skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Inductive learning as a fusion engine for mine detection

Abstract

Semiotics is defined by some researchers as {open_quotes}the study of the appearance (visual or otherwise) meaning, and use of symbols and symbol systems.{close_quotes} Semiotic fusion of data from multiple sensory sources is a potential solution to the problem of landmine detection. This turns out to be significant, because notwithstanding the diversity of sensor technologies being used to attack the problem, there is no single effective landmine sensor technology. The only practical, general-purpose mine detector presently available is the trained dog. Most research into mine-detection technology seeds to emulate the dog`s seemingly uncanny abilities. An ideal data-fusion system would mimic animal reaction, with the brain`s perceptive power melding multiple sensory cues into an awareness of the size and location of a mine. Furthermore, the fusion process should be adaptive, with the skill at combining cues into awareness improving with experience. Electronic data-fusion systems reported in the countermine literature use conventional vector-based pattern recognition methods. Although neural nets are popular, they have never satisfactorily met the challenge. Despite years of investigation, nobody has ever found a vector space representation that reliably characterizes mine identity. This strongly suggests that the features have not been found because researchers have been looking for the wrongmore » characteristics. It is worth considering that dogs probably do not represent data as mathematical number lists, but they almost certainly represent data via semiotic structures.« less

Authors:
;
Publication Date:
Research Org.:
Oak Ridge National Lab., TN (United States)
Sponsoring Org.:
USDOE, Washington, DC (United States)
OSTI Identifier:
527927
Report Number(s):
CONF-971068-1
ON: DE97007787; TRN: 97:005170
DOE Contract Number:  
AC05-96OR22464
Resource Type:
Conference
Resource Relation:
Conference: IEEE international conference on systems, man and cybernetics, Orlando, FL (United States), 12-15 Oct 1997; Other Information: PBD: 1997
Country of Publication:
United States
Language:
English
Subject:
45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEFENSE; 99 MATHEMATICS, COMPUTERS, INFORMATION SCIENCE, MANAGEMENT, LAW, MISCELLANEOUS; MILITARY EQUIPMENT; DETECTION; EXPLOSIVES; ARTIFICIAL INTELLIGENCE; ALGORITHMS

Citation Formats

Kercel, S W, and Dress, W B. Inductive learning as a fusion engine for mine detection. United States: N. p., 1997. Web.
Kercel, S W, & Dress, W B. Inductive learning as a fusion engine for mine detection. United States.
Kercel, S W, and Dress, W B. Fri . "Inductive learning as a fusion engine for mine detection". United States. https://www.osti.gov/servlets/purl/527927.
@article{osti_527927,
title = {Inductive learning as a fusion engine for mine detection},
author = {Kercel, S W and Dress, W B},
abstractNote = {Semiotics is defined by some researchers as {open_quotes}the study of the appearance (visual or otherwise) meaning, and use of symbols and symbol systems.{close_quotes} Semiotic fusion of data from multiple sensory sources is a potential solution to the problem of landmine detection. This turns out to be significant, because notwithstanding the diversity of sensor technologies being used to attack the problem, there is no single effective landmine sensor technology. The only practical, general-purpose mine detector presently available is the trained dog. Most research into mine-detection technology seeds to emulate the dog`s seemingly uncanny abilities. An ideal data-fusion system would mimic animal reaction, with the brain`s perceptive power melding multiple sensory cues into an awareness of the size and location of a mine. Furthermore, the fusion process should be adaptive, with the skill at combining cues into awareness improving with experience. Electronic data-fusion systems reported in the countermine literature use conventional vector-based pattern recognition methods. Although neural nets are popular, they have never satisfactorily met the challenge. Despite years of investigation, nobody has ever found a vector space representation that reliably characterizes mine identity. This strongly suggests that the features have not been found because researchers have been looking for the wrong characteristics. It is worth considering that dogs probably do not represent data as mathematical number lists, but they almost certainly represent data via semiotic structures.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {1997},
month = {8}
}

Conference:
Other availability
Please see Document Availability for additional information on obtaining the full-text document. Library patrons may search WorldCat to identify libraries that hold this conference proceeding.

Save / Share: