Dragana Radosavljević
Research Interests
Dragana Radosavljević has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Aleksandra Petrović
University of Priština in Kosovska Mitrovica - Faculty of Technical Sciences
1 shared publication Biljana Vitošević
Faculty for Sport and Physical Education, University of Priština, Leposavić
1 shared publication- Dardan Klimenta
Faculty of Technical Sciences, University of Priština in Kosovska Mitrovica, RS-38220 Kosovska Mitrovica, Serbia
1 shared publication Fakultet tehničkih nauka u Kosovskoj Mitrovici Univerzitet u Prištini
1 shared publication- Iwona Florek
WSGE University of Applied Sciences
1 shared publication - Ljiljana Savić1 shared publication
Latest Publications
- Open Access
- 29 October 2026
- Published by Akademia Nauk Stosowanych WSGE im. A. De Gasperi w Józefowie in Journal of Modern Science
- Vol. 67 (3) , 145-157
Traffic safety, sustainable mobility and human rights: data-driven analysis of traffic accidents in Serbia
Objectives: This paper presents the application of data mining methods in the analysis of traffic accidents in the Republic of Serbia during the period 2022–2025, based on the open dataset available through the Open Data Portal of the Republic of Serbia. The aim of the study is to examine the extent to which spatial, temporal, and structural attributes enable the differentiation between accidents involving material damage only and accidents involving injured or deceased persons. Material and methods: The analysis was conducted in the Weka environment using the J48, Random Forest, Naive Bayes, kNN, and Logistic algorithms, with evaluation based on Accuracy, Precision, Recall, F1-score, and ROC AUC measures. Results: The results indicate that the Logistic algorithm achieved the best overall performance, while Naive Bayes demonstrated the highest recall for the class of accidents involving injured or deceased persons. Conclusions: The results indicate that the Logistic algorithm achieved the best overall performance, while Naive Bayes demonstrated the highest recall for the class of accidents involving injured or deceased persons.
- 29 October 2026
- Published by Akademia Nauk Stosowanych WSGE im. A. De Gasperi w Józefowie in Journal of Modern Science
- Vol. 67 (3) , 145-157
Open AccessTraffic safety, sustainable mobility and human rights: data-driven analysis of traffic accidents in Serbia
Objectives: This paper presents the application of data mining methods in the analysis of traffic accidents in the Republic of Serbia during the period 2022–2025, based on the open dataset available through the Open Data Portal of the Republic of Serbia. The aim of the study is to examine the extent to which spatial, temporal, and structural attributes enable the differentiation between accidents involving material damage only and accidents involving injured or deceased persons. Material and methods: The analysis was conducted in the Weka environment using the J48, Random Forest, Naive Bayes, kNN, and Logistic algorithms, with evaluation based on Accuracy, Precision, Recall, F1-score, and ROC AUC measures. Results: The results indicate that the Logistic algorithm achieved the best overall performance, while Naive Bayes demonstrated the highest recall for the class of accidents involving injured or deceased persons. Conclusions: The results indicate that the Logistic algorithm achieved the best overall performance, while Naive Bayes demonstrated the highest recall for the class of accidents involving injured or deceased persons.
- 1 January 2021
- Published by University Library in Kragujevac in Energija Ekonomija Ekologija
- Vol. 23 (3) , 45-53
Određivanje optimalnih nagibnih uglova fotonaponskih panela uz uvažavanje smanjenja direktne komponente iradijacije usled efekata senki u fotonaponskim sistemima
This paper considers the influence of the tilt angle of photovoltaic (PV) panels on the total amount of insolation on the surface of these panels on a monthly and annual basis, with and without consideration of shading effect. Based on the obtained results, optimal tilt angles of the PV panels in order to achieve maximum insolation, are determined, as well as the optimal tilt angles for achieving maximum generated electrical energy, taking into account the temperature of the panel. Special attention in the paper is paid to the shading effect created by the panel rows within the PV system and its influence on the reduction of direct component of irradiation and optimal tilt angles for different distances between PV panel rows. In the paper two different models for solar insolation calculation were considered and described in detail, clear day model and real cloud condition model. In order to obtain the average daily solar irradiation on the inclined surface, in addition to appropriate extraterrestrial irradiations, available measurements of the irradiation on the horizontal surface during one year period were used.
- 1 January 2021
- Published by University Library in Kragujevac in Energija Ekonomija Ekologija
- Vol. 23 (3) , 45-53
Određivanje optimalnih nagibnih uglova fotonaponskih panela uz uvažavanje smanjenja direktne komponente iradijacije usled efekata senki u fotonaponskim sistemima
This paper considers the influence of the tilt angle of photovoltaic (PV) panels on the total amount of insolation on the surface of these panels on a monthly and annual basis, with and without consideration of shading effect. Based on the obtained results, optimal tilt angles of the PV panels in order to achieve maximum insolation, are determined, as well as the optimal tilt angles for achieving maximum generated electrical energy, taking into account the temperature of the panel. Special attention in the paper is paid to the shading effect created by the panel rows within the PV system and its influence on the reduction of direct component of irradiation and optimal tilt angles for different distances between PV panel rows. In the paper two different models for solar insolation calculation were considered and described in detail, clear day model and real cloud condition model. In order to obtain the average daily solar irradiation on the inclined surface, in addition to appropriate extraterrestrial irradiations, available measurements of the irradiation on the horizontal surface during one year period were used.
