Претрага

Упит dcterms_subject_txt:document classification

238 items

  • Laboratory testing of fly ash

    Miloš Šešlija, Aleksandra Rosić, Nebojša Radović, Milinko Vasić, Mitar Đogo, Milovan Jotić (2016)
    Fly ash is one of the most common waste materials created by burning of coal. It is composed of smaller particles, consisting mainly of aluminosilicate glass, mullite and quartz, which are collected by electrostatic separators (filter) of gaseous products arising from the combustion of coal. This paper presents the pozzolanic properties, mechanical properties, chemical and mineral composition of fly ash obtained in the combustion process in a power plant Nikola Tesla A (PPNT A) with the addition of a ...
    chemical composition, fly ash, mechanical properties, mineral properties, pozzolanic properties, X-ray diffraction
    ... Gazette 23, 6(2016), 1839-1848 3.1.1 Classification of fly ash according to chemical composition According to international system of fly ash classification, the fly ash from PPNT A belongs to group I, that is, aluminosilicate ashes. Classification of the module R size, fly ash from PPNT ...
    ... 27 2,66 2.2.1 The classification of fly ash on the basis of chemical composition There are several fly ash and slag classifications based on chemical composition, among which the following are the most important: 1. International system of fly ash classification Table 2 The international ...
    ... international system of classification of fly ash Group Ash SiO2/Al2O3 CaO / % SO3 I Aluminosilicate >2 <15 undefined II Silicate - Aluminate <2 <15 <3 III Sulfate - Alkaline undefined >15 >3 IV Other (lime) undefined >15 <3 2. The classification of fly ash according to the module R size ...

  • Concepts for Improving Machine Learning Based Landslide Assessment

    Miloš Marjanović, Mileva Samardžić Petrović, Biljana Abolmasov, Uroš Đurić (2019)
    Katastar klizišta, Podložnost, Hazard, Mašinsko učenje, Uzorkovanje, Validacija

  • Definisanje parametara čvrstoće na smicanje kod izvođenja kosina u ispucalom stenskom masivu

    Zoran M. Berisavljević (2016-04-01)
    Definisanje parametara čvrstoće na smicanje ispucalih stenskih masa predstavlja jedanod najzahtevnijih zadataka mehanike stena. Geotehnička istraživanja su uglavnomograničena na rezultate laboratorijskih ispitivanja malih makroskopski homogenihuzoraka, sa kojih se vrši ekstrapolacija rezultata na terensku razmeru. Ispitivanja semogu vršiti in situ, ali su i ona ograničena veličinom korišćene aparature imikrolokacijom na kojoj se vrše ispitivanja. Pored toga, moguće je vršiti različitaispitivanja na fizičkim modelima, koja su veoma složena i skupa. Ekstrapolacijapodataka sa malog uzorka na terensku razmeru daje mnogo bolje rezultate ...
    naponsko stanje, ispucalost, heterogenost, čvrstoća na smicanje, geološki indeksčvrstoće, Hoek-Brownov materijal, kompozitni uzorci, dezintegracija, povratna analiza

  • Dvodimenzionalna geometrijska morfometrija prvih gornjih molara hominina sa teritorije Srbije - taksonomska i metodološka analiza

    Predrag N. Radović (2022)
    Primarni cilj ove studije tiče se taksonomske identifikacije fosilnih prvih gornjih molara (M1) hominina pronađenih u Srbiji, primenom metoda dvodimenzionalne (2D) geometrijske morfometrije. U prvoj (metodološkoj) fazi istraživanja ispitana je efikasnost 16 različitih pristupa (geometrijskih modela) u klasifikaciji M1 neandertalaca i anatomski modernog čoveka. Modeli su testirani na dva seta okluzalnih projekcija krunica (n = 34 i n = 64) dobijenih orijentisanjem digitalnih 3D modela u virtuelnom okruženju ili fotografisanjem fizičkih primeraka zuba. Prilikom testiranja primenjena je klasifikacija zasnovana ...
    2D geometrijska morfometrija, prvi gornji molar (M1), taksonomska identifikacija, neandertalci, anatomski moderni ljudi, Pešturina, Velika Balanica, Srbija

  • 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
    ... The formula for the F1 score is shown in Equation (4). 2*precision*recall (4) Faiscor = — precision+recall Unlike binary classification, in multi-class classification, the F1 score is calculated for each class individually. If a single F1 score is needed for easier comparison, the F1- macro ...
    ... sampling rates, convert the data into a format that is easier to process, and begin manual classification with the help of experts. In this study, a tool was developed to facilitate manual classification of well logs by accessing a PostgreSQL database and allowing quick navigation between wells ...
    ... „O F Store cards V I V I I I I I ) Card visualization Label cards Discard cards Figure 6.9. Classification and manual selection schema for well logs used in this study After classification, the application saves the normalized well logs, well data, and log information. Normalization ensures ...

