Using Physics-Based Modeler Outputs to Train Probabilistic Neural Networks for Unexploded Ordnance (UXO) Classification in Magnetometry Surveys.

Autor: Hart, Sean J., Shaffer, Ronald E., Rose-Pehrsson, Susan L., McDonald, Jim R.
Předmět:
Zdroj: IEEE Transactions on Geoscience & Remote Sensing; Apr2001, Vol. 39 Issue 4, p797, 8p, 2 Diagrams, 3 Charts, 5 Graphs
Abstrakt: Deals with a study that discussed the use of outputs from a physics-based modeler of magnetometry data with a probabilistic neural network to discriminate unexploded ordnance from ordnance-related scrap. Experimentation; Intra-data set analysis; Conclusions.
Databáze: Complementary Index