- Open Access
- 1 January 2020
- Published by Centre for Evaluation in Education and Science (CEON/CEES) in Podzemni radovi
- No. 37,p. 41-49
Theoretical analysis of hydromixture transport
This paper presents theoretical considerations and working parameters analyzes of hydrotransport during unstable flow. The variable flow of hydraulic mixture in installations causes unsteady operation and pipes spraying, pump damage, obturation in various sections of the pipeline, reduced capacity as well as higher operating costs. Using mathematical equations presented in this paper, such parameters of the hydraulic mixture, hydrotransport installation and control devices can be determined which protect system from possible clogging. Considering the fact that critical speed of hydraulic mixture depends on transported material grain size, mixture volume mass, diameter of pipeline and specific gravity of solid phase, it is possible to accurately analyze obturation in hydrotransport installations depending on those parameters. In order to prevent hydraulic impacts in hydrotransport installation pipelines, which value can be determined mathematically, it is necessary to adjust installation to hydromixture parameters and pump, or vice versa.
- 1 January 2020
- Published by Centre for Evaluation in Education and Science (CEON/CEES) in Podzemni radovi
- No. 37,p. 41-49
Open AccessTheoretical analysis of hydromixture transport
This paper presents theoretical considerations and working parameters analyzes of hydrotransport during unstable flow. The variable flow of hydraulic mixture in installations causes unsteady operation and pipes spraying, pump damage, obturation in various sections of the pipeline, reduced capacity as well as higher operating costs. Using mathematical equations presented in this paper, such parameters of the hydraulic mixture, hydrotransport installation and control devices can be determined which protect system from possible clogging. Considering the fact that critical speed of hydraulic mixture depends on transported material grain size, mixture volume mass, diameter of pipeline and specific gravity of solid phase, it is possible to accurately analyze obturation in hydrotransport installations depending on those parameters. In order to prevent hydraulic impacts in hydrotransport installation pipelines, which value can be determined mathematically, it is necessary to adjust installation to hydromixture parameters and pump, or vice versa.
- Open Access
- 19 November 2019
- Published by University of Nis in Facta Universitatis. Series: Physical Education and Sport
- p. 221-236
REGRESSION ALGORITHMS IN ASSESSING THE IMPACT OF MORPHOLOGICAL AND MOTOR CHARACTERISTICS ON 60-M SPRINT
The aim of the present study was to identify the relationship between morphological parameters and motor skills that are important for sprint performance in children aged 8 to 16 years divided into four age groups (U10, U12, U14, U16) in both genders. The sample consisted of two hundred eighty one participant who trained sprinting in various athletic clubs. A prediction set of twenty-five variables for assessing morphological characteristics and motor skills was applied, and the criterion variable was a sprint at 60m. Using multiple correlation, it has been established that a large number of morphological characteristics are statistically significant positive correlation with the sprint, especially the longitudinal variables, while the variables of skinfolds showed a low negative statistical significance in relation to the given criterion. In the field of motor skills, the highest number of positive statistically significant correlations were found in the tests of explosive power of the upper and lower extremities, agility test and horizontal and vertical jump tests. In order to determine which morphological features and motor skills should be applied in sprint running training, we tested related attributes using different algorithms for data mining (LR, M5, KNN, SVM, MLP, RBF). The results suggests that the predictors that we use can continue to be applied with high reliability in assessing sprint performance, but also in the monitoring of the training process in order to profile the better sprint achievements.
- 19 November 2019
- Published by University of Nis in Facta Universitatis. Series: Physical Education and Sport
- p. 221-236
Open AccessREGRESSION ALGORITHMS IN ASSESSING THE IMPACT OF MORPHOLOGICAL AND MOTOR CHARACTERISTICS ON 60-M SPRINT
The aim of the present study was to identify the relationship between morphological parameters and motor skills that are important for sprint performance in children aged 8 to 16 years divided into four age groups (U10, U12, U14, U16) in both genders. The sample consisted of two hundred eighty one participant who trained sprinting in various athletic clubs. A prediction set of twenty-five variables for assessing morphological characteristics and motor skills was applied, and the criterion variable was a sprint at 60m. Using multiple correlation, it has been established that a large number of morphological characteristics are statistically significant positive correlation with the sprint, especially the longitudinal variables, while the variables of skinfolds showed a low negative statistical significance in relation to the given criterion. In the field of motor skills, the highest number of positive statistically significant correlations were found in the tests of explosive power of the upper and lower extremities, agility test and horizontal and vertical jump tests. In order to determine which morphological features and motor skills should be applied in sprint running training, we tested related attributes using different algorithms for data mining (LR, M5, KNN, SVM, MLP, RBF). The results suggests that the predictors that we use can continue to be applied with high reliability in assessing sprint performance, but also in the monitoring of the training process in order to profile the better sprint achievements.