Претрага

Упит dcterms_subject_txt:neural networks

116 items

  • WS4LR - a Worksation for Lexical Resources

    Cvetana Krstev, Ranka Stanković, Duško Vitas, Ivan Obradović (2006)
    Lexical Resources, Wordnet, Serbian
    ... Translation Corpora, Dordrecht: Kluwer Academic Publishers Vossen, P. (ed.) (1998) EuroWordNet: A Multilingual Database with Lexical Semantic Networks, Dordrecht: Kluwer Academic Publishers Appendices A. Morphological Dictionary Formats DELAS farmakolog,N12+Hum dokolicyarenxe,N300+VN ...

  • Control of substructure construction of railways in the Republic of Serbia

    Dragan Lukić, Dragoslav Rakić, Irena Basarić Ikodinović (2022)
    Контрола збијености природног тла (у ископу) или збијеног у насипу при изградњи саобраћајница представља један од основних облика контроле квалитета доњег строја. Код изградње брзих саобраћајница (аутопутеви и брза железница) приоритет је постизање високог нивоа контроле извршених радова. У циљу онемогућавања диференцијалног слегања (при изградњи насипа), или промене запремине услед допунског збијања материјала, које неминовно доводе до деформација, потребно је извршити оптимално збијање материјала. У оквиру овог рада приказује се техничка регулатива која регулише контролу збијености при изградњи железничке ...
    доњи строј, техничка регулатива, насип, збијеност, контрола
    ... XV 1. INTRODUCTION For many years, the railway network of the Republic of Serbia was unmaintained, technically lagging behind the railway networks of surrounding and developed European countries. With the started works of reconstruction and modernization of the railway, there was a need, for ...

  • Fuzzy Model for Risk Assessment of Machinery Failures

    Dejan V. Petrović, Miloš Tanasijević, Saša Stojadinović, Jelena Ivaz, Pavle Stojković (2020)
    The main goal of this research was the development of an algorithm for the implementation of negative risk parameters in a synthesis model for a risk level assessment for a specific machine used in the mining industry. Fuzzy sets and fuzzy logic theory, in combination with statistical methods, were applied to analyze the time picture state of the observed machine. Fuzzy logic is presented through fuzzy proposition and a fuzzy composition module. Using these tools, the symmetric position of the ...
    fazi teorija, rizik, otkaz rudarskih mašina
    ... Wheel Excavator. Ph.D. Thesis, Faculty of Mining and Geology, University of Belgrade, Belgrade, Serbia, 2007. 6. Subašić, P. Fuzzy Logic and Neural Networks; Technical Book: Belgrade, Serbia, 1997; pp. 35–90. 7. Cai, K.Y. System failure engineering and fuzzy methodology. An introductory overview. Fuzzy ...
    ... methodologies based on fuzzy set theory that have been applied to safety and reliability, such as fuzzy FTA, fuzzy FMEA, fuzzy ETA, fuzzy Bayesian networks, fuzzy Markov chains, and fuzzy Petri nets. Similar analyses have been presented by Liu et al. [22]. Their review showed the potential applicability ...
    ... integral. Saf. Sci. 2018, 110, 152–163. [CrossRef] 25. Vamvakas, P.; Tsiropoulou, E.E.; Papavassiliou, S. Dynamic spectrum management in 5G wireless networks: A real-life modeling approach. In Proceedings of the IEEE INFOCOM 2019—IEEE Conference on Computer Communications, Paris, France, 29 April–2 May ...

