Library Subscription: Guest
Home Begell Digital Library eBooks Journals References & Proceedings Research Collections
Journal of Automation and Information Sciences

Impact factor: 0.040

ISSN Print: 1064-2315
ISSN Online: 2163-9337

You have access to:
Volume 46, 2014 Volume 45, 2013 Volume 44, 2012 Volume 43, 2011 Volume 42, 2010 Volume 41, 2009 Volume 40, 2008 Volume 39, 2007 Volume 38, 2006 Volume 37, 2005 Volume 36, 2004 Volume 35, 2003 Volume 34, 2002 Volume 33, 2001 Volume 32, 2000 Volume 31, 1999 Volume 30, 1998 Volume 29, 1997 Volume 28, 1996

Journal of Automation and Information Sciences

DOI: 10.1615/JAutomatInfScien.v35.i4.10
10 pages

Determination of Regularities of Ions and Surface Interaction by Combinatorial GMDH Algorithm

Grigoriy A. Ivakhnenko
"Information Recourses Inc." company, London, Great Britain
Evgeniya A. Savchenko
International Research and Training Center of Information Technologies and Systems of National Academy of Sciences of Ukraine and Ministry of Education and Science of Ukraine, Kyiv, Ukraine
Alexey G. Ivakhnenko
International Research and Training Center of Information Technlogies and Systems of National Academy of Sciences of Ukraine and Ministry of Education and Science of Ukraine, Kyiv
Andrey B. Nadiradze
Moscow Aviation Institute, Russia
Andrey 0. Rogov
Moscow State Academy of Light Chemical Technology, Russia

ABSTRACT

The example of application of a Group method data handling algorithm to detect the models of dependencies in data sample has been demonstrated. The algorithm was applied to detecting these dependencies by sampling the data of observations of ions and surface interaction. The account of secondary arguments enabled us to decrease the model (bias), i.e., to obtain more adequate model of approximation of the dependence searched for. For polynomial functions the algorithms of selecting the model optimal with respect to the external criterion and test of location were developed. These algorithms were developed by comparing the two versions of computations. In the first version at first a small set of the most accurate models was found, then one the most unbiased model was selected from them. In the second version one the most precise model was chosen from the set of the least biased models.