TY  - JOUR
AU  - Arnaut, Filip
AU  - Cvetkov, Vesna
AU  - Đurić, Dragana
AU  - Samardžić-Petrović, Mileva
PY  - 2023
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/3275
AB  - We  demonstrate  the  use  of  Facebook's  Prophet  (usually  just  called  Prophet) model  for  short-term  air  quality  forecasting  at  Belgrade-Zeleno  brdo  monitoring station. To address missing data, we applied minimally-altering data distribution imputation techniques. Linear interpolation proved effective for short-term gaps (1–3 hours), hourly mean method for mid-term gaps (24–26 hours), and Hermite interpolation polynomial for long-term gaps (132–148 hours). The most significant data change was a 3.4% shift in skewness. Partitioning the time series enabled a detailed  quality  assessment  of  the  Prophet  model,  with  PM2.5predictions  being more  precise  than  PM10.  Using  the  longest  time  series  for  forecasting  yielded absolute  errors  of  6.5μg/m3forPM10and  2.7μg/m3for  PM2.5.  Based  on  173 forecasts, we anticipate Prophet model root-mean-square values under 6.26μg/m3and   9.99μg/m3for   PM2.5 and   PM10in   50%   of   cases.   The   Prophet   model demonstrates   several   advantages   and   yields   satisfactory   results.   In   future research,  the  results  obtained  from  the  Prophet  model  will  serve  as  benchmark values  for other models.  Additionally,  the Prophet model  is  capable of  providing satisfactory air quality forecasting results and will be utilized in future researc
T2  - Geofizika
T1  - Short-term forecasting of PM10and PM2.5 concentrations with Facebook's Prophet Model at the Belgrade-Zeleno brdo
VL  - 40
DO  - 10.15233/gfz.2023.40.7
ER  - 

@article{
author = "Arnaut, Filip and Cvetkov, Vesna and Đurić, Dragana and Samardžić-Petrović, Mileva",
year = "2023",
abstract = "We  demonstrate  the  use  of  Facebook's  Prophet  (usually  just  called  Prophet) model  for  short-term  air  quality  forecasting  at  Belgrade-Zeleno  brdo  monitoring station. To address missing data, we applied minimally-altering data distribution imputation techniques. Linear interpolation proved effective for short-term gaps (1–3 hours), hourly mean method for mid-term gaps (24–26 hours), and Hermite interpolation polynomial for long-term gaps (132–148 hours). The most significant data change was a 3.4% shift in skewness. Partitioning the time series enabled a detailed  quality  assessment  of  the  Prophet  model,  with  PM2.5predictions  being more  precise  than  PM10.  Using  the  longest  time  series  for  forecasting  yielded absolute  errors  of  6.5μg/m3forPM10and  2.7μg/m3for  PM2.5.  Based  on  173 forecasts, we anticipate Prophet model root-mean-square values under 6.26μg/m3and   9.99μg/m3for   PM2.5 and   PM10in   50%   of   cases.   The   Prophet   model demonstrates   several   advantages   and   yields   satisfactory   results.   In   future research,  the  results  obtained  from  the  Prophet  model  will  serve  as  benchmark values  for other models.  Additionally,  the Prophet model  is  capable of  providing satisfactory air quality forecasting results and will be utilized in future researc",
journal = "Geofizika",
title = "Short-term forecasting of PM10and PM2.5 concentrations with Facebook's Prophet Model at the Belgrade-Zeleno brdo",
volume = "40",
doi = "10.15233/gfz.2023.40.7"
}

Arnaut, F., Cvetkov, V., Đurić, D.,& Samardžić-Petrović, M.. (2023). Short-term forecasting of PM10and PM2.5 concentrations with Facebook's Prophet Model at the Belgrade-Zeleno brdo. in Geofizika, 40.
https://doi.org/10.15233/gfz.2023.40.7

Arnaut F, Cvetkov V, Đurić D, Samardžić-Petrović M. Short-term forecasting of PM10and PM2.5 concentrations with Facebook's Prophet Model at the Belgrade-Zeleno brdo. in Geofizika. 2023;40.
doi:10.15233/gfz.2023.40.7 .

Arnaut, Filip, Cvetkov, Vesna, Đurić, Dragana, Samardžić-Petrović, Mileva, "Short-term forecasting of PM10and PM2.5 concentrations with Facebook's Prophet Model at the Belgrade-Zeleno brdo" in Geofizika, 40 (2023),
https://doi.org/10.15233/gfz.2023.40.7 . .

Алексић, И., Самарџић-Петровић, М.,& Поповић, Ј.. (2022). Практикум - Геодетски премер 2. 
Грађевински факултет, Универзитет у Београду..
https://hdl.handle.net/21.15107/rcub_grafar_3342

Алексић И, Самарџић-Петровић М, Поповић Ј. Практикум - Геодетски премер 2. 2022;.
https://hdl.handle.net/21.15107/rcub_grafar_3342 .

Алексић, Иван, Самарџић-Петровић, Милева, Поповић, Јован, "Практикум - Геодетски премер 2" (2022),
https://hdl.handle.net/21.15107/rcub_grafar_3342 .

TY  - CONF
AU  - Ilijević, Slavica
AU  - Miljković, Stefan 
AU  - Cvijetinović, Željko
AU  - Samardžić-Petrović, Mileva
PY  - 2022
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/2907
AB  - Mobile Laser Scanning (MLS) is a technique characterized by high data acquisition efficiency and 
level of detail. However, a lot of information contained in the LiDAR point cloud is only implicitly 
available.  Therefore,  in order to create a  digital topographic map from a large quantity of  MLS  survey data, it is necessary to define a methodology that requires a combination of various software tools. In general, the applied methodology mainly depends on the final product specifications (data model, accuracy, level of detail, etc.). This paper describes the standard methodology of creating a detailed digital topographic map using data collected by MLS, which proved to be two times faster than the conventional methods (total station or GNSS survey).
PB  - University of Banja Luka Faculty of Architecture, Civil Engineering and Geodesy
C3  - Proceedings of International conference on Contemporary Theory and Practice in Construction XV
T1  - Mobile laser scanning for detailed digital topographic mapping
T1  - Мобилно ласерско скенирање за детаљно дигитално топографско  картирање
EP  - 304
SP  - 294
DO  - 10.7251/STP2215294L
ER  - 

@conference{
author = "Ilijević, Slavica and Miljković, Stefan  and Cvijetinović, Željko and Samardžić-Petrović, Mileva",
year = "2022",
abstract = "Mobile Laser Scanning (MLS) is a technique characterized by high data acquisition efficiency and 
level of detail. However, a lot of information contained in the LiDAR point cloud is only implicitly 
available.  Therefore,  in order to create a  digital topographic map from a large quantity of  MLS  survey data, it is necessary to define a methodology that requires a combination of various software tools. In general, the applied methodology mainly depends on the final product specifications (data model, accuracy, level of detail, etc.). This paper describes the standard methodology of creating a detailed digital topographic map using data collected by MLS, which proved to be two times faster than the conventional methods (total station or GNSS survey).",
publisher = "University of Banja Luka Faculty of Architecture, Civil Engineering and Geodesy",
journal = "Proceedings of International conference on Contemporary Theory and Practice in Construction XV",
title = "Mobile laser scanning for detailed digital topographic mapping, Мобилно ласерско скенирање за детаљно дигитално топографско  картирање",
pages = "304-294",
doi = "10.7251/STP2215294L"
}

Ilijević, S., Miljković, S., Cvijetinović, Ž.,& Samardžić-Petrović, M.. (2022). Mobile laser scanning for detailed digital topographic mapping. in Proceedings of International conference on Contemporary Theory and Practice in Construction XV
University of Banja Luka Faculty of Architecture, Civil Engineering and Geodesy., 294-304.
https://doi.org/10.7251/STP2215294L

Ilijević S, Miljković S, Cvijetinović Ž, Samardžić-Petrović M. Mobile laser scanning for detailed digital topographic mapping. in Proceedings of International conference on Contemporary Theory and Practice in Construction XV. 2022;:294-304.
doi:10.7251/STP2215294L .

Ilijević, Slavica, Miljković, Stefan , Cvijetinović, Željko, Samardžić-Petrović, Mileva, "Mobile laser scanning for detailed digital topographic mapping" in Proceedings of International conference on Contemporary Theory and Practice in Construction XV (2022):294-304,
https://doi.org/10.7251/STP2215294L . .

TY  - CONF
AU  - Filipović, Aljoša
AU  - Dobrić, Jelena
AU  - Blagojević, Dragan
AU  - Samardžić - Petrović, Mileva
AU  - Buđevac, Dragan
AU  - Marković, Zlatko
PY  - 2021
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/2609
AB  - Rad  prikazuje  merenje  početnih  geometrijskih  imperfekcija  i  zaostalih  napona  u  okviru 
istraživanja nosivosti centrično pritisnutih elemenata L poprečnog preseka od nerđajućeg čelika. 
Istraživanjem su obuhvaćena tri različita tipa L profila – hladnooblikovani, vrućevaljani i laserski 
zavareni. Postupak i rezultati merenja početnih geometrijskih imperfekcija primenom sistema za 
lasersko merenje prezentovani su u radu. Merenje zaostalih napona metodom sečenja sprovedeno 
je  na  vrućevaljanom  i  laserski  zavarenom  uzorku  nominalnih  dimenzija  100  ×  100  ×  10, 
napraveljenih od austenitnog nerđajućeg čelika EN 1.4301. Postupak merenja zaostalih napona 
i rezultati u formi rasporeda zaostalih napona i ekstremnih vrednosti prikazni su u radu.
AB  - The paper presents initial geometric imperfections and residual stresses measurment as a part of 
a research on ultimate capacity of axially compressed angle columns made from stainless steel. 
The research covers three different angle types – cold-formed, hot-rolled and laser-welded. The 
procedure and results of initial geometric imperfections measurments using a laser measurement 
system are presented. Measurement of residual stresses using a sectioning method was performed 
on hot-rolled and laser-welded samples with nominal dimensions of 100 × 100 × 10, made of 
austenitic  stainless  steel  EN  1.4301.  The  procedure  of  residual  stresses  measurement  and 
obtained results in form of residual stresses distribution and extreme values are presented.
PB  - Univerzitet u Beogradu Građevinski fakultet
PB  - Društvo građevinskih konstruktera Srbije
C3  - Zbornik radova sa Nacionalnog simpozijuma DGKS  / Društvо  građevinskih konstruktera Srbije, Simpozijum 2020
T1  - Početne imperfekcije stubova ravnokrakog L poprečnog preseka od nerđajućeg čelika
EP  - 521
SP  - 513
UR  - https://hdl.handle.net/21.15107/rcub_grafar_2609
ER  - 