  • Application of machine learning for diagnosing the operation of a deep well pump in oil production

    Maja Trikić (2024)
    This paper will thoroughly examine how machine learning can improve the diagnosis of deep well pumps by analyzing the role and function of the pumps, dynamograms, sensor technologies, and diagnostic methods.Our analysis will provide insights into modern techniques and approaches for enhancing the performance and reliability of oil production systems, targeting cost reduction and increased operational efficiency.
    deep well pump, dynamograms, machine learning, diagnostics of operating coditions,Random Forest, XGBoost
    ... example, in 1990, Dickinson and Jennings compared various pattern recognition methods. Over the years, different methods and algorithms, including neural networks and deep learning, have been used to analyze and classify cards.Recent studies have shown that the latest algorithms achieve high accuracy ...
    ... hyperparameters, which are values set before model training. Hyperparameters, such as the depth of decision trees or the number of neurons in a neural network, play a crucial role in how the model behaves and adapts.There are several methods for hyperparameter tuning: 49 -Grid Search: This ...
    ... decision-making based on combinations of different variables and can be useful for identifying important features indicating faults. d.Neural Networks- Deep models capable of learning complex patterns in large datasets, useful for recognizing specific types of faults. 22 • ForRegression ...

  • The Usage of Various Lexical Resources and Tools to Improve the Performance of Web Search Engines

    Krstev Cvetana, Stanković Ranka, Vitas Duško, Obradović Ivan (2008)
    In this paper we present how resources and tools developed within the Human Language Technology Group at the University of Belgrade can be used for tuning queries before submitting them to a web search engine. We argue that the selection of words chosen for a query, which are of paramount importance for the quality of results obtained by the query, can be substantially improved by using various lexical resources, such as morphological dictionaries and wordnets. These dictionaries enable semantic ...
    LR web services, MultiWord Expressions & Collocations, Information Extraction, Information Retrieval
    ... Publishing house of the Romanian academy, Vol. 7, No.1-2. Vossen, P. (ed.) (1998).: EuroWordNet: A Multilingual Database with Lexical Semantic Networks. Dordrecht: Kluwer Academic Publishers 224 ...

  • The state and perspective of the natural gas sector in Serbia

    Dejan Ivezić, Marija Živković, Dušan Danilović, Aleksandar Madžarević, Miloš Tanasijević (2016)
    The strategy of long-term energy development of Serbia identifies an increase of share of natural gas in final energy consumption as one of the main aims. Serbia has signed a strategic agreement with the Russian Federation on cooperation in the oil and gas sector, within which the project South Stream pipeline is planned to be realized. In addition, the Republic of Serbia has signed the Treaty that establishes the Energy Community and accepted the obligation to implement the Energy ...
    Consumption, natural gas, scenarios of development

  • Značaj geografske širine za lociranje uzročnika magnetnih anomalija kod prospekcije arheoloških lokaliteta

    Vesna Cvetkov (2020)
    ... Geophysics XXIX/ 1: 67-79. Bescoby, D. J., Gavin, C. C., Chroston, P. N., 2004. Enhanced interpretation of magnetic survey data using artifi- cial neural networks: a case study from Butrint, southern Albania. Archaeologi- cal Prospection 11, 4: 189-199. Bevan, B.W. 1998. Geophysical explo- ration for a ...

  • Debris-flow Susceptibility Assessment in Flow-R: Ribnica River Case Study

    Ksenija Micić, Miloš Marjanović, Biljana Abolmasov (2024)
    Debris flows are among the most dangerous erosional geohazards due to the fast rate of movement and long runout zones. Even though the initiation can be triggered in mountainous areas, inhabited and with steep slopes, their propagation and deposition can endanger not only buildings and infrastructure in the urbanized areas, but also threaten human lives. As these initiation areas usually represent unattainable terrains with rapid vegetation cover development, field observations and aerial photo analysis become high-demanding tasks. Consequently, medium-to-regional ...
    tečenje drobine, Flow-R, procena podložnosti, empirijski model

  • Prioritization of strategic measures for strengthening the security of supply of the Serbian natural gas sector

    Boban Pavlović, Dejan Ivezić, Marija Živković (2020)
    To strengthen the security of supply of the Serbian gas sector, it is necessary to analyze the impact of planned strategic measures. The analysis involves the identification of the most influential threats to the security of natural gas supply and prioritization of the strategic measures for overcoming the consequences of threats. The proposed methodology is based on Fuzzy Analytic Hierarchy Process. The obtained weights for the identified threats and strategic measures are formed according to experts' judgments. The results ...
    Sigurnost snabdevanja, Donošenje odluka, Snabdevanje prirodnim gasom, Fazi AHP, Energetski indikatori

