Title
Optimalno prepoznavanje i lokalizacija izvora zvuka primenom metoda veštačke inteligencije
Creator
Kovandžić, Marko 1974-
Copyright date
2020
Object Links
Select license
Autorstvo 3.0 Srbija (CC BY 3.0)
License description
Dozvoljavate umnožavanje, distribuciju i javno saopštavanje dela, i prerade, ako se navede ime autora na način odredjen od strane autora ili davaoca licence, čak i u komercijalne svrhe. Ovo je najslobodnija od svih licenci. Osnovni opis Licence: http://creativecommons.org/licenses/by/3.0/rs/deed.sr_LATN Sadržaj ugovora u celini: http://creativecommons.org/licenses/by/3.0/rs/legalcode.sr-Latn
Language
Serbian
Cobiss-ID
Theses Type
Doktorska disertacija
description
Datum odbrane: 14.02.2020.
Other responsibilities
mentor
Nikolić, Vlastimir 1954-
član komisije
Antić, Dragan 1963-
član komisije
Ćojbašić, Žarko 1968-
član komisije
Simonović, Miloš 1973-
član komisije
Ćirić, Ivan 1980-
Academic Expertise
Prirodno-matematičke nauke
Academic Title
-
University
Univerzitet u Nišu
Faculty
Mašinski fakultet
Group
Katedra za proizvodno-informacione tehnologije i menadžment
Alternative title
Optimal recognition and localization of acoustic source using artificial intelligence methods
Publisher
[M. N. Kovandžić]
Format
[17], 165 listova
description
Biografija autora: list 165;
Bibliografija: listovi 154-164.
description
Automatic control and robotics
Abstract (en)
Тhe subject of the thesis is sound source recognition and sound source localization, in real
conditions, using artificial intelligence algorithms. The main goal is optimal procedure for sound
source observation using artificial neural networks for signal procesing, because of their extreme
procesing speed. It has to provide implementation of hybrid system capable to recognize and
locate sound source in the presence of disturbances. For the training and the testing of neural
networks two sets of data are provided, from two different experiments, and to increase
robustness genetic algorithm is applied. The results of the investigation will contribute the
existing body of acoustic observation knowledge.
Authors Key words
Veštačka inteligencija, Akustična opservacija, Akustično prepoznavanje, Prepoznavanje
obrazaca, Neuronske mreže, Evolucioni račun
Authors Key words
Artificial intelligence, Acoustic perception, Acoustic recognition, Pattern recognition, Neural
networks, Evolutionary algorithm
Classification
007.52:519.8]:004.8.032.26:534.88(043.3)
Subject
T 125
Type
Tekst
Abstract (en)
Тhe subject of the thesis is sound source recognition and sound source localization, in real
conditions, using artificial intelligence algorithms. The main goal is optimal procedure for sound
source observation using artificial neural networks for signal procesing, because of their extreme
procesing speed. It has to provide implementation of hybrid system capable to recognize and
locate sound source in the presence of disturbances. For the training and the testing of neural
networks two sets of data are provided, from two different experiments, and to increase
robustness genetic algorithm is applied. The results of the investigation will contribute the
existing body of acoustic observation knowledge.
“Data exchange” service offers individual users metadata transfer in several different formats. Citation formats are offered for transfers in texts as for the transfer into internet pages. Citation formats include permanent links that guarantee access to cited sources. For use are commonly structured metadata schemes : Dublin Core xml and ETUB-MS xml, local adaptation of international ETD-MS scheme intended for use in academic documents.