Inductive learning as a fusion engine for mine detection

Semiotics is defined by some researchers as “the study of the appearance (visual or otherwise) meaning, and use of symbols and symbol systems”. 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 seeks 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. The authors explore the feasibility of applying inductive learning to the problem of mine sensor-fusion