Marijana Pavlov-Kagadejev
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Marijana Pavlov-Kagadejev has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
- Aleksandra Milosavljević
Mining and Metallurgy Institute Bor Alberta Ajnštajna 1 19210 Bor Serbia
6 shared publications - Milan Radivojević
Institut za rudarstvo I metalurgiju Bor, Bor, Srbija
4 shared publications - Ana Kostov
Mining and Metallurgy Institute Bor Alberta Ajnštajna 1 19210 Bor Serbia
3 shared publications - Darko Brodić
University of Belgrade
2 shared publications - Nikola Milivojevic
University of Colorado at Boulder, UCB, Boulder, USA
2 shared publications - Predrag Stolić
University of Belgrade -Technical faculty in Bor Bor Serbia
2 shared publications
Latest Publications
- 1 January 2026
- Published by Akademska Misao
- p. 342-344
Low-cost sistem za monitoring koncentracije ugljen-monoksida zasnovan na Arduino platformi
Rad prikazuje realizovani low-cost sistem za monitoring koncentracije ugljen-monoksida (CO) u realnom vremenu, zasnovanog na Arduino Mega mikrokontroleru i elektrohemijskom senzorskom modulu (ZE07-CO). Sistem omogućava kontinuirano merenje koncentacije CO u opsegu od 0–500 ppm, akviziciju podataka, vremensko označavanje i skladištenje na SD kartici. Integracija sata realnog vremena omogućava preciznu vremensku analizu, dok dodatni senzori obezbeđuju merenje temperature i relativne vlažnosti. Eksperimentalna validacija pokazala je visoku korelaciju sa komercijalnim CO monitorom (R² > 0.8), čime je potvrđena primenljivost sistema za indikativni monitoring i analizu trendova koncentracija CO u zatvorenim prostorima.
- 1 January 2026
- Published by Akademska Misao
- p. 342-344
Low-cost sistem za monitoring koncentracije ugljen-monoksida zasnovan na Arduino platformi
Rad prikazuje realizovani low-cost sistem za monitoring koncentracije ugljen-monoksida (CO) u realnom vremenu, zasnovanog na Arduino Mega mikrokontroleru i elektrohemijskom senzorskom modulu (ZE07-CO). Sistem omogućava kontinuirano merenje koncentacije CO u opsegu od 0–500 ppm, akviziciju podataka, vremensko označavanje i skladištenje na SD kartici. Integracija sata realnog vremena omogućava preciznu vremensku analizu, dok dodatni senzori obezbeđuju merenje temperature i relativne vlažnosti. Eksperimentalna validacija pokazala je visoku korelaciju sa komercijalnim CO monitorom (R² > 0.8), čime je potvrđena primenljivost sistema za indikativni monitoring i analizu trendova koncentracija CO u zatvorenim prostorima.
- Open Access
- 1 January 2026
- Published by Centre for Evaluation in Education and Science (CEON/CEES)
- No. Chemistry,,p. 189-192
XRD investigations of some multifunctional alloys based on silver, tin and indium
In this paper, multifunctional alloys based on silver, tin and indium were investigated. Only small part of characterization methods was performed because there were complex investigations in domain of mentioned alloys. So, XRD results of some Ag-In-Sn alloys were presented here.
- 1 January 2026
- Published by Centre for Evaluation in Education and Science (CEON/CEES)
- No. Chemistry,,p. 189-192
Open AccessXRD investigations of some multifunctional alloys based on silver, tin and indium
In this paper, multifunctional alloys based on silver, tin and indium were investigated. Only small part of characterization methods was performed because there were complex investigations in domain of mentioned alloys. So, XRD results of some Ag-In-Sn alloys were presented here.
- Open Access
- 1 January 2025
- Published by Centre for Evaluation in Education and Science (CEON/CEES)
- No. Industrial,p. 721-724
Application of metaheuristic algorithms in metallurgical industry: A review of methods and applications
Optimization is important in metallurgy due to the complexity of processes, the large number of parameters, and the challenge of finding a balance between cost and quality. Problems associated with the traditional experimental approach are common due to nonlinearity, multi-objective goals, the high cost of experiments, as well as the time required for their execution. The application of metaheuristic algorithms has proven to be effective in solving complex problems. This paper aims to provide an overview of metaheuristic algorithms and their application in the metallurgical industry.
- 1 January 2025
- Published by Centre for Evaluation in Education and Science (CEON/CEES)
- No. Industrial,p. 721-724
Open AccessApplication of metaheuristic algorithms in metallurgical industry: A review of methods and applications
Optimization is important in metallurgy due to the complexity of processes, the large number of parameters, and the challenge of finding a balance between cost and quality. Problems associated with the traditional experimental approach are common due to nonlinearity, multi-objective goals, the high cost of experiments, as well as the time required for their execution. The application of metaheuristic algorithms has proven to be effective in solving complex problems. This paper aims to provide an overview of metaheuristic algorithms and their application in the metallurgical industry.