@conference{
author = "Filipović, Aljoša and Dobrić, Jelena and Blagojević, Dragan and Samardžić - Petrović, Mileva and Buđevac, Dragan and Marković, Zlatko",
year = "2021",
abstract = "Rad  prikazuje  merenje  početnih  geometrijskih  imperfekcija  i  zaostalih  napona  u  okviru 
istraživanja nosivosti centrično pritisnutih elemenata L poprečnog preseka od nerđajućeg čelika. 
Istraživanjem su obuhvaćena tri različita tipa L profila – hladnooblikovani, vrućevaljani i laserski 
zavareni. Postupak i rezultati merenja početnih geometrijskih imperfekcija primenom sistema za 
lasersko merenje prezentovani su u radu. Merenje zaostalih napona metodom sečenja sprovedeno 
je  na  vrućevaljanom  i  laserski  zavarenom  uzorku  nominalnih  dimenzija  100  ×  100  ×  10, 
napraveljenih od austenitnog nerđajućeg čelika EN 1.4301. Postupak merenja zaostalih napona 
i rezultati u formi rasporeda zaostalih napona i ekstremnih vrednosti prikazni su u radu., The paper presents initial geometric imperfections and residual stresses measurment as a part of 
a research on ultimate capacity of axially compressed angle columns made from stainless steel. 
The research covers three different angle types – cold-formed, hot-rolled and laser-welded. The 
procedure and results of initial geometric imperfections measurments using a laser measurement 
system are presented. Measurement of residual stresses using a sectioning method was performed 
on hot-rolled and laser-welded samples with nominal dimensions of 100 × 100 × 10, made of 
austenitic  stainless  steel  EN  1.4301.  The  procedure  of  residual  stresses  measurement  and 
obtained results in form of residual stresses distribution and extreme values are presented.",
publisher = "Univerzitet u Beogradu Građevinski fakultet, Društvo građevinskih konstruktera Srbije",
journal = "Zbornik radova sa Nacionalnog simpozijuma DGKS  / Društvо  građevinskih konstruktera Srbije, Simpozijum 2020",
title = "Početne imperfekcije stubova ravnokrakog L poprečnog preseka od nerđajućeg čelika",
pages = "521-513",
url = "https://hdl.handle.net/21.15107/rcub_grafar_2609"
}

Filipović, A., Dobrić, J., Blagojević, D., Samardžić - Petrović, M., Buđevac, D.,& Marković, Z.. (2021). Početne imperfekcije stubova ravnokrakog L poprečnog preseka od nerđajućeg čelika. in Zbornik radova sa Nacionalnog simpozijuma DGKS  / Društvо  građevinskih konstruktera Srbije, Simpozijum 2020
Univerzitet u Beogradu Građevinski fakultet., 513-521.
https://hdl.handle.net/21.15107/rcub_grafar_2609

Filipović A, Dobrić J, Blagojević D, Samardžić - Petrović M, Buđevac D, Marković Z. Početne imperfekcije stubova ravnokrakog L poprečnog preseka od nerđajućeg čelika. in Zbornik radova sa Nacionalnog simpozijuma DGKS  / Društvо  građevinskih konstruktera Srbije, Simpozijum 2020. 2021;:513-521.
https://hdl.handle.net/21.15107/rcub_grafar_2609 .

Filipović, Aljoša, Dobrić, Jelena, Blagojević, Dragan, Samardžić - Petrović, Mileva, Buđevac, Dragan, Marković, Zlatko, "Početne imperfekcije stubova ravnokrakog L poprečnog preseka od nerđajućeg čelika" in Zbornik radova sa Nacionalnog simpozijuma DGKS  / Društvо  građevinskih konstruktera Srbije, Simpozijum 2020 (2021):513-521,
https://hdl.handle.net/21.15107/rcub_grafar_2609 .

TY  - CONF
AU  - Abolmasov, Biljana
AU  - Đurić, Uroš
AU  - Popović, Jovan
AU  - Pejić, Marko
AU  - Samardžić-Petrović, Mileva
AU  - Brodić, Nenad
PY  - 2021
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/2557
AB  - Results of recent monitoring activities conducted from 2014 to 2019 are presented in the paper as a part of IPL 181 Project progress report. Recent monitoring activities are concentrated on several landslide monitoring techniques— automated GNSS monitoring system measurements, geodetic benchmark survey monitoring, UAV imaging, processing and analysis, and PSInSAR data processing and analysis. Results of all monitoring activities were analysed and used for cross-correlation and for verification of monitoring results obtained from different techniques. Displacement rates from GNSS measurements indicate that object point UmkaGNSS2 has moved 0.30 m towards the North and 0.50 m towards the West, while the vertical displacement was approximately −0.15 m for the 2014–2018 time span. Similar range of GNSS displacement rates were found in previously published results from monitoring activities realized from 2010–2014. PSInSAR data analysis also showed good correlation between nearest PS points and GNSS point for the same period of monitoring. Results from UAV and geodetic benchmarks survey showed very good correlation in displacement vectors’ direction. According to the analyzed data it could be concluded that all monitoring results are in compliance with previous research results and confirm that the Umka is slow tovery slow moving landslide with cyclic acceleration and deceleration phases.
PB  - Gewerbestrasse: Springer Nature Switzerland AG
C3  - Understanding and Reducing Landslide Disaster Risk
T1  - Results of Recent Monitoring Activities on Landslide Umka, Belgrade, Serbia—IPL 181
EP  - 234
SP  - 225
VL  - 1
DO  - 10.1007/978-3-030-60196-6_14
ER  - 

@conference{
author = "Abolmasov, Biljana and Đurić, Uroš and Popović, Jovan and Pejić, Marko and Samardžić-Petrović, Mileva and Brodić, Nenad",
year = "2021",
abstract = "Results of recent monitoring activities conducted from 2014 to 2019 are presented in the paper as a part of IPL 181 Project progress report. Recent monitoring activities are concentrated on several landslide monitoring techniques— automated GNSS monitoring system measurements, geodetic benchmark survey monitoring, UAV imaging, processing and analysis, and PSInSAR data processing and analysis. Results of all monitoring activities were analysed and used for cross-correlation and for verification of monitoring results obtained from different techniques. Displacement rates from GNSS measurements indicate that object point UmkaGNSS2 has moved 0.30 m towards the North and 0.50 m towards the West, while the vertical displacement was approximately −0.15 m for the 2014–2018 time span. Similar range of GNSS displacement rates were found in previously published results from monitoring activities realized from 2010–2014. PSInSAR data analysis also showed good correlation between nearest PS points and GNSS point for the same period of monitoring. Results from UAV and geodetic benchmarks survey showed very good correlation in displacement vectors’ direction. According to the analyzed data it could be concluded that all monitoring results are in compliance with previous research results and confirm that the Umka is slow tovery slow moving landslide with cyclic acceleration and deceleration phases.",
publisher = "Gewerbestrasse: Springer Nature Switzerland AG",
journal = "Understanding and Reducing Landslide Disaster Risk",
title = "Results of Recent Monitoring Activities on Landslide Umka, Belgrade, Serbia—IPL 181",
pages = "234-225",
volume = "1",
doi = "10.1007/978-3-030-60196-6_14"
}

Abolmasov, B., Đurić, U., Popović, J., Pejić, M., Samardžić-Petrović, M.,& Brodić, N.. (2021). Results of Recent Monitoring Activities on Landslide Umka, Belgrade, Serbia—IPL 181. in Understanding and Reducing Landslide Disaster Risk
Gewerbestrasse: Springer Nature Switzerland AG., 1, 225-234.
https://doi.org/10.1007/978-3-030-60196-6_14

Abolmasov B, Đurić U, Popović J, Pejić M, Samardžić-Petrović M, Brodić N. Results of Recent Monitoring Activities on Landslide Umka, Belgrade, Serbia—IPL 181. in Understanding and Reducing Landslide Disaster Risk. 2021;1:225-234.
doi:10.1007/978-3-030-60196-6_14 .

Abolmasov, Biljana, Đurić, Uroš, Popović, Jovan, Pejić, Marko, Samardžić-Petrović, Mileva, Brodić, Nenad, "Results of Recent Monitoring Activities on Landslide Umka, Belgrade, Serbia—IPL 181" in Understanding and Reducing Landslide Disaster Risk, 1 (2021):225-234,
https://doi.org/10.1007/978-3-030-60196-6_14 . .

TY  - CONF
AU  - Samardžić-Petrović, Mileva
AU  - Popović, Jovan
AU  - Đurić, Uroš
AU  - Abolmasov, Biljana
AU  - Pejić, Marko
AU  - Marjanović, Miloš
PY  - 2020
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/2214
AB  - The Umka landslide is one of the biggest inhabited active landslides in Serbia. The Umka landslide activity has been monitored for a period longer than 85 years, by various geotechnical and geodetic techniques. Since 2010, landslide activity has been continuously monitored by automated permanent Global Navigation Satellite System (GNSS) based monitoring system in real time. Furthermore, since 2018 landslide activity has been monitored by GNSS kinematic positioning of a set of characteristic points as well as by UAV (Unmanned Aerial Vehicle) photogrammetry. The main issue of this paper is the presentation of the results gained with GNSS kinematic positioning of characteristic points of Umka landslide within three observation epochs.
PB  - University of Banja Luka Faculty of Architecture, Civil Engineering and Geode
C3  - XIV International Conference On Contemporary Theory And Practice In Construction XIV Stepgrad XIV Proceedings, 2020
T1  - Permanent GNSS monitoring of landslide Umka
DO  - 10.7251/STP2014091S
ER  - 

@conference{
author = "Samardžić-Petrović, Mileva and Popović, Jovan and Đurić, Uroš and Abolmasov, Biljana and Pejić, Marko and Marjanović, Miloš",
year = "2020",
abstract = "The Umka landslide is one of the biggest inhabited active landslides in Serbia. The Umka landslide activity has been monitored for a period longer than 85 years, by various geotechnical and geodetic techniques. Since 2010, landslide activity has been continuously monitored by automated permanent Global Navigation Satellite System (GNSS) based monitoring system in real time. Furthermore, since 2018 landslide activity has been monitored by GNSS kinematic positioning of a set of characteristic points as well as by UAV (Unmanned Aerial Vehicle) photogrammetry. The main issue of this paper is the presentation of the results gained with GNSS kinematic positioning of characteristic points of Umka landslide within three observation epochs.",
publisher = "University of Banja Luka Faculty of Architecture, Civil Engineering and Geode",
journal = "XIV International Conference On Contemporary Theory And Practice In Construction XIV Stepgrad XIV Proceedings, 2020",
title = "Permanent GNSS monitoring of landslide Umka",
doi = "10.7251/STP2014091S"
}

Samardžić-Petrović, M., Popović, J., Đurić, U., Abolmasov, B., Pejić, M.,& Marjanović, M.. (2020). Permanent GNSS monitoring of landslide Umka. in XIV International Conference On Contemporary Theory And Practice In Construction XIV Stepgrad XIV Proceedings, 2020
University of Banja Luka Faculty of Architecture, Civil Engineering and Geode..
https://doi.org/10.7251/STP2014091S

Samardžić-Petrović M, Popović J, Đurić U, Abolmasov B, Pejić M, Marjanović M. Permanent GNSS monitoring of landslide Umka. in XIV International Conference On Contemporary Theory And Practice In Construction XIV Stepgrad XIV Proceedings, 2020. 2020;.
doi:10.7251/STP2014091S .

