Zobrazeno 1 - 10
of 14
pro vyhledávání: '"Dušan Petrovački"'
Publikováno v:
Computers & Geosciences. 35:1620-1630
We present a new method to simultaneously estimate cylindrical object radius (R) and electromagnetic (EM) wave propagation velocity (v) from ground penetrating radar (GPR) data. R estimation methods have been investigated since the middle of the prev
Autor:
Dušan Petrovački, Vladimir Pavlica
Publikováno v:
Fuzzy Sets and Systems. 101:41-47
The paper discusses fuzzy controllers based on fuzzy relational equations in the case when fuzzy controllers' inputs are exact. Godelian implication and minimum function as t-norm are considered. Fuzzy relational equation with sup-t composition resul
Publikováno v:
Neural Networks. 6:583-595
The paper describes changes in the structure (anatomy) of a multilevel neural network which is trained by back-propagation algorithm. A structural change is both a random process and an environment-dependent process. The mechanisms of cell propagatio
Publikováno v:
Geodetski list
Volume 64 (87)
Issue 4
Volume 64 (87)
Issue 4
This paper gives the short review of the Open Geospatial Consortium (OGC) metadata catalogue services that have the key role in geospatial resource discovery in Spatial Data Infrastructures (SDI). The notion of Spatial Data Infrastructure comprises a
Publikováno v:
2008 9th Symposium on Neural Network Applications in Electrical Engineering.
In this paper a new, generalized PSO (GPSO) algorithm is presented and analyzed, both theoretically and empirically. The new optimizer enables direct control over the properties of the search process. In addition, PSO is addressed in conceptually dif
Publikováno v:
2007 8th International Conference on Telecommunications in Modern Satellite, Cable and Broadcasting Services.
The paper presents an overview of the GPS technology, satellite remote sensing technologies, ground remote sensing technologies, and GIS technologies applications to the land use management. The technological method, developed by the Centre for Geo-I
Publikováno v:
6th Seminar on Neural Network Applications in Electrical Engineering.
This paper involves the evolution of neural networks based on parameters gained from a backpropagation training algorithm. The bridging of layers of neural networks is suggested as a new process in this evolutionary process, in addition to cell divis
Autor:
Vladimir Pavlica, Dušan Petrovački
Publikováno v:
Proceedings of the 1998 IEEE International Conference on Control Applications (Cat. No.98CH36104).
The paper presents an application of the PID-fuzzy hybrid controller on two laboratory experimental plants; level and temperature controls are observed. Identified models were used for tuning of the PID controller. In the presence of disturbance, the
Autor:
D.M. Marganović, Dušan Petrovački
Publikováno v:
IFAC Proceedings Volumes. 14:213-218
Use of an approxinate method for solving the minirrum tirre problem for nonlinear heat conduction, when the dependence of thermal conductivity on temperature is of the Friedmann type, is presented. Integral method is used to transform the original op
Autor:
Dušan Petrovački, D.M. Marganović
Publikováno v:
IFAC Proceedings Volumes. 15:325-330
A procedure for the calculation of sensitivity functions for nonlinear optimal control systems is treated in this paper. Determination of sensitivity functions is carried out in two phases by the same programme based on Warner's algorithm. In the fir