TY  - JOUR
AU  - Đorđević, Filip
PY  - 2024
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/3484
AB  - Masonry structures in addition to their long heritage are still widely used in civil engineering practice. It should be emphasized that a lot of research has already been done on the seismic behavior of masonry structures. However, due to the nature of such a problem, its complexity and seriousness, the development of numerical models and their connection with experimental tests are always important. This is particularly significant considering their vulnerability to the action of horizontal forces generated during seismic excitations. In recent decades, many researchers have tried to capture the behavior of unreinforced masonry (URM) structures or reinforced concrete (RC) frames with masonry infills exposed to earthquakes, using different approaches. This paper tackles numerical modeling based on the finite element method (FEM) for the estimation of the dynamic response of two adjacent interacting URM units, subjected to shaking table motions. Geometrical and material properties of the specimen are provided by the Horizon 2020 project SERA-AIMS (The Seismology and Earthquake Engineering Research Infrastructure Alliance for Europe – Seismic Testing of Adjacent Interacting Masonry Structures). The analyses of dynamic performance were executed in SAP2000 software. Obtained results on the numerical model provide useful guidelines for modeling the nonlinear seismic behavior of masonry buildings.
PB  - IPSI, Belgrade
T2  - IPSI Transactions on Internet Research
T1  - Numerical Modeling of Two Adjacent Interacting URM Structures
EP  - 78
IS  - 1
SP  - 70
VL  - 20
DO  - 10.58245/ipsi.tir.2401.07
ER  - 

@article{
author = "Đorđević, Filip",
year = "2024",
abstract = "Masonry structures in addition to their long heritage are still widely used in civil engineering practice. It should be emphasized that a lot of research has already been done on the seismic behavior of masonry structures. However, due to the nature of such a problem, its complexity and seriousness, the development of numerical models and their connection with experimental tests are always important. This is particularly significant considering their vulnerability to the action of horizontal forces generated during seismic excitations. In recent decades, many researchers have tried to capture the behavior of unreinforced masonry (URM) structures or reinforced concrete (RC) frames with masonry infills exposed to earthquakes, using different approaches. This paper tackles numerical modeling based on the finite element method (FEM) for the estimation of the dynamic response of two adjacent interacting URM units, subjected to shaking table motions. Geometrical and material properties of the specimen are provided by the Horizon 2020 project SERA-AIMS (The Seismology and Earthquake Engineering Research Infrastructure Alliance for Europe – Seismic Testing of Adjacent Interacting Masonry Structures). The analyses of dynamic performance were executed in SAP2000 software. Obtained results on the numerical model provide useful guidelines for modeling the nonlinear seismic behavior of masonry buildings.",
publisher = "IPSI, Belgrade",
journal = "IPSI Transactions on Internet Research",
title = "Numerical Modeling of Two Adjacent Interacting URM Structures",
pages = "78-70",
number = "1",
volume = "20",
doi = "10.58245/ipsi.tir.2401.07"
}

Đorđević, F.. (2024). Numerical Modeling of Two Adjacent Interacting URM Structures. in IPSI Transactions on Internet Research
IPSI, Belgrade., 20(1), 70-78.
https://doi.org/10.58245/ipsi.tir.2401.07

Đorđević F. Numerical Modeling of Two Adjacent Interacting URM Structures. in IPSI Transactions on Internet Research. 2024;20(1):70-78.
doi:10.58245/ipsi.tir.2401.07 .

Đorđević, Filip, "Numerical Modeling of Two Adjacent Interacting URM Structures" in IPSI Transactions on Internet Research, 20, no. 1 (2024):70-78,
https://doi.org/10.58245/ipsi.tir.2401.07 . .

TY  - JOUR
AU  - Đorđević, Filip
AU  - Kostić, Svetlana M.
PY  - 2023
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/3107
AB  - In this study, two machine-learning algorithms based on the artificial neural network
(ANN) model are proposed to estimate the ultimate compressive strength of square
concrete-filled steel tubular columns. The development of such prognostic models is
achievable since an extensive set of experimental tests exist for these members. The
models are developed to use the simplest possible network architecture but attain
very high accuracy. A total dataset of 1022 specimens with 685 stub columns and 337
slender columns subjected to pure axial compression is collected from the available literature.
This is significant for the development of the initial model considering that for
this field it falls under the scope of big data analysis. The ANN models are validated by
comparison with experimental results. The validation study has shown the superiority
of surrogate models over the Eurocode 4 design code. The empirical equation derived
from the best-tuned Bayesian regularization algorithm shows a better agreement with
the experimental results than those obtained by the Levenberg–Marquardt algorithm,
and Eurocode 4 design code. A similar conclusion applies to stub and slender columns
independently. The Bayesian regularization-based model is negligibly slower than the
one developed on the Levenberg–Marquardt algorithm but gives a better generalization
even with simplified ANN. Generally, besides its high accuracy, one of the key
benefits of the presented ANN model is its applicability to a broader range of columns
than Eurocode 4 and other studies.
PB  - Springer
T2  - Journal of Big Data
T1  - Practical ANN prediction models for the axial capacity of square CFST columns
VL  - 10
DO  - 10.1186/s40537-023-00739-y
ER  - 

@article{
author = "Đorđević, Filip and Kostić, Svetlana M.",
year = "2023",
abstract = "In this study, two machine-learning algorithms based on the artificial neural network
(ANN) model are proposed to estimate the ultimate compressive strength of square
concrete-filled steel tubular columns. The development of such prognostic models is
achievable since an extensive set of experimental tests exist for these members. The
models are developed to use the simplest possible network architecture but attain
very high accuracy. A total dataset of 1022 specimens with 685 stub columns and 337
slender columns subjected to pure axial compression is collected from the available literature.
This is significant for the development of the initial model considering that for
this field it falls under the scope of big data analysis. The ANN models are validated by
comparison with experimental results. The validation study has shown the superiority
of surrogate models over the Eurocode 4 design code. The empirical equation derived
from the best-tuned Bayesian regularization algorithm shows a better agreement with
the experimental results than those obtained by the Levenberg–Marquardt algorithm,
and Eurocode 4 design code. A similar conclusion applies to stub and slender columns
independently. The Bayesian regularization-based model is negligibly slower than the
one developed on the Levenberg–Marquardt algorithm but gives a better generalization
even with simplified ANN. Generally, besides its high accuracy, one of the key
benefits of the presented ANN model is its applicability to a broader range of columns
than Eurocode 4 and other studies.",
publisher = "Springer",
journal = "Journal of Big Data",
title = "Practical ANN prediction models for the axial capacity of square CFST columns",
volume = "10",
doi = "10.1186/s40537-023-00739-y"
}

Đorđević, F.,& Kostić, S. M.. (2023). Practical ANN prediction models for the axial capacity of square CFST columns. in Journal of Big Data
Springer., 10.
https://doi.org/10.1186/s40537-023-00739-y

Đorđević F, Kostić SM. Practical ANN prediction models for the axial capacity of square CFST columns. in Journal of Big Data. 2023;10.
doi:10.1186/s40537-023-00739-y .

Đorđević, Filip, Kostić, Svetlana M., "Practical ANN prediction models for the axial capacity of square CFST columns" in Journal of Big Data, 10 (2023),
https://doi.org/10.1186/s40537-023-00739-y . .