Samardžić-Petrović, Mileva, Popović, Jovan, Đurić, Uroš, Abolmasov, Biljana, Pejić, Marko, Marjanović, Miloš, "Permanent GNSS monitoring of landslide Umka" in XIV International Conference On Contemporary Theory And Practice In Construction XIV Stepgrad XIV Proceedings, 2020 (2020),
https://doi.org/10.7251/STP2014091S . .

TY  - CHAP
AU  - Marjanović, Miloš
AU  - Samardžić-Petrović, Mileva
AU  - Abolmasov, Biljana
AU  - Đurić, Uroš
PY  - 2019
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/989
AB  - The main idea of this chapter is to address some of the key issues that were recognized in Machine Learning (ML) based Landslide Assessment Modeling (LAM). Through the experience of the authors, elaborated in several case studies, including the City of Belgrade in Serbia, the City of Tuzla in Bosnia and Herzegovina, Ljubovija Municipality in Serbia, and Halenkovice area in Czech Republic, eight key issues were identified, and appropriate options, solutions, and some new concepts for overcoming them were introduced. The following issues were addressed: Landslide inventory enhancements (overcoming small number of landslide instances), Choice of attributes (which attributes are appropriate and pros and cons on attribute selection/extraction), Classification versus regression (which type of task is more appropriate in particular cases), Choice of ML technique (discussion of most popular ML techniques), Sampling strategy (overcoming the overfit by choosing training instances wisely), Cross-scaling (a new concept for improving the algorithm’s learning capacity), Quasi-hazard concept (introducing artificial temporal base for upgrading from susceptibility to hazard assessment), and Objective model evaluation (the best practice for validating resulting models against the existing inventory). All of them are followed by appropriate practical examples from one of abovementioned case studies. The ultimate objective is to provide guidance and inspire LAM community for a more innovative approach in modeling.
PB  - Springer Netherlands
T2  - Advances in Natural and Technological Hazards Research
T1  - Concepts for improving machine learning based landslide assessment
EP  - 58
SP  - 27
VL  - 48
DO  - 10.1007/978-3-319-73383-8_2
ER  - 

@inbook{
author = "Marjanović, Miloš and Samardžić-Petrović, Mileva and Abolmasov, Biljana and Đurić, Uroš",
year = "2019",
abstract = "The main idea of this chapter is to address some of the key issues that were recognized in Machine Learning (ML) based Landslide Assessment Modeling (LAM). Through the experience of the authors, elaborated in several case studies, including the City of Belgrade in Serbia, the City of Tuzla in Bosnia and Herzegovina, Ljubovija Municipality in Serbia, and Halenkovice area in Czech Republic, eight key issues were identified, and appropriate options, solutions, and some new concepts for overcoming them were introduced. The following issues were addressed: Landslide inventory enhancements (overcoming small number of landslide instances), Choice of attributes (which attributes are appropriate and pros and cons on attribute selection/extraction), Classification versus regression (which type of task is more appropriate in particular cases), Choice of ML technique (discussion of most popular ML techniques), Sampling strategy (overcoming the overfit by choosing training instances wisely), Cross-scaling (a new concept for improving the algorithm’s learning capacity), Quasi-hazard concept (introducing artificial temporal base for upgrading from susceptibility to hazard assessment), and Objective model evaluation (the best practice for validating resulting models against the existing inventory). All of them are followed by appropriate practical examples from one of abovementioned case studies. The ultimate objective is to provide guidance and inspire LAM community for a more innovative approach in modeling.",
publisher = "Springer Netherlands",
journal = "Advances in Natural and Technological Hazards Research",
booktitle = "Concepts for improving machine learning based landslide assessment",
pages = "58-27",
volume = "48",
doi = "10.1007/978-3-319-73383-8_2"
}

Marjanović, M., Samardžić-Petrović, M., Abolmasov, B.,& Đurić, U.. (2019). Concepts for improving machine learning based landslide assessment. in Advances in Natural and Technological Hazards Research
Springer Netherlands., 48, 27-58.
https://doi.org/10.1007/978-3-319-73383-8_2

Marjanović M, Samardžić-Petrović M, Abolmasov B, Đurić U. Concepts for improving machine learning based landslide assessment. in Advances in Natural and Technological Hazards Research. 2019;48:27-58.
doi:10.1007/978-3-319-73383-8_2 .

Marjanović, Miloš, Samardžić-Petrović, Mileva, Abolmasov, Biljana, Đurić, Uroš, "Concepts for improving machine learning based landslide assessment" in Advances in Natural and Technological Hazards Research, 48 (2019):27-58,
https://doi.org/10.1007/978-3-319-73383-8_2 . .

TY  - CHAP
AU  - Marjanović, Miloš
AU  - Abolmasov, Biljana
AU  - Milenković, Svetozar
AU  - Đurić, Uroš
AU  - Samardžić-Petrović, Mileva
PY  - 2019
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/1892
PB  - Elsevier
T2  - Spatial Modeling in GIS and R for Earth and Environmental Sciences
T1  - Multihazard Exposure Assessment on the Valjevo City Road Network
EP  - 688
SP  - 671
DO  - https://doi.org/10.1016/B978-0-12-815226-3.00031-4
ER  - 

@inbook{
author = "Marjanović, Miloš and Abolmasov, Biljana and Milenković, Svetozar and Đurić, Uroš and Samardžić-Petrović, Mileva",
year = "2019",
publisher = "Elsevier",
journal = "Spatial Modeling in GIS and R for Earth and Environmental Sciences",
booktitle = "Multihazard Exposure Assessment on the Valjevo City Road Network",
pages = "688-671",
doi = "https://doi.org/10.1016/B978-0-12-815226-3.00031-4"
}

Marjanović, M., Abolmasov, B., Milenković, S., Đurić, U.,& Samardžić-Petrović, M.. (2019). Multihazard Exposure Assessment on the Valjevo City Road Network. in Spatial Modeling in GIS and R for Earth and Environmental Sciences
Elsevier., 671-688.
https://doi.org/https://doi.org/10.1016/B978-0-12-815226-3.00031-4

Marjanović M, Abolmasov B, Milenković S, Đurić U, Samardžić-Petrović M. Multihazard Exposure Assessment on the Valjevo City Road Network. in Spatial Modeling in GIS and R for Earth and Environmental Sciences. 2019;:671-688.
doi:https://doi.org/10.1016/B978-0-12-815226-3.00031-4 .

Marjanović, Miloš, Abolmasov, Biljana, Milenković, Svetozar, Đurić, Uroš, Samardžić-Petrović, Mileva, "Multihazard Exposure Assessment on the Valjevo City Road Network" in Spatial Modeling in GIS and R for Earth and Environmental Sciences (2019):671-688,
https://doi.org/https://doi.org/10.1016/B978-0-12-815226-3.00031-4 . .

TY  - JOUR
AU  - Todorović-Drakul, Miljana
AU  - Samardžić-Petrović, Mileva
AU  - Grekulović, Sanja
AU  - Odalović, Oleg
AU  - Blagojević, Dragan
PY  - 2018
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/955
AB  - This paper is dedicated to modeling extreme TEC (Total Electron Content) values at the territory of Serbia. For the extreme TEC values, we consider the maximum values from the peak of the 11-year cycle of solar activity in the years 2013, 2014 and 2015 for the days of the winter and summer solstice and autumnal and vernal equinox. The average TEC values between 10 and 12 UT (Universal Time) were treated. As the basic data for all processing, we used GNSS (Global Navigation Satellite System) observation obtained by three permanent stations located in the territory of Serbia. Those data, we accept as actual, i. e. as a "true TEC values". The main objectives of this research were to examine the possibility to use two machine learning techniques: neural networks and support vector machine. In order to emphasize the quality of applied techniques, all results are adequately compared to the TEC values obtained by using International Reference Ionosphere global model. In addition, we separately analyzed the quality of techniques throughout temporal and spatial-temporal approach.
PB  - Geofizicki Zavod
T2  - Geofizika
T1  - Modelling extreme values of the total electron content: Case study of Serbia
EP  - 314
IS  - 2
SP  - 297
VL  - 34
DO  - 10.15233/gfz.2017.34.12
ER  - 

@article{
author = "Todorović-Drakul, Miljana and Samardžić-Petrović, Mileva and Grekulović, Sanja and Odalović, Oleg and Blagojević, Dragan",
year = "2018",
abstract = "This paper is dedicated to modeling extreme TEC (Total Electron Content) values at the territory of Serbia. For the extreme TEC values, we consider the maximum values from the peak of the 11-year cycle of solar activity in the years 2013, 2014 and 2015 for the days of the winter and summer solstice and autumnal and vernal equinox. The average TEC values between 10 and 12 UT (Universal Time) were treated. As the basic data for all processing, we used GNSS (Global Navigation Satellite System) observation obtained by three permanent stations located in the territory of Serbia. Those data, we accept as actual, i. e. as a "true TEC values". The main objectives of this research were to examine the possibility to use two machine learning techniques: neural networks and support vector machine. In order to emphasize the quality of applied techniques, all results are adequately compared to the TEC values obtained by using International Reference Ionosphere global model. In addition, we separately analyzed the quality of techniques throughout temporal and spatial-temporal approach.",
publisher = "Geofizicki Zavod",
journal = "Geofizika",
title = "Modelling extreme values of the total electron content: Case study of Serbia",
pages = "314-297",
number = "2",
volume = "34",
doi = "10.15233/gfz.2017.34.12"
}

Todorović-Drakul, M., Samardžić-Petrović, M., Grekulović, S., Odalović, O.,& Blagojević, D.. (2018). Modelling extreme values of the total electron content: Case study of Serbia. in Geofizika
Geofizicki Zavod., 34(2), 297-314.
https://doi.org/10.15233/gfz.2017.34.12

Todorović-Drakul M, Samardžić-Petrović M, Grekulović S, Odalović O, Blagojević D. Modelling extreme values of the total electron content: Case study of Serbia. in Geofizika. 2018;34(2):297-314.
doi:10.15233/gfz.2017.34.12 .

