Optimal bandwidth assignment for distributed sequential detection

Qi Cheng, Pramod K. Varshney, Kishan G. Mehrotra, Chilukuri K. Mohan

Research output: Contribution to conferencePaper

3 Scopus citations

Abstract

In this paper, distributed sequential detection problems with quantized observations are investigated. The observations available at each sensor are first compressed to multi-bit sensor decisions (soft decisions) and sent to the fusion center. At the fusion center, a sequential data fusion scheme is implemented in order to reach a global decision. Optimal bandwidth distribution among sensors is considered under communication constraints as well as under a generalized cost formulation. A system optimization algorithm is developed, including optimal fusion center design and optimal local quantizer design, for the minimization of the average sample number, given prespecified values of the probabilities of false alarm and miss. Simulations of the algorithm show that this approach succeeds in effective optimal bandwidth assignment.

Original languageEnglish (US)
Pages49-55
Number of pages7
DOIs
StatePublished - Jan 1 2002
Event5th International Conference on Information Fusion, FUSION 2002 - Annapolis, MD, United States
Duration: Jul 8 2002Jul 11 2002

Other

Other5th International Conference on Information Fusion, FUSION 2002
CountryUnited States
CityAnnapolis, MD
Period7/8/027/11/02

Keywords

  • bandwidth management
  • distributed detec-tributed detectiontion
  • fusion
  • Sequential detection

ASJC Scopus subject areas

  • Information Systems

Fingerprint Dive into the research topics of 'Optimal bandwidth assignment for distributed sequential detection'. Together they form a unique fingerprint.

  • Cite this

    Cheng, Q., Varshney, P. K., Mehrotra, K. G., & Mohan, C. K. (2002). Optimal bandwidth assignment for distributed sequential detection. 49-55. Paper presented at 5th International Conference on Information Fusion, FUSION 2002, Annapolis, MD, United States. https://doi.org/10.1109/ICIF.2002.1021130