FDTD data extrapolation using multilayer perceptron (MLP)

Goksu H., POMMERENKE D., WUNSCH D.

IEEE Symposium on Electromagnetic Compatibility (EMC 2003), Massachusetts, United States Of America, 18 - 22 August 2003, pp.735-737 identifier identifier

  • Publication Type: Conference Paper / Full Text
  • City: Massachusetts
  • Country: United States Of America
  • Page Numbers: pp.735-737
  • Keywords: FDTD, neural networks, multiplayer perceptron, EMC, data extrapolation, prediction, time series, complex exponentials
  • Akdeniz University Affiliated: No

Abstract

This work compares MLP with the Matrix Pencil Method, a linear eigenanalysis-based extrapolator, in terms of their effectiveness in Finite Difference Time Domain (FDTD) data extrapolation. Matrix Pencil Method considers the signal as superposed complex exponentials while MLP considers each time step to be a nonlinear function of previous time steps.