Претрага
817 items
-
Primena fuzzy optimizacije u hidrodinamičkoj analizi
znanje eksperta, optimizacija, trougaoni fuzzy brojevi, upravljanje podzemnim vodama, fuzzy logika, hidrodinamički modelDragoljub Bajić, Dušan Polomčić, Jelena Ratković, Predrag Pajić. "Primena fuzzy optimizacije u hidrodinamičkoj analizi" in XVII Kongres geologa Srbije (Zbornik radova XVII srpskog geološkog kongresa), Vrnjačka Banja, 17-20.05.2018., Srpsko geološko društvo (2018)
-
Machine Learning and Deep Neural Network-Based Lemmatization and Morphosyntactic Tagging for Serbian
The training of new tagger models for Serbian is primarily motivated by the enhancement of the existing tagset with the grammatical category of a gender. The harmonization of resources that were manually annotated within different projects over a long period of time was an important task, enabled by the development of tools that support partial automation. The supporting tools take into account different taggers and tagsets. This paper focuses on TreeTagger and spaCy taggers, and the annotation schema alignment ...... (DNNs) (Huang et al., 2015; Choi, 2016; Akbik et al., 2018). The first operational tagger and lemmatization model for Serbian were produced as a parameter file (TT11) for the TreeTagger model (Schmid, 1999) after a thorough anal- ysis of the state-of-the-art solutions (Popović, 2010), and subsequently ...
... two taggers trained on the largest train- ing set (SR-{100}). We used it to train the following tag- gers: 1) SerSpaCy, a spaCy model, and 2) TT19, a Tree- Tagger model. We used T11 as the baseline for evaluation, since it was already tested and evaluated as part of a pre- vious research (Popović ...
... final schema in Subsection 3.2. The main fea- tures of the tools used for tagging are described in Subsec- tion 3.3. Evaluation results of spaCy model are compared with the results obtained by the TreeTagger trained on the same dataset, as well as with a previous version of TreeTag- ger for Serbian ...Ranka Stanković, Branislava Šandrih, Cvetana Krstev, Miloš Utvić, Mihailo Škorić. "Machine Learning and Deep Neural Network-Based Lemmatization and Morphosyntactic Tagging for Serbian" in Proceedings of the 12th Language Resources and Evaluation Conference, May Year: 2020, Marseille, France, European Language Resources Association (2020)
-
Optimizacija parametara reza rotornog bagera pri otkopavanju materijala sa povećanom čvrstoćom
Saša D. Bošković (2016-09-09)Otkopavanje materijala rotornim bagerom je veoma sloţen fiziĉko-mehaniĉki proces. Pokazatelji efektivnosti tog procesa zavise od velikog broja raznovrsnih ĉinilaca od kojih se posebno mogu istaći: fiziĉko-mehaniĉke karakteristike materijala koji se otkopava, reţim rada bagera i izbor tehnoloških parametara bloka, odreska i reza, geometrije vedrica i zuba itd. Poseban problem se javlja kod otkopavanja materijala povećane ĉvrstoće, što je ĉest sluĉaj na našim površinskim kopovima. Dimenzionisanje specifiĉne sile kopanja bagera prema manjim masama izuzetno ĉvrstog materijala je neracionalno i rešenje ...rotorni bager, parametri reza, otpor na kopanje, dinamika bagera, kapacitet, optimizacija, specifična potrošnja energije... .. 117 Slika 5.8. Model strele rotora ............................................................................. 124 Slika 5.9. Model rotora ....................................................................................... 125 Slika 5.10. Raĉunski modeli strele rotora ......... ...
... nauĉni doprinos kroz definisanje metodologije, izradu simulacionog modela rada rotornog bagera, izradu modela radnog organa rotornog bagera (strele i rotora) metodom konaĉnih elemenata i terenska merenja koja će verifikovati model rada bagera i dinamiĉko ponašanje pri otkopavanju materijala sa povećanom ...
