Email this article Neural network algorithm of spatial relief data organization
- Authors: Boronnikov D.A1, Pantiukhin D.V2, Danko S.V2
-
Affiliations:
- Moscow State University of Mechanical Engineering (MAMI)
- Moscow Institute of Physics and Technology (State University)
- Issue: Vol 7, No 3-1 (2013)
- Pages: 157-164
- Section: Articles
- URL: https://journals.rcsi.science/2074-0530/article/view/68086
- DOI: https://doi.org/10.17816/2074-0530-68086
- ID: 68086
Cite item
Full Text
Abstract
Neural network algorithm of spatial relief data organization and its implementation in Matlab language are developed. Experimental studies on the example of terrain data of the Ozerniy mining and processing plant showed that the neural network has successfully memorized and generalize input information about the terrain (110149 spatial points ) with an error less than 0.5 meters. Compression ratio of the input data is about 12 to one.
Full Text
##article.viewOnOriginalSite##About the authors
D. A Boronnikov
Moscow State University of Mechanical Engineering (MAMI)
Email: unir@mami.ru
+7 (495) 223-05-23, ext. 1510
D. V Pantiukhin
Moscow Institute of Physics and Technology (State University)
Email: unir@mami.ru
+7 (495) 223-05-23, ext. 1510
S. V Danko
Moscow Institute of Physics and Technology (State University)
Email: unir@mami.ru
+7 (495) 223-05-23, ext. 1510
References
- M.F. Moller, "A scaled conjugate gradient algorithm for fast supervised learning," Neural Networks, Vol. 6, 1993, pp. 525–533.
- T.P. Vogl, J.K. Mangis, A.K. Rigler, W.T. Zink, and D.L. Alkon, "Accelerating the convergence of the backpropagation method," Biological Cybernetics, Vol. 59, 1988, pp. 257–263.
Supplementary files
