Title :
Classifying sonar returns for the presence of mines: evolving neural networks and evolving rules
Author :
Porto, Vincent W. ; Fogel, David B. ; Fogel, Lawrence J. ; Fogel, GaryB ; Johnson, Nathan ; Cheung, Mars
Author_Institution :
Natural Selection, Inc., La Jolla, CA
fDate :
March 31 2005-April 1 2005
Abstract :
Sea mines present a danger to commercial shipping, military operations, relief efforts, and can impact a nation´s homeland and economic security. This paper presents results of using evolutionary neural networks or rule-based classifiers to discriminate between active sonar returns from simulated sea mines and other background. The results indicate that both evolutionary methods can be used with considerable success
Keywords :
evolutionary computation; neural nets; pattern classification; sonar signal processing; active sonar returns; evolutionary computation; evolutionary neural networks; evolutionary rule-based classifiers; sea mines; sonar return classification; Business; Evolutionary computation; Irrigation; Marine vehicles; Neural networks; Reflection; Reverberation; Sonar detection; Terrorism; Testing;
Conference_Titel :
Computational Intelligence for Homeland Security and Personal Safety, 2005. CIHSPS 2005. Proceedings of the 2005 IEEE International Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-9176-4
DOI :
10.1109/CIHSPS.2005.1500626
