About
47
Publications
3,746
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
186
Citations
Introduction
Drazen Draskovic, PhD, is an Associate Professor at the School of Electrical Engineering, University of Belgrade, Serbia. Drazen does research in Software Engineering, Data Mining and Analytics and Artificial Intelligence.
Current institution
Publications
Publications (47)
Machine learning (ML) models have gained significant attention in a variety of applications, from computer vision to natural language processing, and are almost always based on big data. There are a growing number of applications and products with built-in machine learning models, and this is the area where software engineering, artificial intellig...
Od osnivanja Odseka za softversko inženjerstvo na Elektrotehničkom fakultetu u Beogradu 11. maja 2004. godine pa sve do danas, ovaj Odsek je rastao i razvijao se paralelno sa IT industrijom Republike Srbije i matičnim Elektrotehničkim fakultetom. Akreditovan je četiri puta, 2008, 2013, 2017. i 2024. godine. Na njemu je diplomiralo 932 studenta, od...
At the School of Electrical Engineering at the University of Belgrade, the course Principles of Software Engineering was formed to make future software engineers familiar with the basic concepts of the field of Software Development. The core of this course presents a team project, where students engage in the complete software development life cycl...
A study on facial keypoints recognition using five deep learning models is presented in this paper, focusing on emphasizing the significance of striking the right balance between model complexity and training data volume. Three convolutional neural networks - LeNet-5, AlexNet, and VGG-16 - are also included in the models that are being presented, a...
Nowadays, we heavily depend on software, as we utilize it daily. Bugs in the software can cause significant damage, loss of private data and money, and even loss of human lives. Software testing and quality assurance discipline, which belongs to the software engineering domain, aims to ensure that the software is good enough before its release to t...
![a View of test set-up [5] and b damage of the infill wall at the...](publication/371175181/figure/fig3/AS:11431281163539010@1685586311068/a-View-of-test-set-up-5-and-b-damage-of-the-infill-wall-at-the-applied-displacement-of_Q320.jpg)
![Index of structural response for the three study areas [27]](publication/371175181/figure/fig4/AS:11431281163582028@1685586312318/Index-of-structural-response-for-the-three-study-areas-27_Q320.jpg)
This article describes a teaching strategy that synergizes computing and management, aimed at the running of complex projects in industry and academia, in the areas of civil engineering, physics, geosciences, and a number of other related fields. The course derived from this strategy includes four parts: (a) Computing with a selected set of modern...
This article presents a taxonomy and represents a repository of open problems in computing for numerically and logically intensive problems in a number of disciplines that have to synergize for the best performance of simulation-based feasibility studies on nature-oriented engineering in general and civil engineering in particular. Topics include b...
This paper explains automatic differentiation, discussing two primary modes - forward and backward - and their respective implementation methods. In the context of issues encountered in machine learning and deep learning, the forward mode is deemed more suitable as it efficiently differentiates functions with numerous inputs compared to outputs. Gi...
Machine learning (ML) has become an increasingly popular choice of scientific research for many students due to its application in various fields. However, students often have difficulty starting with machine learning concepts due to too much focus on programming. Therefore, they are deprived of a more profound knowledge of machine learning concept...
In this research, a method of developing a machine model for sentiment processing in the Serbian language is presented. The Serbian language, unlike English and other popular languages, belongs to the group of languages with limited resources. Three different data sets were used as a data source: a balanced set of music album reviews, a balanced se...
The use of version control tools together with the code review techniques is the basis of modern software development. In order to introduce future software engineers to these tools, as well as the process of software development, and to
better prepare them for the industry work, the course “Principles of Software Engineering” was formed at the Sc...
One way of testing a malware detection tool is to expose it to a large number of diverse malware samples and verify its detection accuracy. During these tests, the host system must not be harmed by malware and yet be able to analyze its harmful behavior. An additional challenge is to run a large number of executables in the shortest amount of time....
Since the Coronavirus outbreak in December of 2019, people have put a lot of effort into its early diagnosis by assessing signs and symptoms obtained from various studies. To this goal, deep learning models are trained to detect the presence of COVID-19 from three most commonly used lung-imaging modes: X-Ray, Ultrasound, and Computed Tomography (CT...
Artificial intelligence (AI) comprises a large spectrum of groups of algorithms: heuristic algorithms for search and planning, formal methods for representation of knowledge and reasoning, algorithms for machine learning and many more. Since these algorithms are complex, there is a need for a system which would enable their application both in ever...
This chapter describes the essence of a course for senior level undergraduate students and for master students of computer science and engineering, and analyzes its effects. The course prepares students for their professional life after graduation, and especially, it prepares them for the challenges related to efforts to bring new paradigm-shifting...
This paper describes a software system for testing students' knowledge using modern web technologies. The goal was to create an application that would help the students to interactively learn the subject Intelligent Systems. As an example, for this learning system the field of formal logic was chosen, but it is possible to implement tests for other...
Machine-learning techniques are widely used in the computer processing of natural language. Software agents are programs that use machine learning and natural language processing to communicate with users and to perform certain tasks or provide specific information. This paper provides an overview of basic software agents and describes the implemen...
Modern education is hard to imagine without the use of e-learning tools, but still the transition from traditional "paper-and-pencil" examining to electronic exams is to some extent cautious. Although course administration and exam evaluation are much easier with learning management systems, there are concerns among teaching staff, that electronic...
In the modern educational process e-learning tools have an increasing application. There are a number of systems that can be used for various purposes and at various levels of education. This paper presents experiences in using one such system as a platform for teaching in higher education. Moodle platform has been successfully used at several comp...
This paper describes a software system for expert systems learning realized at the School of Electrical Engineering at the University of Belgrade. This software has been developed as visual interactive educational system for students and is aimed to be used within undergraduate and graduate courses. The system guides students through examples and s...
This paper examines a possible application of Java technology for an implementation of a software tool for processing and visualization of input signals originating from a thermal power plant’s coal-supply system. Performance of the tool is evaluated from the aspects of algorithms, architecture, and scalability. During the evaluation the performanc...
Genetic algorithms for Internet search have been classified in a recent paper of the same authors, as indicated in the reference section of this paper. The proposed new classification was based on a survey of the open literature and recognizes four basic approaches. This paper analyses these four approaches, and discusses their potentials, especial...
Genetic algorithms for Internet Search were classified a lot in the open literature, but one specific aspect there off - the mutational approaches - was not. This paper represents an effort to shot light on the existing mutational approaches in the context of the genetic algorithms that they are a part of. Major contributions of this paper are: (a)...
In this paper a model of software system for parking using search algorithms has been described. The basic idea is to provide a system user with a fast and simplified way to find the nearest empty place while entering the parking lot of large surface. During the searching procedure, modified branch and bound method is used. On entering the parking...
U radu je opisan softverski sistem, koji je realizovan na Elektrotehničkom fakultetu u Beogradu, za učenje predmeta Ekspertski sistemi. Softver je razvijen kao edukacioni sistem namenjen studentima i koristi se za potrebe nastave na osnovnim i master studijama. Sistem omogućava pregled primera i zadataka korak po korak po temama kojima pripadaju i...