... bagera; 8 - Definisanje metodologije kroz izradu simulacionog modela rada rotornog bagera, izradu modela radnog elementa rotornog bagera (strele i rotora) metodom konaĉnih elemenata i terenska merenja koja će verifikovati model rada bagera i dinamiĉko ponašanje pri otkopavanju materijala sa ...Saša D. Bošković. "Optimizacija parametara reza rotornog bagera pri otkopavanju materijala sa povećanom čvrstoćom" in Универзитет у Београду, Универзитет у Београду, Рударско-геолошки факултет (2016-09-09)
-
Sorpcija herbicida na neorganski i organski modifikovanom prirodnom montmorionitu iz Bogovine
Lazar M. Kaluđerović (2018-01-17)fikasnost prilikom sorpcije S-metolahlora i klomazona od strane neorganskih iorganski modifikovanih montmorionita sa lokaliteta Bogovina odreĎena je metodombach adsorpcije. Uzorci montmorionita su tretirani prvo rastvorom NaCl a zatim irazličitim koncentracijama organskih kompleksa. Adsorpcione izoterme su dobijenetretiranjem uzoraka različitim koncentracijama herbicida. Detaljna mineraloškakarakterizacija uzoraka uraĎena je metodom rendgenske difrakcije. Rezultati interakcijemontmorionita sa organskim kompleksima i herbicidima dobijeni su primenomrendgenskih, optičkih, termičkih i spektroskopskih metoda.Na osnovu rezultata rendgenskih ispitivanja uzoraka, utvrĎeno je prisustvoorganskih kompleksa i herbicida u meĎuslojnom prostoru montmorionita.Montmorioniti modifikovani ...adsorpcija, montmorionit, heksadeciltrimetilamonijum bromid,feniltrimetilamonijum hlorid, S-metolahlor, klomazon... izoterma predstavlja Langmuirovim modelom ili Frojndlihovim modelom. 9 Langmuirova izoterma (Langmuir) se moţe primeniti na adsorpciju iz gasovite faze, a u nekim slučajevima i na adsorpciju iz rastvora. Langmuirova adsorpciona izoterma predstavlja model koji se koristi u slučaju da su sva ...
... bentonita izgraĎeni od 90 do 97 % 7 montmorionita u Istočnom polju i gotovo su monomineralni a prema oceni istraţivača posebno se ističu bentoniti sive i crne boje po hemijskom sastavu i kapacitetu izmene katjona (Milenković i dr., 2005). 1.2.3 Proces sorpcije Kao kod tečnosti, i kod čvrstih ...
... druge pa se njihove meĎusobne interakcije mogu zanemariti (Gojković, 2014). Prilikom proširenja Langmuirovog modela na višeslojnu adsorpciju koristi se BET izoterma. Pretpostavke ovog modela su da se na površini čvrstog supstrata nalazi odreĎeni broj aktivnih mesta koja su energetski homogena, da ...Lazar M. Kaluđerović. "Sorpcija herbicida na neorganski i organski modifikovanom prirodnom montmorionitu iz Bogovine" in Универзитет у Београду, Универзитет у Београду, Рударско-геолошки факултет (2018-01-17)
-
Production information system of the Pljevlja coal mine
Božo Kolonja, Ranka Stanković, Filip Vuković . "Production information system of the Pljevlja coal mine" in Mine Planning and Equipment Selection 2000, Routledge (2018). https://doi.org/10.1201/9780203747124-154
-
Numerical simulation of the Late Jurassic closure of the Vardar Tethys
... utilizes marker in cellapproach with finite difference discretization of equations on a staggered grid [Gerya et al., 2000;Gerya&Yuen, 2003]. The 2D model consists of two continental plates separated by two oceanic slabs connected at amid-oceanic ridge. Intraoceanic subduction is initiated along the ridge ...
... ridge by assigning a weak zonebeneath the ridge. Time-dependent boundary conditions for velocity are imposed on thesimulation in order to model a transient spreading period. The change of sign in plate velocities isfound to be useful for both obtaining obduction / ophiolite emplacement [Duretz et al. ...
... two convergent phases separated bya single divergent phase where spreading regime is dominant. Effect of duration and magnitude ofthe second phase on model evolution is also explored. Our so far obtained simulations were able to reproduce the westward obduction and certainextension processes along the active ...Nikola Stanković, Vesna Cvetkov, Vladica Cvetković. "Numerical simulation of the Late Jurassic closure of the Vardar Tethys" in EGU General Assembly 2021, Copernicus GmbH (2021). https://doi.org/10.5194/egusphere-egu21-9893
-
2D Numerical Simulation of Intraoceanic Subduction during the Upper Jurassic Closure of the Vardar Tethys
... utilizes marker in cellapproach with finite difference discretization of equations on a staggered grid [Gerya et al., 2000;Gerya&Yuen, 2003]. The 2D model consists of two continental plates separated by two oceanic slabs connected at amid-oceanic ridge. Intraoceanic subduction is initiated along the ridge ...