TY  - JOUR
AU  - Babović, Zoran
AU  - Bajat, Branislav
AU  - Đokić, Vladan
AU  - Đorđević, Filip
AU  - Drašković, Dražen
AU  - Filipović, Nenad
AU  - Furht, Borko
AU  - Gačić, Nikola
AU  - Ikodinović, Igor
AU  - Ilić, Marija
AU  - Irfanoglu, Ayhan
AU  - Jelenković, Branislav
AU  - Kartelj, Aleksandar
AU  - Klimeck, Gerhard
AU  - Korolija, Nenad
AU  - Kotlar, Miloš
AU  - Kovačević, Miloš
AU  - Kuzmanović, Vladan
AU  - Marinković, Marko
AU  - Marković, Slobodan
AU  - Mendelson, Avi
AU  - Milutinović, Veljko
AU  - Nešković, Aleksandar
AU  - Nešković, Nataša
AU  - Mitić, Nenad
AU  - Nikolić, Boško
AU  - Novoselov, Konstantin
AU  - Prakash, Arun
AU  - Ratković, Ivan
AU  - Stojadinović, Zoran
AU  - Ustyuzhanin, Andrey
AU  - Zak, Stan
PY  - 2023
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/3113
AB  - This article presents a taxonomy and represents a repository of open problems in computing for numerically and logically intensive problems in a number of disciplines that have to synergize for the best performance of simulation-based feasibility studies on nature-oriented engineering in general and civil engineering in particular. Topics include but are not limited to: Nature-based construction, genomics supporting nature-based construction, earthquake engineering, and other types of geophysical disaster prevention activities, as well as the studies of processes and materials of interest for the above. In all these fields, problems are discussed that generate huge amounts of Big Data and are characterized with mathematically highly complex Iterative Algorithms. In the domain of applications, it has been stressed that problems could be made less computationally demanding if the number of computing iterations is made smaller (with the help of Artificial Intelligence or Conditional Algorithms), or if each computing iteration is made shorter in time (with the help of Data Filtration and Data Quantization). In the domain of computing, it has been stressed that computing could be made more powerful if the implementation technology is changed (Si, GaAs, etc.…), or if the computing paradigm is changed (Control Flow, Data Flow, etc.…).
PB  - Springer
T2  - Journal of Big Data
T1  - Research in computing‑intensive simulations for nature‑oriented civil‑engineering and related scientific fields, using machine learning and big data: an overview of open problems
VL  - 10
DO  - 10.1186/s40537-023-00731-6
ER  - 

@article{
author = "Babović, Zoran and Bajat, Branislav and Đokić, Vladan and Đorđević, Filip and Drašković, Dražen and Filipović, Nenad and Furht, Borko and Gačić, Nikola and Ikodinović, Igor and Ilić, Marija and Irfanoglu, Ayhan and Jelenković, Branislav and Kartelj, Aleksandar and Klimeck, Gerhard and Korolija, Nenad and Kotlar, Miloš and Kovačević, Miloš and Kuzmanović, Vladan and Marinković, Marko and Marković, Slobodan and Mendelson, Avi and Milutinović, Veljko and Nešković, Aleksandar and Nešković, Nataša and Mitić, Nenad and Nikolić, Boško and Novoselov, Konstantin and Prakash, Arun and Ratković, Ivan and Stojadinović, Zoran and Ustyuzhanin, Andrey and Zak, Stan",
year = "2023",
abstract = "This article presents a taxonomy and represents a repository of open problems in computing for numerically and logically intensive problems in a number of disciplines that have to synergize for the best performance of simulation-based feasibility studies on nature-oriented engineering in general and civil engineering in particular. Topics include but are not limited to: Nature-based construction, genomics supporting nature-based construction, earthquake engineering, and other types of geophysical disaster prevention activities, as well as the studies of processes and materials of interest for the above. In all these fields, problems are discussed that generate huge amounts of Big Data and are characterized with mathematically highly complex Iterative Algorithms. In the domain of applications, it has been stressed that problems could be made less computationally demanding if the number of computing iterations is made smaller (with the help of Artificial Intelligence or Conditional Algorithms), or if each computing iteration is made shorter in time (with the help of Data Filtration and Data Quantization). In the domain of computing, it has been stressed that computing could be made more powerful if the implementation technology is changed (Si, GaAs, etc.…), or if the computing paradigm is changed (Control Flow, Data Flow, etc.…).",
publisher = "Springer",
journal = "Journal of Big Data",
title = "Research in computing‑intensive simulations for nature‑oriented civil‑engineering and related scientific fields, using machine learning and big data: an overview of open problems",
volume = "10",
doi = "10.1186/s40537-023-00731-6"
}

Babović, Z., Bajat, B., Đokić, V., Đorđević, F., Drašković, D., Filipović, N., Furht, B., Gačić, N., Ikodinović, I., Ilić, M., Irfanoglu, A., Jelenković, B., Kartelj, A., Klimeck, G., Korolija, N., Kotlar, M., Kovačević, M., Kuzmanović, V., Marinković, M., Marković, S., Mendelson, A., Milutinović, V., Nešković, A., Nešković, N., Mitić, N., Nikolić, B., Novoselov, K., Prakash, A., Ratković, I., Stojadinović, Z., Ustyuzhanin, A.,& Zak, S.. (2023). Research in computing‑intensive simulations for nature‑oriented civil‑engineering and related scientific fields, using machine learning and big data: an overview of open problems. in Journal of Big Data
Springer., 10.
https://doi.org/10.1186/s40537-023-00731-6

Babović Z, Bajat B, Đokić V, Đorđević F, Drašković D, Filipović N, Furht B, Gačić N, Ikodinović I, Ilić M, Irfanoglu A, Jelenković B, Kartelj A, Klimeck G, Korolija N, Kotlar M, Kovačević M, Kuzmanović V, Marinković M, Marković S, Mendelson A, Milutinović V, Nešković A, Nešković N, Mitić N, Nikolić B, Novoselov K, Prakash A, Ratković I, Stojadinović Z, Ustyuzhanin A, Zak S. Research in computing‑intensive simulations for nature‑oriented civil‑engineering and related scientific fields, using machine learning and big data: an overview of open problems. in Journal of Big Data. 2023;10.
doi:10.1186/s40537-023-00731-6 .

Babović, Zoran, Bajat, Branislav, Đokić, Vladan, Đorđević, Filip, Drašković, Dražen, Filipović, Nenad, Furht, Borko, Gačić, Nikola, Ikodinović, Igor, Ilić, Marija, Irfanoglu, Ayhan, Jelenković, Branislav, Kartelj, Aleksandar, Klimeck, Gerhard, Korolija, Nenad, Kotlar, Miloš, Kovačević, Miloš, Kuzmanović, Vladan, Marinković, Marko, Marković, Slobodan, Mendelson, Avi, Milutinović, Veljko, Nešković, Aleksandar, Nešković, Nataša, Mitić, Nenad, Nikolić, Boško, Novoselov, Konstantin, Prakash, Arun, Ratković, Ivan, Stojadinović, Zoran, Ustyuzhanin, Andrey, Zak, Stan, "Research in computing‑intensive simulations for nature‑oriented civil‑engineering and related scientific fields, using machine learning and big data: an overview of open problems" in Journal of Big Data, 10 (2023),
https://doi.org/10.1186/s40537-023-00731-6 . .