- Open Access
- 1 January 2025
- Published by Centre for Evaluation in Education and Science (CEON/CEES)
- No. Extractive,p. 304-307
Artificial intelligence challenges in modern alloys design
Artificial intelligence (AI) is used in everyday research and in all fields, including materials science. Various AI models can predict the optimal chemical compositions, mechanical properties, microstructure and phase transformations of materials instead of long-term experiments or expensive simulations, especially for multicomponent alloys. However, its application, in addition to multiple advantages, also brings numerous challenges. This paper presents a brief overview of these challenges in modern alloy design.
- 1 January 2025
- Published by Centre for Evaluation in Education and Science (CEON/CEES)
- No. Extractive,p. 304-307
Open AccessArtificial intelligence challenges in modern alloys design
Artificial intelligence (AI) is used in everyday research and in all fields, including materials science. Various AI models can predict the optimal chemical compositions, mechanical properties, microstructure and phase transformations of materials instead of long-term experiments or expensive simulations, especially for multicomponent alloys. However, its application, in addition to multiple advantages, also brings numerous challenges. This paper presents a brief overview of these challenges in modern alloy design.
- Open Access
- 1 January 2025
- Published by Centre for Evaluation in Education and Science (CEON/CEES)
- No. Papers,p. 587-591
IR camera application in control of the current state of an induction furnace in laboratory conditions
This paper presents the application of a thermal imaging camera (IR camera) in laboratory conditions in order to obtain data for current state of induction furnace. Therefore thermal imaging measurements were done inside the furnace as well as outside, on different areas to check heating and possible overheating of furnace's inner wall. In this manner, these data can help solving some problems in work and maintenance the furnace itself.
- 1 January 2025
- Published by Centre for Evaluation in Education and Science (CEON/CEES)
- No. Papers,p. 587-591
Open AccessIR camera application in control of the current state of an induction furnace in laboratory conditions
This paper presents the application of a thermal imaging camera (IR camera) in laboratory conditions in order to obtain data for current state of induction furnace. Therefore thermal imaging measurements were done inside the furnace as well as outside, on different areas to check heating and possible overheating of furnace's inner wall. In this manner, these data can help solving some problems in work and maintenance the furnace itself.
- Top Cited PapersOpen Access
- 12 February 2024
- Published by Springer Nature in Artificial Intelligence Review
- Vol. 57 (3) , 1-57
Optimizing long-short-term memory models via metaheuristics for decomposition aided wind energy generation forecasting
Power supply from renewable energy is an important part of modern power grids. Robust methods for predicting production are required to balance production and demand to avoid losses. This study proposed an approach that incorporates signal decomposition techniques with Long Short-Term Memory (LSTM) neural networks tuned via a modified metaheuristic algorithm used for wind power generation forecasting. LSTM networks perform notably well when addressing time-series prediction, and further hyperparameter tuning by a modified version of the reptile search algorithm (RSA) can help improve performance. The modified RSA was first evaluated against standard CEC2019 benchmark instances before being applied to the practical challenge. The proposed tuned LSTM model has been tested against two wind production datasets with hourly resolutions. The predictions were executed without and with decomposition for one, two, and three steps ahead. Simulation outcomes have been compared to LSTM networks tuned by other cutting-edge metaheuristics. It was observed that the introduced methodology notably exceed other contenders, as was later confirmed by the statistical analysis. Finally, this study also provides interpretations of the best-performing models on both observed datasets, accompanied by the analysis of the importance and impact each feature has on the predictions.
- 12 February 2024
- Published by Springer Nature in Artificial Intelligence Review
- Vol. 57 (3) , 1-57
Top Cited PapersOpen AccessOptimizing long-short-term memory models via metaheuristics for decomposition aided wind energy generation forecasting
Power supply from renewable energy is an important part of modern power grids. Robust methods for predicting production are required to balance production and demand to avoid losses. This study proposed an approach that incorporates signal decomposition techniques with Long Short-Term Memory (LSTM) neural networks tuned via a modified metaheuristic algorithm used for wind power generation forecasting. LSTM networks perform notably well when addressing time-series prediction, and further hyperparameter tuning by a modified version of the reptile search algorithm (RSA) can help improve performance. The modified RSA was first evaluated against standard CEC2019 benchmark instances before being applied to the practical challenge. The proposed tuned LSTM model has been tested against two wind production datasets with hourly resolutions. The predictions were executed without and with decomposition for one, two, and three steps ahead. Simulation outcomes have been compared to LSTM networks tuned by other cutting-edge metaheuristics. It was observed that the introduced methodology notably exceed other contenders, as was later confirmed by the statistical analysis. Finally, this study also provides interpretations of the best-performing models on both observed datasets, accompanied by the analysis of the importance and impact each feature has on the predictions.