  • The impact of calculation of resources and reserves on mining activity in Serbia

    Jelena Zakonović, Katarina Urošević, Radmila Gaćina (2019)
    The appearance of interest of the world's most important mining companies i for investment in Serbia imposes the problem of harmonization of domestic legislation with foreign ones. In this paper, specific categorization and classification of mineral raw materials, which do not match in domestic and foreign practice, are treated. The existence of such a conflict of criteria in use for categorization and classification can lead to misunderstanding and create certain complications in business. The following sections outline some of ...
    geological exploration, deposits, solid mineral raw materials, mineral projects, mineral resources and reserves

  • Damage quantification of built stone on Dark Gate (Belgrade, Serbia): sample of damage index application for decay rate evaluation

    Maja Franković, Nevenka Novaković, Vesna Matović (2015)
    The Dark Gate is the monument of culture, part of the cultural and historical complex of the Belgrade Fortress. It is constructed of limestone blocks that after 270 years of exposure to environmental conditions and different anthropogenic influences show wide ranges of decay forms. During 2007, detail registration of all built limestone microfacies and weathering forms was done using tools of monument mapping. A correlation scheme ‘‘intensity– damage category’’ was made according to the type, intensity, and distribution of ...
    Krečnjak, mapiranje, Indeks raspadanja, brzina raspadanja, progresija
    ... stone deterioration has to be done by classification of weathering forms. Weathering forms are described with the aid of specific terminology utilizing: morphological and geometrical criteria (Siedal et al. 2011). In the attempt to harmonize classification approaches and overcome termi- nology ...
    ... was connected to a Leica DC 300 digital camera. Classification of built stone was done according to textural characteristics (Folk 1959, 1962; Fliigel 2004) Weathering mapping was carried out using the interna- tionally accepted classification scheme developed by the Aachen working group “Natural ...
    ... the cast side (Table 3). This seemingly illogical inconsistency lies in the classification scheme of weath- ering forms (Table 1), i.c., in the intensities related to damage categories. According to chosen classification scheme in our study, loss of material higher than 5 cm in depth, or 1,000 ...

  • Influence of Initial Treatment on the Survival and Recurrence in Patients With Differentiated Thyroid Microcarcinoma

    Jasna Mihailović, Ljubomir Stefanović, Ranka Stanković (2013)
    ... survival for PTM is excel- lent.23,24 Our analysis of 130 patients with DTM confirms the TABLE 2. Patients’ TNM Classification and Staging Initial N + M Classification Revised N + M Classification at the End of Follow-up Period Group n % Group n % N0M0 76 62.8 N0M0 75 62.0 N1M0 43 35.5 N1M0 41 33.9 ...
    ... to the UICC 7th TNM classification and staging system. However, 9 patients submitted to surgical procedures less than TT/NTT were not staged. There were 88 patients (72.7%) with unifocal tumor (T1a) and 33 patients (27.3%) with multifocal spread of the tumor (T1b). Classification of patients according ...
    ... lymph nodes (N1M0), whereas 1.7% of the patients had distant metastases combined with regional metastases (N1M1). During the course of disease, TNM classification and staging were revised owing to the alteration in the course of disease. Thus, one patient whowas initially free of metastases (N0M0) developed ...

