Zobrazeno 1 - 10
of 18
pro vyhledávání: '"Miloš Racković"'
Autor:
Miloš Racković, Nemanja Milošević
Publikováno v:
Neural Computing and Applications. 33:7593-7602
In recent times, convolutional neural networks became an irreplaceable tool in many different machine learning applications, especially in image classification. On the other hand, new research about robustness and susceptibility of these models to di
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fdf684ad18570327e42f939a4c5ea256
https://doi.org/10.1007/s00521-020-05503-4
https://doi.org/10.1007/s00521-020-05503-4
Autor:
Nemanja Milošević, Miloš Racković
Publikováno v:
Neural Network World. 29:221-234
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5ee4593ba6ffc7652c276e68834ee4e0
https://doi.org/10.14311/nnw.2019.29.015
https://doi.org/10.14311/nnw.2019.29.015
Publikováno v:
Advances in Electrical and Computer Engineering, Vol 18, Iss 3, Pp 3-8 (2018)
© 2018 University of Suceava. Scientific computing community has been in close connection with high performance computing (HPC), which has been privilege of a limited group of scientists. Recently, with rapid development of Graphics Processing Units
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2e9bf126db87ba955b14aa4ae72b59b8
https://doaj.org/article/43ba0c3474d441e88780c630ee19f42b
https://doaj.org/article/43ba0c3474d441e88780c630ee19f42b
Autor:
Miloš Racković, Predrag Pecev
Publikováno v:
Computer Science and Information Systems. 14:467-490
The subject of research presented in this paper is to model a neural network structure and appropriate training algorithm that is most suited for multiple dependent time series prediction / deduction. The basic idea is to take advantage of neural net
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ca84e80632ec5d2579d9d91282a7a794
https://doi.org/10.2298/csis150815004p
https://doi.org/10.2298/csis150815004p
Publikováno v:
Multimedia Tools and Applications. 75:16389-16416
This paper presents us with an automatic prediction and analysis of basketball referees movement which is useful for educational software. Such software would be very beneficial in training the young basketball referees. The paper proposes that the m
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1f1dd31b4a3ad5558cc7bbd3f9a75936
https://doi.org/10.1007/s11042-015-2938-1
https://doi.org/10.1007/s11042-015-2938-1
Publikováno v:
Journal of Intelligent & Fuzzy Systems. 26:303-316
In real life, as opposed to virtual, most information comes in the form of imprecise or incomplete values. XML technology has made great progress in the field of storage and data transfer. We developed XML extension which combines indefiniteness in t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::18549e88acc58ed5f008d938b46efa4a
https://doi.org/10.3233/ifs-120739
https://doi.org/10.3233/ifs-120739
Publikováno v:
Multimedia Tools and Applications. 72(3):2741-2767
This paper presents us with a framework for the automatic player position detection (APPD) in the game of basketball. Court players are detected in the images broadcasted via television stations. In them, at any point of time, the view is from only o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0f24fb358f0419180509a395394dd0ea
https://www.cris.uns.ac.rs/record.jsf?recordId=89982&source=OpenAIRE&language=en
https://www.cris.uns.ac.rs/record.jsf?recordId=89982&source=OpenAIRE&language=en
Publikováno v:
Knowledge-Based Systems. 38:62-73
Many years of research related to fuzzy logic and fuzzy set theory extensions to relational databases have not lead to stable implementations, standardized languages or fuzzy relational database application development tools and methods. The main goa
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bd5a10777ac420e803cda2a0de88dc2d
https://doi.org/10.1016/j.knosys.2012.01.017
https://doi.org/10.1016/j.knosys.2012.01.017
Publikováno v:
Advances in Electrical and Computer Engineering, Vol 12, Iss 1, Pp 51-56 (2012)
The Lattice Boltzmann method (LBM) has become an alternative method for computational fluid dynamics with a wide range of applications. Besides its numerical stability and accuracy, one of the major advantages of LBM is its relatively easy paralleliz
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9957f3f29ca31335955630ccd1827f8d
https://doi.org/10.4316/aece.2012.01009
https://doi.org/10.4316/aece.2012.01009
Publikováno v:
Computer Science and Information Systems. 8:27-40
In this paper we examine the possibilities to extend the relational data model with the mechanisms that can handle imprecise, uncertain and inconsistent attribute values using fuzzy logic and fuzzy sets. We present a fuzzy relational data model which
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c07635a48b33c4be9175f83b039b1009
https://doi.org/10.2298/csis100102010s
https://doi.org/10.2298/csis100102010s