TY - GEN
T1 - Identification of unexploded ordnance from clutter using neural neworks
AU - Szidarovszky, Anna
AU - Poulton, Mary
AU - Macinnes, Scott C.
PY - 2008
Y1 - 2008
N2 - The largest costs associated with subsurface Unexploded Ordnance (UXO) remediation are associated with removing non-UXO. 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 TEM data. There are two stages for the learning process of neural network, training and validation. 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. The level of success for classification is based on the classification Receiver Operating Characteristic (ROC) curves. The ROC curve represents the relationship between UXO classified correctly (Hit rate) versus clutter miss classified (False alarm).
AB - The largest costs associated with subsurface Unexploded Ordnance (UXO) remediation are associated with removing non-UXO. 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 TEM data. There are two stages for the learning process of neural network, training and validation. 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. The level of success for classification is based on the classification Receiver Operating Characteristic (ROC) curves. The ROC curve represents the relationship between UXO classified correctly (Hit rate) versus clutter miss classified (False alarm).
UR - http://www.scopus.com/inward/record.url?scp=84865519180&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84865519180&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:84865519180
SN - 9781605603001
T3 - Environmental and Engineering Geophysical Society - 21st Symposium on the Application of Geophysics to Engineering and Environmental Problems 2008
SP - 525
EP - 535
BT - Environmental and Engineering Geophysical Society - 21st Symposium on the Application of Geophysics to Engineering and Environmental Problems 2008
T2 - 21st Symposium on the Application of Geophysics to Engineering and Environmental Problems 2008
Y2 - 6 April 2008 through 10 April 2008
ER -