Претрага

Упит dcterms_subject_txt:machine learning

119 items

  • 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

  • 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
    ... evaluating pump performance.. ..16 4. MACHINE LEARNING ... a aaaaaaaaaaaaaaaaaaaaataktt 17 4.1. Fundamental elements of applying machine learning in diagnosing deep well pump operations are: al aaaaaaaaaaaaaaaaaaaaaaaaaeaaaeaataaoata 20 4.2. Types of machine learning ..........aaaaaaaaaaaaaaaaaanaaa ...
    ... technology to increase productivity. The use of machine learning can help advance technologies and processes, especially in areas where traditional engineering methods have been ineffective. 6.3.1. Fundamentals of machine learning Machine learning techniques use data to create models that can predict ...
    ... using machine learning, we can improve diagnostics and maintenance by recognizing faults before they lead to more serious issues.Finally, we will consider the diagnosis of operational conditions and sensor faults using machine learning in deep well pumping. This segment explores how machine learning ...

  • Sentiment Analysis of Serbian Old Novels

    Ranka Stanković, Miloš Košprdić, Milica Ikonić Nešić, Tijana Radović (2022)
    In this paper we present first study of Sentiment Analysis (SA) of Serbian novels from the 1840-1920 period. The preparation of sentiment lexicon was based on three existing lexicons: NRC, AFFIN and Bing with additional extensive corrections. The first phase of dataset refinement included filtering the word that are not found in Serbian morphological dictionary and in second automatic POS tagging and lemma were manually corrected. The polarity lexicon was extracted and transformed into ontolex-lemon and published as initial ...
    sentiment lexicon, sentiment analysis, distant-reading, machine learning, old novels

  • Integrating landslide magnitude in the susceptibility assessment of the City of Doboj, using machine learning and heuristic approach

    Cvjetko Sandić, Miloš Marjanović, Biljana Abolmasov, Radislav Tošić (2023)
    In this work, landslide assessment of the Doboj City area was modeled by combining machine learning and heuristic tools. The machine learning part was used to map the Morphometric factor. i.e. probability of landslides based on relation between the magnitude of events and morphometric parameters: elevation, distance to streams, slope, profile curvature, and aspect. The Random Forest and Support Vector Machines algorithms were implemented in the learning protocol, which included several strategies: balancing of the training/testing set size, algorithm ...
    podložnost na kliženje, magnituda klizišta, mašinsko učenje, heuristički pristup, Doboj

  • 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

  • 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 ...
    obrada prirodnog jezika, mašinsko učenje, neuronske mreže
    ... were demonstrated with the Perceptron tagger: 92,52 – 95,76% accuracy for the different tagsets. Index Terms—Natural Language Processing; Machine Learning; Neural Network. I. INTRODUCTION In the last couple of years, a big advancement in the field of Natural Language Processing has occurred ...
    ... Goodman, K. Gimpel, P. Sharma, and R. Soricut, “ALBERT: A Lite BERT for Self-supervised Learning of Language Representations,” Feb. 2020 [3] Z. Zhang, J. Yang, and H. Zhao, “Retrospective Reader for Machine Reading Comprehension,” Jan. 2020 [4] B. Li, N. Jiang, J. Sham, H. Shi, and H. Fazal, ...
    ... language processing (ANLC '92), Stroudsburg, Pennsylvania, USA, Mar. 1992. [23] R. Stanković, B. Šandrih, C. Krstev, M. Utvić, and M. Škorić, “Machine Learning and Deep Neural Network-Based Lemmatization and Morphosyntactic Tagging for Serbian,” Proc. International Conference on Language Resources ...

