TY - GEN
T1 - Identification of unexploded ordnance from clutter using neural networks
AU - Szidarovszky, Anna
AU - Poulton, Mary
AU - MacInnes, Scott
N1 - Funding Information:
The authors would like to thank The University of Arizona Mining and Geological Engineering Department and Zonge Engineering and Research Organization for supporting this work under SERDP Project 1309.
Publisher Copyright:
Copyright © (2008) by the Society of Exploration Geophysicists All rights reserved.
PY - 2018
Y1 - 2018
N2 - The largest costs associated with subsurface Unexploded Ordnance (UXO) remediation are associated with removing non-UXO debris. Discrimination between UXO and non-UXO is important for both cost and safety reasons. A neural network was developed to distinguish between UXO and non-UXO clutter using Time Domain Electromagnetic Method (TEM) data. There are two stages for the learning process of neural network: training and testing. A synthetic dataset was created using actual acquisition configurations, with varying amounts of random noise. This dataset included 934 UXO targets representing 7 different UXO types, and 789 clutter objects based on four templates with varying size and random asymmetry. The results show 97% accuracy for correctly classifying clutter, and 97% accuracy for correctly classifying UXO.
AB - The largest costs associated with subsurface Unexploded Ordnance (UXO) remediation are associated with removing non-UXO debris. Discrimination between UXO and non-UXO is important for both cost and safety reasons. A neural network was developed to distinguish between UXO and non-UXO clutter using Time Domain Electromagnetic Method (TEM) data. There are two stages for the learning process of neural network: training and testing. A synthetic dataset was created using actual acquisition configurations, with varying amounts of random noise. This dataset included 934 UXO targets representing 7 different UXO types, and 789 clutter objects based on four templates with varying size and random asymmetry. The results show 97% accuracy for correctly classifying clutter, and 97% accuracy for correctly classifying UXO.
UR - http://www.scopus.com/inward/record.url?scp=85059092150&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85059092150&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85059092150
SN - 9781605607856
T3 - 78th Society of Exploration Geophysicists International Exposition and Annual Meeting, SEG 2008
SP - 2912
EP - 2916
BT - 78th Society of Exploration Geophysicists International Exposition and Annual Meeting, SEG 2008
PB - Society of Exploration Geophysicists
T2 - 78th Society of Exploration Geophysicists International Exposition and Annual Meeting, SEG 2008
Y2 - 9 November 2008 through 14 November 2008
ER -