Welcome!
To use the personalized features of this site, please log in or register.
If you have forgotten your username or password, we can help.
My Menu
Saved Items

89. Performance of MGMDH Network on Structural Piecewise System Identification

Ali K. SetoodehniaContact Information and Hong LiContact Information

(4)  Computer Science, McNeese State University, Lake Charles, Louisiana, 70609
(5)  Conoco, Lake Charles, Louisiana, 70601
Abstract
This paper will address the capability of the Modified Group Method of Data Handling (MGMDH) for continuous and piecewise continuous approximation functions. The MGMDH is used to construct the mathematical structure of dynamic system, which is observable only from its input and output with large number of input variables. The paper present the theory and simulation results for estimation of piecewise continuous polynomial function. The output performance evaluation is included.

Keywords  GMDH - Modeling - Self-Organized Network - Multi-Layer Perceptron - Prediction - Identification


Contact Information Ali K. Setoodehnia
Email: setoodeh@mail.mcneese.edu

Contact Information Hong Li
Email: Li.Hong@usa.conoco.com
Fulltext Preview (Small, Large)
Image of the first page of the fulltext

References secured to subscribers.



Export this chapter
Export this chapter as RIS | Text
 
Remote Address: 38.107.191.107 • Server: mpweb18
HTTP User Agent: CCBot/1.0 (+http://www.commoncrawl.org/bot.html)