In this paper, we present the development of a two dimensional feed-forward functionally expanded neural network (2D FFENN) surface modeler. Two application models of the generic design are also proposed. The scope of this work is the development of a two-dimensional system able to produce surface data mappings. The main application area of interest is sea surface modeling and target detection by sea clutter suppression. New nonlinear multi-level surface basis functions are proposed for the network’s functional expansion. A network optimization technique based on an iterative function selection strategy is also described. Results for surface mappings generated by the multi-level 2D FFENN and interpolation 2D FFENN designs are presented.
|Publication status||Published - 2002|
|Event||Signal Processing, Pattern Recognition, and Applications (SPPRA 2002) - Crete, Greece|
Duration: 25 Jun 2002 → 28 Jun 2002
|Conference||Signal Processing, Pattern Recognition, and Applications (SPPRA 2002)|
|Period||25/06/02 → 28/06/02|
- neural networks
- surface modeling
- sea clutter
- surface approximation
- 2d ffenn
Panagopolous, S., & Soraghan, J. J. (2002). Surface approximation using the multi-level and interpolation 2D FFENN. Paper presented at Signal Processing, Pattern Recognition, and Applications (SPPRA 2002) , Crete, Greece.