- Open Access
- 1 January 2024
- Published by Centre for Evaluation in Education and Science (CEON/CEES)
- No. Related fi,p. 441-446
Comparative analysis of the time series decomposition techniques in the energy sector applications
Time series decomposition is significant for understanding the consumption, production, and pricing in the energy sector analysis. This paper presents the comparative analyses of three important decomposition techniques: the Empirical Mode Decomposition (EMD), Variational Mode Decomposition (VMD), and Seasonal-Trend decomposition using the Loess (STL). The methodology, advantages, limitations, and applications of these techniques are described to help users selecting the most appropriate method.
- 1 January 2024
- Published by Centre for Evaluation in Education and Science (CEON/CEES)
- No. Related fi,p. 441-446
Open AccessComparative analysis of the time series decomposition techniques in the energy sector applications
Time series decomposition is significant for understanding the consumption, production, and pricing in the energy sector analysis. This paper presents the comparative analyses of three important decomposition techniques: the Empirical Mode Decomposition (EMD), Variational Mode Decomposition (VMD), and Seasonal-Trend decomposition using the Loess (STL). The methodology, advantages, limitations, and applications of these techniques are described to help users selecting the most appropriate method.
- Open Access
- 1 January 2024
- Published by Centre for Evaluation in Education and Science (CEON/CEES) in Mining and Metallurgy Engineering Bor
- No. 1,p. 1-6
The importance of design of experiments
Design of experiments (DOE) is very meaningful and applied in various investigations from science to the industry in order to optimize the process itself. There are several such techniques and each of them has its own advantages, so it is very important to know the basics of DOE. Besides that, every problem, technology, product etc. is unique, so the knowledge about those is crucial as the first step. The most relevant fact is the dependence among variables-input factors and output responses as well as mutual connection between factors. In order to demonstrate the usability and adaptability of DOE for various purposes, some examples are given in this paper.
- 1 January 2024
- Published by Centre for Evaluation in Education and Science (CEON/CEES) in Mining and Metallurgy Engineering Bor
- No. 1,p. 1-6
Open AccessThe importance of design of experiments
Design of experiments (DOE) is very meaningful and applied in various investigations from science to the industry in order to optimize the process itself. There are several such techniques and each of them has its own advantages, so it is very important to know the basics of DOE. Besides that, every problem, technology, product etc. is unique, so the knowledge about those is crucial as the first step. The most relevant fact is the dependence among variables-input factors and output responses as well as mutual connection between factors. In order to demonstrate the usability and adaptability of DOE for various purposes, some examples are given in this paper.
- Open Access
- 1 January 2024
- Published by Centre for Evaluation in Education and Science (CEON/CEES) in Bakar
- Vol. 49 (1) , 21-30
Example of modeling SO2 blower vibrations using the machine learning method
This paper describes an example of applying the machine learning to predict the SO2 blower vibrations. The SVR (Support Vector Regression) algorithm was used to form the model. The paper includes an overview of machine learning and mathematical fundamentals of the SVM model. Based on a large amount of data, obtained from the monitoring system, a mathematical model was constructed. After testing, the measures of model accuracy such as the MSE (Mean Squared Error) and R2 were provided.
- 1 January 2024
- Published by Centre for Evaluation in Education and Science (CEON/CEES) in Bakar
- Vol. 49 (1) , 21-30
Open AccessExample of modeling SO2 blower vibrations using the machine learning method
This paper describes an example of applying the machine learning to predict the SO2 blower vibrations. The SVR (Support Vector Regression) algorithm was used to form the model. The paper includes an overview of machine learning and mathematical fundamentals of the SVM model. Based on a large amount of data, obtained from the monitoring system, a mathematical model was constructed. After testing, the measures of model accuracy such as the MSE (Mean Squared Error) and R2 were provided.
- Open Access
- 1 January 2023
- Published by Centre for Evaluation in Education and Science (CEON/CEES) in Bakar
- Vol. 48 (2) , 35-48
Application of thermovision and computer systems for monitoring vital systems in electrotechnics, mechanical engineering and construction
The paper presents the application of computer systems for monitoring in the fields of electrotehnics, mechanical engineering, and construction. It outlines the basic principles of thermal radiation from objects and describes the operation and structure of a thermal imaging camera, providing practical examples in the mentioned fields. The document showcases examples of in-formation systems for monitoring, along with thermograms obtained through this method.
- 1 January 2023
- Published by Centre for Evaluation in Education and Science (CEON/CEES) in Bakar
- Vol. 48 (2) , 35-48
Open AccessApplication of thermovision and computer systems for monitoring vital systems in electrotechnics, mechanical engineering and construction
The paper presents the application of computer systems for monitoring in the fields of electrotehnics, mechanical engineering, and construction. It outlines the basic principles of thermal radiation from objects and describes the operation and structure of a thermal imaging camera, providing practical examples in the mentioned fields. The document showcases examples of in-formation systems for monitoring, along with thermograms obtained through this method.