Information Fusion and Performance Modeling with Distributed Sensor Networks

Abstract

The focus of this project is to develop and demonstrate the fusion methodologies to enhance the ability to integrate multi-source information and to assess fusion performance for numerous applications such as situational awareness, surveillance, and tracking. The focus of the Year 1 effort was on developing a solid theoretical foundation and on developing autonomous and efficient information fusion algorithms with distributed sensors. The focus of Year 2 effort was to develop a set of fusion performance modeling methodologies based on explicit links of spatial and temporal relationships between target features and sensor observations. We have accomplished the goals. Specifically, we developed a set of scalable fusion algorithms and the corresponding theoretical performance analysis in a dynamic sensor network environment. We have also developed a framework for quantifying the classification performance of a set of sensors with varying qualities based on local confusion matrix and global confusion matrix using Bayesian network model. In addition, we have developed a software tool based on UnBBayes open source environment to test the performance modeling. The resulting methodology has significant potential for applications in high level fusion and situational assessment.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Nov 01, 2010
Accession Number
ADA550431

Entities

People

  • Kuochu Chang

Organizations

  • George Mason University

Tags

Communities of Interest

  • Biomedical
  • C4I
  • Energy and Power Technologies
  • Materials and Manufacturing Processes
  • Space
  • Weapons Technologies

DTIC Thesaurus Topics

  • Air Force Research Laboratories
  • Algorithms
  • Artificial Intelligence
  • Bayesian Networks
  • Communication Networks
  • Computational Science
  • Detectors
  • Electrical Engineering
  • Gaussian Distributions
  • Networks
  • Operations Research
  • Probability Distributions
  • Random Variables
  • Reasoning
  • Sensor Networks
  • Systems Engineering
  • Wireless Sensor Networks

Fields of Study

  • Computer science
  • Engineering

Readers

  • Distributed Systems and Data Platform Development
  • Theoretical Analysis.

Technology Areas

  • AI & ML