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

Conference ·
OSTI ID:527927

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.

Research Organization:
Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
Sponsoring Organization:
USDOE, Washington, DC (United States)
DOE Contract Number:
AC05-96OR22464
OSTI ID:
527927
Report Number(s):
CONF-971068-1; ON: DE97007787; TRN: 97:005170
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