... ridge by assigning a weak zonebeneath the ridge. Time-dependent boundary conditions for velocity are imposed on thesimulation in order to model a transient spreading period. The change of sign in plate velocities isfound to be useful for both obtaining obduction / ophiolite emplacement [Duretz et al. ...
... two convergent phases separated bya single divergent phase where spreading regime is dominant. Effect of duration and magnitude ofthe second phase on model evolution is also explored. Our so far obtained simulations were able to reproduce the westward obduction and certainextension processes along the active ...Nikola Stanković, Vesna Cvetkov, Vladica Cvetković. "2D Numerical Simulation of Intraoceanic Subduction during the Upper Jurassic Closure of the Vardar Tethys" in EGU General Assembly 2020, Copernicus GmbH (2020). https://doi.org/10.5194/egusphere-egu2020-5919
-
Stochastic Prediction of Temporal Variations of Karst Groundwater Regime in Function of Sustainable Management: Case Study Mokra Karst Spring (SE Serbia)
Veljko Marinović, Branislav Petrović (2021)Veljko Marinović, Branislav Petrović. "Stochastic Prediction of Temporal Variations of Karst Groundwater Regime in Function of Sustainable Management: Case Study Mokra Karst Spring (SE Serbia)" in Karst: From Top to Bottom, Belgrade, 6.6.2021., Belgrade : Centre for Karst Hydrogeology (2021)
-
Concept od predictive hydrodynamic calculations: An overview of the case studies from Serbia
Dušan Polomčić, Dragoljub Bajić, Jelena Ratković, Vesna Ristić Vakanjac, Marina Čokorilo Ilić (2019)groundwater management, hydrodynamic model, multiple-criteria decision making, open cast mine, groundwater source.0Dušan Polomčić, Dragoljub Bajić, Jelena Ratković, Vesna Ristić Vakanjac, Marina Čokorilo Ilić. "Concept od predictive hydrodynamic calculations: An overview of the case studies from Serbia" in National Conference with international participation “Geosciences 2019”, Bulgaria, 2019, Sofia : Bulgarian Geological Society (2019)
-
An oilfield in Libya: A new model to enhance waste water disposal
Dušan Danilović, Vesna Karović Maričić, Nori Elhaddad, Branko Leković. "An oilfield in Libya: A new model to enhance waste water disposal" in Energy & Environment (2016)
-
Дефинисање археолошких објеката на локалитету Кремените њиве применом Ојлерове 3Д деконволуције на магнетометријске податке
... Razmatran je model obli‐ ka prizme, konačne debljine, na manjoj i većoj dubini zaleganja, kao i model na kome je prikazano više tela na različitim dubinama, koja se nalaze u sredini koja ima različitu vrednost magnetske susceptibilosti u odnosu na zadata tela. Za formiranje sintetičkih modela korišćene su ...
... polja sa rastojanjem od uzročnika anomalija. Za jednostavne modele se tumači kao strukturni indeks (Thompson, 1982) i definiše vrstu mete korišćene u proceduri O3DD (Reid i dr, 1990). U radu su na sintetičkim modelima testirane Standardna i Locirana O3DD sa različitim struktur‐ nim ...
... to magnetic inclination, declination and remanent magnetization (Bastani & Kero, 2004). A model of a prism of definite thickness which lies on shallower and deeper depth was considered, as well as the model on which are shown several bodies at different depths, in an environment with different m ...Весна Цветков, Илија Васиљевић, Бранислав Сретеновић, Весна Дамњановић. "Дефинисање археолошких објеката на локалитету Кремените њиве применом Ојлерове 3Д деконволуције на магнетометријске податке" in Књига апстраката 17. Конгрес геолога Србије, Врњачка Бања 17-20. мај, Српско геолошко друштво (2018)
-
Towards translation of educational resources using GIZA++
... dX.clean 1 80 Language Model Training A language model (LM) is used to ensure fluent output, built with the target language, in our case English. Following script creates lm folder, positions in it and finally execute command that will build an 3-gram language model. mkdir ~/lm cd ~/lm ...