  • Interpretation of Trace Element Chemistry of Zircons from Bor and Cukaru Peki: Conventional Approach and Random Forest Classification

    Dina Klimentyeva, Milos Velojic , Albrecht Von Quadt, Shawn Hood (2022)
    Geohemija cirkona, Mašinsko učenje, Timočki magmatski komplkes, Bor, Čukaru Peki

  • 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
    ... selected 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 ...
    ... dictionary production projects. Keywords: Serbian; good dictionary examples; automatization of dictionary-making; feature extraction; machine learning 1. Introduction 1.1 The aim of the paper This paper outlines an approach to providing support for building different kinds of monolingual descriptive ...
    ... suitability to serve as examples. Sentences from the prepared dataset, represented as feature-vectors, were used as the dataset for a supervised Machine Learning (ML) model, which was then used in a GDEX classifier for contemporary Serbian sentences. Since the dataset of examples was unbalanced, with ...

  • Formative evaluation of e-learning projects with the logical framework approach

    Roberto Linzalone, Giovani Schiuma, Ivan Obradović, Ranka Stanković (2015)
    ... l model for web-based e-learning education with a blended learning process approach, British Journal of Educational Technology, 36(2), 2005. [17] Aldrich, C., Simulations and the future of learning: An innovative (and perhaps revolutionary) approach to e-learning, San Francisco: Pfeiffer ...
    ... improve one or more significant parts of a learning value chain, including management and delivery [17]. E-Learning supports the educational processes utilizing information and communications technology to mediate synchronous as well as asynchronous learning and teaching activities” [18]. Despite ...
    ... there are still few definitions of E-Learning as project, reflecting a managerial focus. A project of E-Learning can be defined as a temporary endeavour aimed to creating an ICT-based infrastructure, to deliver support services to education, learning, whose effects are detectable along the ...

  • Using Metadata For Content Indexing Within An OER Network

    Ranka Stanković, Olivera Kitanović, Ivan Obradović, Roberto Linzalone, Giovanni Schiuma, Daniela Carlucci (2014)
    ... understand what specific learning objectsare about, what is their learning content and prerequisites for their use,without even seeing them [5]. When a large amount of OER is reached, it is even more important that they are well described and tagged in a standard way in machine readable form. In that ...
    ... understand what specific learning objectsare about, what is their learning content and prerequisites for their use, without even seeing them [5]. When a large amount of OER is reached, it is even more important that they are well described and tagged in a standard way in machine readable form. In that ...
    ... these resources need to bediscoverable, accessible and shared by potential learners across the learning environment, it is very important that they are well described and tagged in a standard way in machine readable form by metadata. Only then can they be successfullyused and reused, especially when ...

  • Building learning capacity by blending different sources of knowledge

    Ivan Obradović, Ranka Stanković, Olivera Kitanović, Dalibor Vorkapić (2016)
    ... that each learning resource is well described and tagged in a standard way, and in machine readable form. This makes resources more easily located by search engines, and results returned by are more relevant. Both educators and learners can find and compare described and tagged learning materials ...
    ... provides for multilinguality of the resources, namely their publishing in different languages. Keywords: learning continuum, blended learning, technology enhanced learning, life- long learning Biographical notes: Ivan Obradović is a professor of mathematics and informatics at the University ...
    ... especially those using new learning technologies, as the one presented in this article. With the advancement of information technology (IT) a powerful mechanism for blending academic and entrepreneurial knowledge is offered by e-learning or technology-enhanced learning (TEL). TEL basically relies ...

  • A Tel Platform Blending Academic And Entrepreneurial Knowledge

    Ivan Obradović, Ranka Stanković, Jelena Prodanović, Olivera Kitanović (2013)
    ... namely: • Tools - software to support the development, use, reuse and delivery of learning content, including content and learning management systems, as well as content development tools; • Learning content - learning resources, both academic and entrepreneurial, and reference resources, where ...
    ... called "big" languages, as it includes a powerful language support system, which enables the publishing of learning materials in various languages. Keywords: Technology enhanced learning, e-Learning, Open courseware, Open educational resources 1. INTRODUCTION It is safe to say that in the majority ...
    ... "Blending Academic and Entrepreneurial Knowledge within Technology Enhanced Learning". The term "technology-enhanced learning" or TEL pertains to activities aimed at improving the quality and outcomes of learning where technology plays a significant supportive role, thus encompassing the ...