TY  - JOUR
AU  - Babović, Zoran
AU  - Bajat, Branislav
AU  - Barac, Dusan
AU  - Bengin, Vesna
AU  - Đokić, Vladan
AU  - Đorđević, Filip
AU  - Drašković, Dražen
AU  - Filipović, Nenad
AU  - French, Stephan
AU  - Furht, Borko
AU  - Ilić, Marija
AU  - Irfanoglu, Ayhan
AU  - Kartelj, Aleksandar
AU  - Kilibarda, Milan
AU  - Klimeck, Gerhard
AU  - Korolija, Nenad
AU  - Kotlar, Miloš
AU  - Kovačević, Miloš
AU  - Kuzmanović, Vladan
AU  - Lehn, Jean-Marie
AU  - Madić, Dejan
AU  - Marinković, Marko
AU  - Mateljević, Miodrag
AU  - Mendelson, Avi
AU  - Mesinger, Fedor
AU  - Milovanović, Gradimir
AU  - Milutinović, Veljko
AU  - Mitić, Nenad
AU  - Nešković, Aleksandar
AU  - Nešković, Nataša
AU  - Nikolić, Boško
AU  - Novoselov, Konstantin
AU  - Prakash, Arun
AU  - Protić, Jelica
AU  - Ratković, Ivan
AU  - Rios, Diego
AU  - Shechtman, Dan
AU  - Stojadinović, Zoran
AU  - Ustyuzhanin, Andrey
AU  - Zak, Stan
PY  - 2023
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/3114
AB  - This article describes a teaching strategy that synergizes computing and management, aimed at the running of complex projects in industry and academia, in the areas of civil engineering, physics, geosciences, and a number of other related fields. The course derived from this strategy includes four parts: (a) Computing with a selected set of modern paradigms—the stress is on Control Flow and Data Flow computing paradigms, but paradigms conditionally referred to as Energy Flow and Diffusion Flow are also covered; (b) Project management that is holistic—the stress is on the wide plethora of issues spanning from the preparation of project proposals, all the way to incorporation activities to follow after the completion of a successful project; (c) Examples from past research and development experiences—the stress is on experiences of leading experts from academia and industry; (d) Student projects that stimulate creativity—the stress is on methods that educators could use to induce and accelerate the creativity of students in general. Finally, the article ends with selected pearls of wisdom that could be treated as suggestions for further elaboration.
PB  - Springer
T2  - Journal of Big Data
T1  - Teaching computing for complex problems in civil engineering and geosciences using big data and machine learning: synergizing four different computing paradigms and four different management domains
VL  - 10
DO  - 10.1186/s40537-023-00730-7
ER  - 

@article{
author = "Babović, Zoran and Bajat, Branislav and Barac, Dusan and Bengin, Vesna and Đokić, Vladan and Đorđević, Filip and Drašković, Dražen and Filipović, Nenad and French, Stephan and Furht, Borko and Ilić, Marija and Irfanoglu, Ayhan and Kartelj, Aleksandar and Kilibarda, Milan and Klimeck, Gerhard and Korolija, Nenad and Kotlar, Miloš and Kovačević, Miloš and Kuzmanović, Vladan and Lehn, Jean-Marie and Madić, Dejan and Marinković, Marko and Mateljević, Miodrag and Mendelson, Avi and Mesinger, Fedor and Milovanović, Gradimir and Milutinović, Veljko and Mitić, Nenad and Nešković, Aleksandar and Nešković, Nataša and Nikolić, Boško and Novoselov, Konstantin and Prakash, Arun and Protić, Jelica and Ratković, Ivan and Rios, Diego and Shechtman, Dan and Stojadinović, Zoran and Ustyuzhanin, Andrey and Zak, Stan",
year = "2023",
abstract = "This article describes a teaching strategy that synergizes computing and management, aimed at the running of complex projects in industry and academia, in the areas of civil engineering, physics, geosciences, and a number of other related fields. The course derived from this strategy includes four parts: (a) Computing with a selected set of modern paradigms—the stress is on Control Flow and Data Flow computing paradigms, but paradigms conditionally referred to as Energy Flow and Diffusion Flow are also covered; (b) Project management that is holistic—the stress is on the wide plethora of issues spanning from the preparation of project proposals, all the way to incorporation activities to follow after the completion of a successful project; (c) Examples from past research and development experiences—the stress is on experiences of leading experts from academia and industry; (d) Student projects that stimulate creativity—the stress is on methods that educators could use to induce and accelerate the creativity of students in general. Finally, the article ends with selected pearls of wisdom that could be treated as suggestions for further elaboration.",
publisher = "Springer",
journal = "Journal of Big Data",
title = "Teaching computing for complex problems in civil engineering and geosciences using big data and machine learning: synergizing four different computing paradigms and four different management domains",
volume = "10",
doi = "10.1186/s40537-023-00730-7"
}

Babović, Z., Bajat, B., Barac, D., Bengin, V., Đokić, V., Đorđević, F., Drašković, D., Filipović, N., French, S., Furht, B., Ilić, M., Irfanoglu, A., Kartelj, A., Kilibarda, M., Klimeck, G., Korolija, N., Kotlar, M., Kovačević, M., Kuzmanović, V., Lehn, J., Madić, D., Marinković, M., Mateljević, M., Mendelson, A., Mesinger, F., Milovanović, G., Milutinović, V., Mitić, N., Nešković, A., Nešković, N., Nikolić, B., Novoselov, K., Prakash, A., Protić, J., Ratković, I., Rios, D., Shechtman, D., Stojadinović, Z., Ustyuzhanin, A.,& Zak, S.. (2023). Teaching computing for complex problems in civil engineering and geosciences using big data and machine learning: synergizing four different computing paradigms and four different management domains. in Journal of Big Data
Springer., 10.
https://doi.org/10.1186/s40537-023-00730-7

Babović Z, Bajat B, Barac D, Bengin V, Đokić V, Đorđević F, Drašković D, Filipović N, French S, Furht B, Ilić M, Irfanoglu A, Kartelj A, Kilibarda M, Klimeck G, Korolija N, Kotlar M, Kovačević M, Kuzmanović V, Lehn J, Madić D, Marinković M, Mateljević M, Mendelson A, Mesinger F, Milovanović G, Milutinović V, Mitić N, Nešković A, Nešković N, Nikolić B, Novoselov K, Prakash A, Protić J, Ratković I, Rios D, Shechtman D, Stojadinović Z, Ustyuzhanin A, Zak S. Teaching computing for complex problems in civil engineering and geosciences using big data and machine learning: synergizing four different computing paradigms and four different management domains. in Journal of Big Data. 2023;10.
doi:10.1186/s40537-023-00730-7 .

Babović, Zoran, Bajat, Branislav, Barac, Dusan, Bengin, Vesna, Đokić, Vladan, Đorđević, Filip, Drašković, Dražen, Filipović, Nenad, French, Stephan, Furht, Borko, Ilić, Marija, Irfanoglu, Ayhan, Kartelj, Aleksandar, Kilibarda, Milan, Klimeck, Gerhard, Korolija, Nenad, Kotlar, Miloš, Kovačević, Miloš, Kuzmanović, Vladan, Lehn, Jean-Marie, Madić, Dejan, Marinković, Marko, Mateljević, Miodrag, Mendelson, Avi, Mesinger, Fedor, Milovanović, Gradimir, Milutinović, Veljko, Mitić, Nenad, Nešković, Aleksandar, Nešković, Nataša, Nikolić, Boško, Novoselov, Konstantin, Prakash, Arun, Protić, Jelica, Ratković, Ivan, Rios, Diego, Shechtman, Dan, Stojadinović, Zoran, Ustyuzhanin, Andrey, Zak, Stan, "Teaching computing for complex problems in civil engineering and geosciences using big data and machine learning: synergizing four different computing paradigms and four different management domains" in Journal of Big Data, 10 (2023),
https://doi.org/10.1186/s40537-023-00730-7 . .

TY  - CONF
AU  - Đorđević, Filip
AU  - Marinković, Marko
PY  - 2023
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/3231
AB  - During the last several decades, the finite element method (FEM) is the most commonly used numerical method for performing seismic structural analysis. It requires careful structural modeling, but also the adjustment of small computation steps, especially for highly complex nonlinearities, which leads to significant time consumption, to ensure the stability and accuracy of the results. The development of new techniques based on machine learning (ML) models attracts considerable attention, due to the possibility to overcome the limitations of traditional techniques. This study presents an implementation of the long short-term memory (LSTM) deep-learning recurrent neural network (RNN) for the estimation of nonlinear seismic structural response. It is established in a data-driven manner. The LSTM model has shown considerable success in capturing structural response during nonlinear dynamic time-history (NDTH) analysis. Even in the case of an insufficient number of data, it shows better performance and greater adaptation to experimental results than the robust FEM model. In order to secure the consistency of the dataset for different ground motion records and increments, resampling and filtering of data is recommended. Such an innovative approach can enable the prevention of catastrophic consequences from devastating earthquakes.  That can be achieved by fast and accurate pre-earthquake response prediction, damage state forecasting, and accelerated development of fragility curves based on previously conducted incremental dynamic analyses (IDA) or experimental tests. The predictive capabilities of the developed model were demonstrated through a comparative analysis of the behavior of two adjacent interacting unreinforced masonry structures (URM), tested on a shaking table. Even with the relative lack of experimental data, LSTM showed superiority over SAP2000 software. In all sequences of the time history records, the LSTM model gave closer results to the experimental ones than the SAP2000. The lack of a massive amount of data was observed as the main reason for the deviation of the results obtained by the LSTM model in certain time intervals, so the expansion of datasets is proposed for upcoming simulations. In future research, to model the dynamic response of different material and structural types, the formation of such models in a physics-driven fashion is recommended.
C3  - International Conference Natural Resources and Environmental Risks: Towards a Sustainable Future, Building of Branch of the Serbian Academy of Sciences and Arts in Novi Sad, Serbia
T1  - A Comparative Study of ML and FEM Models for the Prediction of Seismic Structural Behavior
UR  - https://hdl.handle.net/21.15107/rcub_grafar_3231
ER  - 