  • Indexing of textual databases based on lexical resources: A case study for Serbian

    Ranka Stanković, Cvetana Krstev, Ivan Obradović, Olivera Kitanović (2015)
    In this paper we describe an approach to improvement of information retrieval results for large textual databases by pre-indexing documents using bag-of-words and Named Entity Recognition. The approach was applied on a database of geological projects financed by the Republic of Serbia in the last half century. Each document within this database is described by metadata, consisting of several fields such as title, domain, keywords, abstract, geographical location and the like. A bag of words was produced from these ...
    ... INFOtheca – Journal of Informatics & Librarianship 12(2), 36a–47a (2011) 17. Vossen, P.: EuroWordNet: a multilingual database with lexical semantic networks. Kluwer Academic Boston (1998) View publication statsView publication stats ...

  • The Nooj System as Module within an Integrated Language Processing Environment

    Ranka Stanković, Duško Vitas, Cvetana Krstev (2008)
    NooJ, electronic dictionary, lexical resources
    ... Greece, eds, S. Piperidis and V. Karkaletsis, pp. 97-104, 2003. Vossen, P. (ed.): EuroWordNet: A Multilingual Database with Lexical Semantic Networks, Kluwer Academic publishers, Dirdrecht, 1998. ...

  • Development and Evaluation of Three Named Entity Recognition Systems for Serbian - The Case of Personal Names

    Branislava Šandrih, Cvetana Krstev, Ranka Stanković (2019)
    In this paper we present a rule- and lexicon-based system for the recognition of Named Entities (NE) in Serbian news paper texts that was used to prepare a gold standard annotated with personal names. It was further used to prepare training sets for four different levels of annota tion, which were further used to train two Named Entity Recognition (NER) sys tems: Stanford and spaCy. All obtained models, together with a rule- and lexicon based system were evaluated on ...
    NER, Named Entity Recognition Systems, Serbian, Personal Names
    ... (COLING 1996). vol- ume 1. Matthew Honnibal and Ines Montani. 2017. spaCy 2: Natural Language Understanding with Bloom Em- beddings, Convolutional Neural Networks and In- cremental Parsing. To appear, https://pypi. org/project/spacy/2.0.16/. Martin Jansche and Steven Abney. 2002. Information Extraction from ...

  • Fuzzy stohastički model izbora sistema otvaranja podzemnog rudnika

    Saša M. Jovanović (2016-05-16)
    Investiciono okruženje skopčano sa rudarskom industrijom je veoma svojstveno kada seuporedi sa okruženjima koje susrećemo u tipičnim proizvodnim industrijama. Neke odkarakterisitka rudarstva, koje su često naznačene kao jedinstvene su: visok intenzitetinvesticija, dugi predproizvodni periodi, visok rizik i neobnovljivost resursa.Investiranje u sistem otvaranja rudnika predstavlja dobar primer ireverzibilneinvesticije. Takva investicija zahteva pažljivu analizu, jer nakon njene realizacije ona sene može nadoknaditi bez značajnog gubitka vrednosti. Očigledno je da izbor sistemaotvaranja podzemnog rudnika pripada strateškom planiranju...
    otkopavanje; otvaranje; mreže i grafovi; fuzzy skupovi; stohastičkiprocesi; indeks konveksnosti; sistemi podrške odlučivanju
    ... order of Convex Index. By evaluating the networks spanned from each access point, it can be seen how depth, access point ore reserves and fixed production rate affect the efficiency of the development system. Key words: mining; development; networks and graphs; fuzzy sets; stochastic processes; ...
    ... Instit Mining Metallurgy, Section A, 164-170. [5] Brazil, M. and Thomas, D.A.(2007) Network Optimization for the Design of Underground Mines, Networks-DOI10.1002/net, 40-50. [6] Brazil, M., Lee, H., Rubinstein, H., Thomas, D., Weng, J., Wormald, C., et al. (2000). Network optimization of underground ...
    ... 1949, "The Monte Carlo Method." J. Amer. Stat. Assoc. 44, 335-341. 157 [31] Newman, M. E. J. (2003). The Structure and function of complex networks. SIAM review, 45 (2), 167-256. doi: 10.1137/S003614450342480 [32] Okada, S., Soper, T. (2000). A shortest path problem on a network with fuzzy ...

