Discrete-Time System Identification Based On Novel Information Criterion Using Genetic Algorithm

Abd Samad, Md Fahmi and Mohd Nasir, Abdul Rahman (2017) Discrete-Time System Identification Based On Novel Information Criterion Using Genetic Algorithm. Journal Of Fundamental And Applied Sciences, 9 (7S). pp. 584-599. ISSN 1112-9867

Text 3353-7186-1-PB_MMETIC_JFAS.pdf - Accepted Version Download (499kB)

Abstract

Model structure selection is a problem in system identification which addresses selecting an adequate model i.e. a model that has a good balance between parsimony and accuracy in approximating a dynamic system. Parameter magnitude-based information criterion 2 (PMIC2), as a novel information criterion, is used alongside Akaike information criterion (AIC). Genetic algorithm (GA) as a popular search method, is used for selecting a model structure. The advantage of using GA is in reduction of computational burden. This paper investigates the identification of dynamic system in the form of NARX (Non-linear AutoRegressive with eXogenous input) model based on PMIC2 and AIC using GA. This shall be tested using computational software on a number of simulated systems. As a conclusion, PMIC2 is able to select optimum model structure better than AIC.

Item Type:	Article
Uncontrolled Keywords:	Akaike information criterion; genetic algorithm; model structure selection; parameter-magnitude information criterion; search method
Subjects:	Q Science > Q Science (General) Q Science > QA Mathematics
Divisions:	Faculty of Mechanical Engineering > Department of Structure and Materials
Depositing User:	Mohd Hannif Jamaludin
Date Deposited:	12 Mar 2019 07:40
Last Modified:	06 Sep 2021 17:11
URI:	http://eprints.utem.edu.my/id/eprint/22715
Statistic Details:	View Download Statistic

Actions (login required)

View Item