Interactive distributed detection: Architecture and performance analysis

Earnest Akofor, Biao Chen

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

This paper studies the impact of interactive fusion on detection performance in tandem fusion networks with conditionally independent observations. Within the Neyman-Pearson framework, two distinct regimes are considered: 1) the fixed sample size test and 2) the large sample test. For the former, it is established that interactive distributed detection may strictly outperform the one-way tandem fusion structure. However, for the large sample regime, it is shown that interactive fusion has no improvement on the asymptotic performance characterized by the Kullback-Leibler distance compared with the simple one-way tandem fusion. The results are then extended to interactive fusion systems where the fusion center and the sensor may undergo multiple steps of memoryless interactions or that involve multiple peripheral sensors, as well as to interactive fusion with soft sensor outputs.

Original languageEnglish (US)
Article number6874577
Pages (from-to)6456-6473
Number of pages18
JournalIEEE Transactions on Information Theory
Volume60
Issue number10
DOIs
StatePublished - Oct 1 2014

Fingerprint

Fusion reactions
regime
performance
Sensors
interaction

Keywords

  • Decision theory
  • distributed detection
  • interactive fusion
  • Kullback-Leibler distance
  • Neyman-Pearson test

ASJC Scopus subject areas

  • Information Systems
  • Computer Science Applications
  • Library and Information Sciences

Cite this

Interactive distributed detection : Architecture and performance analysis. / Akofor, Earnest; Chen, Biao.

In: IEEE Transactions on Information Theory, Vol. 60, No. 10, 6874577, 01.10.2014, p. 6456-6473.

Research output: Contribution to journalArticle

@article{a927234e40b04c8f87db26929ffe036b,
title = "Interactive distributed detection: Architecture and performance analysis",
abstract = "This paper studies the impact of interactive fusion on detection performance in tandem fusion networks with conditionally independent observations. Within the Neyman-Pearson framework, two distinct regimes are considered: 1) the fixed sample size test and 2) the large sample test. For the former, it is established that interactive distributed detection may strictly outperform the one-way tandem fusion structure. However, for the large sample regime, it is shown that interactive fusion has no improvement on the asymptotic performance characterized by the Kullback-Leibler distance compared with the simple one-way tandem fusion. The results are then extended to interactive fusion systems where the fusion center and the sensor may undergo multiple steps of memoryless interactions or that involve multiple peripheral sensors, as well as to interactive fusion with soft sensor outputs.",
keywords = "Decision theory, distributed detection, interactive fusion, Kullback-Leibler distance, Neyman-Pearson test",
author = "Earnest Akofor and Biao Chen",
year = "2014",
month = "10",
day = "1",
doi = "10.1109/TIT.2014.2346497",
language = "English (US)",
volume = "60",
pages = "6456--6473",
journal = "IEEE Transactions on Information Theory",
issn = "0018-9448",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "10",

}

TY - JOUR

T1 - Interactive distributed detection

T2 - Architecture and performance analysis

AU - Akofor, Earnest

AU - Chen, Biao

PY - 2014/10/1

Y1 - 2014/10/1

N2 - This paper studies the impact of interactive fusion on detection performance in tandem fusion networks with conditionally independent observations. Within the Neyman-Pearson framework, two distinct regimes are considered: 1) the fixed sample size test and 2) the large sample test. For the former, it is established that interactive distributed detection may strictly outperform the one-way tandem fusion structure. However, for the large sample regime, it is shown that interactive fusion has no improvement on the asymptotic performance characterized by the Kullback-Leibler distance compared with the simple one-way tandem fusion. The results are then extended to interactive fusion systems where the fusion center and the sensor may undergo multiple steps of memoryless interactions or that involve multiple peripheral sensors, as well as to interactive fusion with soft sensor outputs.

AB - This paper studies the impact of interactive fusion on detection performance in tandem fusion networks with conditionally independent observations. Within the Neyman-Pearson framework, two distinct regimes are considered: 1) the fixed sample size test and 2) the large sample test. For the former, it is established that interactive distributed detection may strictly outperform the one-way tandem fusion structure. However, for the large sample regime, it is shown that interactive fusion has no improvement on the asymptotic performance characterized by the Kullback-Leibler distance compared with the simple one-way tandem fusion. The results are then extended to interactive fusion systems where the fusion center and the sensor may undergo multiple steps of memoryless interactions or that involve multiple peripheral sensors, as well as to interactive fusion with soft sensor outputs.

KW - Decision theory

KW - distributed detection

KW - interactive fusion

KW - Kullback-Leibler distance

KW - Neyman-Pearson test

UR - http://www.scopus.com/inward/record.url?scp=84907200777&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84907200777&partnerID=8YFLogxK

U2 - 10.1109/TIT.2014.2346497

DO - 10.1109/TIT.2014.2346497

M3 - Article

AN - SCOPUS:84907200777

VL - 60

SP - 6456

EP - 6473

JO - IEEE Transactions on Information Theory

JF - IEEE Transactions on Information Theory

SN - 0018-9448

IS - 10

M1 - 6874577

ER -