  • Preparation of Multimedia Document “YU Rock Scene”

    Milena Obradović, Aleksandra Arsenijević, Mihailo Škorić (2017)
    SUMMARY: This study will present the preparation process of a multimedia document entitled YU ROCK SCENE in which participants were senior students of undergraduate studies of the Department of Library and Information Science at the University of Belgrade Faculty of Philology during the academic year 2014/2015, as a part of the subject Multimedia Documents. This study gives an overview of the historical development of rock and roll in the territory of the former Yugoslavia, rock scene in Yugoslav republics, ...
    multimedia document, library science, information science, rock and roll, music, Yugoslavia
    ... the material – photos, audio tracks and videos were found either in cultural and media institutions (libraries, archives, radio stations, television networks, movie libraries and studios) or on the World Wide Web. In four months, over twenty insti- tutions in seven cities had been visited and cooperation ...

  • Vebran Web Services for Corpus Query Expansion

    Ranka Stanković, Miloš Utvić (2020)
    U ovom radu se govori o razvoju veb usluga Vebran i njihovoj primeni u poboljšanju pretraživanja korpusa. Veb-servisi Vebran koriste se za konsultovanje spoljnih leksičkih izvora za srpski jezik (uglavnom elektronski morfološki rečnici i srpski Vordnet) i proširivanje korisničkih upita radi dobijanja relevantnijih rezultata iz srpskih korpusa.
    corpus search, web service, Serbian lexical resources, query expansion
    ... More details about multi-word units mapping, markers and relations between lexical entries can be found in (Stanković et al., 2018). 3.2 Semantic networks The Serbian wordnet (SWN) has been developed in the scope of the Balkanet project following the model adopted for the EuroWordnet project (Krstev ...

  • Глаголи у кухињи и за столом

    Цветана Крстев, Биљана Лазић (2015)
    У раду је приказано истраживање лексике на српском језику кулинарског домена које се заснива на коришћењу доменског корпуса, електронских лексичких ресурса, пре свега WordNet-а и морфолошких речника, и локалних граматика. Приказане су доменске специфичности ових ресурса, како се користе, и међусобно употпуњују. Посебно је приказано како се коришћењем доменског корпуса могу екстраховати глаголи специфични за кулинарски домен и описати начини њиховог коришћења. Дат је попис глагола са основним подацима који је добијен применом представљених метода.
    аутоматска обрада, коначни трансдуктори, електронски речници, семантичке мреже, локалне граматике, кулинарство
    ... 09-12.IX 2009, Београд, Језик и култура. 23. ТЕНГ И ДР. 2012: Chun-YuenTeng, Yu-RuLin, LadaA. Adamic. "Recipe recommendation using ingredient networks." In Proceedings of the 3rd Annual ACM Web Science Conference, pp. 298-307. ACM. 24. ТОМИЋ 2014: Бојана Томић. „Категорије броја и бројивости ...

