Abstract
The electric field scattered from the buried cylindrical target is calculated by using Equivalence Principle and Moment Method, and the database is formed by using the scattered fields from three cylindrical targets at certain frequencies. Radial Basis Function Network is proposed for target classification. A portion of the database is used to train the network and the rest is used to test the performance of the neural network. This target classification process has been repeated by changing the surface roughness of the medium, in which is the target buried, and effects of the surface roughness to the target classification are investigated.
Keywords
Surface roughness
Surface finish
Artificial neural network
Moment (physics)
Electric field
Equivalence (formal languages)
Surface (topology)
Computer science
Radial basis function
Field (mathematics)
Pattern recognition (psychology)
Artificial intelligence
Materials science
Physics
Engineering
Mathematics
Geometry
Mechanical engineering
Classical mechanics
Subject Areas
Geophysical Methods and Applications
·Ocean Engineering ·Physical Sciences
Underwater Acoustics Research
·Oceanography ·Physical Sciences
Ultrasonics and Acoustic Wave Propagation
·Mechanics of Materials ·Physical Sciences
Loading…