RUS
|
Information
The project goal is to popularize ideas of applying operation
methods of natural mechanisms in finding solutions to forecasting,
optimization, decision making and decision support problems
Contacts
Vitaliy Snytyuk
Postal Address:
Cherkasy State Technological University,
Shevchenko Avenue 460,
Cherkasy, 18006, Ukraine
E-mail:
snytyuk@gmail.com
Tel: +380(472)730235 +380(50)3131342
Fax: +380(472)710089
|
|
|
Papers
|
-
A. Zlatkin, V. Snytyuk.
«Composite method of evolutionary modelling in the design tasks».
In the paper the composite method for the optimum values of the input
parameters definition is offered. On the biocybernetic methods basis:
neural nets and genetic algorithms the synthetic procedure of prediction
of a designing system effectiveness, without a construction of analytical
functions is developed.
Download
(PDF, 88 Kb).
-
V. Snytyuk.
«Neural network techniques of indeterminacy minimization in nonlinear identification tasks».
In the paper problem of entropy minimization is considered which is present
at an initial information necessary for a solution of identification task.
The procedure of redundancy diminution of datas based on a composition of
techniques of principal components, "whitening" of inputs and artificial
neural nets using is offered. The obtained solutions specify effectiveness
of such procedure, at the expense of time minimization of nets learning and
magnification of solutions exactitude.
Download
(PDF, 135 Kb).
New!
-
V. Snytyuk.
«Evolutionary clustering of complex systems and processes».
In a paper the method of complex systems and processes
clustering based use of genetic algorithm is offered.
The aspects of its realization and shaping of fitness-function
are considered. The solution of clustering task of Ukraine
areas on socio-economic indexes is represented and comparative
analysis with outcomes of classical methods is realized.
Download
(PDF, 92 Kb).
New!
-
V. Snytyuk, O. Dghulay
«Evolutionary technique of shorter route determination of fire brigade following to fire place with the optimized space of search».
In this paper the technique of shorter route determination
of fire engine to the fire place on time minimization criterion
with the use of evolutionary modeling is offered. The algorithm
of its realization on the base of complete and optimized space
of search of possible decisions is explored. The aspects of goal
function forming and program realization of method having a special
purpose are considered. Experimental verification is executed and
the results of comparative analysis with the expert conclusions are considered.
Download
(PDF, 166 Kb).
New!
-
Vitaliy E. Snytyuk, Sergiy O. Govorukhin
«Evolutionary technique for filling data gaps in outcome variable vales».
In this paper the analysis of methods for renewal data gaps
in tables of among the values of outcome variable in supposition
about existence of its linear dependence from input factors is executed.
For the decision of the indicated problem a technique, integrating evolutionary
modeling, neural networks technologies and application of external criterion, is offered.
Download
(PDF, Kb).
New!
-
Vitaliy E. Snytyuk.
«Neuro-Evolutionary Techniques for Filling Data Gaps».
This paper provides an analysis of models and methods
of data gap filling and offers an evolutionary method
based on the composition of a neural network and genetic
algorithm. The technology for filling data gaps does not
require to observe the limitations related to linear models,
parameter distribution, etc.
Download
(PDF, 92 Kb).
|
|
Abstracts
|
-
V. Snytyuk.
«Identification of goal function of a special type by neural nets technique».
In thesis an effectiveness of neural networks technique
using to realizing structural and parametrical identification of
goal function wich takes non-numerical values is analysed.
Download
(PDF, 26 Kb).
-
V. Snytyuk.
«Prognostizieren von Umweltverschmutzungsprozessen».
Download
(PDF, 21 Kb).
|
|
|
News
|
- New paper on this page (15.12.08)
|
|
Software
|
- Group method of data handling based program-algorithmic system information and demo-version
here
- Brandon method based program-algorithmic system information and demo-version
here
|
|