  • Хазард од клизишта у Србији у 21. веку

    Biljana Abolmasov (2019)
    клизишта, хазард од клизишта, промене климе
    ... D., D. F. VanDine (2013). Classification, Description, Caus Effects-Canadian Technical Guidelines and Best Practices related t national initiative for loss reduction, Geological Survey �f Canad 2013. [6] Hungr O., Leroueil S., Picarelli L. (2012). Varnes classification o an update. Proceedings ...
    ... Cruden D., D. F. VanDine (2013). Classification, Description, Cau Effects-Canadian Technical Guidelines and Best Practices related national initiative for loss reduction, Geological Survey f Cana 2013. Hungr O., Leroueil S., Picarelli L. (2012). Varnes classification an update. Proceedings dintthimdtli ...
    ... vulnerable to natural haza floods, torrential floods and landslides. Landslides are one of hazards in Serbia (according to the international classification). E or areas prone to landslides are covering more than 16% of the S (according to a rough estimation and published scientific researc the type ...

  • Дефинисање механичких својстава алтерисаног стенског материјала лабораторијским методама

    Вељко М. Рупар (2022)
    Основни циљ овог рада је да представи методологију одређивања механичких својстава хетерогеног стенског масива који изграђују дацит (Д) и алтерисани дацит (АД), где је уочена је зона постепеног преласка од алтерисаног дацита до дацита. Механичка својства стенског масива у тој зони утврђена су на основу лабораторијских испитивања једноосне и троосне чврстоће на притисак стенског материјала композитних узорака. Композитни узорци су се састојали од дискова стенског материјала, при чему је висина дискова h дефинисала различити процентуални удео појединог стенског материјала, ...
    дацит, алтерисани дацит, једноосна чврстоћа на притисак, троосна чврстоћа на притисак, композитни узорци, механика стена, стабилност косина

  • An Approach to Management Decision Support: The Coal Mine Pljevlja Management Information System

    Božo Kolonja, Ranka Stanković, Filip Vuković, Ivan Obradović (2006)
    In this paper we describe the approach that has been used in the development of the Management Information System (MIS) in the Coal Mine Pljevlja in Montenegro. The methodology of this approach was based on new information technologies and management techniques which have already been successfully applied in other related fields. Its main goal was to introduce modern management techniques to mining, adapted to specific features of the mining industry, its operations and environment, thus enabling the tactical management ...
    ... maintenance of the employee files (identification, classification and general information about the employee, professional training, occupation, state of health, etc.); monitoring of labour relations (organizational entities, job classification, all kinds of decisions pertaining to labour relations ...
    ... Technological Information System (TIS) encompasses the most important segments of mine business operations, namely: personnel record keeping and job classification; mining equipment data management; monitoring of coal production; managing of equipment maintenance information; and MIS - management information ...
    ... TIS encompasses the most important segments of Coal Mine Pljevlja business operations, and they refer to: personnel records keeping and job classification, data on equipment included in the production process, production monitoring and coal preparation, maintenance information that influences the ...

  • From post-disaster landslides inventory to open landslides data

    Biljana Abolmasov, Miloš Marjanović, Uroš Đurić, Jelka Krušić (2021)

  • Phase relations and physical indicators of municipal waste from old landfills in Serbia

    Dragoslav R Rakić, Irena G Basarić Ikodinović, Jovana M Janković, Tina D Đurić (2021)
    Due to certain similarities of municipal waste and soil, usually for the determination of basic parameters of physical state, laboratory and field tests which are common in geotechnical investigations are used. It is often to construct an apparatus for special purpose to perform some specific laboratory and field tests. Therefore, different values of indicators of municipal waste physical state can be found in the literature. The basic reasons should be found in different definitions and methods that researchers use ...
    municipal waste, moisture content, unit weight, specific gravity, grain size distribution, porosityGeneral Computer Science
    ... municipal waste classification. The main objective of this methodology is to increase the accuracy and comparablility of data related to the characteristics, 1.e. the amount of municipal waste at the European level. It is proposed that after sampling, sorting and classification of municipal waste ...
    ... Determination of grain size distribution is necessary for the classification of municipal waste. Besides, knowledge of grain size distribution is particularly important in the construction of facilities for municipal waste classification within separation and transfer stations. Grain size distribution ...
    ... Smederevo steel mill, Serbia. J Knviron Prot Ecol,17(2), 512-522. 2) Rakić D.,Basarić l., Čaki L., Ćorić, S. (2018):Contribution to geotechnical classification of municipal wasteJowrmna!l of” FEnvironmental Geotechnics,DO1:10.1680/jenge.18.00028. 3) Skempton A.W., Petley J. (1970): Ignition loss and ...

