GoFFish: Graph-Oriented Framework for Foresight and Insight Using Scalable Heuristics

Abstract

In this project, designed, developed, and built GoFFish, which is a scalable platform for graph - oriented event analytics that accelerates a wide class of DoD algorithms significantly. GoFFish is designed to be a scalable, modular, integrated, open - source analytics platform to fish for insight from massive event reservoirs archived from interconnected sensor event streams. The experiments performed under this effort showed speedups for certain classes of graph algorithms and also for their parallel algorithms for Louvain community detection and high betweenness centrality. This final report summarizes the GoFFish framework, and several parallel algorithms for graph processing.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Sep 01, 2015
Accession Number
ADA623562

Entities

People

  • Viktor K. Prasanna

Organizations

  • University of Southern California

Tags

Communities of Interest

  • C4I
  • Cyber
  • Energy and Power Technologies
  • Engineered Resilient Systems
  • Human Systems

DTIC Thesaurus Topics

  • Algorithms
  • Big Data
  • Cloud Computing
  • Computational Science
  • Computer Networks
  • Computer Programming
  • Computers
  • Data Analysis
  • Data Centers
  • Data Mining
  • Databases
  • Information Science
  • Load Monitoring
  • Machine Learning
  • Network Science
  • Online Communications
  • Social Media

Fields of Study

  • Computer science

Readers

  • Cybersecurity.
  • Neural Network Machine Learning.
  • Systems Analysis and Design