Vladan Devedzic

University of Belgrade, Beograd, Central Serbia, Serbia

Are you Vladan Devedzic?

Claim your profile

Publications (190)58.76 Total impact

  • Jelena Jovanovic · Vladan Devedzic
    [Show abstract] [Hide abstract]
    ABSTRACT: The paper looks at the increasingly popular concept of Open Badges (OBs) and the technology that supports it, and provides several insights that might help researchers and practitioners decide on how to make the best use of OBs in specific educational settings. In spite of the current big hype around OBs among practitioners, academic literature on them is still scarce. There is a number of challenges that developers and the wider educational community face when it comes to developing and enacting an OB system – from pedagogical and motivational ones, to technological, to those related to institutional policies and to validity and credibility of badges. By discussing these challenges, the paper offers a critical overview and a reality check of practical opportunities for using OBs, thus indicating several avenues to inspire further research.
    Lecture Notes in Computer Science 08/2014; 8613:56-65. DOI:10.1007/978-3-319-09635-3_6 · 0.51 Impact Factor
  • Source
    Jelena Jovanovic · Vladan Devedzic
    [Show abstract] [Hide abstract]
    ABSTRACT: This report is centered on the emerging concept and technology of Open Badges (OBs) that are offering novel means and practices of motivating, scaffolding, recognizing, and credentialing learning. OBs are closely associated with values such as openness and learners’ agency, participatory learning and peer-learning communities. This report points to the distinctive features of OBs and how they have positioned OBs as suitable candidates for addressing some of the pressing challenges in the context of lifelong learning, including (but not limited to) (1) recognition of learning in multiple and diverse environments that go beyond traditional classrooms; (2) recognition of diverse kinds of skills and knowledge, including soft and general skills; (3) support for alternative forms of assessment; (4) the need for transparent and easily verifiable digital credentials. The report also offers an overview of the major issues and challenges that might delay or even prevent widespread adoption of this emerging technology.
    04/2014; 20(1). DOI:10.1007/s10758-014-9232-6
  • Vladan Devedzic
    [Show abstract] [Hide abstract]
    ABSTRACT: Although Technology Enhanced Learning (TEL) is still developing and attracts a lot of R&D attention, initiatives and funding worldwide, it has been around for quite some time and allows for a critical assessment. Once just "somewhere at the intersection of pedagogy and learning technology", today TEL spans many other fields and phenomena, like social and organizational processes, computer games, knowledge management, standardization, policy making in various sectors, sustaining the impact of learning, and efforts to overcome digital divide. Still, not everything goes smoothly. As reports and surveys indicate, there are many challenges ahead, still waiting to be tackled.
    5th ICT Innovations Conference; 01/2014
  • [Show abstract] [Hide abstract]
    ABSTRACT: Online human textual interaction often carries important emotional meanings inaccessible to computers. We propose an approach to textual emotion recognition in the context of computer-mediated communication. The proposed recognition approach works at the sentence level and uses the standard Ekman emotion classification. It is grounded in a refined keyword-spotting method that employs: a WordNet-based word lexicon, a lexicon of emoticons, common abbreviations and colloquialisms, and a set of heuristic rules. The approach is implemented through the Synesketch software system. Synesketch is published as a free, open source software library. Several Synesketch-based applications presented in the paper, such as the the emotional visual chat, stress the practical value of the approach. Finally, the evaluation of the proposed emotion recognition algorithm shows high accuracy and promising results for future research and applications.
    IEEE Transactions on Affective Computing 07/2013; 4(3):312-325. DOI:10.1109/T-AFFC.2013.18 · 2.68 Impact Factor
  • Zoran Sevarac · Vladan Devedzic · Jelena Jovanovic
    [Show abstract] [Hide abstract]
    ABSTRACT: Neuro-Fuzzy Pedagogical Recommender (NFPR) is adaptive recommender based on neuro-fuzzy inference, that can be used to create pedagogical rules in Technology Enhanced Learning (TEL) systems. NFPR is domain independent, provides easy to use API for integration with other systems, and comes with specialized tool (wizard) for creation of NFPR software components. The most important feature of NFPR is its flexibility, that allows teachers to create their own set of pedagogical rules. The proposed model has been implemented and tested with simulated data. Our effort in bringing neuro-fuzzy recommender to the field of TEL (Technology Enhanced Learning) seems to be the first attempt of its kind.
    Expert Systems with Applications 08/2012; 39(10):9797-9806. DOI:10.1016/j.eswa.2012.02.174 · 2.24 Impact Factor
  • Vladan Devedzic
    Computer Science and Information Systems 06/2012; 9(2):V-VIII. · 0.48 Impact Factor
  • Dragan Djuric · Vladan Devedzic
    [Show abstract] [Hide abstract]
    ABSTRACT: There is a notable overlap of the challenges with which the semantic technologies and software engineering deal. They can also complement and mutually improve each other. Current efforts mostly focus on improving software tools around the resource description framework (RDF) and Web Ontology Language (OWL) Web-oriented ecosystem that helps ontology engineers but is alien to software engineers. This paper presents an opposite approach taken from the software developer's viewpoint - an incorporation of the ontology paradigm into a general-purpose programming language, in a simple and agile way, on a small scale, and in an unpretentious manner. The objective is to help programmers write simple domain-driven code with richer semantics. The means to achieve this objective relies on metaprogramming to internalize the ontology modeling paradigm into a mainstream programming environment based on the Java ecosystem, in a lightweight manner suitable for small teams. An embedded meta domain-specific language (DSL), which is called Magic Potion, is implemented in Clojure and blends ontology, functional, object-oriented, and concurrent paradigms. An example from the technology enhanced learning (TEL) domain is used to illustrate Magic Potion in action.
