Various network measures were compared between the simulated and empirical networks and MSE were also computed to investigate the efficacy of the simulation. The result showed that although the proposed methods are not able to completely capture certain properties of an empirical network, they are able to completely capture the degree distribution and density of the network.
|
Authors who are presenting talks have a * after their name.
