Performance evaluation of a non-linear error model for underwater range computation utilizing GPS sonobuoys

Ahmed El-Shafie, Abdalla Osman, Aboelmagd Noureldin, Aini Hussain

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Deployed from an airborne platform or a surface vessel, arrays of GPS sonobuoys can be used to efficiently track and localize submarines. The range of the target of interest can be monitored with the deployed sonobuoys. However, the accuracy deteriorates when the target is on the detection range of only one sonobuoy. The objective of this research is to improve the range computation of the target of interest by establishing a non-linear error model for range error using adaptive neuro-fuzzy inference systems (ANFIS), which has the capabilities of dealing with data of high level of uncertainty and the advantage of being based on neural computation. Furthermore, the performance of the proposed model is examined with both experimental real field data and contact-level simulation data considering different scenarios for both the array of GPS sonobuoys and the target. The results discuss merits and the limitations of the proposed method.

Original languageEnglish
Pages (from-to)1057-1067
Number of pages11
JournalNeural Computing and Applications
Volume19
Issue number7
DOIs
Publication statusPublished - 2010

Fingerprint

Global positioning system
Fuzzy inference
Uncertainty

Keywords

  • Data fusion
  • GPS sonobuoys
  • Neuro-fuzzy systems
  • Tracking

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software

Cite this

Performance evaluation of a non-linear error model for underwater range computation utilizing GPS sonobuoys. / El-Shafie, Ahmed; Osman, Abdalla; Noureldin, Aboelmagd; Hussain, Aini.

In: Neural Computing and Applications, Vol. 19, No. 7, 2010, p. 1057-1067.

Research output: Contribution to journalArticle

El-Shafie, Ahmed ; Osman, Abdalla ; Noureldin, Aboelmagd ; Hussain, Aini. / Performance evaluation of a non-linear error model for underwater range computation utilizing GPS sonobuoys. In: Neural Computing and Applications. 2010 ; Vol. 19, No. 7. pp. 1057-1067.
@article{22849fda00b94043b2169685137cfdaa,
title = "Performance evaluation of a non-linear error model for underwater range computation utilizing GPS sonobuoys",
abstract = "Deployed from an airborne platform or a surface vessel, arrays of GPS sonobuoys can be used to efficiently track and localize submarines. The range of the target of interest can be monitored with the deployed sonobuoys. However, the accuracy deteriorates when the target is on the detection range of only one sonobuoy. The objective of this research is to improve the range computation of the target of interest by establishing a non-linear error model for range error using adaptive neuro-fuzzy inference systems (ANFIS), which has the capabilities of dealing with data of high level of uncertainty and the advantage of being based on neural computation. Furthermore, the performance of the proposed model is examined with both experimental real field data and contact-level simulation data considering different scenarios for both the array of GPS sonobuoys and the target. The results discuss merits and the limitations of the proposed method.",
keywords = "Data fusion, GPS sonobuoys, Neuro-fuzzy systems, Tracking",
author = "Ahmed El-Shafie and Abdalla Osman and Aboelmagd Noureldin and Aini Hussain",
year = "2010",
doi = "10.1007/s00521-010-0340-5",
language = "English",
volume = "19",
pages = "1057--1067",
journal = "Neural Computing and Applications",
issn = "0941-0643",
publisher = "Springer London",
number = "7",

}

TY - JOUR

T1 - Performance evaluation of a non-linear error model for underwater range computation utilizing GPS sonobuoys

AU - El-Shafie, Ahmed

AU - Osman, Abdalla

AU - Noureldin, Aboelmagd

AU - Hussain, Aini

PY - 2010

Y1 - 2010

N2 - Deployed from an airborne platform or a surface vessel, arrays of GPS sonobuoys can be used to efficiently track and localize submarines. The range of the target of interest can be monitored with the deployed sonobuoys. However, the accuracy deteriorates when the target is on the detection range of only one sonobuoy. The objective of this research is to improve the range computation of the target of interest by establishing a non-linear error model for range error using adaptive neuro-fuzzy inference systems (ANFIS), which has the capabilities of dealing with data of high level of uncertainty and the advantage of being based on neural computation. Furthermore, the performance of the proposed model is examined with both experimental real field data and contact-level simulation data considering different scenarios for both the array of GPS sonobuoys and the target. The results discuss merits and the limitations of the proposed method.

AB - Deployed from an airborne platform or a surface vessel, arrays of GPS sonobuoys can be used to efficiently track and localize submarines. The range of the target of interest can be monitored with the deployed sonobuoys. However, the accuracy deteriorates when the target is on the detection range of only one sonobuoy. The objective of this research is to improve the range computation of the target of interest by establishing a non-linear error model for range error using adaptive neuro-fuzzy inference systems (ANFIS), which has the capabilities of dealing with data of high level of uncertainty and the advantage of being based on neural computation. Furthermore, the performance of the proposed model is examined with both experimental real field data and contact-level simulation data considering different scenarios for both the array of GPS sonobuoys and the target. The results discuss merits and the limitations of the proposed method.

KW - Data fusion

KW - GPS sonobuoys

KW - Neuro-fuzzy systems

KW - Tracking

UR - http://www.scopus.com/inward/record.url?scp=77956875961&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77956875961&partnerID=8YFLogxK

U2 - 10.1007/s00521-010-0340-5

DO - 10.1007/s00521-010-0340-5

M3 - Article

VL - 19

SP - 1057

EP - 1067

JO - Neural Computing and Applications

JF - Neural Computing and Applications

SN - 0941-0643

IS - 7

ER -