Parameter Magnitude-Based Information Criterion in Identification of Discrete-Time Dynamic System / Md Fahmi Abd Samad and Abdul Rahman Mohd Nasir

Abd Samad, Md Fahmi and Mohd Nasir, Abdul Rahman (2017) Parameter Magnitude-Based Information Criterion in Identification of Discrete-Time Dynamic System / Md Fahmi Abd Samad and Abdul Rahman Mohd Nasir. Journal of Mechanical Engineering (JMechE), SI 4 (1). pp. 119-128. ISSN 18235514

Download

[thumbnail of 39242.pdf] Text
39242.pdf

Download (509kB)

Abstract

Information criterion is an important factor for model structure selection in system identification. It is used to determine the optimality of a particular model structure with the aim of selecting an adequate model. A good information criterion not only evaluate predictive accuracy but also the parsimony of model. There are many information criterions those are widely used such as Akaike information criterion (AIC), corrected Akaike information criterion (AICc) and Bayesian information criterion (BIC). This paper introduces a new parameter-magnitude based information criterion (PMIC2) for identification of linear and non-linear discrete time model. It presents a study on comparison between AIC, AICc, BIC and PMIC2 in selecting the correct model structure for simulated models. This shall be tested using computational software on a number of simulated systems in the form of discrete-time models of various lag orders and number of terms/variables. It is shown that PMIC2 performed in optimum model structure selection better than AIC, AICc and BIC.

Metadata

Item Type: Article
Creators:
Creators
Email
Abd Samad, Md Fahmi
UNSPECIFIED
Mohd Nasir, Abdul Rahman
UNSPECIFIED
Subjects: T Technology > TJ Mechanical engineering and machinery
T Technology > TJ Mechanical engineering and machinery > Mechanics applied to machinery. Dynamics
Divisions: Universiti Teknologi MARA, Shah Alam > Faculty of Mechanical Engineering
Journal or Publication Title: Journal of Mechanical Engineering (JMechE)
UiTM Journal Collections: UiTM Journal > Journal of Mechanical Engineering (JMechE)
ISSN: 18235514
Volume: SI 4
Number: 1
Page Range: pp. 119-128
Item ID: 39242
Uncontrolled Keywords: Akaike Information Criterion, Bayesian Information Criterion, Model Structure Selection, Parameter Magnitude-Based Information Criterion
URI: https://ir.uitm.edu.my/id/eprint/39242

ID Number

39242

Indexing


View in Google Scholar

Edit Item
Edit Item