Combination of finite impulse response neural network technique with FDTD method for simulation of electromagnetic problems

Electronics Letters

Volumn 32, Issue 12, 1996, Pages 1112-1113

  Wu, C ^a   Navarro, A ^b   Litva, J ^a  

^a MCMASTER UNIVERSITY   (Canada)

^b UNIVERSITY OF VALENCIA   (Spain)

Author keywords

Finite difference time domain method; Neural networks

Indexed keywords

ALGORITHMS; COMPUTER SIMULATION; CONVERGENCE OF NUMERICAL METHODS; DIGITAL FILTERS; ELECTROMAGNETIC FIELD THEORY; FINITE DIFFERENCE METHOD; ITERATIVE METHODS; MATHEMATICAL MODELS; RECTANGULAR WAVEGUIDES; TIME DOMAIN ANALYSIS; VECTORS;

AUTOREGRESSIVE TOTAL LEAST SQUARES; FINITE DIFFERENCE TIME DOMAIN METHOD; FINITE IMPULSE RESPONSE NEURAL NETWORK TECHNIQUE; WAVEGUIDE FILTER;

FEEDFORWARD NEURAL NETWORKS;

EID: 0030572271     PISSN: 00135194     EISSN: None     Source Type: Journal    
DOI: 10.1049/el:19960691     Document Type: Article

References (4)

1. HAYKIN, S.: 'Neural network - A comprehensive foundation' (McMillan 1994)
2. WAN, E. A.: 'Finite impulse response neural network and its time series prediction applications'. PhD dissertation, McMaster University, 1993
3. TAFLOVE, A., and UMASHANKAR, K.R.: 'Review of FDTD numerical modeling of electromagnetic wave scattering and radar cross section', Proc. IEEE, 1989, 77, pp. 682-699
4. WU, C.: 'An application of autoregressive process to speed-up finite difference time domain method for solving electromagnetic problems'. Course project for EE731, McMaster University, December 1994