  • An aproach to Implementation of blended learning in a university setting

    Ivan Obradović, Ranka Stanković, Olivera Kitanović, Jelena Prodanović (2011)
    ... of traditional and e-learning paradigms, which is thus hybrid in its nature, offers a great extent of flexibility in applying ICT to learning, and often goes under the name of blended learning [3]. For several years now, computer-mediated activities in the learning process have been gradually ...
    ... motivation for introducing a blended learning system came from the fact that in traditional face-to-face learning, the students were prone to taking a basically passive role. Thus the new learning system was aimed at turning the student role in the learning process to a more active one, and ...
    ... and Learning Management Systems – Global E-learning in a Scandinavian Perspective, NKI Forlaget, Oslo, 2003. [3] Zdravkova, K., E-learning 2.0 and its implementation, INFOtheca, Journal of informatics and librarianship, Vol. XI, No.2, pp.3-19, 2010. [4] Teresa Martin-Blas, E-learning Platforms ...

  • Using technology for knowledge transfer between academia and enterprises

    Ivan Obradović, Ranka Stanković (2014)
    ... metadata, thus providing enhanced searching capabilities. Namely, when a critical amount of learning resources is reached, it is very important that they are well described and tagged in a standard way in machine readable form. This approach has many advantages: • Results returned by search engines ...
    ... Faculty of Mining and Geology (FMG), the Learning management system encompassing several specific content and learning management software tools, and Development tools, software to support the development, use, reuse and delivery of learning content; • Learning resources - both academic, in the form ...
    ... and thus foster enhanced learning within higher education institutions and life-long learning within enterprises. Students will be offered an insight into expert knowledge gained through practice within enterprises, whereas employees involved in life-long learning will have access to state of ...

  • LRMI markup of OER content within the BAEKTEL project

    Ranka Stanković, Daniela Carlucci, Olivera Kitanović, Nikola Vulović, Bojan Zlatić (2015)
    ... educational community. The main rationale for the approach is that the choice of a standardized learning object metadata vocabulary has valuable and beneficial implications. Within the BAEKTEL platform, machine readable information is inserted into the code of web pages, which helps search engines interpret ...
    ... choice of a standardized learning object metadata vocabulary has valuable and beneficial institutional and pedagogical implications. When a large amount of OER is reached, it is even more important that they are well described and tagged in a standard way in machine readable form. In that ...
    ... strategies and individualized learning. In order to make OER accessible and discoverable by potential users across the web, they should be annotated in such a way that the users can understand what specific learning objects are about, what is their learning content and prerequisites for ...

  • Developing Students’ Mining and Geology Vocabulary Through Flashcards and L1 in the CLIL Classroom

    Lidija Beko, Ivan Obradović, Ranka Stanković (2015)
    ... the central terminological resource is an invaluable tool in the learning process, it is included in the blended learning approach through an export of its subsets to the Moodle e-learning environment. (Stanković et al 2012, e-Learning). In search of acceptable flashcard system, we have opted for ...
    ... of their exposure to English inside and outside the school. We hypothesized that CLIL method will lead to better learning results compared with traditional foreign language learning method due to bigger and better opportunity to enlarge both receptive and productive vocabularies. On the other hand ...
    ... Nation 2001). Explicit learning with flashcards falls into the category of deep strategies which take more time but ensure greater retention and ease retrieval memory (Nation 2003 22). By making extensive use of dictionaries and exposure to relevant items, this type of learning builds up deeper knowledge ...

