Skip to main content

Index Geophysics

Methods of Artificial Intelligence used for Transforming a System of Coordinates

Item

Title (Dublin Core)

eng Methods of Artificial Intelligence used for Transforming a System of Coordinates
hrv Metode umjetne inteligencije korištene za transformaciju koordinatnog sustava

Description (Dublin Core)

eng The article discusses the problem of transformation in the form of the function f:R2>R2 as dependence between the coordinates [x,y] of the original system and the coordinates [X,Y] of the secondary system. The task of the transformation of [X,Y]=f(x,y) technically understood as the transformation of a system of coordinates has been solved by means of the feed-forward neural networks of the sigmoidal type, radial neural networks, recurrent cascade neural networks, and neuro-fuzzy systems with the use of the Takagi-Sugeno-Kang model. The numerical procedures applied make it possible to obtain a level of accuracy of the task equivalent to the cartographic accuracy of pictures in the Spatial Information Systems.
hrv Članak razmatra problem transformacije u obliku funkcije f:R2>R2 kao ovisnosti između koordinata prvobitnog sustava [x,y] i koordinata sekundarnog sustava [X,Y]. Zadatak transformacije [X,Y]=f(x,y), koja tehnički znači transformaciju koordinatnog sustava, riješen je uz pomoć feed-forward neuronskih mreža sigmoidalne vrste, radijalnih neuronskih mreža, povratnih ukomponiranih neuronskih mreža i neuro-fuzzy sustava koristeći model Takagi-Sugeno-Kang. Primijenjeni numerički postupci omogućavaju dobivanje razine točnosti zadatka koja je jednaka kartografskoj točnosti snimaka Prostornih informacijskih sustava.

Creator (Dublin Core)

Gil, Józef
Mrówczyńska, Maria

Subject (Dublin Core)

eng feed-forward neural networks; fuzzy networks; coordinate transformation; geodesy
hrv feed-forward neuronske mreže; fuzzy mreže; transformacija koordinata; geodezija

Publisher (Dublin Core)

Croatian geodetic society

Date (Dublin Core)

2012

Type (Dublin Core)

text
info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion

Format (Dublin Core)

application/pdf

Identifier (Dublin Core)

https://hrcak.srce.hr/102917
eng https://hrcak.srce.hr/file/151467

Source (Dublin Core)

Geodetski list
ISSN 0016-710X (Print)
ISSN 1849-0611 (Online)
Volume 66 (89)
Issue 4

Language (Dublin Core)

eng

Rights (Dublin Core)

info:eu-repo/semantics/openAccess
Full-text papers can be used for personal or educational purposes only. Authors' and publisher's copyrights must be acknowledged.