Indian Journal of Science and Technology
DOI: 10.17485/ijst/2014/v7i5.5
Year: 2014, Volume: 7, Issue: 5, Pages: 622–627
Original Article
Z. Goudarzi1 and A. Abedian2*
1 Department of Computer Engineering, University of Isfahan, Isfahan, Iran.
2 Department of Mechanical Engineering, Daneshpajoohan Higher Education Institute, Isfahan, Iran; abedian@me.iut.ac.ir
This paper deals with a comparative performance of traditional elements and high order elements, making use of their formulation as vectors (or patterns) in a multi-dimensional space of proper attributes. The classification can be carried out with the help a self-organizing feature map of Kohonen with the patterns corresponding to the input space. The work makes use of the four attributes: its number of nodes, number of Lejendre terms, maximum degree of interpolation polynomials and number of degrees of freedom per node, though a more general characterization is also possible.
Keywords: Classification, Finite Elements, Kohonen’s Network, Neural Networks
Subscribe now for latest articles and news.