  • Open Educational Resources in Serbia

    Ivan Obradović, Ranka Stanković, Marija Blagojević, Danijela Milošević (2020)
    Open educational resources, BAEKTEL, Metadata portal
    ... applying OER. -Learners are able to use OER in education or lifelong learning Beside traditional teaching/learning process in Serbia, blended learning is also very common. In this kind of learning teachers usually use some of learning management systems in addition to traditional teaching. In recent ...
    ... International Conference on e-Learning (eLearning-2013), Belgrade, Serbia. Stanković, R., Obradović, I., Kitanović, O., & Kolonja, L. (2012). Building Terminological Resources in an e-Learning Environment. Proceedings of The Fourth International Conference on e-Learning (eLearning-2012), Belgrade ...
    ... implementation of blended learning in a university setting. Proceedings of the Second International Conference on e-Learning, eLearning 2011 , 61-66. Stefanovic N., & Milosevic D. (2017) Innovative OER Model for Technology-Enhanced Academic and Entrepreneurial Learning. In: Jemni M., Kinshuk, Khribi ...

  • Building Terminological Resources in an e-Learning Environment

    Ranka Stanković, Ivan Obradović, Olivera Kitanović, Ljiljana Kolonja (2012)
    ... As a central terminological resource it is also invaluable in the learning process, and it is included in the blended learning approach at the Faculty of Mining and Geology through an export of its subsets to the Moodle e-learning environment. This paper gives an outline of RudOnto, details about ...
    ... make students familiar with the appropriate terminology in at least one of the "major" languages. When blended learning is implemented, where e-learning is an important part of the learning process, then the ever expanding number of available texts in electronic form on the web makes this issue even ...
    ... importance of such resources in e-learning is growing rapidly. Namely, ontologies are in the core of the Web of knowledge – the Semantic Web, which can serve as an invaluable e- learning tool [4]. In the Semantic Web ontologies are integrated into repositories of learning objects, with the aim of organizing ...

  • A Mathematical Learning Environment Based on Serbian Language Resources

    Radojičić Marija, Obradović Ivan, Stanković Ranka, Utvić Miloć, Kaplar Sebastijan (2018)
    In recent years, in line with ever growing usage of Information technology, the learning environments are changing. The amount of available learning materials in various forms has increased. These new environments demand comprehensive learning systems, which enable management of the learning corpus with special attention paid to relevant lexical resources. In this paper we present the concept of a Mathematical Learning Environment in Serbian (MLES), which is based on a corpus of mathematical materials and various lexical resources, enabling ...
    mathematical content, text processing, mathematical formulae
    ... growing usage of Information technology, the learning environments are changing. The amount of available learning materials in various forms has increased. These new environments demand comprehensive learning systems, which enable management of the learning corpus with special attention paid to relevant ...
    ... resulting in a growing number and availability of learning materials, had a strong impact on changes in learning environments. New learning environments are needed, requiring appropriate technology to facilitate access to and management of learning materials in specific domains. Bearing this in ...
    ... 04:06:32 A Mathematical Learning Environment Based on Serbian Language Resources Radojičić Marija, Obradović Ivan, Stanković Ranka, Utvić Miloć, Kaplar Sebastijan Дигитални репозиторијум Рударско-геолошког факултета Универзитета у Београду [ДР РГФ] A Mathematical Learning Environment Based on Serbian ...

  • Advantages and challenges in presenting mathematical content using EDX platform

    Marija Radojičić, Ivan Obradović, Ranka Stanković, Olivera Kitanović, Roberto Linzalone (2016)
    ... technologies has contributed to faster development of Open Educational Resources. OERs have had significant impact on lifelong learning and on the availability of learning content. Despite worldwide trends, in Serbia the idea of implementing OER materials in higher education is still new. This paper ...
    ... [4]: 1) Improvement of the quality of learning materials through peer review processes and use of modern technology. 2) Innovation in the teaching process, openness and availability with low costs. 3) Short periods for publishing learning material, while serving the needs of particular ...
    ... Linzalone, R., Schiuma, G., & Carlucci, D. “Creating an environment for free education and technology enhanced learning”, in Proc. The Fifth International Conference on e-Learning, pp. 44- 47, Sep. 2014. [6] Adeel, M., Cheung, H. S., & Khiyal, S. H. .” Math GO! prototype of a content based ...