  • Петролошке карактеристике тријаских карбоната у околини Толића (Мионица)

    Михаило Вујашевић (2024)
    У тријаским теренима у околини Толића код Мионице извршено је узорковање карбонатних стена које су предмет овог рада. На одабраним узорцима утврђене су петролошке карактеристике. Главни задатак овог завршног рада представља испитивање минералошких и петрографских карактеристика карбонатних стена, применом оптичке анализе, рендгенске дифракције и калциметрије. Макроскопском детерминацијом и применом Данхамове класификације испитивани узорци су сврстани у кречњаке калкаренитског до калклутитског склопа, односно mudstone, packestone и grainstone типа. Микроскопским прегледом кречњака и применом Фолкове класификације утврђен је њихов састав и ...
    тријаски карбонати, петрографске карактеристике, класификације кречњака
    ... of Dunham's classification, the examined samples were classified as limestones of calcarenitic to calclutitic composition, specifically of the mudstone, packstone, and grainstone types. Through microscopic examination of the limestones and the application of Folk's classification, their composition ...
    ... narodne privrede, str. 176, Beograd. (IIpey3ero 3 nareparype HaBc/neHe moji p. op.15) 3. Dunham, R.J. 1962: Classification of carbonate rocks according to depositional texture. In: Classification of carbonate rocks, A Symposium. (Ed. Ham, W.E.). American Association of Petroleum Geologists Memoir. 1 ...
    ... identified as fossiliferous micrites, micrites, and microsparites. Key words: Triassic carbonates, petrographic characteristics, limestone classification CAJIP;KAJ IBA :4:1071 RRRAAAAAA RAAAAAA 1 PAJ.0) III i 2a |0 AAAAAA AAAAAA AAAAAA AAAAAA AAAAAA AAAAAA AAAAAA AAAR 2 2.1. Teorpadicku ...

  • 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
    ... As a classification feature, either as a binary indicator of the abusive word occurrence in the examined text (Pamungkas and Patti, 2019), or a numerical value corresponding to the number of abusive words and its level of abusiveness (Razavi et al., 2010); (2) When applying rules for classification of ...
    ... word expressions, while specific markers that point to their abusive usage were added according to the prior classification: HRT=yes and HRT=maybe. This is certainly a very rough classification, but a sys- tematic annotation with more granulated classes is an ongoing activity. In Table 5 we present some ...
    ... put into on of three categories: YES - abusive speech (1260), MAYBE – could lead to abusive content (462), NO – not abusive (2902). The manual classification was supported by search over a Twitter corpus collected specifically for his research, Web 79 A ADV N PRO V (blank) Total maybe 93 12 152 ...

  • Machine learning based landslide assessment of the Belgrade metropolitan area: Pixel resolution effects and a cross-scaling concept

    Uroš Đurić, Miloš Marjanović, Zoran Radić, Biljana Abolmasov (2019)
    Improvements of Machine Learning-based landslide prediction models can be made by optimizing scale, customizing training samples to provide sets with the best examples, feature selection, etc. Herein, a novel approach, named Cross-Scaling, is proposed that includes the mixing of training and testing set resolutions. Hypothetically, training on a coarser resolution dataset and testing the model on a finer resolution should help the algorithm to better generalize ambiguous examples of landslide classes and yield fewer over/underestimations in the model. This ...
    klizišta, podložnost, mašinsko učenje

  • A Twitter Corpus and Lexicon for Abusive Speech Detection in Serbian

    Danka Jokić, Ranka Stanković, Cvetana Krstev, Branislava Šandrih (2021)
    Uvredljivi govor na društvenim medijima, uključujući psovke, pogrdni govor i govor mržnje, dostigao je nivo pandemije. Sistem koji bi bio u stanju da detektuje takve tekstove mogao bi da pomogne da internet i društveni mediji postanu bolji virtuelni prostor sa više poštovanja. Istraživanja i komercijalna primena u ovoj oblasti do sada su bili fokusirani uglavnom na engleski jezik. Ovaj rad predstavlja rad na izgradnji AbCoSER-a, prvog korpusa uvredljivog govora na srpskom jeziku. Korpus se sastoji od 6.436 ručno označenih ...
    uvredljivi jezik, govor mržnje, srpski, tviter, leksikon, korpus
    ... Internet have been presented. From the natural language processing (NLP) perspective, the detection of hate speech can be viewed as a problem of classification: for a given statement, the system needs to determine whether it contains hate speech or not [36]. To achieve this goal systems usually apply text ...
    ... presence of a word in a tweet just indicates the possibility of offensive speech, and manual annotation is necessary to guarantee accurate tweets classification. The same lexicon was used in [48] to extract toxic conversations among adolescents on Twitter. While Pedersen [32] reported high accuracy of hate ...
    ... agreement score was 92%. In the last few years, various data sets with multi-layered annotation appeared, which enabled both coarse and fine-grained classification. While Wiegand et al. [47] in the second layer classifies the type of insult (vulgar speech, insult, attack), Zampieri et al. [50] and Fisher et ...