@conference{
author = "Đorđević, Filip and Marinković, Marko",
year = "2023",
abstract = "During the last several decades, the finite element method (FEM) is the most commonly used numerical method for performing seismic structural analysis. It requires careful structural modeling, but also the adjustment of small computation steps, especially for highly complex nonlinearities, which leads to significant time consumption, to ensure the stability and accuracy of the results. The development of new techniques based on machine learning (ML) models attracts considerable attention, due to the possibility to overcome the limitations of traditional techniques. This study presents an implementation of the long short-term memory (LSTM) deep-learning recurrent neural network (RNN) for the estimation of nonlinear seismic structural response. It is established in a data-driven manner. The LSTM model has shown considerable success in capturing structural response during nonlinear dynamic time-history (NDTH) analysis. Even in the case of an insufficient number of data, it shows better performance and greater adaptation to experimental results than the robust FEM model. In order to secure the consistency of the dataset for different ground motion records and increments, resampling and filtering of data is recommended. Such an innovative approach can enable the prevention of catastrophic consequences from devastating earthquakes.  That can be achieved by fast and accurate pre-earthquake response prediction, damage state forecasting, and accelerated development of fragility curves based on previously conducted incremental dynamic analyses (IDA) or experimental tests. The predictive capabilities of the developed model were demonstrated through a comparative analysis of the behavior of two adjacent interacting unreinforced masonry structures (URM), tested on a shaking table. Even with the relative lack of experimental data, LSTM showed superiority over SAP2000 software. In all sequences of the time history records, the LSTM model gave closer results to the experimental ones than the SAP2000. The lack of a massive amount of data was observed as the main reason for the deviation of the results obtained by the LSTM model in certain time intervals, so the expansion of datasets is proposed for upcoming simulations. In future research, to model the dynamic response of different material and structural types, the formation of such models in a physics-driven fashion is recommended.",
journal = "International Conference Natural Resources and Environmental Risks: Towards a Sustainable Future, Building of Branch of the Serbian Academy of Sciences and Arts in Novi Sad, Serbia",
title = "A Comparative Study of ML and FEM Models for the Prediction of Seismic Structural Behavior",
url = "https://hdl.handle.net/21.15107/rcub_grafar_3231"
}

Đorđević, F.,& Marinković, M.. (2023). A Comparative Study of ML and FEM Models for the Prediction of Seismic Structural Behavior. in International Conference Natural Resources and Environmental Risks: Towards a Sustainable Future, Building of Branch of the Serbian Academy of Sciences and Arts in Novi Sad, Serbia.
https://hdl.handle.net/21.15107/rcub_grafar_3231

Đorđević F, Marinković M. A Comparative Study of ML and FEM Models for the Prediction of Seismic Structural Behavior. in International Conference Natural Resources and Environmental Risks: Towards a Sustainable Future, Building of Branch of the Serbian Academy of Sciences and Arts in Novi Sad, Serbia. 2023;.
https://hdl.handle.net/21.15107/rcub_grafar_3231 .

Đorđević, Filip, Marinković, Marko, "A Comparative Study of ML and FEM Models for the Prediction of Seismic Structural Behavior" in International Conference Natural Resources and Environmental Risks: Towards a Sustainable Future, Building of Branch of the Serbian Academy of Sciences and Arts in Novi Sad, Serbia (2023),
https://hdl.handle.net/21.15107/rcub_grafar_3231 .

TY  - JOUR
AU  - Tomić, Igor
AU  - Penna, Andrea
AU  - DeJong, Matthew
AU  - Butenweg, Christoph
AU  - Correia, Antonio
AU  - Candeias, Paulo Xavier
AU  - Senaldi, Ilaria
AU  - Guerrini, Gabriele
AU  - Malomo, Daniele
AU  - Wilding, Bastian
AU  - Pettinga, Didier
AU  - Spanenburg, Mark
AU  - Galanakis, N.
AU  - Oliver, S.
AU  - Parisse, Francesco
AU  - Marques, Rui
AU  - Cattari, Serena
AU  - Lourenco, Paulo
AU  - Galvez, Francisco
AU  - Dizhur, Dmytro
AU  - Ingham, Jason
AU  - Ramaglia, Giancarlo
AU  - Lignola, Gian Piero
AU  - Prota, Andrea
AU  - AlShawa, Omar
AU  - Liberatore, Domenico
AU  - Sorrentino, Luigi
AU  - Gagliardo, Raffaele
AU  - Godio, Michele
AU  - Portioli, Francesco
AU  - Landolfo, Raffaele
AU  - Solarino, Fabio
AU  - Bianchini, Nicoletta
AU  - Ciocci, Maria Pia
AU  - Romanazzi, Antonio
AU  - Asikoglu, Abide
AU  - D'Anna, Jennifer
AU  - Ramirez, Rafael
AU  - Romis, Federico
AU  - Marinković, Marko
AU  - Đorđević, Filip
AU  - Beyer, Katrin
PY  - 2023
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/3060
AB  - City centres of Europe are often composed of unreinforced masonry structural aggregates, whose seismic response is challenging to predict. To advance the state of the art on the seismic response of these aggregates, the Adjacent Interacting Masonry Structures (AIMS) subproject from Horizon 2020 project Seismology and Earthquake Engineering Research Infrastructure Alliance for Europe (SERA) provides shake-table test data of a two-unit, double-leaf stone masonry aggregate subjected to two horizontal components of dynamic excitation. A blind prediction was organized with participants from academia and industry to test modelling approaches and assumptions and to learn about the extent of uncertainty in modelling for such masonry aggregates. The participants were provided with the full set of material and geometrical data, construction details and original seismic input and asked to predict prior to the test the expected seismic response in terms of damage mechanisms, base-shear forces, and roof displacements. The modelling approaches used differ significantly in the level of detail and the modelling assumptions. This paper provides an overview of the adopted modelling approaches and their subsequent predictions. It further discusses the range of assumptions made when modelling masonry walls, floors and connections, and aims at discovering how the common solutions regarding modelling masonry in general, and masonry aggregates in particular, affect the results. The results are evaluated both in terms of damage mechanisms, base shear forces, displacements and interface openings in both directions, and then compared with the experimental results. The modelling approaches featuring Discrete Element Method (DEM) led to the best predictions in terms of displacements, while a submission using rigid block limit analysis led to the best prediction in terms of damage mechanisms. Large coefficients of variation of predicted displacements and general underestimation of displacements in comparison with experimental results, except for DEM models, highlight the need for further consensus building on suitable modelling assumptions for such masonry aggregates.
T2  - Bulletin of Earthquake Engineering
T1  - Shake‑table testing of a stone masonry building aggregate: overview of blind prediction study
DO  - 10.1007/s10518-022-01582-x
ER  - 

