Earthquake engineering problems in parallel neuro environment

Authors:
Sanjay Singh;S V Barai
Affiliations:
IBM Global Services India Pvt Ltd., Bangalore, India;Department of Civil Engineering, IIT Kharagpur, Kharagpur, India
Venue:
HiPC'04 Proceedings of the 11th international conference on High Performance Computing
Year:
2004

Citing 2
Cited 0

Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
Neural networks approach and microtremor measurements in estimating peak ground acceleration due to strong motion

Advances in Engineering Software

Quantified Score

Hi-index	0.00

Visualization

Abstract

The aim of the paper is to explore the application of Parallel Neuro Simulator for the generation of artificial earthquake Parallel Neuro Simulator is a neural network code developed on PARAM 10000 using ‘C' language and MPI library subroutines In this study, two artificial neural network (ANN) models have been proposed to replace the auto-regressive moving average (ARMA) model First ANN model substitutes the polynomial model that represents the relation of initial site information and coefficients of polynomial and the second ANN based model substitutes the estimated parameters of the ARMA model Several Indian earthquake records have been used for present study on PARAM 10000 The variation in computational time with increasing number of processors has also been studied.