  • Coupling of artificial intelligence methods in the development of hybrid intelligent systems

    Ranka Stanković, Ivan Obradović, Nikola Lilić (2001)
    In this paper we present an approach which couples various artificial intelligence (AI) methods in the solution of complex problems that cannot adequately be solved by a single AI method. We argue that the resulting, hybrid intelligent systems (HIS) can be successfully implemented with the use of available AI software libraries. Different coupling methods are analyzed and a classification of hybrid systems based on the chosen method is given. Two case studies of hybrid systems used in mining engineering ...
    hibridni inteligentni sistemi, spregnuti sistemi, metode veštačke inteligencije, rudarske primene veštačke inteligencije
    ... systems (HIS) can be successfully implemented with the use of available AI software libraries. Different coupling methods are analyzed and a classification of hybrid systems based on the chosen method is given. Two case studies of hybrid systems used in mining engineering are presented: a system ...
    ... algorithms (Gene Hunter). In Section 2 we give a brief overview of the approaches to the coupling of AI methods in hybrid systems and their classification based on the coupling method used. An outline of the development process follows. Section 3 describes the main features of an intercommunicating ...

  • Parallel Stylometric Document Embeddings with Deep Learning Based Language Models in Literary Authorship Attribution

    Mihailo Škorić, Ranka Stanković, Milica Ikonić Nešić, Joanna Byszuk, Maciej Eder (2022)
    This paper explores the effectiveness of parallel stylometric document embeddings in solving the authorship attribution task by testing a novel approach on literary texts in 7 different languages, totaling in 7051 unique 10,000-token chunks from 700 PoS and lemma annotated documents. We used these documents to produce four document embedding models using Stylo R package (word-based, lemma-based, PoS-trigrams-based, and PoS-mask-based) and one document embedding model using mBERT for each of the seven languages. We created further derivations of these ...
    General Mathematics, Engineering (miscellaneous), Computer Science (miscellaneous)

  • Digital Library From A Domain Of Criminalistics As A Foundation For A Forensic Text Analysis

    Dalibor Vorkapić, Aleksandra Tomašević, Miljana Mladenović, Ranka Stanković, Nikola Vulović (2017)
    U ovom radu predstavljen je model koji omogućava prikupljanje, pripremu, opis metapodataka, upravljanje i eksploataciju, uključujući pretragu punog teksta dokumenata iz domena kriminalistike napisanih na srpskom jeziku. Predloženi pristup primenjuje se na veb portalu koji sakuplja različite tekstove nastale iz časopisa Akademije za kriminalistiku i policijske studije, Krivičnog zakona Srbije, konferencija „Tara“ i „Reiss“, kao i iz nekih doktorskih disertacija vezanih za ovu oblast istraživanje. Nakon obrade teksta, korpus koji sadrži preko 5500 stranica običnog teksta, kreiran je i ...
    Omeka, Wordnet, pretraga punog teksta, morfološka i semantička pretraga teksta, proširenje upita
    ... text search expansion. The paper outlines possibilities for further use and analysis on a digital library as a corpus, annotation, tagging, document classification and clustering, as well as sentiment analysis with first results in that direction. Keywords: Omeka, WordNet, full text search, mor ...
    ... authorized use. The digital library document collection is accessible through user friendly application, that is organised in several categories: Journal for criminalistics and right, Archibald Reiss, Doctoral Dissertation, and other (final process). Further classification is possible, so categories can ...
    ... keywords, subject headings, abstract etc.; structural – describe types, versions and links between digital objects (e.g. connect the original document and all its versions, whereby include information about versions and the information about latest change in them etc.); administrative – contain ...