    IEEE Transactions on Systems Man and Cybernetics Part C (Applications and Reviews) 02/2012; 42(1-42):3 - 14. DOI:10.1109/TSMCC.2011.2140316 · 2.17 Impact Factor
  • Bojan Jovicic · Vladan Devedzic · Dragan Djuric · Ramo Sendelj
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper analyzes different technical quantitative aspects of ERP systems development and maintenance in agile approach context. ERP systems usually have huge numbers of tables and related classes, with a growing complexity that easily gets difficult to manage. The problem is to identify what are the things that are used often, what are the things that not used, and which ones are worthy of investing our time in improving. To determine these points precisely from technical perspective this paper analyzes the data from several technical aspects. Usually an upgrade is worth up to 1/3 of initial investment and this approach has helped us achieve productive ERP system development environment, and enabled us to perform an ERP system upgrade to second next version, skipping a whole version, which is even more worthier. The analysis that was performed is shown to be advantageous in the way of quantitative technical approach, in comparison to previous, more soft skills oriented, approaches.
    Proceeding of the 5th Annual India Software Engineering Conference, ISEC 2012, Kanpur, India, February 22-25, 2012; 01/2012
  • Source
  • Article: Editorial.
    Marco Bertini · Vladan Devedzic · Dragan Gasevic · Carlo Torniai
  • Danijela Grahovac · Vladan Devedzic
    [Show abstract] [Hide abstract]
    ABSTRACT: Understanding and using cost management is a key to success in any type of organization, because it helps managers to collect important data about the costs assigned to products, services and customers and use it for planning and control function. This paper discusses development and application of an expert system for reasonable cost related decision making and continuous cost management process improvement. The system is called COMEX (cost management expert system). This paper also shows how COMEX can be used for improvement of the billing department business processes. COMEX relies on information generated using the activity-based costing (ABC) method, accounting method based on activities, created to improve cost management system by focusing on the driver costs of individual activities. Still, this paper focuses on design and implementation of the COMEX system, and only briefly surveys the ABC method.
    Expert Systems with Applications 12/2010; 37(12-37):7684-7695. DOI:10.1016/j.eswa.2010.04.073 · 2.24 Impact Factor
  • Source
    Ana Kovacevic · Vladan Devedzic · Viktor Pocajt
    [Show abstract] [Hide abstract]
    ABSTRACT: Purpose – This paper aims to propose a solution for recommending digital library services based on data mining techniques (clustering and predictive classification). Design/methodology/approach – Data mining techniques are used to recommend digital library services based on the user's profile and search history. First, similar users were clustered together, based on their profiles and search behavior. Then predictive classification for recommending appropriate services to them was used. It has been shown that users in the same cluster have a high probability of accepting similar services or their patterns. Findings – The results indicate that k-means clustering and Naive Bayes classification may be used to improve the accuracy of service recommendation. The overall accuracy is satisfying, while average accuracy depends on the specific service. The results were better for frequently occurring services. Research limitations/implications – Datasets were used from the KOBSON digital library. Only clustering and predictive classification was applied. If the correlation between the service and the institution were higher, it would have better accuracy. Originality/value – The paper applied different and efficient data mining techniques for clustering digital library users based on their profiles and their search behavior, i.e. users' interaction with library services, and obtain user patterns with respect to the library services they use. A digital library may apply this approach to offer appropriate services to new users more easily. The recommendations will be based on library items that similar users have already found useful.
    The Electronic Library 11/2010; 28(6):829-843. DOI:10.1108/02640471011093525 · 0.50 Impact Factor
  • Dragan Djuric · Vladan Devedzic
    [Show abstract] [Hide abstract]
    ABSTRACT: Software environments are typically based on a single programming paradigm, such as ontologies, functions, objects, or concurrency. This can limit what developers can represent and how elegant their solutions can be, so today's applications usually involve mixing and matching languages, platforms, and paradigms. However, cross-mapping multiple paradigms and platforms generates an impedance mismatch that increases a solution's complexity. Metaprogramming supports a lightweight process to incorporate different programming paradigms in a single development environment that's suitable for small development teams.
    IEEE Software 09/2010; 27:38-44. DOI:10.1109/MS.2010.90 · 1.05 Impact Factor
  • Ana Kovacevic · Vladan Devedzic · Viktor Pocajt
    [Show abstract] [Hide abstract]