@article{
author = "Tomić, Igor and Penna, Andrea and DeJong, Matthew and Butenweg, Christoph and Correia, Antonio and Candeias, Paulo Xavier and Senaldi, Ilaria and Guerrini, Gabriele and Malomo, Daniele and Wilding, Bastian and Pettinga, Didier and Spanenburg, Mark and Galanakis, N. and Oliver, S. and Parisse, Francesco and Marques, Rui and Cattari, Serena and Lourenco, Paulo and Galvez, Francisco and Dizhur, Dmytro and Ingham, Jason and Ramaglia, Giancarlo and Lignola, Gian Piero and Prota, Andrea and AlShawa, Omar and Liberatore, Domenico and Sorrentino, Luigi and Gagliardo, Raffaele and Godio, Michele and Portioli, Francesco and Landolfo, Raffaele and Solarino, Fabio and Bianchini, Nicoletta and Ciocci, Maria Pia and Romanazzi, Antonio and Asikoglu, Abide and D'Anna, Jennifer and Ramirez, Rafael and Romis, Federico and Marinković, Marko and Đorđević, Filip and Beyer, Katrin",
year = "2023",
abstract = "City centres of Europe are often composed of unreinforced masonry structural aggregates, whose seismic response is challenging to predict. To advance the state of the art on the seismic response of these aggregates, the Adjacent Interacting Masonry Structures (AIMS) subproject from Horizon 2020 project Seismology and Earthquake Engineering Research Infrastructure Alliance for Europe (SERA) provides shake-table test data of a two-unit, double-leaf stone masonry aggregate subjected to two horizontal components of dynamic excitation. A blind prediction was organized with participants from academia and industry to test modelling approaches and assumptions and to learn about the extent of uncertainty in modelling for such masonry aggregates. The participants were provided with the full set of material and geometrical data, construction details and original seismic input and asked to predict prior to the test the expected seismic response in terms of damage mechanisms, base-shear forces, and roof displacements. The modelling approaches used differ significantly in the level of detail and the modelling assumptions. This paper provides an overview of the adopted modelling approaches and their subsequent predictions. It further discusses the range of assumptions made when modelling masonry walls, floors and connections, and aims at discovering how the common solutions regarding modelling masonry in general, and masonry aggregates in particular, affect the results. The results are evaluated both in terms of damage mechanisms, base shear forces, displacements and interface openings in both directions, and then compared with the experimental results. The modelling approaches featuring Discrete Element Method (DEM) led to the best predictions in terms of displacements, while a submission using rigid block limit analysis led to the best prediction in terms of damage mechanisms. Large coefficients of variation of predicted displacements and general underestimation of displacements in comparison with experimental results, except for DEM models, highlight the need for further consensus building on suitable modelling assumptions for such masonry aggregates.",
journal = "Bulletin of Earthquake Engineering",
title = "Shake‑table testing of a stone masonry building aggregate: overview of blind prediction study",
doi = "10.1007/s10518-022-01582-x"
}

Tomić, I., Penna, A., DeJong, M., Butenweg, C., Correia, A., Candeias, P. X., Senaldi, I., Guerrini, G., Malomo, D., Wilding, B., Pettinga, D., Spanenburg, M., Galanakis, N., Oliver, S., Parisse, F., Marques, R., Cattari, S., Lourenco, P., Galvez, F., Dizhur, D., Ingham, J., Ramaglia, G., Lignola, G. P., Prota, A., AlShawa, O., Liberatore, D., Sorrentino, L., Gagliardo, R., Godio, M., Portioli, F., Landolfo, R., Solarino, F., Bianchini, N., Ciocci, M. P., Romanazzi, A., Asikoglu, A., D'Anna, J., Ramirez, R., Romis, F., Marinković, M., Đorđević, F.,& Beyer, K.. (2023). Shake‑table testing of a stone masonry building aggregate: overview of blind prediction study. in Bulletin of Earthquake Engineering.
https://doi.org/10.1007/s10518-022-01582-x

Tomić I, Penna A, DeJong M, Butenweg C, Correia A, Candeias PX, Senaldi I, Guerrini G, Malomo D, Wilding B, Pettinga D, Spanenburg M, Galanakis N, Oliver S, Parisse F, Marques R, Cattari S, Lourenco P, Galvez F, Dizhur D, Ingham J, Ramaglia G, Lignola GP, Prota A, AlShawa O, Liberatore D, Sorrentino L, Gagliardo R, Godio M, Portioli F, Landolfo R, Solarino F, Bianchini N, Ciocci MP, Romanazzi A, Asikoglu A, D'Anna J, Ramirez R, Romis F, Marinković M, Đorđević F, Beyer K. Shake‑table testing of a stone masonry building aggregate: overview of blind prediction study. in Bulletin of Earthquake Engineering. 2023;.
doi:10.1007/s10518-022-01582-x .

Tomić, Igor, Penna, Andrea, DeJong, Matthew, Butenweg, Christoph, Correia, Antonio, Candeias, Paulo Xavier, Senaldi, Ilaria, Guerrini, Gabriele, Malomo, Daniele, Wilding, Bastian, Pettinga, Didier, Spanenburg, Mark, Galanakis, N., Oliver, S., Parisse, Francesco, Marques, Rui, Cattari, Serena, Lourenco, Paulo, Galvez, Francisco, Dizhur, Dmytro, Ingham, Jason, Ramaglia, Giancarlo, Lignola, Gian Piero, Prota, Andrea, AlShawa, Omar, Liberatore, Domenico, Sorrentino, Luigi, Gagliardo, Raffaele, Godio, Michele, Portioli, Francesco, Landolfo, Raffaele, Solarino, Fabio, Bianchini, Nicoletta, Ciocci, Maria Pia, Romanazzi, Antonio, Asikoglu, Abide, D'Anna, Jennifer, Ramirez, Rafael, Romis, Federico, Marinković, Marko, Đorđević, Filip, Beyer, Katrin, "Shake‑table testing of a stone masonry building aggregate: overview of blind prediction study" in Bulletin of Earthquake Engineering (2023),
https://doi.org/10.1007/s10518-022-01582-x . .

TY  - CONF
AU  - Đorđević, Filip
AU  - Marinković, Marko
PY  - 2023
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/3108
AB  - The fundamental period (TFP) of vibration is one of the most important parameters in structural design since it is used to assess the dynamic response of the structures. It is the time taken by a structure or system to vibrate back and forth in its most natural way, without any external forces applied. Simultaneously, TFP depends on the mass distribution and stiffness of the structure, which is largely influenced by infill walls in RC frame structures, and which is why their careful design is necessary. This study aims to develop a fast, accurate, and efficient machine learning (ML) method for the prediction of the fundamental period of masonry-infilled reinforced concrete (RC) frame structures. Hybridization of the stochastic gradient descent (SGD) based artificial neural network (ANN), and meta-heuristic grey wolf optimization (GWO) algorithm is proposed as an effortless computational method. This approach provided even more reliable solutions than robust second-order procedure based on single ML models. A total of 2178 samples of infilled RC frames were collected from available literature, where the number of storeys (NoSt), number of spans (NoSp), length of spans (LoSp), opening percentage (OP), and masonry wall stiffness (MWS) were considered as input parameters for predicting the output TFP results. The accuracy and exploration efficiency of the proposed ANN-GWO paradigm have demonstrated superiority over existing seismic design codes and other conventional ML methods.
C3  - Second Serbian International Conference on Applied Artificial Intelligence, Kragujevac, Serbia
T1  - Implementation of Hybrid ANN-GWO Algorithm for Estimation of the Fundamental Period of RC-Frame Structures
UR  - https://hdl.handle.net/21.15107/rcub_grafar_3108
ER  - 

