FDTD data extrapolation using multilayer perceptron (MLP)

Hüseyin Göksu; David J. Pommerenke; Donald C. Wunsch

FDTD data extrapolation using multilayer perceptron (MLP)

Hüseyin Göksu^*, David J. Pommerenke, Donald C. Wunsch

^*Corresponding author for this work

Research output: Contribution to journal › Conference article › peer-review

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.

Original language	English
Pages (from-to)	735-737
Number of pages	3
Journal	IEEE International Symposium on Electromagnetic Compatibility
Volume	2
Publication status	Published - 20 Oct 2003
Externally published	Yes
Event	2003 IEEE Symposium on Electromagnetic Compatibility - Boston, MA, United States Duration: 18 Aug 2003 → 22 Aug 2003

Keywords

Complex exponentials
Data extrapolation
EMC
FDTD
Multiplayer perceptron
Neural networks
Prediction
Time series

ASJC Scopus subject areas

Condensed Matter Physics
Electrical and Electronic Engineering

Cite this

@article{666da522b31e4a00a3679628d9109b6b,

title = "FDTD data extrapolation using multilayer perceptron (MLP)",

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 = "Complex exponentials, Data extrapolation, EMC, FDTD, Multiplayer perceptron, Neural networks, Prediction, Time series",

author = "H{\"u}seyin G{\"o}ksu and Pommerenke, {David J.} and Wunsch, {Donald C.}",

year = "2003",

month = oct,

day = "20",

language = "English",

volume = "2",

pages = "735--737",

journal = "IEEE International Symposium on Electromagnetic Compatibility",

issn = "0190-1494",

publisher = "Institute of Electrical and Electronics Engineers",

note = "2003 IEEE Symposium on Electromagnetic Compatibility ; Conference date: 18-08-2003 Through 22-08-2003",

}

TY - JOUR

T1 - FDTD data extrapolation using multilayer perceptron (MLP)

AU - Göksu, Hüseyin

AU - Pommerenke, David J.

AU - Wunsch, Donald C.

PY - 2003/10/20

Y1 - 2003/10/20

N2 - 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.

AB - 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.

KW - Complex exponentials

KW - Data extrapolation

KW - EMC

KW - FDTD

KW - Multiplayer perceptron

KW - Neural networks

KW - Prediction

KW - Time series

UR - http://www.scopus.com/inward/record.url?scp=0141905768&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:0141905768

SN - 0190-1494

VL - 2

SP - 735

EP - 737

JO - IEEE International Symposium on Electromagnetic Compatibility

JF - IEEE International Symposium on Electromagnetic Compatibility

T2 - 2003 IEEE Symposium on Electromagnetic Compatibility

Y2 - 18 August 2003 through 22 August 2003

ER -

FDTD data extrapolation using multilayer perceptron (MLP)

Abstract

Keywords

ASJC Scopus subject areas

Other files and links

Cite this