Todorović-Drakul, Miljana, Samardžić-Petrović, Mileva, Grekulović, Sanja, Odalović, Oleg, Blagojević, Dragan, "Modelling extreme values of the total electron content: Case study of Serbia" in Geofizika, 34, no. 2 (2018):297-314,
https://doi.org/10.15233/gfz.2017.34.12 . .

TY  - CONF
AU  - Đurić, Uroš
AU  - Abolmasov, Biljana
AU  - Marjanović, M.
AU  - Samardžić-Petrović, Mileva
AU  - Pejić, Marko
AU  - Brodić, Nenad
AU  - Popović, Jovan
PY  - 2018
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/1615
AB  - This paper presents a brief working progress report on realization of the IPL project 181 “Study of slow moving landslide Umka near Belgrade, Serbia”. In this paper we will present results of the project targets performed by Project participants during 2017 and 2018, with plans for future project realization.
PB  - The International Consortium on Landslides (ICL), Kyoto
C3  - 2018 IPL Symposium on landslides, 03 December 2018, Kyoto University, Uji campus, Kyoto, Japan
T1  - IPL Project 181 Study of slow moving landslide Umka near Belgrade, Serbia progress report for 2017 & 2018
EP  - 46
SP  - 41
UR  - https://hdl.handle.net/21.15107/rcub_grafar_1615
ER  - 

@conference{
author = "Đurić, Uroš and Abolmasov, Biljana and Marjanović, M. and Samardžić-Petrović, Mileva and Pejić, Marko and Brodić, Nenad and Popović, Jovan",
year = "2018",
abstract = "This paper presents a brief working progress report on realization of the IPL project 181 “Study of slow moving landslide Umka near Belgrade, Serbia”. In this paper we will present results of the project targets performed by Project participants during 2017 and 2018, with plans for future project realization.",
publisher = "The International Consortium on Landslides (ICL), Kyoto",
journal = "2018 IPL Symposium on landslides, 03 December 2018, Kyoto University, Uji campus, Kyoto, Japan",
title = "IPL Project 181 Study of slow moving landslide Umka near Belgrade, Serbia progress report for 2017 & 2018",
pages = "46-41",
url = "https://hdl.handle.net/21.15107/rcub_grafar_1615"
}

Đurić, U., Abolmasov, B., Marjanović, M., Samardžić-Petrović, M., Pejić, M., Brodić, N.,& Popović, J.. (2018). IPL Project 181 Study of slow moving landslide Umka near Belgrade, Serbia progress report for 2017 & 2018. in 2018 IPL Symposium on landslides, 03 December 2018, Kyoto University, Uji campus, Kyoto, Japan
The International Consortium on Landslides (ICL), Kyoto., 41-46.
https://hdl.handle.net/21.15107/rcub_grafar_1615

Đurić U, Abolmasov B, Marjanović M, Samardžić-Petrović M, Pejić M, Brodić N, Popović J. IPL Project 181 Study of slow moving landslide Umka near Belgrade, Serbia progress report for 2017 & 2018. in 2018 IPL Symposium on landslides, 03 December 2018, Kyoto University, Uji campus, Kyoto, Japan. 2018;:41-46.
https://hdl.handle.net/21.15107/rcub_grafar_1615 .

Đurić, Uroš, Abolmasov, Biljana, Marjanović, M., Samardžić-Petrović, Mileva, Pejić, Marko, Brodić, Nenad, Popović, Jovan, "IPL Project 181 Study of slow moving landslide Umka near Belgrade, Serbia progress report for 2017 & 2018" in 2018 IPL Symposium on landslides, 03 December 2018, Kyoto University, Uji campus, Kyoto, Japan (2018):41-46,
https://hdl.handle.net/21.15107/rcub_grafar_1615 .

TY  - CHAP
AU  - Bajat, Branislav
AU  - Kilibarda, Milan
AU  - Pejović, Milutin
AU  - Samardžić-Petrović, Mileva
PY  - 2018
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/1106
PB  - Berlin Heidelberg: Springer
T2  - Spatial Analysis and Location Modeling in Urban and Regional Systems
T1  - Spatial Hedonic Modeling of Housing Prices Using Auxiliary Maps
EP  - 122
SP  - 97
DO  - 10.1007/978-3-642-37896-6_5
ER  - 

@inbook{
author = "Bajat, Branislav and Kilibarda, Milan and Pejović, Milutin and Samardžić-Petrović, Mileva",
year = "2018",
publisher = "Berlin Heidelberg: Springer",
journal = "Spatial Analysis and Location Modeling in Urban and Regional Systems",
booktitle = "Spatial Hedonic Modeling of Housing Prices Using Auxiliary Maps",
pages = "122-97",
doi = "10.1007/978-3-642-37896-6_5"
}

Bajat, B., Kilibarda, M., Pejović, M.,& Samardžić-Petrović, M.. (2018). Spatial Hedonic Modeling of Housing Prices Using Auxiliary Maps. in Spatial Analysis and Location Modeling in Urban and Regional Systems
Berlin Heidelberg: Springer., 97-122.
https://doi.org/10.1007/978-3-642-37896-6_5

Bajat B, Kilibarda M, Pejović M, Samardžić-Petrović M. Spatial Hedonic Modeling of Housing Prices Using Auxiliary Maps. in Spatial Analysis and Location Modeling in Urban and Regional Systems. 2018;:97-122.
doi:10.1007/978-3-642-37896-6_5 .

Bajat, Branislav, Kilibarda, Milan, Pejović, Milutin, Samardžić-Petrović, Mileva, "Spatial Hedonic Modeling of Housing Prices Using Auxiliary Maps" in Spatial Analysis and Location Modeling in Urban and Regional Systems (2018):97-122,
https://doi.org/10.1007/978-3-642-37896-6_5 . .

TY  - CONF
AU  - Abolmasov, Biljana
AU  - Marjanović, M.
AU  - Đurić, Uroš
AU  - Samardžić-Petrović, Mileva
AU  - Krušić, Jelka
PY  - 2018
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/1640
AB  - The IPL project No 210 titled “Massive landsliding in Serbia following Cyclone Tamara in May 2014” started at March 2016. The study area is located in the Western and Central part of the Republic of Serbia territory affected by Cyclone Tamara in May 2014. The project aims to summarize and analyse all relevant collected data, including historic/current rainfall, landslide records, aftermath reports, and environmental features datasets from the May 2014 sequence. Objectives of the proposed project include: collecting all available and acquiring new landslides data, analysing the trigger/landslide relation in affordable time span and May 2014 event, relating the landslide mechanisms and magnitudes versus the trigger, locating spatial patterns and relationships between landslides and geological and environmental controls, proposing an overview susceptibility map of the event and numerical modelling on the site specific location/landslide mechanism. The Project is organized by University of Belgrade, Faculty of Mining and Geology and Faculty of Civil Engineering. Project beneficiaries are local community and local and regional authorities. In this paper we will present progress report of the proposed project targets performed by project participants.
PB  - The International Consortium on Landslides (ICL), Kyoto
C3  - 2018 IPL Symposium on landslides, 03 December 2018, Kyoto University, Uji campus, Kyoto, Japan
T1  - IPL Project 210 Massive landsliding in Serbia following Cyclone Tamara in May 2014 progress report
EP  - 51
SP  - 47
UR  - https://hdl.handle.net/21.15107/rcub_grafar_1640
ER  - 

@conference{
author = "Abolmasov, Biljana and Marjanović, M. and Đurić, Uroš and Samardžić-Petrović, Mileva and Krušić, Jelka",
year = "2018",
abstract = "The IPL project No 210 titled “Massive landsliding in Serbia following Cyclone Tamara in May 2014” started at March 2016. The study area is located in the Western and Central part of the Republic of Serbia territory affected by Cyclone Tamara in May 2014. The project aims to summarize and analyse all relevant collected data, including historic/current rainfall, landslide records, aftermath reports, and environmental features datasets from the May 2014 sequence. Objectives of the proposed project include: collecting all available and acquiring new landslides data, analysing the trigger/landslide relation in affordable time span and May 2014 event, relating the landslide mechanisms and magnitudes versus the trigger, locating spatial patterns and relationships between landslides and geological and environmental controls, proposing an overview susceptibility map of the event and numerical modelling on the site specific location/landslide mechanism. The Project is organized by University of Belgrade, Faculty of Mining and Geology and Faculty of Civil Engineering. Project beneficiaries are local community and local and regional authorities. In this paper we will present progress report of the proposed project targets performed by project participants.",
publisher = "The International Consortium on Landslides (ICL), Kyoto",
journal = "2018 IPL Symposium on landslides, 03 December 2018, Kyoto University, Uji campus, Kyoto, Japan",
title = "IPL Project 210 Massive landsliding in Serbia following Cyclone Tamara in May 2014 progress report",
pages = "51-47",
url = "https://hdl.handle.net/21.15107/rcub_grafar_1640"
}

Abolmasov, B., Marjanović, M., Đurić, U., Samardžić-Petrović, M.,& Krušić, J.. (2018). IPL Project 210 Massive landsliding in Serbia following Cyclone Tamara in May 2014 progress report. in 2018 IPL Symposium on landslides, 03 December 2018, Kyoto University, Uji campus, Kyoto, Japan
The International Consortium on Landslides (ICL), Kyoto., 47-51.
https://hdl.handle.net/21.15107/rcub_grafar_1640

Abolmasov B, Marjanović M, Đurić U, Samardžić-Petrović M, Krušić J. IPL Project 210 Massive landsliding in Serbia following Cyclone Tamara in May 2014 progress report. in 2018 IPL Symposium on landslides, 03 December 2018, Kyoto University, Uji campus, Kyoto, Japan. 2018;:47-51.
https://hdl.handle.net/21.15107/rcub_grafar_1640 .

Abolmasov, Biljana, Marjanović, M., Đurić, Uroš, Samardžić-Petrović, Mileva, Krušić, Jelka, "IPL Project 210 Massive landsliding in Serbia following Cyclone Tamara in May 2014 progress report" in 2018 IPL Symposium on landslides, 03 December 2018, Kyoto University, Uji campus, Kyoto, Japan (2018):47-51,
https://hdl.handle.net/21.15107/rcub_grafar_1640 .

