DocumentCode :
2145591
Title :
FDTD data extrapolation using multilayer perceptron (MLP)
Author :
Göksu, Hüseyin ; Pommerenke, David J. ; Wunsch, Donald C., II
Author_Institution :
Dept. of Electr. & Comput. Eng., Missouri Univ., Rolla, MO, USA
Volume :
2
fYear :
2003
fDate :
18-22 Aug. 2003
Firstpage :
735
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.
Keywords :
eigenvalues and eigenfunctions; extrapolation; finite difference time-domain analysis; multilayer perceptrons; EMC; FDTD; MLP; data extrapolation; finite difference time domain; linear eigenanalysis-based extrapolator; matrix pencil method; multilayer perceptron; neural networks; nonlinear function; superposed complex exponentials; time series; time step; Computational modeling; Electromagnetic compatibility; Extrapolation; Finite difference methods; Frequency; Multilayer perceptrons; Neural networks; Predictive models; Resonance; Time domain analysis;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Electromagnetic Compatibility, 2003 IEEE International Symposium on
Print_ISBN :
0-7803-7835-0
Type :
conf
DOI :
10.1109/ISEMC.2003.1236698
Filename :
1236698
Link To Document :
بازگشت