Browsing by Title
-
Ševaković, Marija (Beograd , 2020)[more][less]
-
Nikolić, Danka (Beograd , 2016)[more][less]
-
Smirnova, A. A.; Moiseev, A. V.; Afanasiev, V. L. (Nenad Milovanović & Milan S. Dimitrijević, Astronomical Observatory, Belgrade , 2007)[more][less]
-
Kamberi, Qerim (Priština)[more][less]
-
Nuri Hadžić, Osman (Beograd , 1931)[more][less]
-
Khan, A. S.; Kazmi, R.; Farrokh, B. (ELSEVIER , 2007)[more][less]
-
Slavcheva-Mihova, L.; Mihov, B.; Petrov, G. T.; Kopchev, V. (Heron Press Ltd, Sofia , 2007)[more][less]
-
Babović, Vukota (Astron. Obs. Belgrade , 1997)[more][less]
-
Tomanović, Jelena (Beograd , 2012)[more][less]
URI: http://hdl.handle.net/123456789/2208 Files in this item: 1
JelenaTomanovicMasterRad.pdf ( 611.6Kb ) -
Smiljanić - Japundža, Dubravka (MATEMATIČKI FAKULTET UNIVERZITETA U BEOGRADU , 2009)[more][less]
URI: http://hdl.handle.net/123456789/1882 Files in this item: 1
multimedijalna sredstva.pdf ( 328.9Kb ) -
Festa, Mirsad; Rizvić, Selma (Sarajevo , 2010)[more][less]
URI: http://hdl.handle.net/123456789/2027 Files in this item: 1
010%20FESTA%20RIZVIC.pdf ( 450.0Kb ) -
Tanasijević, Ivana (Beograd , 2020)[more][less]
Abstract: The motivation for writing this doctoral dissertation is a multimedia col-lection that is the result of many years of field research conducted by researchers from the Institute for Balkan studies of the Serbian Academy of Sciences and Arts. The collection consists of materials in the form of recorded interviews, various recorded customs, associated textual descriptions (protocols) and numerous other documents.The subject of research of this dissertation is the study of possibilities and the development of new methods that could be used as a starting point in solving the problem of managing the intangible cultural heritage of the Balkans. The subtasksthat emerge in this endeavor are the development of adequate design and implemen-tation of a multimedia database of intangible cultural heritage that would meet the needs of different types of users, automatic semantic annotation of protocols using natural language processing methods, as a basis for semi-automatic annotation of the multimedia collection, and successful search by metadata which comply with the CIDOC CRM standard, study of additional search possibilities of this collection in order to gain new knowledge, as well as development of selected methods.The main problem with the available methods is that there is still not enough developed infrastructure in the context of natural language processing, organization and management in the field of cultural heritage in the Balkans and especially for the Serbian language, which could be effectively used to solve the proposed problem.There is thus a strong need to develop methods to reach an appropriate solution.For the semi-automatic annotation of multimedia materials, automatic semantic annotation of the protocols associated with the materials was used. It was carriedout by methods of information extraction, recognition of named entities and topicextraction, using rule-based techniques with the help of additional resources suchas electronic dictionaries, thesauri and vocabularies from a specific domain.To classify textual protocols in relation to the topic, research was conducted onmethods that can be used to solve the problem of classifying texts in the Serbianlanguage, and a method was offered that is adapted to the specific domain beingprocessed (intangible cultural heritage), to the specific problems being solved (clas-sification of protocols in relation to the topic) and to the Serbian language, as one of the morphologically rich languages.To work with spatial data, a spatial model has been developed that is suitable for displaying results on a map, as well as for creating spatial queries through an interactive graphical display of a map of locations.The results of experiments conducted on the developed methods show that the use of a rule-based approach in combination with additional language resources an dwith putting in a reasonable amount of effort gives very good results for the task of information extraction. An F measure of 0.87 was reached for the extraction of named entities, while an F measure of 0.90 was reached for the extraction of topics,which is in the range of measures from published research from similar problem sand domains.The results of the text classification indicate that the selected statistical methods of machine learning in their basic form when applied to the protocols, although generally successful, give a bad F measure, 0.44, while significant improvement is achieved with the use of semantic techniques, in which case an F measure of 0.88 is reached.Some of the results presented in this dissertation are contained in the papers[266], [265], [94], [264], [267], which have been published or accepted for publication.The conclusion drawn from the research is that to solve the given problem it is necessary to engage experts from several fields, that the needs of different groups of users are complex, which complicates the task of organizing and managing them ultimedia collection, that the domain of cultural heritage is very rich in semantics,that context plays a major role in the tasks of information extraction and text classification, and finally that for these tasks the developed rule-based methods of natural language processing as well as statistical techniques of machine learning prove to be successful. URI: http://hdl.handle.net/123456789/5093 Files in this item: 1