TY  - CONF
AU  - Marjanović, M.
AU  - Stojaković, A.
AU  - Abolmasov, Biljana
AU  - Đurić, D.
AU  - Đurić, Uroš
AU  - Krušić, Jelka
AU  - Andrejev, Katarina
AU  - Samardžić-Petrović, Mileva
PY  - 2018
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/1602
AB  - Terroir depicts a set of pedologic, micro‐climatic and historical factors that have a say in deciding whether and where to practice viticulture and determines its qualitative and quantitative exploitation potential. For winemakers, it is paramount for targeting a viticulture variety. European winemakers use to guide their choices by the family tradition. Scientific breakthroughs, i.e. pedological characterization of the soil, introduced a new approach for viticulture, and drove the world‐leading wineries to turn to scientific approach in the last 30 years. In this research, we went one step further in respect to pedological approach. Since the soil itself is considered as a product of its bedrock and climate, it is logical to also include those factors that condition the properties of the soil itself in the terroir context, such as geological and morphologic factors (Burns, 2010). It is thereby, possible to perform a preliminary delineation of zones with suitable set of factors at regional scales, and direct the subsequent, more detailed soil investigations. By analyzing wider areas, it becomes possible to plan more strategically, especially when it comes to preservation of rare and indigenous vine varieties. From winemakers’ perspective, indigenous vine varieties represent the true genetic potential. Smederevka, which is shyly re‐introduced, but without any planning and consulting the profession is one such example. Before the 2nd World War, Smederevka (colloquially known as “the Yellow”) was grown predominantly in the Smederevo wine region, but with caution to the micro‐location, soil composition, slope aspect, sun reflection off the water surface, etc. The quality was unparalleled in comparison to the same vine from 1950–1990, a period marked by a high‐yield, collective farming practice of the “Godomin” company back in the socialism. Locality Plavinac in Smederevo (from experience) has the Smederevka vine with the best sensory characteristics, although micro‐localities Zlatno Brdo (Mons Aureus) and Petrijevo are more familiar.
PB  - Srpsko geološko društvo, Beograd
C3  - Knjiga apstrakata / 17. Kongres geologa Srbije, Vrnjačka Banja, 17-20. maj 2018. = Book of abstracts / 17th Serbian Geological Congress, Vrnjačka banja, Maz 17-20, 2018. Vol. 2
T1  - Geological, morphologic and pedologic components of the teroir of Smederevka
T1  - Geološki, morfološki i pedološki činioci teorara Smederevke
EP  - 813
SP  - 808
VL  - 2
UR  - https://hdl.handle.net/21.15107/rcub_grafar_1602
ER  - 

@conference{
author = "Marjanović, M. and Stojaković, A. and Abolmasov, Biljana and Đurić, D. and Đurić, Uroš and Krušić, Jelka and Andrejev, Katarina and Samardžić-Petrović, Mileva",
year = "2018",
abstract = "Terroir depicts a set of pedologic, micro‐climatic and historical factors that have a say in deciding whether and where to practice viticulture and determines its qualitative and quantitative exploitation potential. For winemakers, it is paramount for targeting a viticulture variety. European winemakers use to guide their choices by the family tradition. Scientific breakthroughs, i.e. pedological characterization of the soil, introduced a new approach for viticulture, and drove the world‐leading wineries to turn to scientific approach in the last 30 years. In this research, we went one step further in respect to pedological approach. Since the soil itself is considered as a product of its bedrock and climate, it is logical to also include those factors that condition the properties of the soil itself in the terroir context, such as geological and morphologic factors (Burns, 2010). It is thereby, possible to perform a preliminary delineation of zones with suitable set of factors at regional scales, and direct the subsequent, more detailed soil investigations. By analyzing wider areas, it becomes possible to plan more strategically, especially when it comes to preservation of rare and indigenous vine varieties. From winemakers’ perspective, indigenous vine varieties represent the true genetic potential. Smederevka, which is shyly re‐introduced, but without any planning and consulting the profession is one such example. Before the 2nd World War, Smederevka (colloquially known as “the Yellow”) was grown predominantly in the Smederevo wine region, but with caution to the micro‐location, soil composition, slope aspect, sun reflection off the water surface, etc. The quality was unparalleled in comparison to the same vine from 1950–1990, a period marked by a high‐yield, collective farming practice of the “Godomin” company back in the socialism. Locality Plavinac in Smederevo (from experience) has the Smederevka vine with the best sensory characteristics, although micro‐localities Zlatno Brdo (Mons Aureus) and Petrijevo are more familiar.",
publisher = "Srpsko geološko društvo, Beograd",
journal = "Knjiga apstrakata / 17. Kongres geologa Srbije, Vrnjačka Banja, 17-20. maj 2018. = Book of abstracts / 17th Serbian Geological Congress, Vrnjačka banja, Maz 17-20, 2018. Vol. 2",
title = "Geological, morphologic and pedologic components of the teroir of Smederevka, Geološki, morfološki i pedološki činioci teorara Smederevke",
pages = "813-808",
volume = "2",
url = "https://hdl.handle.net/21.15107/rcub_grafar_1602"
}

Marjanović, M., Stojaković, A., Abolmasov, B., Đurić, D., Đurić, U., Krušić, J., Andrejev, K.,& Samardžić-Petrović, M.. (2018). Geological, morphologic and pedologic components of the teroir of Smederevka. in Knjiga apstrakata / 17. Kongres geologa Srbije, Vrnjačka Banja, 17-20. maj 2018. = Book of abstracts / 17th Serbian Geological Congress, Vrnjačka banja, Maz 17-20, 2018. Vol. 2
Srpsko geološko društvo, Beograd., 2, 808-813.
https://hdl.handle.net/21.15107/rcub_grafar_1602

Marjanović M, Stojaković A, Abolmasov B, Đurić D, Đurić U, Krušić J, Andrejev K, Samardžić-Petrović M. Geological, morphologic and pedologic components of the teroir of Smederevka. in Knjiga apstrakata / 17. Kongres geologa Srbije, Vrnjačka Banja, 17-20. maj 2018. = Book of abstracts / 17th Serbian Geological Congress, Vrnjačka banja, Maz 17-20, 2018. Vol. 2. 2018;2:808-813.
https://hdl.handle.net/21.15107/rcub_grafar_1602 .

Marjanović, M., Stojaković, A., Abolmasov, Biljana, Đurić, D., Đurić, Uroš, Krušić, Jelka, Andrejev, Katarina, Samardžić-Petrović, Mileva, "Geological, morphologic and pedologic components of the teroir of Smederevka" in Knjiga apstrakata / 17. Kongres geologa Srbije, Vrnjačka Banja, 17-20. maj 2018. = Book of abstracts / 17th Serbian Geological Congress, Vrnjačka banja, Maz 17-20, 2018. Vol. 2, 2 (2018):808-813,
https://hdl.handle.net/21.15107/rcub_grafar_1602 .

TY  - CONF
AU  - Abolmasov, Biljana
AU  - Pejić, Marko
AU  - Samardžić-Petrović, Mileva
AU  - Đurić, Uroš
AU  - Milenković, S.
PY  - 2018
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/1589
PB  - Geological Survey of Slovenia, Ljubljana
C3  - Advances in Landslide Research: Proceedings of the 3rd Regional Symposium on Landslides in the Adriatic Balkan Region, 11-13 October 2017, Ljubljana, Slovenia
T1  - Automated GNSS monitoring of Umka landslide review of seven years experience and results
EP  - 71
SP  - 65
DO  - 10.5474/9789616498593
ER  - 

@conference{
author = "Abolmasov, Biljana and Pejić, Marko and Samardžić-Petrović, Mileva and Đurić, Uroš and Milenković, S.",
year = "2018",
publisher = "Geological Survey of Slovenia, Ljubljana",
journal = "Advances in Landslide Research: Proceedings of the 3rd Regional Symposium on Landslides in the Adriatic Balkan Region, 11-13 October 2017, Ljubljana, Slovenia",
title = "Automated GNSS monitoring of Umka landslide review of seven years experience and results",
pages = "71-65",
doi = "10.5474/9789616498593"
}

Abolmasov, B., Pejić, M., Samardžić-Petrović, M., Đurić, U.,& Milenković, S.. (2018). Automated GNSS monitoring of Umka landslide review of seven years experience and results. in Advances in Landslide Research: Proceedings of the 3rd Regional Symposium on Landslides in the Adriatic Balkan Region, 11-13 October 2017, Ljubljana, Slovenia
Geological Survey of Slovenia, Ljubljana., 65-71.
https://doi.org/10.5474/9789616498593

Abolmasov B, Pejić M, Samardžić-Petrović M, Đurić U, Milenković S. Automated GNSS monitoring of Umka landslide review of seven years experience and results. in Advances in Landslide Research: Proceedings of the 3rd Regional Symposium on Landslides in the Adriatic Balkan Region, 11-13 October 2017, Ljubljana, Slovenia. 2018;:65-71.
doi:10.5474/9789616498593 .

Abolmasov, Biljana, Pejić, Marko, Samardžić-Petrović, Mileva, Đurić, Uroš, Milenković, S., "Automated GNSS monitoring of Umka landslide review of seven years experience and results" in Advances in Landslide Research: Proceedings of the 3rd Regional Symposium on Landslides in the Adriatic Balkan Region, 11-13 October 2017, Ljubljana, Slovenia (2018):65-71,
https://doi.org/10.5474/9789616498593 . .

TY  - JOUR
AU  - Krušić, Jelka
AU  - Marjanović, Miloš
AU  - Samardžić-Petrović, Mileva
AU  - Abolmasov, Biljana
AU  - Andrejev, Katarina
AU  - Miladinović, Aleksandar
PY  - 2017
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/1084
T2  - Geofizika
T1  - Comparison of expert, deterministic and Machine Learning approach for landslide susceptibility assessment in Ljubovija Municipality, Serbia
EP  - 273
IS  - 2
SP  - 251
VL  - 34
DO  - 10.15233/gfz.2017.34.15
ER  - 

@article{
author = "Krušić, Jelka and Marjanović, Miloš and Samardžić-Petrović, Mileva and Abolmasov, Biljana and Andrejev, Katarina and Miladinović, Aleksandar",
year = "2017",
journal = "Geofizika",
title = "Comparison of expert, deterministic and Machine Learning approach for landslide susceptibility assessment in Ljubovija Municipality, Serbia",
pages = "273-251",
number = "2",
volume = "34",
doi = "10.15233/gfz.2017.34.15"
}

Krušić, J., Marjanović, M., Samardžić-Petrović, M., Abolmasov, B., Andrejev, K.,& Miladinović, A.. (2017). Comparison of expert, deterministic and Machine Learning approach for landslide susceptibility assessment in Ljubovija Municipality, Serbia. in Geofizika, 34(2), 251-273.
https://doi.org/10.15233/gfz.2017.34.15

Krušić J, Marjanović M, Samardžić-Petrović M, Abolmasov B, Andrejev K, Miladinović A. Comparison of expert, deterministic and Machine Learning approach for landslide susceptibility assessment in Ljubovija Municipality, Serbia. in Geofizika. 2017;34(2):251-273.
doi:10.15233/gfz.2017.34.15 .