... about the text: ~/mosesdecoder/scripts/recaser/train-truecaser.perl \ --model ~/corpus/truecase-model.en --corpus \ ~/corpus/edX.tok.en ~/mosesdecoder/scripts/recaser/train-truecaser.perl \ --model ~/corpus/truecase-model.sr --corpus \ ~/corpus/edX.tok.sr Finally ...
... perl \ --model ~/corpus/truecase-model.en \ < ~/corpus/edX.tok.en \ > ~/corpus/edX.true.en 1 http://www.statmt.org/moses/glossary/SMT_glossary.html ~/mosesdecoder/scripts/recaser/truecase.perl \ --model ~/corpus/t ...Ivan Obradović, Dalibor Vorkapić, Ranka Stanković, Nikola Vulović, Miladin Kotorčević. "Towards translation of educational resources using GIZA++" in The Seventh International Conference on e-Learning (eLearning-2016), September 2016, Belgrade : Metropolitan Univesity (2016)
-
Part of Speech Tagging for Serbian language using Natural Language Toolkit
Ranka Stanković, Boro Milovanović (2020)Dok se razvijaju složeni algoritmi za NLP (obrada prirodnog jezika), osnovni zadaci kao što je označavanje ostaju veoma važni i još uvek izazovni. NLTK (Natural Language Toolkit) je moćna Python biblioteka za razvoj programa zasnovanih na NLP-u. Pokušavamo da iskoristimo ovu biblioteku za kreiranje PoS (vrsta reči) oznake za savremeni srpski jezik. Jedanaest različitih modela je kreirano korišćenjem NLTK API-ja za označavanje. Najbolji modeli se transformišu sa Brill tagerom da bi se poboljšala tačnost. Obučili smo modele na označenom ...... will be used for comparing different taggers. The simplest model in NLTK is Default tagger which tags every token with one selected PoS category [17]. Because the noun is by far the most represented PoS tag, the accuracy for this model on all tokens will be exactly 21,51%. This is the baseline tagger ...
... reasoning. NLTK API makes it possible to create multiple standalone tagger models as well as to combine them. We are going to try and test every model available in the version 3.5 released in March 2020. Having a plethora of different algorithms makes this library a good choice for a research. ...
... is picked. At the end of the chain, there is a rule which states that the word is of Noun category – same as for Default tagger. Obviously, this model AII 1.1.2 will perform better than the baseline tagger, but making the right rules demands significant effort. We did not invest much time in ...Ranka Stanković, Boro Milovanović. "Part of Speech Tagging for Serbian language using Natural Language Toolkit" in 7th International Conference on Electrical, Electronic and Computing Engineering IcETRAN 2020, Academic Mind, Belgrade (2020)
-
Towards a Mining Equipment Ontology
... equipment. The structure of RudOnto can be described by an UML (Unified Modeling Language) model, as depicted in Figure 2. A brief description of this model follows. The lexicographic superclass within the model is the class Rečnik, implemented as an abstract class. Concepts, which can be either general ...
... domain. At the same time an ontology is a data model of the domain and it can be used for drawing inferences on the basis of the information stored in the objects within that domain and the interconnections existing between them. 3 2.2. Model of the RudOnto terminological resource RudOnto ...
