A Factor-Graph Clustering Approach for Detection of Underwater Acoustic Signals

Dror Kipnis, Roee DIamant

Research output: Contribution to journalArticlepeer-review

Abstract

We address the challenge of detecting an arbitrary-shaped underwater acoustic signal. Instead of setting a detection threshold, which due to noise transients may result in a high false alarm rate (FAR), our method classifies each measured sample as either 'noise' or 'signal.' Utilizing a priori knowledge of only the minimal duration of the signal, the decision is made using loopy belief propagation over a factor graph. Numerical simulations and sea experimental results show that our scheme achieves a favorable tradeoff between the Recall and FAR, and noise robustness, which far exceeds that of benchmark schemes.

Original languageEnglish
Article number8579234
Pages (from-to)702-706
Number of pages5
JournalIEEE Geoscience and Remote Sensing Letters
Volume16
Issue number5
DOIs
StatePublished - May 2019

Bibliographical note

Funding Information:
Manuscript received July 4, 2018; revised September 20, 2018; accepted October 23, 2018. Date of publication December 17, 2018; date of current version April 22, 2019. This work was supported in part by the European Union’s Horizon 2020 Research and Innovation Program under Grant 773753 (Symbiosis) and in part by the NATO Science for Peace and Security Program under Grant G5293. (Corresponding author: Dror Kipnis.) The authors are with the Department of Marine Technology, University of Haifa, Haifa 3498838, Israel (e-mail: dkipnis@campus.haifa.ac.il; roeed@univ.haifa.ac.il).

Publisher Copyright:
© 2004-2012 IEEE.

Keywords

  • Clustering
  • factor graphs
  • loopy belief propagation (LBP)
  • sea experiment
  • signal detection
  • underwater acoustics

ASJC Scopus subject areas

  • Geotechnical Engineering and Engineering Geology
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'A Factor-Graph Clustering Approach for Detection of Underwater Acoustic Signals'. Together they form a unique fingerprint.

Cite this