A speed and accuracy comparative study of metallic collector-up InP/InGaAsP/InGaAs HBT neural model for small signal equivalent circuit parameters extraction

Authors:
Alireza Rastegar Abbasalizadeh;Babak Mohammadian;Pourya Roozban;Ali Yazdipour
Affiliations:
Electrical and Electronic Engineering Department, Islamic AZAD University of Qazvin, Qazvin, Iran;Electrical and Electronic Engineering Department, Islamic AZAD University of Qazvin, Qazvin, Iran;Electrical and Electronic Engineering Department, Islamic AZAD University of Qazvin, Qazvin, Iran;Electrical and Electronic Engineering Department, Islamic AZAD University of Qazvin, Qazvin, Iran
Venue:
ISPRA'09 Proceedings of the 8th WSEAS international conference on Signal processing, robotics and automation
Year:
2009

Citing 3
Cited 0

Applications of neural networks to digital communications: a survey

Signal Processing - Special issue on emerging techniques for communication terminals
Neural Networks for RF and Microwave Design (Book + Neuromodeler Disk)

Neural Networks for RF and Microwave Design (Book + Neuromodeler Disk)
Neural network modeling and identification of nonlinear channelswith memory: algorithms, applications, and analytic models

IEEE Transactions on Signal Processing

Quantified Score

Hi-index	0.01

Visualization

Abstract

In this paper we compare different architectures of Multi-Layer Perception (MLP) and radial basis function (RBFN) neural networks to model metallic collector-up InP/InGaAsP/InGaAs HBT small signal equivalent circuit parameters. It is proved that RBFN provides much better performance than MLP neural networks when it comes to this type of modeling. First, different architectures of MLP networks are created to determine the best topology and training algorithm in term of convergence speed and accuracy. Then, the MLP network, are compared to the best RBFN neural network in terms of speed and accuracy. Simulation results are presented in tables and figures for better understanding. All test and simulations for the MLP and RBFN are done using Matlab's Neural Network toolbox.