    ABSTRACT: Purpose – This paper aims to address the problem of enhancing the selection of titles offered by a digital library, by analysing the differences in these titles when they are cited by local authors in their publications and when they are listed in the digital library offer. Design/methodology/approach – Text mining techniques were used to identify duplicate references. Moreover, the process of identifying syntactically different data was improved with the automated discovery of thesauri from correctly matched data, and the generated thesaurus was further used in semantic clustering. The results were effectively visually represented. Findings – The paper finds that the function based on the Jaro-Winkler algorithm may be efficiently used in the de-duplication process. A generated thesaurus that utilises domain-specific knowledge can also be used in the semantic clustering of references. It was shown that semantic clustering may be most useful in partitioning data, which is particularly significant when dealing with large amounts of data, which is usually the case. Moreover, those references that have the same or similar scores may be considered as candidate matches in the further de-duplication process. Finally, it proved to be a more efficient way of visually representing the results. Originality/value – This function can be implemented to enhance the selection of titles to be offered by a digital library, in terms of making that offer more compliant with what the library users frequently cite.
    Program electronic library and information systems 04/2010; 44(2):132-148. DOI:10.1108/00330331011039490 · 0.65 Impact Factor
  • Dragan Djuric · Jelena Jovanovic · Vladan Devedzic · Ramo Sendelj
    [Show abstract] [Hide abstract]
    ABSTRACT: Ontologies, one of the cornerstone technologies of the Semantic Web are a very expressive and powerful means for domain modeling. To become really usable and ubiquitous, the implementations of ontology languages yet have to deliver satisfactory performance and before anything else have to be developer-friendly. We present an example of using Magic Potion, a description logics-based domain specific meta-language for building executable domain models. We are using LOCO ontology framework developed to support personalised learning contexts in learning applications to illustrate how ontologies in the form of executable domain-specific languages can blend the Semantic Web ideas into classical software engineering to improve expressiveness of domain models.
    Proceeding of the 3rd Annual India Software Engineering Conference, ISEC 2010, Mysore, India, February 25-27, 2010; 01/2010
  • Source
    Nenad Krdzavac · Dragan Gasevic · Vladan Devedzic
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents a method for implementing tableau algorithm for description logics (DLs). The architectures of the present DL reasoners such as RACER or FaCT were developed using programming languages as Java or LISP. The implementations are not based on original definition of the abstract syntax, but they require transformation of abstract syntax into concrete syntax implementation languages use. In order to address these issues, we propose the use of model-driven engineering principles for the development of a DL reasoner where a definition of a DL abstract syntax is provided by means of metamodels. The presented approach is based on the use of a MOF-based model repository and QVT-like transformations, which transform models compliant to the DL metamodel taken from the OMG's Ontology Definition Metamodel specification into models compliant to the Tableau metamodel defined in this paper.
    Computer Science and Information Systems 06/2009; 6(1):23-43. DOI:10.2298/CSIS0901023K · 0.48 Impact Factor
  • Dragan Gasevic · Dragan Djuric · Vladan Devedzic
    01/2009; Springer., ISBN: 978-3-642-00281-6
  • Dragan Gasevic · Dragan Djuric · Vladan Devedzic
    [Show abstract] [Hide abstract]
    ABSTRACT: The MOF-based ontology metamodels of ontology languages presented in this book, namely the ODM and the Ontology UML Profile (OUP), are defined in the context of the MDA's metamodeling architecture. However, such a definition is not sufficient; they need to interact with real-word ontologies, for example with OWL ontologies. It is obvious that we need to develop transformations to support conversions between MDA ontology languages and OWL. The current ODM specification itself provides a solution to this problem by defining the QVT transformations among the defined metamodels in the specification. In this chapter, we analyze the problem of transformations in terms of the modeling and technical spaces that we described earlier in the book (see Chap. 5).
  • Dragan Gasevic · Dragan Djuric · Vladan Devedzic
    [Show abstract] [Hide abstract]
    ABSTRACT: It is well known from software project management practice that developers' familiarity with the principles of several different modeling approaches can be beneficial for the development team. Changing the modeling and design aspects from time to time during the system development, e.g., from OO to relational, from relational to functional, and the like, often helps prevent schedule overruns (Zahniser 1993).
  • Source
    Computer Science and Information Systems 01/2009; 6:47-85. DOI:10.2298/CSIS0902047M · 0.48 Impact Factor

Publication Stats

2k Citations
58.76 Total Impact Points


  • 1997–2014
    • University of Belgrade
      • • Faculty of Organizational Sciences
      • • Chair of Software Engineering
      • • Chair of Information Technology
      • • Chair of Information Systems
      Beograd, Central Serbia, Serbia
  • 2006
    • Simon Fraser University
      Burnaby, British Columbia, Canada
  • 2005
    • Carl von Ossietzky Universität Oldenburg
      Oldenburg, Lower Saxony, Germany
  • 2003
    • Technische Universität München
      München, Bavaria, Germany
  • 2000
    • University of Novi Sad
      • Faculty of Science
      Varadinum Petri, Autonomna Pokrajina Vojvodina, Serbia
  • 1995
    • Mihajlo Pupin Institute
      Beograd, Central Serbia, Serbia