@conference{
author = "Đorđević, Filip and Marinković, Marko",
year = "2023",
abstract = "The fundamental period (TFP) of vibration is one of the most important parameters in structural design since it is used to assess the dynamic response of the structures. It is the time taken by a structure or system to vibrate back and forth in its most natural way, without any external forces applied. Simultaneously, TFP depends on the mass distribution and stiffness of the structure, which is largely influenced by infill walls in RC frame structures, and which is why their careful design is necessary. This study aims to develop a fast, accurate, and efficient machine learning (ML) method for the prediction of the fundamental period of masonry-infilled reinforced concrete (RC) frame structures. Hybridization of the stochastic gradient descent (SGD) based artificial neural network (ANN), and meta-heuristic grey wolf optimization (GWO) algorithm is proposed as an effortless computational method. This approach provided even more reliable solutions than robust second-order procedure based on single ML models. A total of 2178 samples of infilled RC frames were collected from available literature, where the number of storeys (NoSt), number of spans (NoSp), length of spans (LoSp), opening percentage (OP), and masonry wall stiffness (MWS) were considered as input parameters for predicting the output TFP results. The accuracy and exploration efficiency of the proposed ANN-GWO paradigm have demonstrated superiority over existing seismic design codes and other conventional ML methods.",
journal = "Second Serbian International Conference on Applied Artificial Intelligence, Kragujevac, Serbia",
title = "Implementation of Hybrid ANN-GWO Algorithm for Estimation of the Fundamental Period of RC-Frame Structures",
url = "https://hdl.handle.net/21.15107/rcub_grafar_3108"
}

Đorđević, F.,& Marinković, M.. (2023). Implementation of Hybrid ANN-GWO Algorithm for Estimation of the Fundamental Period of RC-Frame Structures. in Second Serbian International Conference on Applied Artificial Intelligence, Kragujevac, Serbia.
https://hdl.handle.net/21.15107/rcub_grafar_3108

Đorđević F, Marinković M. Implementation of Hybrid ANN-GWO Algorithm for Estimation of the Fundamental Period of RC-Frame Structures. in Second Serbian International Conference on Applied Artificial Intelligence, Kragujevac, Serbia. 2023;.
https://hdl.handle.net/21.15107/rcub_grafar_3108 .

Đorđević, Filip, Marinković, Marko, "Implementation of Hybrid ANN-GWO Algorithm for Estimation of the Fundamental Period of RC-Frame Structures" in Second Serbian International Conference on Applied Artificial Intelligence, Kragujevac, Serbia (2023),
https://hdl.handle.net/21.15107/rcub_grafar_3108 .

TY  - CONF
AU  - Đorđević, Filip
AU  - Kostić, Svetlana M.
PY  - 2022
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/2764
AB  - This paper proposes the use of artificial neural network (ANN) algorithms to estimate the ultimate compressive strength of slender circular concrete-filled steel tubular (CCFST) columns. A dataset of 1051 samples was applied to generate an appropriate ANN prognostic model. Empirical equations were also developed from the best neural network, and their results were compared with those obtained by Eurocode 4 (EC4) design code. Analyses show that the proposed ANN model has a better agreement with experimental results than those created with provisions of the EC4 design code.
C3  - 16th Congress of Association of Structural Engineers of Serbia
T1  - Estimation of ultimate strength of slender ccfst columns using artificial neural networks
UR  - https://hdl.handle.net/21.15107/rcub_grafar_2764
ER  - 

@conference{
author = "Đorđević, Filip and Kostić, Svetlana M.",
year = "2022",
abstract = "This paper proposes the use of artificial neural network (ANN) algorithms to estimate the ultimate compressive strength of slender circular concrete-filled steel tubular (CCFST) columns. A dataset of 1051 samples was applied to generate an appropriate ANN prognostic model. Empirical equations were also developed from the best neural network, and their results were compared with those obtained by Eurocode 4 (EC4) design code. Analyses show that the proposed ANN model has a better agreement with experimental results than those created with provisions of the EC4 design code.",
journal = "16th Congress of Association of Structural Engineers of Serbia",
title = "Estimation of ultimate strength of slender ccfst columns using artificial neural networks",
url = "https://hdl.handle.net/21.15107/rcub_grafar_2764"
}

Đorđević, F.,& Kostić, S. M.. (2022). Estimation of ultimate strength of slender ccfst columns using artificial neural networks. in 16th Congress of Association of Structural Engineers of Serbia.
https://hdl.handle.net/21.15107/rcub_grafar_2764

Đorđević F, Kostić SM. Estimation of ultimate strength of slender ccfst columns using artificial neural networks. in 16th Congress of Association of Structural Engineers of Serbia. 2022;.
https://hdl.handle.net/21.15107/rcub_grafar_2764 .

Đorđević, Filip, Kostić, Svetlana M., "Estimation of ultimate strength of slender ccfst columns using artificial neural networks" in 16th Congress of Association of Structural Engineers of Serbia (2022),
https://hdl.handle.net/21.15107/rcub_grafar_2764 .

TY  - CONF
AU  - Đorđević, Filip
AU  - Kostić, Svetlana M.
PY  - 2022
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/2683
AB  - Due to numerous advantages, concrete-filled steel tubular (CFST) columns have an increasingly important role in the civil engineering industry. Because of the expensive experimental testing of these members, it is beneficial to provide prognostic models. In this study, an artificial neural network (ANN) model for predicting the axial compressive strength of square CFST columns has been developed. A dataset of 1022 samples (685 stub columns and 337 slender columns) was collected from available literature in order to compare the accuracy of the fast predictive Levenberg-Marquardt algorithm (LM) and Eurocode 4 (EC4) design code. Analyses showed that the ANN model has better accuracy than EC4. Over a whole domain, the ANN model has higher coefficient of determination (R2), and lower root mean squared error (RMSE). The same conclusion is valid when two separate datasets are considered: one for stub columns and the other for slender columns. The benefit of the ANN model is its applicability in a broader range of column parameters. At the same time, EC4 puts several limitations on its use and gives satisfactory results only in limited circumstances. Empirical equations have also been proposed from the best ANN model, which is useful for engineering practice.
C3  - First Serbian International Conference on Applied Artificial Intelligence, Kragujevac, Serbia
T1  - Axial Strength Prediction of Square CFST Columns Based on The ANN Model
UR  - https://hdl.handle.net/21.15107/rcub_grafar_2683
ER  - 

@conference{
author = "Đorđević, Filip and Kostić, Svetlana M.",
year = "2022",
abstract = "Due to numerous advantages, concrete-filled steel tubular (CFST) columns have an increasingly important role in the civil engineering industry. Because of the expensive experimental testing of these members, it is beneficial to provide prognostic models. In this study, an artificial neural network (ANN) model for predicting the axial compressive strength of square CFST columns has been developed. A dataset of 1022 samples (685 stub columns and 337 slender columns) was collected from available literature in order to compare the accuracy of the fast predictive Levenberg-Marquardt algorithm (LM) and Eurocode 4 (EC4) design code. Analyses showed that the ANN model has better accuracy than EC4. Over a whole domain, the ANN model has higher coefficient of determination (R2), and lower root mean squared error (RMSE). The same conclusion is valid when two separate datasets are considered: one for stub columns and the other for slender columns. The benefit of the ANN model is its applicability in a broader range of column parameters. At the same time, EC4 puts several limitations on its use and gives satisfactory results only in limited circumstances. Empirical equations have also been proposed from the best ANN model, which is useful for engineering practice.",
journal = "First Serbian International Conference on Applied Artificial Intelligence, Kragujevac, Serbia",
title = "Axial Strength Prediction of Square CFST Columns Based on The ANN Model",
url = "https://hdl.handle.net/21.15107/rcub_grafar_2683"
}

Đorđević, F.,& Kostić, S. M.. (2022). Axial Strength Prediction of Square CFST Columns Based on The ANN Model. in First Serbian International Conference on Applied Artificial Intelligence, Kragujevac, Serbia.
https://hdl.handle.net/21.15107/rcub_grafar_2683

Đorđević F, Kostić SM. Axial Strength Prediction of Square CFST Columns Based on The ANN Model. in First Serbian International Conference on Applied Artificial Intelligence, Kragujevac, Serbia. 2022;.
https://hdl.handle.net/21.15107/rcub_grafar_2683 .

