Andjelija Djordjevic

Ms. Andjelija Djordjevic


Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
12 July 2022 in Electronics
Verified
Journal Article
Open access
PDF file
PRPetar Rajkovic
Petar Rajkovic
DADejan Aleksić
Dejan Aleksić
Andjelija DjordjevicAndjelija Djordjevic
Andjelija Djordjevic
DJDragan Jankovic
Dragan Jankovic
Complex industrial systems run the different pieces of software in several interconnected physical layers. The software update in such an environment must be performed in the shortest possible period with the lowest possible resource usage. Namely, it is critical to minimize the data traffic, decrease software downtime, and reduce the impact of the transitional stage during the update process. To meet these requirements and to unify the update process, the common software node structure along with a hybrid software deployment strategy is proposed. The hybrid strategy is defined as a combination of the existing and well-tested techniques—blue/green, canary, and feature flags. The main aim was to utilize their positive sides and to obtain a better overall effect. The approach was tested in the simulation environment, based on the realistic factory layout, and running the software related to the enterprise resource planning (ERP) level. For successful updates, the proposed hybrid deployment method reduced downtime on server nodes to less than 5% and on client nodes to a half compared with the standard approach. The volume of data traffic reduction in a configuration with sentinel nodes is reduced by one-third. The presented results look promising, especially in cases of erroneous updates when a roll back is needed, where the downtime on the server nodes is reduced to the level of 3%. Achieved results are used to define the set of recommendations that could be extended for the other software layers, followed by a discussion about further potential problems and strategy variations.

7 August 2025 in Computers
Verified
Journal Article
Open access
PDF file
Aleksandar MilenkovicAleksandar Milenkovic
Aleksandar Milenkovic
Andjelija DjordjevicAndjelija Djordjevic
Andjelija Djordjevic
DJDragan Jankovic
Dragan Jankovic
PRPetar Rajkovic
Petar Rajkovic
KEKofi Edee
Kofi Edee
Tatjana GricTatjana Gric
Tatjana Gric
This paper aims to leverage artificial intelligence (AI) to assist physicians in utilizing advanced deep learning techniques integrated into developed models within electronic health records (EHRs) in medical information systems (MISes), which have been in use for over 15 years in health centers across the Republic of Serbia. This paper presents a human-centered AI approach that emphasizes physician decision-making supported by AI models. This study presents two developed and implemented deep neural network (DNN) models in the EHR. Both models were based on data that were collected during the COVID-19 outbreak. The models were evaluated using five-fold cross-validation. The convolutional neural network (CNN), based on the pre-trained VGG19 architecture for classifying chest X-ray images, was trained on a publicly available smaller dataset containing 196 entries, and achieved an average classification accuracy of 91.83 ± 2.82%. The DNN model for optimizing patient appointment scheduling was trained on a large dataset (341,569 entries) and a rich feature design extracted from the MIS, which is daily used in Serbia, achieving an average classification accuracy of 77.51 ± 0.70%. Both models have consistent performance and good generalization. The architecture of a realized MIS, incorporating the positioning of developed AI tools that encompass both developed models, is also presented in this study.

1 January 2025 in Facta universitatis - series: Electronics and Energetics
Verified
Journal Article
Open access
PDF file
Aleksandar MilenkovicAleksandar Milenkovic
Aleksandar Milenkovic
DJDragan Jankovic
Dragan Jankovic
Andjelija DjordjevicAndjelija Djordjevic
Andjelija Djordjevic
VSVladimir Sibinović
Vladimir Sibinović
AVAleksandar Veljanovski
Aleksandar Veljanovski
DJDimitrije Jankovic
Dimitrije Jankovic
This paper presents the new concept of Medicine Vending Machine (MVM), called Personalized Medicine Vending Machines (PMVM), motivated by the need to increase social distancing during the COVID-19 pandemic. The conceptual model, the scenarios of using PMVM, and all the necessary preconditions are provided. This paper proposes modifying the existing MVM concept, which can provide better social distancing in times of pandemics and epidemics, emphasizing personalization and picking up prescribed therapy. The medical information system MEDIS.NET has been used as a keystone in the development of PMVM. Pharmacies and patients use prescription data stored in patient electronic health records in MEDIS.NET to provide all conditions needed for the operation of PMVM. Real data from the Pharmacy Institution Nis and Health Center Nis are used to define the scenarios for the use of PMVM. The proposed PMVM would be a new service for smart cities that can contribute to the significant increase of the efficiency of smart cities during the combat against COVID-19 and any similar pandemics in the future.

1 January 2025 in Computer Science and Information Systems
Verified
Journal Article
Open access
PDF file
PRPetar Rajkovic
Petar Rajkovic
DADejan Aleksic
Dejan Aleksic
DJDragan Jankovic
Dragan Jankovic
Aleksandar MilenkovicAleksandar Milenkovic
Aleksandar Milenkovic
Andjelija DjordjevicAndjelija Djordjevic
Andjelija Djordjevic
Complex industrial systems consist of many heterogeneous devices running different hardware and software in a connected, layer-organized environment. Since all these software instances must be updated occasionally, and since they could affect the layers under and above, the definition of deployment strategies that will reduce downtime is necessary. In previous work, we focused on identifying common problems in software update processes and concentrated on the most effective update strategies running at the lowest (Internet of Things ? IoT) and highest (Enterprise Resource Planning ? ERP) levels. The result was a set of recommendations and strategies that should help minimize network utilization and processing resources and make the process as energy-efficient as possible. After that, the core effort of the research is shifted toward the Manufacturing Execution System (MES) layer ? the layer that brings the higher complexity, both in terms of connectivity and software complexity. Following the actual Industry 4.0 paradigm, the software in the MES layer becomes even more critical since it is expected to integrate a whole new set of responsibilities previously belonging to various levels or external solutions. To facilitate further requests, deployment strategies are reevaluated and enriched with innovative approaches such as A/B testing and the separate update service. This paper shows the possible further development of the hybrid software deployment system when applied to the multiconnected levels, such as the MES. The adaptation shows positive results regarding the network load distribution and significant effort reduction when a rollback is needed.