Krušić, Jelka, Marjanović, Miloš, Samardžić-Petrović, Mileva, Abolmasov, Biljana, Andrejev, Katarina, Miladinović, Aleksandar, "Comparison of expert, deterministic and Machine Learning approach for landslide susceptibility assessment in Ljubovija Municipality, Serbia" in Geofizika, 34, no. 2 (2017):251-273,
https://doi.org/10.15233/gfz.2017.34.15 . .

TY  - JOUR
AU  - Krušić, Jelka
AU  - Marjanović, Miloš
AU  - Samardžić-Petrović, Mileva
AU  - Abolmasov, Biljana
AU  - Andrejev, Katarina
AU  - Miladinović, Aleksandar
PY  - 2017
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/1936
AB  - Landslide  Susceptibility  Assessment  is  becoming  a  very  productive  re-search area, wherein different modeling approaches are practiced to delineate zones of the high-low likelihood of landslide occurrence. However, there is no strong consensus on which approach is the most adequate. The reason behind the lack of the general view on the performance of different approaches could be partially explained by the particularity of each study. To evaluate the effi-ciency of different approaches they need to be applied under the same conditions for the same study area. Herein, we examined three different approaches, in-cluding expert, deterministic and Machine Learning, on the example of Ljubo-vija Municipality in western Serbia. The study area has been known as suscep-tible to landslides, and represents good ground for assessing the chosen methods. It  is  represented  by  complex  geology,  prone  to  landslides  that  are  commonly  hosted in thick weathering crust of Paleozoic formations, composed of schists and meta-sediments. Under extreme triggering conditions, such as the one that unfolded in May 2014, these thick weathering crusts saturate, and give way to a variety of landslide and flash-flood processes that we will be focusing on in this study. The application of the expert-approach, through Analytical Hierarchy Process  provided  a  rough  assessment  map.  The  deterministic  model,  which  couples simple infinite slope and hydrological model, provided us with lower quality results, when compared to the expert-based one. This could be explained by the assumptions used in the model are too simplistic to generically model a wide range of landslide typology. Finally, Machine Learning approach, using the Random Forest algorithm, provided significantly better results and showed that  it  can  cope  with  versatile  landslide  typology  over  larger  scales.  Its  AUC  performance is about 0.75 which is considerably outperforming the AUC values of the other two models, which were up to 0.55, i.e. at the level of random guess
T2  - Geofizika
T1  - Comparison of expert, deterministic and Machine Learning approach for landslide susceptibility assessment in Ljubovija Municipality, Serbia
VL  - 34
DO  - 10.15233/gfz.2017.34.15
DO  - 10.15233/gfz.2017.34.15
ER  - 

@article{
author = "Krušić, Jelka and Marjanović, Miloš and Samardžić-Petrović, Mileva and Abolmasov, Biljana and Andrejev, Katarina and Miladinović, Aleksandar",
year = "2017",
abstract = "Landslide  Susceptibility  Assessment  is  becoming  a  very  productive  re-search area, wherein different modeling approaches are practiced to delineate zones of the high-low likelihood of landslide occurrence. However, there is no strong consensus on which approach is the most adequate. The reason behind the lack of the general view on the performance of different approaches could be partially explained by the particularity of each study. To evaluate the effi-ciency of different approaches they need to be applied under the same conditions for the same study area. Herein, we examined three different approaches, in-cluding expert, deterministic and Machine Learning, on the example of Ljubo-vija Municipality in western Serbia. The study area has been known as suscep-tible to landslides, and represents good ground for assessing the chosen methods. It  is  represented  by  complex  geology,  prone  to  landslides  that  are  commonly  hosted in thick weathering crust of Paleozoic formations, composed of schists and meta-sediments. Under extreme triggering conditions, such as the one that unfolded in May 2014, these thick weathering crusts saturate, and give way to a variety of landslide and flash-flood processes that we will be focusing on in this study. The application of the expert-approach, through Analytical Hierarchy Process  provided  a  rough  assessment  map.  The  deterministic  model,  which  couples simple infinite slope and hydrological model, provided us with lower quality results, when compared to the expert-based one. This could be explained by the assumptions used in the model are too simplistic to generically model a wide range of landslide typology. Finally, Machine Learning approach, using the Random Forest algorithm, provided significantly better results and showed that  it  can  cope  with  versatile  landslide  typology  over  larger  scales.  Its  AUC  performance is about 0.75 which is considerably outperforming the AUC values of the other two models, which were up to 0.55, i.e. at the level of random guess",
journal = "Geofizika",
title = "Comparison of expert, deterministic and Machine Learning approach for landslide susceptibility assessment in Ljubovija Municipality, Serbia",
volume = "34",
doi = "10.15233/gfz.2017.34.15, 10.15233/gfz.2017.34.15"
}

Krušić, J., Marjanović, M., Samardžić-Petrović, M., Abolmasov, B., Andrejev, K.,& Miladinović, A.. (2017). Comparison of expert, deterministic and Machine Learning approach for landslide susceptibility assessment in Ljubovija Municipality, Serbia. in Geofizika, 34.
https://doi.org/10.15233/gfz.2017.34.15

Krušić J, Marjanović M, Samardžić-Petrović M, Abolmasov B, Andrejev K, Miladinović A. Comparison of expert, deterministic and Machine Learning approach for landslide susceptibility assessment in Ljubovija Municipality, Serbia. in Geofizika. 2017;34.
doi:10.15233/gfz.2017.34.15 .

Krušić, Jelka, Marjanović, Miloš, Samardžić-Petrović, Mileva, Abolmasov, Biljana, Andrejev, Katarina, Miladinović, Aleksandar, "Comparison of expert, deterministic and Machine Learning approach for landslide susceptibility assessment in Ljubovija Municipality, Serbia" in Geofizika, 34 (2017),
https://doi.org/10.15233/gfz.2017.34.15 . .

TY  - JOUR
AU  - Samardžić-Petrović, Mileva
AU  - Kovačević, Miloš
AU  - Bajat, Branislav
AU  - Dragićević, Suzana
PY  - 2017
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/865
AB  - The representation of land use change (LUC) is often achieved by using data-driven methods that include machine learning (ML) techniques. The main objectives of this research study are to implement three ML techniques, Decision Trees (DT), Neural Networks (NN), and Support Vector Machines (SVM) for LUC modeling, in order to compare these three ML techniques and to find the appropriate data representation. The ML techniques are applied on the case study of LUC in three municipalities of the City of Belgrade, the Republic of Serbia, using historical geospatial data sets and considering nine land use classes. The ML models were built and assessed using two different time intervals. The information gain ranking technique and the recursive attribute elimination procedure were implemented to find the most informative attributes that were related to LUC in the study area. The results indicate that all three ML techniques can be used effectively for short-term forecasting of LUC, but the SVM achieved the highest agreement of predicted changes.
PB  - MDPI AG
T2  - Isprs International Journal of Geo-Information
T1  - Machine Learning Techniques for Modelling Short Term Land-Use Change
IS  - 12
VL  - 6
DO  - 10.3390/ijgi6120387
ER  - 

@article{
author = "Samardžić-Petrović, Mileva and Kovačević, Miloš and Bajat, Branislav and Dragićević, Suzana",
year = "2017",
abstract = "The representation of land use change (LUC) is often achieved by using data-driven methods that include machine learning (ML) techniques. The main objectives of this research study are to implement three ML techniques, Decision Trees (DT), Neural Networks (NN), and Support Vector Machines (SVM) for LUC modeling, in order to compare these three ML techniques and to find the appropriate data representation. The ML techniques are applied on the case study of LUC in three municipalities of the City of Belgrade, the Republic of Serbia, using historical geospatial data sets and considering nine land use classes. The ML models were built and assessed using two different time intervals. The information gain ranking technique and the recursive attribute elimination procedure were implemented to find the most informative attributes that were related to LUC in the study area. The results indicate that all three ML techniques can be used effectively for short-term forecasting of LUC, but the SVM achieved the highest agreement of predicted changes.",
publisher = "MDPI AG",
journal = "Isprs International Journal of Geo-Information",
title = "Machine Learning Techniques for Modelling Short Term Land-Use Change",
number = "12",
volume = "6",
doi = "10.3390/ijgi6120387"
}

Samardžić-Petrović, M., Kovačević, M., Bajat, B.,& Dragićević, S.. (2017). Machine Learning Techniques for Modelling Short Term Land-Use Change. in Isprs International Journal of Geo-Information
MDPI AG., 6(12).
https://doi.org/10.3390/ijgi6120387

Samardžić-Petrović M, Kovačević M, Bajat B, Dragićević S. Machine Learning Techniques for Modelling Short Term Land-Use Change. in Isprs International Journal of Geo-Information. 2017;6(12).
doi:10.3390/ijgi6120387 .

Samardžić-Petrović, Mileva, Kovačević, Miloš, Bajat, Branislav, Dragićević, Suzana, "Machine Learning Techniques for Modelling Short Term Land-Use Change" in Isprs International Journal of Geo-Information, 6, no. 12 (2017),
https://doi.org/10.3390/ijgi6120387 . .

TY  - CONF
AU  - Marjanović, M.
AU  - Abolmasov, Biljana
AU  - Pejić, Marko
AU  - Bogdanović, S.
AU  - Samardžić-Petrović, Mileva
PY  - 2017
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/1542
PB  - Geological Survey of Slovenia, Ljubljana
C3  - Symposium programme = Book of abstracts / 3rd Regional Symposium on Landslides in the Adriatic - Balkan Region, Ljubljana - RESYLAB 2017, 11-13 October 2017, Ljubljana, Slovenia
T1  - Rockfall monitoring and simulation on a rock slope near Ljig in Serbia
EP  - 36
SP  - 36
UR  - https://hdl.handle.net/21.15107/rcub_grafar_1542
ER  - 

@conference{
author = "Marjanović, M. and Abolmasov, Biljana and Pejić, Marko and Bogdanović, S. and Samardžić-Petrović, Mileva",
year = "2017",
publisher = "Geological Survey of Slovenia, Ljubljana",
journal = "Symposium programme = Book of abstracts / 3rd Regional Symposium on Landslides in the Adriatic - Balkan Region, Ljubljana - RESYLAB 2017, 11-13 October 2017, Ljubljana, Slovenia",
title = "Rockfall monitoring and simulation on a rock slope near Ljig in Serbia",
pages = "36-36",
url = "https://hdl.handle.net/21.15107/rcub_grafar_1542"
}

Marjanović, M., Abolmasov, B., Pejić, M., Bogdanović, S.,& Samardžić-Petrović, M.. (2017). Rockfall monitoring and simulation on a rock slope near Ljig in Serbia. in Symposium programme = Book of abstracts / 3rd Regional Symposium on Landslides in the Adriatic - Balkan Region, Ljubljana - RESYLAB 2017, 11-13 October 2017, Ljubljana, Slovenia
Geological Survey of Slovenia, Ljubljana., 36-36.
https://hdl.handle.net/21.15107/rcub_grafar_1542

Marjanović M, Abolmasov B, Pejić M, Bogdanović S, Samardžić-Petrović M. Rockfall monitoring and simulation on a rock slope near Ljig in Serbia. in Symposium programme = Book of abstracts / 3rd Regional Symposium on Landslides in the Adriatic - Balkan Region, Ljubljana - RESYLAB 2017, 11-13 October 2017, Ljubljana, Slovenia. 2017;:36-36.
https://hdl.handle.net/21.15107/rcub_grafar_1542 .