Đorđević, Filip, Kostić, Svetlana M., "Axial Strength Prediction of Square CFST Columns Based on The ANN Model" in First Serbian International Conference on Applied Artificial Intelligence, Kragujevac, Serbia (2022),
https://hdl.handle.net/21.15107/rcub_grafar_2683 .

TY  - CONF
AU  - Đorđević, Filip
AU  - Kostić, Svetlana M.
PY  - 2022
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/2682
AB  - The composite concrete-filled steel tube columns are structural members with numerous advantages over the traditional reinforced concrete or the pure steel members. The behavior of these columns is highly nonlinear. This paper analyses the determination of the ultimate compressive capacity of circular concrete-filled tubes according to the Eurocode 4 design code and its accuracy in comparison with the experimentally available results from the literature. In order to improve the predictions of the column’s ultimate compressive capacity, two efficient machine learning algorithms are employed separately for the stub and the slender columns. The analyzed algorithms are the Decision tree and the Random forest. The research used an experimental dataset of 508 samples: 236 tests on the stub columns and 272 tests on the slender columns. It adapted the dataset to the provision of the Eurocode 4 design code. The predictions of the column’s ultimate axial capacity obtained by two ML algorithms and the Eurocode 4 are compared with the experimental test results on the validation dataset. The calculated R2 error measure has shown that the predictions obtained by the tree-based algorithms are superior compared to the design formulas offered by the Eurocode 4. The decision tree algorithm achieved the best accuracy measured with the highest value of R2 error measure between the two algorithms. The two analyzed algorithms are used to perform the sensitivity analysis on the considered problem. The sensitivity analysis used the feature importance, a technique that assigns a score to each of the input features based on their influence on the prediction of the output variable. As expected, the sensitivity analysis identified the outer diameter of the columns’ cross-section as the parameter with the most significant impact on the results.
C3  - 8th International Conference Science and Practice, Kolasin, Montenegro
T1  - Prediction of Ultimate Compressive Strength of CCFT Columns Using Machine Learning Algorithms
UR  - https://hdl.handle.net/21.15107/rcub_grafar_2682
ER  - 

@conference{
author = "Đorđević, Filip and Kostić, Svetlana M.",
year = "2022",
abstract = "The composite concrete-filled steel tube columns are structural members with numerous advantages over the traditional reinforced concrete or the pure steel members. The behavior of these columns is highly nonlinear. This paper analyses the determination of the ultimate compressive capacity of circular concrete-filled tubes according to the Eurocode 4 design code and its accuracy in comparison with the experimentally available results from the literature. In order to improve the predictions of the column’s ultimate compressive capacity, two efficient machine learning algorithms are employed separately for the stub and the slender columns. The analyzed algorithms are the Decision tree and the Random forest. The research used an experimental dataset of 508 samples: 236 tests on the stub columns and 272 tests on the slender columns. It adapted the dataset to the provision of the Eurocode 4 design code. The predictions of the column’s ultimate axial capacity obtained by two ML algorithms and the Eurocode 4 are compared with the experimental test results on the validation dataset. The calculated R2 error measure has shown that the predictions obtained by the tree-based algorithms are superior compared to the design formulas offered by the Eurocode 4. The decision tree algorithm achieved the best accuracy measured with the highest value of R2 error measure between the two algorithms. The two analyzed algorithms are used to perform the sensitivity analysis on the considered problem. The sensitivity analysis used the feature importance, a technique that assigns a score to each of the input features based on their influence on the prediction of the output variable. As expected, the sensitivity analysis identified the outer diameter of the columns’ cross-section as the parameter with the most significant impact on the results.",
journal = "8th International Conference Science and Practice, Kolasin, Montenegro",
title = "Prediction of Ultimate Compressive Strength of CCFT Columns Using Machine Learning Algorithms",
url = "https://hdl.handle.net/21.15107/rcub_grafar_2682"
}

Đorđević, F.,& Kostić, S. M.. (2022). Prediction of Ultimate Compressive Strength of CCFT Columns Using Machine Learning Algorithms. in 8th International Conference Science and Practice, Kolasin, Montenegro.
https://hdl.handle.net/21.15107/rcub_grafar_2682

Đorđević F, Kostić SM. Prediction of Ultimate Compressive Strength of CCFT Columns Using Machine Learning Algorithms. in 8th International Conference Science and Practice, Kolasin, Montenegro. 2022;.
https://hdl.handle.net/21.15107/rcub_grafar_2682 .

Đorđević, Filip, Kostić, Svetlana M., "Prediction of Ultimate Compressive Strength of CCFT Columns Using Machine Learning Algorithms" in 8th International Conference Science and Practice, Kolasin, Montenegro (2022),
https://hdl.handle.net/21.15107/rcub_grafar_2682 .

TY  - CONF
AU  - Tomić, Igor
AU  - Penna, Andrea
AU  - DeJong, Matthew
AU  - Butenweg, Christoph
AU  - Correia, Antonio
AU  - Candeias, Paulo Xavier
AU  - Senaldi, Ilaria
AU  - Guerrini, Gabriele
AU  - Malomo, Daniele
AU  - Wilding, Bastian
AU  - Pettinga, Didier
AU  - Spanenburg, Mark
AU  - Parisse, Francesco
AU  - Marques, Rui
AU  - Cattari, Serena
AU  - Lourenco, Paulo
AU  - Galvez, Francisco
AU  - Dizhur, Dmytro
AU  - Ingham, Jason
AU  - Ramaglia, Giancarlo
AU  - Lignola, Gian Piero
AU  - Prota, Andrea
AU  - AlShawa, Omar
AU  - Liberatore, Domenico
AU  - Sorrentino, Luigi
AU  - Gagliardo, Raffaele
AU  - Godio, Michele
AU  - Portioli, Francesco
AU  - Landolfo, Raffaele
AU  - Solarino, Fabio
AU  - Bianchini, Nicoletta
AU  - Ciocci, Maria Pia
AU  - Romanazzi, Antonio
AU  - Asikoglu, Abide
AU  - D'Anna, Jennifer
AU  - Ramirez, Rafael
AU  - Romis, Federico
AU  - Marinković, Marko
AU  - Đorđević, Filip
AU  - Beyer, Katrin
PY  - 2022
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/2876
AB  - Across historical centres in Europe, stone masonry buildings form building aggregates that developed as the layout of the city or village was densified. In these aggregates, adjacent buildings can share structural walls with an older and a newer unit connected either by interlocking stones or by a layer of mortar. Observations after for example the recent Central Italy earthquakes showed that joints between the buildings were often the first elements to be damaged, leading to a complex interaction between the units. The analysis of such building aggregates is difficult due to the lack of guidelines, as the advances were impeded by the scarce experimental data. Therefore, the objective of the project AIMS (Seismic Testing of Adjacent Interacting Masonry Structures), included in the H2020 project SERA, was to provide such data by testing an aggregate of two double-leaf stone masonry buildings under two horizontal components of dynamic excitation. The test units were constructed at half-scale, with a two-storey building and a one-storey building. The buildings shared one common wall, while only a layer of mortar connected the façade walls. The floors were at different heights and had different beam orientations. Prior to the test, a blind prediction competition was organized with twelve participants from academia and industry that were provided with all the geometrical and material data, construction details, and the seismic input. The participants were asked to report results in terms of damage mechanisms, recorded displacements and base shear values. Results of the shake-table campaign are reported, together with a comparison with the blind predictions. Large scatter in terms of reported predictions highlights the impact of modelling uncertainties and the need for further tests.
C3  - 3rd European Conference on Earthquake Engineering & Seismology
T1  - Seismic testing of adjacent interacting masonry structures – shake table test and blind prediction competition
UR  - https://hdl.handle.net/21.15107/rcub_grafar_2876
ER  - 

