Dušan Bogićević

Mr. Dušan Bogićević

orcid

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2021 in Vojnotehnicki glasnik
Verified
Journal Article
Open access
PDF file
ITIvan Tot
Ivan Tot
JBJovan B. Bajčetić
Jovan B. Bajčetić
BJBoriša Jovanović
Boriša Jovanović
MTMladen B. Trikoš
Mladen B. Trikoš
DBDušan Bogićević
Dušan Bogićević
TGTamara M. Gajić
Tamara M. Gajić
Introduction/purpose: Nowadays, user identification systems play a very important role in modern society. Complex security requirements have led experts to explore ways in which biometric data can be used to identify user identities. This paper presents an overview of biometric standards and methods which can be used to identify users in biometric systems, and therefore to protect information and communication systems. Methods: This paper deals with the problem of standardization in the field of biometrics. The first part of the paper presents concrete examples of the most widely used biometric standards. The second part of the paper gives an overview of the most used biometric methods. Results: The obtained results show that the development of biometric systems and biometric sensors contributes to better protection of identity from misuse, because biometric technologies have great potential for improving the security and accuracy of system operation. Biometric systems improve the security of users and also provide much greater precision in establishing identity. Conclusion: The development of biometric standards should focus on their interconnectivity, as well as on increasing connectivity with other IT standards.

1 January 2018 in Vojnotehnicki glasnik
Verified
Journal Article
Open access
PDF file
ITIvan Tot
Ivan Tot
DBDušan Bogićević
Dušan Bogićević
MTMladen B. Trikoš
Mladen B. Trikoš
Komlen LalovićKomlen Lalović
Komlen Lalović
As an extension to the concept of the Internet of Things (IoT), Web of Things (WoT) represents a step towards connecting smart things to the existing web environment while considering issues such as heterogeneity, scalability, and usability. This paper is dedicated to current opportunities as well as challenges for development in the concept of WoT. The theoretical foundations of the Internet of Things concept, such as architecture, protocols, services, and things themselves, which form the basis of both concepts, are described in the paper. The paper deals with the necessary preconditions for developing the concept of Web of Things. The main contribution of the paper is a proposal of architecture based on the FIWARE platform as the basis for the development of Web of Things. The demonstration of the proposed architecture is described by a real case scenario.

1 January 2021 in Vojnotehnicki glasnik
Verified
Journal Article
Open access
PDF file
DBDušan Bogićević
Dušan Bogićević
ITIvan Tot
Ivan Tot
RPRadomir Prodanović
Radomir Prodanović
BTBojan J. Todorović
Bojan J. Todorović
Introduction/purpose: The process of issuing and retrieving weapons in the military should be fast enough and should provide immediate availability of accurate information on the status of weapons. Methods: This paper deals with the problem of digitizing the recording of issuing and returning weapons through the use of modern Edge computing technology. The problem is presented through two approaches. The first approach is based on the application of machine learning algorithms for recognizing the serial number of a weapon based on the camera image, while the second approach concerns the application of RFID technology. User authentication is based on the application of biometrics. Results: The results obtained from testing the architecture for identifying weapons using a camera indicate that such an architecture is not suitable for identifying weapons. A weapon identification solution using RFID technology overcomes the problems of the previously mentioned solution. However, RFID technology requires additional modifications regarding the implementation of tags on or into weapons so that readings can be made. Conclusion: The implemented weapon identification solution based on RFID technology and a user identification solution with biometric authentication enables easy and reliable identification, speed of issuing and retrieval of weapons, network relieving, and real-time monitoring of the weapon status.

17 April 2026 in Electronics
Verified
Journal Article
Open access
PDF file
DBDušan Bogićević
Dušan Bogićević
DSDragan Stojanović
Dragan Stojanović
MGMilan Gnjatović
Milan Gnjatović
ITIvan Tot
Ivan Tot
BJBoriša Jovanović
Boriša Jovanović
This paper evaluates the feasibility of real-time traffic data analysis on resource-constrained edge devices using a hybrid processing approach. The proposed architecture integrates an LF Edge eKuiper complex event processing engine, deployed within Docker containers, with a native YOLO deep learning model for pedestrian detection. The model processes video frames at 480 × 240 resolution on CPU-only Raspberry Pi devices, achieving up to 30 FPS. The research specifically investigates the performance limits of Raspberry Pi 3 and Raspberry Pi 4 platforms when simultaneously processing high-throughput simulated traffic data from the SUMO simulator (Belgrade scenario, with vehicle distributions and densities adjusted for small, medium, and large traffic volumes) and live video streams, respectively. Experimental results indicate that while both platforms can process up to 2600 messages per second in the settings without image processing, the introduction of a camera sensor reveals a significant hardware bottleneck. The Raspberry Pi 4 maintains robust real-time performance with an average complex event detection latency of less than 500 ms. In contrast, the Raspberry Pi 3 exhibits severe performance degradation, with image processing delays exceeding 8 s, rendering it unsuitable for real-time safety alerts. The findings demonstrate that with appropriate hardware selection, edge-based complex event processing can successfully detect critical safety events, such as sudden vehicle acceleration near pedestrians, without relying on cloud infrastructure.