Invention Grant
- Patent Title: Systems and methods for extracting structure from large, dense, and noisy networks
-
Application No.: US16050138Application Date: 2018-07-31
-
Publication No.: US10826781B2Publication Date: 2020-11-03
- Inventor: Matt Hobby , Barry Norton , Jacek Szejda , Peter Wooldridge
- Applicant: Elsevier, Inc.
- Applicant Address: US NY New York
- Assignee: ELSEVIER, INC.
- Current Assignee: ELSEVIER, INC.
- Current Assignee Address: US NY New York
- Agency: Dinsmore & Shohl LLP
- Main IPC: H04L12/24
- IPC: H04L12/24

Abstract:
A method for extracting structure from networks includes receiving an edge list, where the edge list defines a network including nodes and edges connecting the nodes to each other, where the edges define a strength of a relationship between connected nodes and filtering nodes from the edge list based on a predetermined filter parameter, thereby forming a filtered network. The method further includes identifying distinct connected components within the filtered network, analyzing each of the distinct connected components of the filtered network for the presence of additional structures within the distinct connected components, where the additional structures are decomposed into additional distinct connected components. The method further includes performing a tree traversal of each of the distinct connected components, where a resulting hierarchical structure from the tree traversal is merged to determine a local modularity optimum and generating, in response to the local modularity optimum, structural components within the network.
Public/Granted literature
- US20190044821A1 SYSTEMS AND METHODS FOR EXTRACTING STRUCTURE FROM LARGE, DENSE, AND NOISY NETWORKS Public/Granted day:2019-02-07
Information query