Invention Grant
- Patent Title: Network characterization, feature extraction and application to classification
- Patent Title (中): 网络表征,特征提取和应用分类
-
Application No.: US12508791Application Date: 2009-07-24
-
Publication No.: US08271414B2Publication Date: 2012-09-18
- Inventor: Guillermo Alberto Cecchi , Srinivas Ravi Viraraghava Iyengar , Avi Ma'ayan , Ravishankar Rao , Gustavo Alejandro Stolovitzky , John Michael Wagner
- Applicant: Guillermo Alberto Cecchi , Srinivas Ravi Viraraghava Iyengar , Avi Ma'ayan , Ravishankar Rao , Gustavo Alejandro Stolovitzky , John Michael Wagner
- Applicant Address: US NY Armonk US NY New York
- Assignee: International Business Machines Corporation,Mount Sinai School of Medicine of New York University
- Current Assignee: International Business Machines Corporation,Mount Sinai School of Medicine of New York University
- Current Assignee Address: US NY Armonk US NY New York
- Agency: Ryan, Mason & Lewis, LLP
- Agent Vazken Alexanian
- Main IPC: G06F17/00
- IPC: G06F17/00 ; G06N5/02

Abstract:
Methods, systems and apparatus for characterizing networks are presented. For example, a method of characterizing a network represented by a plurality of nodes and a plurality of edges is provided. The method may be implemented on a processor device and includes calculating, for example, by the processor device, a passthrough count of at least a portion of the network. The passthrough count includes a count of a number of passthroughs in the at least a portion of the network. A passthrough includes one of the plurality of nodes, a directed edge of the plurality of edges coupled to the one of the plurality of nodes, and another edge of the plurality of edges coupled to the one of the plurality of nodes. At most one of the directed edge and the other edge is directed towards the one of the plurality of nodes. At most one of the directed edge and the other edge is directed away from the one of the plurality of nodes.
Public/Granted literature
- US20110022355A1 Network Characterization, Feature Extraction and Application to Classification Public/Granted day:2011-01-27
Information query