Marjanović, M., Abolmasov, Biljana, Pejić, Marko, Bogdanović, S., Samardžić-Petrović, Mileva, "Rockfall monitoring and simulation on a rock slope near Ljig in Serbia" in Symposium programme = Book of abstracts / 3rd Regional Symposium on Landslides in the Adriatic - Balkan Region, Ljubljana - RESYLAB 2017, 11-13 October 2017, Ljubljana, Slovenia (2017):36-36,
https://hdl.handle.net/21.15107/rcub_grafar_1542 .

TY  - JOUR
AU  - Samardžić-Petrović, Mileva
AU  - Dragićević, Suzana
AU  - Kovačević, Miloš
AU  - Bajat, Branislav
PY  - 2016
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/777
AB  - Support Vector Machines (SVM) is a machine learning (ML) algorithm commonly applied to the classification of remotely sensing data and more recently for modeling land use changes. However, in most geospatial applications the current literature does not elaborate on specifications of the SVM method with respect to data sampling, attribute selection and optimal parameters choices. Therefore the main objective of this study is to present and investigate the SVM technique for modeling urban land use change. The SVM model building procedure is presented together with the detailed evaluation of the output results with respect to the choice of datasets, attributes and the change of SVM parameters. Geospatial datasets containing nine land use classes and spatial attributes for the Municipality of Zemun, Republic of Serbia were used for years 2001, 2003, 2007 and 2011. The Correlation-based Feature Subset method, kappa coefficient, Area Under Receiver Operating Characteristic Curve (AUC) and kappa simulation were used to perform the model evaluation and compare the model outputs with the real land use datasets. The obtained results indicate that the SVM-based models perform better when implementing balanced data sampling, reduced data sets to informative subsets of attributes and properly identify the optimal learning parameters.
PB  - Blackwell Publishing Ltd
T2  - Transactions in Gis
T1  - Modeling Urban Land Use Changes Using Support Vector Machines
EP  - 734
IS  - 5
SP  - 718
VL  - 20
DO  - 10.1111/tgis.12174
ER  - 

@article{
author = "Samardžić-Petrović, Mileva and Dragićević, Suzana and Kovačević, Miloš and Bajat, Branislav",
year = "2016",
abstract = "Support Vector Machines (SVM) is a machine learning (ML) algorithm commonly applied to the classification of remotely sensing data and more recently for modeling land use changes. However, in most geospatial applications the current literature does not elaborate on specifications of the SVM method with respect to data sampling, attribute selection and optimal parameters choices. Therefore the main objective of this study is to present and investigate the SVM technique for modeling urban land use change. The SVM model building procedure is presented together with the detailed evaluation of the output results with respect to the choice of datasets, attributes and the change of SVM parameters. Geospatial datasets containing nine land use classes and spatial attributes for the Municipality of Zemun, Republic of Serbia were used for years 2001, 2003, 2007 and 2011. The Correlation-based Feature Subset method, kappa coefficient, Area Under Receiver Operating Characteristic Curve (AUC) and kappa simulation were used to perform the model evaluation and compare the model outputs with the real land use datasets. The obtained results indicate that the SVM-based models perform better when implementing balanced data sampling, reduced data sets to informative subsets of attributes and properly identify the optimal learning parameters.",
publisher = "Blackwell Publishing Ltd",
journal = "Transactions in Gis",
title = "Modeling Urban Land Use Changes Using Support Vector Machines",
pages = "734-718",
number = "5",
volume = "20",
doi = "10.1111/tgis.12174"
}

Samardžić-Petrović, M., Dragićević, S., Kovačević, M.,& Bajat, B.. (2016). Modeling Urban Land Use Changes Using Support Vector Machines. in Transactions in Gis
Blackwell Publishing Ltd., 20(5), 718-734.
https://doi.org/10.1111/tgis.12174

Samardžić-Petrović M, Dragićević S, Kovačević M, Bajat B. Modeling Urban Land Use Changes Using Support Vector Machines. in Transactions in Gis. 2016;20(5):718-734.
doi:10.1111/tgis.12174 .

Samardžić-Petrović, Mileva, Dragićević, Suzana, Kovačević, Miloš, Bajat, Branislav, "Modeling Urban Land Use Changes Using Support Vector Machines" in Transactions in Gis, 20, no. 5 (2016):718-734,
https://doi.org/10.1111/tgis.12174 . .

TY  - CONF
AU  - Todorović-Drakul, Miljana
AU  - Samardžić-Petrović, Mileva
AU  - Grekulović, Sanja
AU  - Odalović, Oleg
AU  - Blagojević, Dragan
PY  - 2016
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/1430
PB  - Faculty of Civil Engineering, Belgrade
C3  - Proceedings of GeoMLA, Geostatistics and Machine Learning, Application in Climate and Environmental Sciences, Belgrade, Serbia 21-24 June 2016
T1  - Total electron content prediction using machine learning techniques
EP  - 44
SP  - 40
UR  - https://hdl.handle.net/21.15107/rcub_grafar_1430
ER  - 

@conference{
author = "Todorović-Drakul, Miljana and Samardžić-Petrović, Mileva and Grekulović, Sanja and Odalović, Oleg and Blagojević, Dragan",
year = "2016",
publisher = "Faculty of Civil Engineering, Belgrade",
journal = "Proceedings of GeoMLA, Geostatistics and Machine Learning, Application in Climate and Environmental Sciences, Belgrade, Serbia 21-24 June 2016",
title = "Total electron content prediction using machine learning techniques",
pages = "44-40",
url = "https://hdl.handle.net/21.15107/rcub_grafar_1430"
}

Todorović-Drakul, M., Samardžić-Petrović, M., Grekulović, S., Odalović, O.,& Blagojević, D.. (2016). Total electron content prediction using machine learning techniques. in Proceedings of GeoMLA, Geostatistics and Machine Learning, Application in Climate and Environmental Sciences, Belgrade, Serbia 21-24 June 2016
Faculty of Civil Engineering, Belgrade., 40-44.
https://hdl.handle.net/21.15107/rcub_grafar_1430

Todorović-Drakul M, Samardžić-Petrović M, Grekulović S, Odalović O, Blagojević D. Total electron content prediction using machine learning techniques. in Proceedings of GeoMLA, Geostatistics and Machine Learning, Application in Climate and Environmental Sciences, Belgrade, Serbia 21-24 June 2016. 2016;:40-44.
https://hdl.handle.net/21.15107/rcub_grafar_1430 .

Todorović-Drakul, Miljana, Samardžić-Petrović, Mileva, Grekulović, Sanja, Odalović, Oleg, Blagojević, Dragan, "Total electron content prediction using machine learning techniques" in Proceedings of GeoMLA, Geostatistics and Machine Learning, Application in Climate and Environmental Sciences, Belgrade, Serbia 21-24 June 2016 (2016):40-44,
https://hdl.handle.net/21.15107/rcub_grafar_1430 .

TY  - JOUR
AU  - Samardžić-Petrović, Mileva
AU  - Dragićević, Suzana
AU  - Bajat, Branislav
AU  - Kovačević, Miloš
PY  - 2015
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/1043
T2  - Geomatica
T1  - Exploring the Decision Tree Method for Modelling Urban Land Use Change
EP  - 325
IS  - 3
SP  - 313
VL  - 69
UR  - https://hdl.handle.net/21.15107/rcub_grafar_1043
ER  - 

@article{
author = "Samardžić-Petrović, Mileva and Dragićević, Suzana and Bajat, Branislav and Kovačević, Miloš",
year = "2015",
journal = "Geomatica",
title = "Exploring the Decision Tree Method for Modelling Urban Land Use Change",
pages = "325-313",
number = "3",
volume = "69",
url = "https://hdl.handle.net/21.15107/rcub_grafar_1043"
}

Samardžić-Petrović, M., Dragićević, S., Bajat, B.,& Kovačević, M.. (2015). Exploring the Decision Tree Method for Modelling Urban Land Use Change. in Geomatica, 69(3), 313-325.
https://hdl.handle.net/21.15107/rcub_grafar_1043

Samardžić-Petrović M, Dragićević S, Bajat B, Kovačević M. Exploring the Decision Tree Method for Modelling Urban Land Use Change. in Geomatica. 2015;69(3):313-325.
https://hdl.handle.net/21.15107/rcub_grafar_1043 .

Samardžić-Petrović, Mileva, Dragićević, Suzana, Bajat, Branislav, Kovačević, Miloš, "Exploring the Decision Tree Method for Modelling Urban Land Use Change" in Geomatica, 69, no. 3 (2015):313-325,
https://hdl.handle.net/21.15107/rcub_grafar_1043 .

TY  - CHAP
AU  - Samardžić-Petrović, Mileva
AU  - Dragićević, Suzana
PY  - 2015
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/1044
PB  - Cham: Springer International Publishing
T2  - Computational Science and Its Applications -- ICCSA 2015
T1  - Modeling the Propagation of Forest Insect Infestation Using Machine Learning Techniques
EP  - 657
SP  - 646
VL  - 9157
DO  - 10.1007/978-3-319-21470-2_47
ER  - 

@inbook{
author = "Samardžić-Petrović, Mileva and Dragićević, Suzana",
year = "2015",
publisher = "Cham: Springer International Publishing",
journal = "Computational Science and Its Applications -- ICCSA 2015",
booktitle = "Modeling the Propagation of Forest Insect Infestation Using Machine Learning Techniques",
pages = "657-646",
volume = "9157",
doi = "10.1007/978-3-319-21470-2_47"
}

Samardžić-Petrović, M.,& Dragićević, S.. (2015). Modeling the Propagation of Forest Insect Infestation Using Machine Learning Techniques. in Computational Science and Its Applications -- ICCSA 2015
Cham: Springer International Publishing., 9157, 646-657.
https://doi.org/10.1007/978-3-319-21470-2_47

Samardžić-Petrović M, Dragićević S. Modeling the Propagation of Forest Insect Infestation Using Machine Learning Techniques. in Computational Science and Its Applications -- ICCSA 2015. 2015;9157:646-657.
doi:10.1007/978-3-319-21470-2_47 .