... relation in the model is implemented by involution, which means that a hyponym can appear only once in the resource hierarchy, with only one hypernym above it. Other semantic relations between concepts are enabled by the RelacijeTermina class, whereas the MultijezičkiLeks class in the UML model is used for ...Ranka Stanković, Ivan Obradović, Olivera Kitanović, Ljiljana Kolonja. "Towards a Mining Equipment Ontology" in Proceedings of the 12th International Conference Research and Development in Mechanical Industry, RaDMI 2012, September 2012, Vrnjačka Banja, Serbia no. 1, Vrnjačka Banja, Serbia : SaTCIP (Scientific and Technical Center for Intellectual Property) Ltd. (2012)
-
Uticaj geološke neizvesnosti u razvoju rudarskih projekata
Rudarstvo je industrija koja se nosi sa različitim vrstama neizvesnosti i rizika zbog svoje prirode i specifičnosti. Neizvesnost u rudarstvu može poticati iz različitih izvora i uticati na različite aspekte rudarskih projekata. Kao jedan od dominantnih faktora, ističe se geološka neizvesnost. Geološka neizvesnost igra ključnu ulogu u rudarstvu i može značajno uticati na procenu resursa i rezervi, planiranje eksploatacije, ekonomsku isplativost i upravljanje rizicima. Ova neizvesnost se ne može eliminisati, ali se uz primenu adekvatnih standarda i zakona može ...... projekta, pod pretpostavkom da je geološka interperetacija ležišta adekvatna i da je zapreminska masa u blok modelu utvrđena sa velikom tačnošću. Raspoloživost višestrukih jednako verovatnih modela ležišta, omogućuje rudarskim inženjerima (projektantima) da povežu osetljivost granica kopa i dugoročnog ...
... modeliranje, • Analizaiprocena sadržaja,i • Procenai kontrola rizika. Procena resursa treba da bude kompletirana sa procenom rizika. Svi numerički modeli imaju višestruke značajne izvore rizika, vezane za podatke, geološku interpretaciju i modeliranje (procenu) sadržaja. Ocena rizika, vezana za promenljive ...
... između istražnih bušotina ı drugih istražnih radova, geološki kontinuitet ležišta, kontinuitet sadržaja, metodu procene i veličinu blokova u blok modelu, mogući način eksploatacije i period eksploatacije (Australasian Code for Reporting of Exploration Results, Mineral Resources and Ore Reserves (The ...Petar Marković, Dejan Stevanović, Mirjana Banković. "Uticaj geološke neizvesnosti u razvoju rudarskih projekata" in XI Međunarodna konferencija "Ugalj i kritični minerali 2023", CCM 2023, Zlatibor, 11-14. oktobar 2023., Beograd : Jugoslovenski komitet za površinsku eksploataciju (2023)
-
High-resolution sequence stratigraphy of carbonates - theory and examples
Jelena Stefanović, Dejan Radivojević (2020)Циљ рада је да кроз теоријски аспект и примере примене представи секвенциону стратиграфију високе резолуције карбонатних седимената. У том смислу први део се односи на појам и значење високе резолуције у секвенционој стратиграфији. Од временских и просторних скала које одговарају сеизмичким профилима у последњих двадесет година метода је нашла примену на скалама које одговарају бушотинским подацима или изданцима. Као најпогоднији седименти за овај тип истраживања су се показали карбонати јер су осетљиви на еустатичке промене, а основе секвенционе стратиграфије ...... 2006). Терминологија и основни модели у оквиру секвенционе стратиграфије су засновани на проучавању силицикластичних система и све до 80-их година прошлог века исти модели су се примењивали на карбонатне системе. Прву значајну модификацију силицикластичног модела ка карбонатним направио је SARG (1988) ...
... осамдесетих година прошлог века. Иако постоји општи модел који се користи у секвенционој стратиграфији, услед одређених недоумица поставља се питање да ли је уопште могуће увести један униформан општи модел. У поједностављеном облику модел је приказан на Слици 1, и ослања се на промену нивоа мора ...
... 1, Табела 1). Општи модел је представио CATUNEANU (2019) интеграцијом модела различитих аутора (Слика 1; MITCHUM et al., 1977; VAN WAGONER et al., 1988; HUNT and TUCKER, 1992; GALLOWAY, 1989; JOHNSON and MURPHY, 1984; и др). 69 Слика 1. Поједностављени основни модел секвенционе стратиграфије ...Jelena Stefanović, Dejan Radivojević. "High-resolution sequence stratigraphy of carbonates - theory and examples" in Zapisnici Srpskog geološkog društva za 2020. godinu, Srpsko geološko društvo (2020)
-
Integrative GHG Assessment in Oil and Gas Industry
Reducing greenhouse gas emissions is one of the main targets of national strategies in European countries. As a main contributor to emissions, the energy sector is recognized as the most promising to apply measures and actions aimed to decrease GHG emissions. The Oil and Gas industry as a significant contributor to global greenhouse gas emissions is facing a growing need for estimating, mitigating, and reducing the impact of their operations on the atmosphere to stay competitive in a newly ...... 005286 model output provides a comprehensive view (Figure 2) of the IV RESULTS AND DISCUSSION company'spGILlIJG emissions prlšflle, broken dow(n lžy facišity and Using the input data described in Section 3, the GHG emissions are calculated for the case of the upstrcam O&G company. Thce model is developed ...
