Development of a methodology for the use of neural networks and simulation modeling in system design

Mahdi Nasereddin, Mansooreh Mollaghasemi

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

In this paper the use of metamodels to approximate the reverse of simulation models is explored. This purpose of the approach is to achieve the opposite of what a simulation model can do. That is, given a set of desired performance measures, the metamodels output a design to meet management goals. The performance of several neural network simulation metamodels was compared to the performance of a stepwise regression metamodel in terms of accuracy. It was found that in most cases, neural network metamodels outperform the regression metamodel. It was also found that a modular neural network performed the best in terms of minimizing the error of prediction.

Original languageEnglish (US)
Pages (from-to)537-542
Number of pages6
JournalWinter Simulation Conference Proceedings
Volume1
StatePublished - 1999

Fingerprint

Network Modeling
Metamodel
System Design
Systems analysis
Neural Networks
Neural networks
Methodology
Computer simulation
Simulation
Simulation Model
Modular Neural Networks
Stepwise Regression
Network Simulation
Performance Measures
Reverse
Regression
Prediction
Output

All Science Journal Classification (ASJC) codes

  • Chemical Health and Safety
  • Software
  • Safety, Risk, Reliability and Quality
  • Applied Mathematics
  • Modeling and Simulation

Cite this

@article{e96bb2dfed924175a4975b255c4a4b93,
title = "Development of a methodology for the use of neural networks and simulation modeling in system design",
abstract = "In this paper the use of metamodels to approximate the reverse of simulation models is explored. This purpose of the approach is to achieve the opposite of what a simulation model can do. That is, given a set of desired performance measures, the metamodels output a design to meet management goals. The performance of several neural network simulation metamodels was compared to the performance of a stepwise regression metamodel in terms of accuracy. It was found that in most cases, neural network metamodels outperform the regression metamodel. It was also found that a modular neural network performed the best in terms of minimizing the error of prediction.",
author = "Mahdi Nasereddin and Mansooreh Mollaghasemi",
year = "1999",
language = "English (US)",
volume = "1",
pages = "537--542",
journal = "Winter Simulation Conference Proceedings",
issn = "0275-0708",

}

Development of a methodology for the use of neural networks and simulation modeling in system design. / Nasereddin, Mahdi; Mollaghasemi, Mansooreh.

In: Winter Simulation Conference Proceedings, Vol. 1, 1999, p. 537-542.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Development of a methodology for the use of neural networks and simulation modeling in system design

AU - Nasereddin, Mahdi

AU - Mollaghasemi, Mansooreh

PY - 1999

Y1 - 1999

N2 - In this paper the use of metamodels to approximate the reverse of simulation models is explored. This purpose of the approach is to achieve the opposite of what a simulation model can do. That is, given a set of desired performance measures, the metamodels output a design to meet management goals. The performance of several neural network simulation metamodels was compared to the performance of a stepwise regression metamodel in terms of accuracy. It was found that in most cases, neural network metamodels outperform the regression metamodel. It was also found that a modular neural network performed the best in terms of minimizing the error of prediction.

AB - In this paper the use of metamodels to approximate the reverse of simulation models is explored. This purpose of the approach is to achieve the opposite of what a simulation model can do. That is, given a set of desired performance measures, the metamodels output a design to meet management goals. The performance of several neural network simulation metamodels was compared to the performance of a stepwise regression metamodel in terms of accuracy. It was found that in most cases, neural network metamodels outperform the regression metamodel. It was also found that a modular neural network performed the best in terms of minimizing the error of prediction.

UR - http://www.scopus.com/inward/record.url?scp=0033351020&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0033351020&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0033351020

VL - 1

SP - 537

EP - 542

JO - Winter Simulation Conference Proceedings

JF - Winter Simulation Conference Proceedings

SN - 0275-0708

ER -