Samardžić-Petrović, Mileva, Dragićević, Suzana, "Modeling the Propagation of Forest Insect Infestation Using Machine Learning Techniques" in Computational Science and Its Applications -- ICCSA 2015, 9157 (2015):646-657,
https://doi.org/10.1007/978-3-319-21470-2_47 . .

TY  - THES
AU  - Samardžić-Petrović, Mileva
PY  - 2014
UR  - http://eteze.bg.ac.rs/application/showtheses?thesesId=3529
UR  - https://fedorabg.bg.ac.rs/fedora/get/o:12234/bdef:Content/download
UR  - http://vbs.rs/scripts/cobiss?command=DISPLAY&base=70036&RID=46210831
UR  - http://nardus.mpn.gov.rs/123456789/6136
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/1985
AB  - One of the main tasks of data-driven modelling methods is to induce arepresentative model of underlying spatial - temporal processes using past dataand data mining and machine learning approach. As relatively new methods,known to be capable of solving complex nonlinear problems, data-driven methodsare insufficiently researched in the field of land use. The main objective of thisdissertation is to develop a methodology for predictive urban land use changemodels using data-driven approach together with evaluation of the performance ofdifferent data-driven methods, which in the stage of finding patterns of land usechanges use three different machine learning techniques: Decision Trees, NeuralNetworks and Support Vector Machines. The proposed methodology of data-drivenmethods was presented and special attention was paid to different datarepresentation, data sampling and the selection of attributes by four methods (χ2,Info Gain, Gain Ratio and Correlation-based Feature Subset) that best describe theprocess of land use change. Additionally, a sensitivity analysis of the SupportVector Machines -based models was performed with regards to attribute selectionand parameter changes. Development and evaluation of the methodology wasperformed using data on three Belgrade municipalities (Zemun, New Belgrade andSurčin), which are represented as 10×10 m grid cells in four different moments intime (2001, 2003, 2007 and 2010).The obtained results indicate that the proposed data-driven methodology providespredictive models which could be successfully used for creation of possiblescenarios of urban land use changes in the future. All three examined machinelearning techniques are suitable for modeling land use change. Accuracy andperformance of models can be improved using proposed balanced data sampling,including the information about neighbourhood and history in datarepresentations and relevant attribute selections. Additionally, using selectedsubset of attributes resulted in a simple model and with less possibility to beoverfitted with higher values of Support Vector Machines parameters.
AB  - Један од главних задатака моделирања метода вођених подацима (Data-driven methods) је проналажење репрезентативног модела испитивног просторно временског процеса, применом података из прошлости и Data Mining и Machine Learning приступа...
PB  - Универзитет у Београду, Грађевински факултет
T2  - Универзитет у Београду
T1  - Predicting land use change with data-driven models
T1  - Predviđanje promena u korišćenju zemljišta primenom modela vođenih podacima (DATA-DRIVEN MODELS)
UR  - https://hdl.handle.net/21.15107/rcub_nardus_6136
ER  - 

@phdthesis{
author = "Samardžić-Petrović, Mileva",
year = "2014",
abstract = "One of the main tasks of data-driven modelling methods is to induce arepresentative model of underlying spatial - temporal processes using past dataand data mining and machine learning approach. As relatively new methods,known to be capable of solving complex nonlinear problems, data-driven methodsare insufficiently researched in the field of land use. The main objective of thisdissertation is to develop a methodology for predictive urban land use changemodels using data-driven approach together with evaluation of the performance ofdifferent data-driven methods, which in the stage of finding patterns of land usechanges use three different machine learning techniques: Decision Trees, NeuralNetworks and Support Vector Machines. The proposed methodology of data-drivenmethods was presented and special attention was paid to different datarepresentation, data sampling and the selection of attributes by four methods (χ2,Info Gain, Gain Ratio and Correlation-based Feature Subset) that best describe theprocess of land use change. Additionally, a sensitivity analysis of the SupportVector Machines -based models was performed with regards to attribute selectionand parameter changes. Development and evaluation of the methodology wasperformed using data on three Belgrade municipalities (Zemun, New Belgrade andSurčin), which are represented as 10×10 m grid cells in four different moments intime (2001, 2003, 2007 and 2010).The obtained results indicate that the proposed data-driven methodology providespredictive models which could be successfully used for creation of possiblescenarios of urban land use changes in the future. All three examined machinelearning techniques are suitable for modeling land use change. Accuracy andperformance of models can be improved using proposed balanced data sampling,including the information about neighbourhood and history in datarepresentations and relevant attribute selections. Additionally, using selectedsubset of attributes resulted in a simple model and with less possibility to beoverfitted with higher values of Support Vector Machines parameters., Један од главних задатака моделирања метода вођених подацима (Data-driven methods) је проналажење репрезентативног модела испитивног просторно временског процеса, применом података из прошлости и Data Mining и Machine Learning приступа...",
publisher = "Универзитет у Београду, Грађевински факултет",
journal = "Универзитет у Београду",
title = "Predicting land use change with data-driven models, Predviđanje promena u korišćenju zemljišta primenom modela vođenih podacima (DATA-DRIVEN MODELS)",
url = "https://hdl.handle.net/21.15107/rcub_nardus_6136"
}

Samardžić-Petrović, M.. (2014). Predicting land use change with data-driven models. in Универзитет у Београду
Универзитет у Београду, Грађевински факултет..
https://hdl.handle.net/21.15107/rcub_nardus_6136

Samardžić-Petrović M. Predicting land use change with data-driven models. in Универзитет у Београду. 2014;.
https://hdl.handle.net/21.15107/rcub_nardus_6136 .

Samardžić-Petrović, Mileva, "Predicting land use change with data-driven models" in Универзитет у Београду (2014),
https://hdl.handle.net/21.15107/rcub_nardus_6136 .

TY  - CONF
AU  - Samardžić-Petrović, Mileva
AU  - Bajat, Branislav
AU  - Kovačević, Miloš
AU  - Dragićević, Suzana
PY  - 2014
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/1196
PB  - Department of Geodesy and Geoinformation, Vienna University of Technology, Vienna
C3  - Extended Abstract Proceedings of the GIScience 2014, 23-26 September, Vienna, Austria
T1  - Sensitivity analysis of Support Vector Machine land use change modelling method
UR  - https://hdl.handle.net/21.15107/rcub_grafar_1196
ER  - 

@conference{
author = "Samardžić-Petrović, Mileva and Bajat, Branislav and Kovačević, Miloš and Dragićević, Suzana",
year = "2014",
publisher = "Department of Geodesy and Geoinformation, Vienna University of Technology, Vienna",
journal = "Extended Abstract Proceedings of the GIScience 2014, 23-26 September, Vienna, Austria",
title = "Sensitivity analysis of Support Vector Machine land use change modelling method",
url = "https://hdl.handle.net/21.15107/rcub_grafar_1196"
}

Samardžić-Petrović, M., Bajat, B., Kovačević, M.,& Dragićević, S.. (2014). Sensitivity analysis of Support Vector Machine land use change modelling method. in Extended Abstract Proceedings of the GIScience 2014, 23-26 September, Vienna, Austria
Department of Geodesy and Geoinformation, Vienna University of Technology, Vienna..
https://hdl.handle.net/21.15107/rcub_grafar_1196

Samardžić-Petrović M, Bajat B, Kovačević M, Dragićević S. Sensitivity analysis of Support Vector Machine land use change modelling method. in Extended Abstract Proceedings of the GIScience 2014, 23-26 September, Vienna, Austria. 2014;.
https://hdl.handle.net/21.15107/rcub_grafar_1196 .

Samardžić-Petrović, Mileva, Bajat, Branislav, Kovačević, Miloš, Dragićević, Suzana, "Sensitivity analysis of Support Vector Machine land use change modelling method" in Extended Abstract Proceedings of the GIScience 2014, 23-26 September, Vienna, Austria (2014),
https://hdl.handle.net/21.15107/rcub_grafar_1196 .

TY  - CONF
AU  - Bajat, Branislav
AU  - Kilibarda, Milan
AU  - Pejović, Milutin
AU  - Samardžić-Petrović, Mileva
PY  - 2014
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/1227
PB  - Faculty of Mining, Geology and Petroleum Engineering, University of Zagreb ; Faculty of Civil Engineering, University of Rijeka, Zagreb ; Rijeka
C3  - Landslide and Flood Hazard Assessment, Proceedings of the 1st Regional Symposium on Landslides in the Adriatic-Balkan Region
T1  - The Preliminary Damage Assessment of Properties Based on Massive Appraisal Maps
UR  - https://hdl.handle.net/21.15107/rcub_grafar_1227
ER  - 

@conference{
author = "Bajat, Branislav and Kilibarda, Milan and Pejović, Milutin and Samardžić-Petrović, Mileva",
year = "2014",
publisher = "Faculty of Mining, Geology and Petroleum Engineering, University of Zagreb ; Faculty of Civil Engineering, University of Rijeka, Zagreb ; Rijeka",
journal = "Landslide and Flood Hazard Assessment, Proceedings of the 1st Regional Symposium on Landslides in the Adriatic-Balkan Region",
title = "The Preliminary Damage Assessment of Properties Based on Massive Appraisal Maps",
url = "https://hdl.handle.net/21.15107/rcub_grafar_1227"
}

Bajat, B., Kilibarda, M., Pejović, M.,& Samardžić-Petrović, M.. (2014). The Preliminary Damage Assessment of Properties Based on Massive Appraisal Maps. in Landslide and Flood Hazard Assessment, Proceedings of the 1st Regional Symposium on Landslides in the Adriatic-Balkan Region
Faculty of Mining, Geology and Petroleum Engineering, University of Zagreb ; Faculty of Civil Engineering, University of Rijeka, Zagreb ; Rijeka..
https://hdl.handle.net/21.15107/rcub_grafar_1227

Bajat B, Kilibarda M, Pejović M, Samardžić-Petrović M. The Preliminary Damage Assessment of Properties Based on Massive Appraisal Maps. in Landslide and Flood Hazard Assessment, Proceedings of the 1st Regional Symposium on Landslides in the Adriatic-Balkan Region. 2014;.
https://hdl.handle.net/21.15107/rcub_grafar_1227 .

Bajat, Branislav, Kilibarda, Milan, Pejović, Milutin, Samardžić-Petrović, Mileva, "The Preliminary Damage Assessment of Properties Based on Massive Appraisal Maps" in Landslide and Flood Hazard Assessment, Proceedings of the 1st Regional Symposium on Landslides in the Adriatic-Balkan Region (2014),
https://hdl.handle.net/21.15107/rcub_grafar_1227 .