Information Fusion from the Point of View of Communication Theory

Abstract

Several aspects of communication theory have been investigated, with the main emphasis on multisensor systems. Among the fundamental results achieved, it has been shown when resolving multiple hypotheses at a desired probability of error, the number of hypotheses to be resolved can be traded off against available signal-to-noise ratio (SNR). It has been shown that the number of resolvable hypotheses can grow no faster than the SNR raised to a certain power. The research also showed that the error probability decreases exponentially fast in the number of sensors, and the error exponent was characterized in general and computed for several examples. In another multisensor setting with randomly deployed sensors, it was desired to detect the possible presence of a randomly located signal emitter. This results in a composite hypothesis-testing problem in which the measurements usually are conditionally dependent. However, it has been shown that if the region of interest is circular or a regular convex polygon, then there are simple least-favorable distributions for the emitter location that reduce the composite hypothesis to a simple one and result in the measurements becoming conditionally independent, resulting in a mathematically tractable problem.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Aug 13, 2013
Accession Number
ADA588145

Entities

People

  • Badri N. Bhaskar
  • Edwin K. Chong
  • J. B. Benedito Jr.
  • Jittpat Bunnag
  • John A. Gubner
  • Kei Hao
  • Louis L. Scharf
  • Luyu Yang
  • P. Fonseca

Organizations

  • University of Wisconsin–Madison

Tags

Communities of Interest

  • Materials and Manufacturing Processes
  • Sensors

DTIC Thesaurus Topics

  • Communication Channels
  • Communication Systems
  • Detection
  • Detectors
  • Frequency
  • Hypotheses
  • Multiple Access
  • Multiplexing
  • Networks
  • Numbers
  • Orthogonal Frequency Division Multiplexing
  • Probability
  • Random Variables
  • Sensor Networks
  • Statistical Inference
  • Students
  • Wireless Sensor Networks

Readers

  • Radar Systems Engineering.
  • Sensor Fusion and Tracking Systems.
  • Statistical inference.