IvanaTanasijevicdr.pdf ( 4.674Mb ) -
Jovanović, Sonja (Beograd , 2021)[more][less]
-
Dechev, Momchil; Koleva, Kostadinka; Duchlev, Peter; Petrov, Nikola (Beograd , 2015)[more][less]
-
Gavrilović, Ljiljana; Stojanović, Marko (Muzejsko društvo Srbije , 2008)[more][less]
URI: http://hdl.handle.net/123456789/980 Files in this item: 1
-
Džamić, Dušan (Beograd , 2021)[more][less]
Abstract: The theory of complex networks has proven to be very important inthe study of the characteristics and structure of various complex systems. In thelast two decades, a large number of researches have been directed towards thedevelopment of methods for clustering in complex networks. In 2012, Center forDiscrete Mathematics and Theoretical Computer Science (DIMACS), which is awell-known consortium of prestigious academic institutions (Rutgers University,Princeton, Colombia) and research laboratories (Microsoft, IBM, AT & T, NEC),included the problem of clustering in complex networks on the list of the mostimportant problems and challenges in computer science. Clustering in complexnetworks can be applied in a variety of contexts to achieve different goals, andtherefore, there is no generally accepted definition of a cluster. For this reason,different approaches are used in developing clustering methods. An approach thathas attracted the most attention of researchers involves two subproblems: defininga function to determine the quality of a partition and constructing methods to finda partition that has the maximum value of the defined quality function. In thisapproach, the problem of clustering is formulated as the problem of combinatorialoptimization and various methods of mathematical optimization can be used tosolve it. One of the most commonly used quality function is the modularity.Clustering by modularity maximization, i.e., finding a partition with the max-imum value of modularity, is NP-hard problem. Thus, only heuristic algorithmsare suitable of processing large datasets. In this dissertation, a novel method formodularity maximization based on the variable neighborhood search heuristic isproposed. For the purpose of efficient application in large-scale complex networks,a procedure for decomposition of the problem into smaller subproblems is devel-oped. In addition, a mechanism for overcoming local maxima of modularity isimproved using criteria for occasional acceptance of solution which is worse thanthe current one. DIMACS instances are used to test the proposed method, and theobtained results are compared with the best ones presented in the literature, ob-tained by two methods developed in DIMACS implementation challenge in 2012.In addition, the obtained results are compared with the results of six methodsdeveloped after 2012, from the literature. A comparative analysis of the resultsshows that the proposed method outperforms the existing methods for modularitymaximization and improves the best known solutions on 9 out of 13 hard instances. Clustering by modularity maximization is not suitable for detecting small clus-ters in large networks. For this reason, a new function for measuring the qualityof a partition has been proposed in the dissertation. Through three theorems, itis shown that the new measure, called E-function, has the potential to identifyclusters in the network and overcome limits of modularity. For testing the pro-posed E-function and comparison with the modularity function, a generic variableneighborhood method is developed to optimize the considered quality function.Computational experiments are performed on generated and real instances fromthe literature for which the correct division into clusters is known. The resultsshow that the expected clusters can be identified, both on artificial and real in-stances, by maximizing the E-function. URI: http://hdl.handle.net/123456789/5214 Files in this item: 1
teza_dzamic.pdf ( 3.074Mb ) -
Gorbatov, Boris (SUVREMENA NAKLADA ZAGREB , 1945)[more][less]
-
Marinković, Vuk (Beograd , 1851)[more][less]
URI: http://hdl.handle.net/123456789/4495 Files in this item: 1
VukMarinkovic_NacelaFizike_Knjiga1_1851_a.pdf ( 119.3Mb ) -
Marinković, Vuk (Beograd , 1851)[more][less]
URI: http://hdl.handle.net/123456789/4496 Files in this item: 1
VukMarinkovic_NacelaFizike_Knjiga2_1851_a.pdf ( 68.89Mb ) -
Holcendorf, Franc (Beograd , 1899)[more][less]