Skip to main content
EURASIP Journal on Advances in Signal Processing
Download PDF

Surface Approximation Using the 2D FFENN Architecture

EURASIP Journal on Advances in Signal Processing volume 2004, Article number: 348702 (2004) Cite this article

Abstract

A new two-dimensional feed-forward functionally expanded neural network (2D FFENN) used to produce surface models in two dimensions is presented. New nonlinear multilevel 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. Comparative simulation results for surface mappings generated by the 2D FFENN, multilevel 2D FFENN, multilayered perceptron (MLP), and radial basis function (RBF) architectures are presented.

Author information

Affiliations

  1. Institute for Communications & Signal Processing, University of Strathclyde, Royal College Building, Glasgow, G1 1XW, UK

    S. Panagopoulos & J. J. Soraghan

Authors
  1. S. Panagopoulos
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. J. J. Soraghan
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to S. Panagopoulos.

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Panagopoulos, S., Soraghan, J.J. Surface Approximation Using the 2D FFENN Architecture. EURASIP J. Adv. Signal Process. 2004, 348702 (2004). https://doi.org/10.1155/S111086570440612X

Download citation

Keywords

  • neural networks
  • sea clutter
  • surface modeling