  • Evaluation of the effects of wastewater heat pump integration into district heating systems by simulation

    Dejan Ivezić, Marija Živković, Dimitrije Manić, Aleksandar Madžarević, Boban Pavlović, Dušan Danilović (2023)
    The integration of wastewater heat pumps (using purified water) in district heating systems is analyzed in this paper. The simulation procedure is proposed to analyze the impacts of stochasticity of purified water temperature and flow to heat pump integration and operation. The analysis includes calculation of the daily and seasonal coefficient of performance, as well as fossil fuel savings and CO2 emission reduction due to wastewater heat pump use. The proposed procedure is implemented for the case study in ...
    otpadne vode, toplotna pumpa, daljinsko grejanje, simulacija

  • Multi-word Expressions for Abusive Speech Detection in Serbian

    Ranka Stanković, Jelena Mitrović, Danka Jokić, Cvetana Krstev (2020)
    Ovaj rad predstavlja istraživanja na usavršavanju i unapređenju srpske verzije rečnika Hurtlex, višejezičnog leksikona uvredljivih reči. Posebnu pažnju posvećujemo dodavanju izraza sa više reči (polileksemskih jedinica) koji se mogu smatrati uvredljivim, jer su takvi leksički zapisi veoma važni za postizanje dobrih rezultata u mnoštvu zadataka otkrivanja uvredljivog jezika. Srpski morfološki rečnici se koriste kao osnova za čišćenje podataka i stvaranje rečnika. Istaknuta je veza sa drugim leksičkim i semantičkim resursima na srpskom jeziku i predviđena je izgradnja sistema za ...
    uvredljiv govor, govor mržnje, leksički izvori, višejezični leksikon, izrazi sa više reči
    ... and B. Klimek, pages 48–56. Ranka Stanković, Branislava Šandrih, Cvetana Krstev, Miloš Utvić, and Mihailo Škorić. 2020. Machine Learning and Deep Neural Network-Based Lemmatization and Morphosyntactic Tagging for Serbian. In Proceedings of The 12th Language Resources and Evaluation Conference, pages ...
    ... 2016b), synsets from the Serbian WordNet (Mladenović et al., 2016a). We plan to use the lexicon for building a corpus of abusive content in social networks in Serbian as well as a classifier using rules and existing resources for Serbian language (Krstev et al., 2007). In addition, we plan to include ...

  • A WebGIS Decision Support System for Management of Abandoned Mines

    Ranka Stanković, Nikola Vulović, Nikola Lilić, Ivan Obradović, Radule Tošović, Milica Pešić-Georgiadis (2016)
    ... federal framework for the exchange of information using free and open source technology that enables connection to similarly configured data exchange networks. This approach offers a long-term solution for the storage and exchange of data without commercial software. USGIN makes available, connects and ...

  • Towards Automatic Definition Extraction for Serbian

    Ranka Stanković, Cvetana Krstev, Rada Stijović, Mirjana Gočanin, Mihailo Škorić (2021)
    U radu su prikazani preliminarni rezultati automatske ekstrakcije kandidata za definicije rečnika iz nestrukturiranih tekstova na srpskom jeziku u cilju ubrzanja razvoja rečnika. Definicije u rečniku Srpske akademije nauka i umetnosti (SANU) korišćene su za modelovanje različitih tipova definicija (opisnih, gramatičkih, referentnih i sinonimskih) koje imaju različite sintaksičke i leksičke karakteristike. Korpus istraživanja sastoji se od 61.213 definicija imenica, koje su analizirane korišćenjem morfoloških e-rečnika i lokalnih gramatika implementiranih kao pretvarači konačnih stanja u paketu za obradu korpusa otvorenog ...
    ... statistical machine learning models with syntax and semantic features; 3) the deep learning approach, using word embeddings via multiple layers of neural networks (Veyseh et al., 2020). Barnbrook (2002) claimed that definition is a basic activity of language, of particular importance to linguists because ...
    ... issue. In order to overcome it, we plan to investigate other methods to complement this approach. Hill et al. (2016) report the effectiveness of both neural embedding architectures and definition-based training for developing models that understand phrases and sentences, with two applications of these ...
    ... Sintra, Portugal, eds. I. Kosem et als., pp. 248–269. Stanković, R., Šandrih, B., Krstev, C., Utvić M. & Škorić M. (2020). Machine Learning and Deep Neural Network-Based Lemmatization and Morphosyntactic Tagging for Serbian. In: Proceedings of the 12th International Conference on Language Resources and ...