... mapping and calculating emissions. This papcr presented a comprehensive assessmcent of forming the GHG model for mapping and calculating emissions in the O&G industry. The presented GHG model was verified through Case Study of annual emissions if a typical upstrcam company where different facilities ...
... Mobile Gasoline) were analysed. The results of the GHG model clearly indicate that the major source of emissions from the typical upstrcam O&G company is gas flaring, mainly due to emission of uncombusted methane. In addition, the presented model highlights the fact that in O&G production, the expected ...Aleksandar Mirković, Marija Živković, Stevan Đenadić, Darja Lubarda, Chinedu Anyanwa. "Integrative GHG Assessment in Oil and Gas Industry" in Energija, ekonomija, ekologija (2023). https://doi.org/10.46793/EEE23-1.51M
-
Strain partitioning along a curved strike-slip fault system during indentation: inferences from analogue modelling
Nemanja Krstekanić, Ernst Willingshofer, Taco Broerse, Liviu Matenco, Marinko Toljić, Uroš Stojadinović (2021)Nemanja Krstekanić, Ernst Willingshofer, Taco Broerse, Liviu Matenco, Marinko Toljić, Uroš Stojadinović. "Strain partitioning along a curved strike-slip fault system during indentation: inferences from analogue modelling" in GeoMod 2021, Doorn, the Netherlands, 19.-23.9.2021., Utrecht University (2021)
-
SASA Dictionary as the Gold Standard for Good Dictionary Examples for Serbian
Ranka Stanković, Branislava Šandrih, Rada Stijović, Cvetana Krstev, Duško Vitas, Aleksandra Marković (2019)У овом раду представљамо модел за избор добрих примера за речник српског језика и развој иницијалних компоненти модела. Метода која се користи заснива се на детаљној анализи различитих лексичких и синтактичких карактеристика у корпусу састављених од примера из пет дигитализованих свезака речника САНУ. Почетни скуп функција био је инспирисан сличним приступом и за друге језике. Дистрибуција карактеристика примера из овог корпуса упоређује се са карактеристиком дистрибуције узорака реченица ексцерпираних из корпуса који садрже различите текстове. Анализа је показала да ...Српски, добри примери из речника, аутоматизација израде речника, издвајање својстава, Машинско учење... ac.rs, vitas@matf.bg.ac.rs, aleksandra.markovic@isj.sanu.ac.r Abstract In this paper we present a model for selection of good dictionary examples for Serbian and the development of initial model components. The method used is based on a thorough analysis of various lexical and syntactic features ...
... candidate examples, represented as feature- vectors, are used with the GDEX ranking tool for Serbian candidate examples and a supervised machine learning model for classification on standard and non-standard Serbian sentences, for further integration into a solution for present and future dictionary production ...
... distribution in sentence samples extracted from corpora is given in Section 4. The research focused on the development of the initial components of a model for example selection is presented in Section 5, followed by ideas for future work and some concluding remarks at the end of the paper. 2. SASA ...Ranka Stanković, Branislava Šandrih, Rada Stijović, Cvetana Krstev, Duško Vitas, Aleksandra Marković. "SASA Dictionary as the Gold Standard for Good Dictionary Examples for Serbian" in Electronic lexicography in the 21st century. Proceedings of the eLex 2019 conference , Lexical Computing CZ, s.r.o. (2019)
-
Quantitative analysis of syllable properties in Croatian, Serbian, Russian, and Ukrainian
Biljana Rujević, Marija Kaplar, Sebastijan Kaplar, Ranka Stanković, Ivan Obradović, Jan Mačutek (2021)Biljana Rujević, Marija Kaplar, Sebastijan Kaplar, Ranka Stanković, Ivan Obradović, Jan Mačutek. "Quantitative analysis of syllable properties in Croatian, Serbian, Russian, and Ukrainian" in Language and Text: Data, models, information and applications, John Benjamins Publishing Company (2021). https://doi.org/10.1075/cilt.356.04ruj