Zobrazeno 1 - 10
of 28
pro vyhledávání: '"M M Tatur"'
Publikováno v:
Sistemnyj Analiz i Prikladnaâ Informatika, Vol 0, Iss 4, Pp 20-28 (2024)
The classification of methods for land surface image segmentation is presented in the paper. Such approaches as template matching, machine learning and deep neural networks, as well as application of knowledge about analyzed objects are considered. P
Externí odkaz:
https://doaj.org/article/4bcdc4a097d74194a96cbb423568af13
Publikováno v:
Doklady Belorusskogo gosudarstvennogo universiteta informatiki i radioèlektroniki, Vol 20, Iss 5, Pp 5-14 (2022)
The article is devoted to the development of a methodology for estimating the probability of an object auto tracking failure by the mobile robot video system under the influence of external factors caused by random vibrations of the mobile platform.
Externí odkaz:
https://doaj.org/article/2a2cd41b64034dc9850d0bc897c88738
Publikováno v:
Doklady Belorusskogo gosudarstvennogo universiteta informatiki i radioèlektroniki, Vol 0, Iss 6, Pp 62-71 (2019)
In this paper the term of «intelligent data analysis» is discussed, the cloud computing concept is described. The system developed and deployed on the computer cluster by ECM department of BSUIR is shown as an example of the intelligent data analys
Externí odkaz:
https://doaj.org/article/f81875d5d95143cd9b3df09da2e22f5c
Autor:
D. A. Lavnikevich, M. M. Tatur
Publikováno v:
Doklady Belorusskogo gosudarstvennogo universiteta informatiki i radioèlektroniki, Vol 0, Iss 6, Pp 98-101 (2019)
The use of genetic and gradient algorithms for learning classifiers based on Z-model was considered. Combined method of consistent applying this algorithms was offered. The resulting method allows to calculate all model parameters including integer o
Externí odkaz:
https://doaj.org/article/2af30b8970ae4778bae2e7283b5912de
Autor:
M. M. Tatur
Publikováno v:
Doklady Belorusskogo gosudarstvennogo universiteta informatiki i radioèlektroniki, Vol 0, Iss 2, Pp 186-193 (2019)
The new approach to use of key statements of pattern recognition theory for the parallel problem oriented processors design is presented. The tasks of classification, clusterization and association are considered from point of view of parallel proces
Externí odkaz:
https://doaj.org/article/77a57f7607014972ae2b505e3e7dcd7b
Autor:
M. M. Tatur
Publikováno v:
Doklady Belorusskogo gosudarstvennogo universiteta informatiki i radioèlektroniki, Vol 0, Iss 4, Pp 93-97 (2019)
The model of the parallel architecture of problem-oriented processor has been developed. For the purpose of verification of delivered technical solutions the simulation of the architecture on the test cases with cluster GPU using CUDA technology has
Externí odkaz:
https://doaj.org/article/8df8093c3f8b445d99f1c48ab386413b
Autor:
M. M. Tatur
Publikováno v:
Informatika, Vol 0, Iss 1, Pp 39-44 (2016)
An approach to the development of problem-oriented parallel computers for a wide range of tasks of intelligent data processing is described. A high level architecture is shown, where Data Mining algorithms are considered as functional elements and a
Externí odkaz:
https://doaj.org/article/b7057b6a3e8f4c1abd1bda9b70981c06
Publikováno v:
Sistemnyj Analiz i Prikladnaâ Informatika, Vol 0, Iss 4, Pp 40-44 (2016)
The methodology for computer modeling of complex eco-biological models is presented in this paper. It is based on system approach of J. Forrester. Developed methodology is universal for complex ecological and biological systems. Modeling algorithm co
Externí odkaz:
https://doaj.org/article/6aa868f7a080419fa1fd55e95c51a3c7
Autor:
M. M. Tatur
Publikováno v:
Sistemnyj Analiz i Prikladnaâ Informatika, Vol 0, Iss 2, Pp 43-49 (2015)
It is announced an innovative project to create a prototype multirobotic system. A distinctive feature of the project – the maximum use of components and software of domestic production. The mobile robot used the concept of multilevel managemen
Externí odkaz:
https://doaj.org/article/1e46857ea363470da83abce519add059
Publikováno v:
Eurasian Journal of Mathematical and Computer Applications. 7:65-78