@conference{
author = "Tomić, Igor and Penna, Andrea and DeJong, Matthew and Butenweg, Christoph and Correia, Antonio and Candeias, Paulo Xavier and Senaldi, Ilaria and Guerrini, Gabriele and Malomo, Daniele and Wilding, Bastian and Pettinga, Didier and Spanenburg, Mark and Parisse, Francesco and Marques, Rui and Cattari, Serena and Lourenco, Paulo and Galvez, Francisco and Dizhur, Dmytro and Ingham, Jason and Ramaglia, Giancarlo and Lignola, Gian Piero and Prota, Andrea and AlShawa, Omar and Liberatore, Domenico and Sorrentino, Luigi and Gagliardo, Raffaele and Godio, Michele and Portioli, Francesco and Landolfo, Raffaele and Solarino, Fabio and Bianchini, Nicoletta and Ciocci, Maria Pia and Romanazzi, Antonio and Asikoglu, Abide and D'Anna, Jennifer and Ramirez, Rafael and Romis, Federico and Marinković, Marko and Đorđević, Filip and Beyer, Katrin",
year = "2022",
abstract = "Across historical centres in Europe, stone masonry buildings form building aggregates that developed as the layout of the city or village was densified. In these aggregates, adjacent buildings can share structural walls with an older and a newer unit connected either by interlocking stones or by a layer of mortar. Observations after for example the recent Central Italy earthquakes showed that joints between the buildings were often the first elements to be damaged, leading to a complex interaction between the units. The analysis of such building aggregates is difficult due to the lack of guidelines, as the advances were impeded by the scarce experimental data. Therefore, the objective of the project AIMS (Seismic Testing of Adjacent Interacting Masonry Structures), included in the H2020 project SERA, was to provide such data by testing an aggregate of two double-leaf stone masonry buildings under two horizontal components of dynamic excitation. The test units were constructed at half-scale, with a two-storey building and a one-storey building. The buildings shared one common wall, while only a layer of mortar connected the façade walls. The floors were at different heights and had different beam orientations. Prior to the test, a blind prediction competition was organized with twelve participants from academia and industry that were provided with all the geometrical and material data, construction details, and the seismic input. The participants were asked to report results in terms of damage mechanisms, recorded displacements and base shear values. Results of the shake-table campaign are reported, together with a comparison with the blind predictions. Large scatter in terms of reported predictions highlights the impact of modelling uncertainties and the need for further tests.",
journal = "3rd European Conference on Earthquake Engineering & Seismology",
title = "Seismic testing of adjacent interacting masonry structures – shake table test and blind prediction competition",
url = "https://hdl.handle.net/21.15107/rcub_grafar_2876"
}

Tomić, I., Penna, A., DeJong, M., Butenweg, C., Correia, A., Candeias, P. X., Senaldi, I., Guerrini, G., Malomo, D., Wilding, B., Pettinga, D., Spanenburg, M., Parisse, F., Marques, R., Cattari, S., Lourenco, P., Galvez, F., Dizhur, D., Ingham, J., Ramaglia, G., Lignola, G. P., Prota, A., AlShawa, O., Liberatore, D., Sorrentino, L., Gagliardo, R., Godio, M., Portioli, F., Landolfo, R., Solarino, F., Bianchini, N., Ciocci, M. P., Romanazzi, A., Asikoglu, A., D'Anna, J., Ramirez, R., Romis, F., Marinković, M., Đorđević, F.,& Beyer, K.. (2022). Seismic testing of adjacent interacting masonry structures – shake table test and blind prediction competition. in 3rd European Conference on Earthquake Engineering & Seismology.
https://hdl.handle.net/21.15107/rcub_grafar_2876

Tomić I, Penna A, DeJong M, Butenweg C, Correia A, Candeias PX, Senaldi I, Guerrini G, Malomo D, Wilding B, Pettinga D, Spanenburg M, Parisse F, Marques R, Cattari S, Lourenco P, Galvez F, Dizhur D, Ingham J, Ramaglia G, Lignola GP, Prota A, AlShawa O, Liberatore D, Sorrentino L, Gagliardo R, Godio M, Portioli F, Landolfo R, Solarino F, Bianchini N, Ciocci MP, Romanazzi A, Asikoglu A, D'Anna J, Ramirez R, Romis F, Marinković M, Đorđević F, Beyer K. Seismic testing of adjacent interacting masonry structures – shake table test and blind prediction competition. in 3rd European Conference on Earthquake Engineering & Seismology. 2022;.
https://hdl.handle.net/21.15107/rcub_grafar_2876 .

Tomić, Igor, Penna, Andrea, DeJong, Matthew, Butenweg, Christoph, Correia, Antonio, Candeias, Paulo Xavier, Senaldi, Ilaria, Guerrini, Gabriele, Malomo, Daniele, Wilding, Bastian, Pettinga, Didier, Spanenburg, Mark, Parisse, Francesco, Marques, Rui, Cattari, Serena, Lourenco, Paulo, Galvez, Francisco, Dizhur, Dmytro, Ingham, Jason, Ramaglia, Giancarlo, Lignola, Gian Piero, Prota, Andrea, AlShawa, Omar, Liberatore, Domenico, Sorrentino, Luigi, Gagliardo, Raffaele, Godio, Michele, Portioli, Francesco, Landolfo, Raffaele, Solarino, Fabio, Bianchini, Nicoletta, Ciocci, Maria Pia, Romanazzi, Antonio, Asikoglu, Abide, D'Anna, Jennifer, Ramirez, Rafael, Romis, Federico, Marinković, Marko, Đorđević, Filip, Beyer, Katrin, "Seismic testing of adjacent interacting masonry structures – shake table test and blind prediction competition" in 3rd European Conference on Earthquake Engineering & Seismology (2022),
https://hdl.handle.net/21.15107/rcub_grafar_2876 .

TY  - CONF
AU  - Đorđević, Filip
PY  - 2022
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/2924
AB  - In recent decades, different concepts of machine learning (ML) have found applications in solving many engineering problems. Less time consumption in performing analyses, better optimization of the quality-price ratio and maintaining high model accuracy are just some ML advantages compared to traditional modeling procedures. There are currently a significant number of pre-trained machine learning models based on classification or regression tasks. However, there is a tendency to improve them through the implementation of the transfer learning (TL) approach. This article proposes an upgrade of the existing, pre-trained artificial neural network (ANN) model for the evaluation of the ultimate compressive strength of square concrete-filled steel tubular (CFST) columns. The aim of the improved TL model is to adapt to the problem of predicting the axial capacity of rectangular CFST columns in a more optimal way. The attractiveness of the TL is reflected through the possibility of overcoming certain shortcomings of classical models. Quick adaptation to the problem with small modifications of the existing surrogate model, better overcoming of potential overfitting even with a small dataset, and improved convergence towards the required solutions are some of the advanced TL strategies. The robustness of the proposed model was demonstrated through verification with experimental solutions and validation with the Eurocode 4 (EC4) design code. The application of such innovative paradigms can also be ensured for other research fields in a similar manner.
C3  - 6th International Conference WE BUILD THE FUTURE 2022 International Construction Management Conference November 17-18, 2022, Belgrade, Serbia
T1  - A Novel ANN Technique for Fast Prediction of Structural Behavior
UR  - https://hdl.handle.net/21.15107/rcub_grafar_2924
ER  - 

@conference{
author = "Đorđević, Filip",
year = "2022",
abstract = "In recent decades, different concepts of machine learning (ML) have found applications in solving many engineering problems. Less time consumption in performing analyses, better optimization of the quality-price ratio and maintaining high model accuracy are just some ML advantages compared to traditional modeling procedures. There are currently a significant number of pre-trained machine learning models based on classification or regression tasks. However, there is a tendency to improve them through the implementation of the transfer learning (TL) approach. This article proposes an upgrade of the existing, pre-trained artificial neural network (ANN) model for the evaluation of the ultimate compressive strength of square concrete-filled steel tubular (CFST) columns. The aim of the improved TL model is to adapt to the problem of predicting the axial capacity of rectangular CFST columns in a more optimal way. The attractiveness of the TL is reflected through the possibility of overcoming certain shortcomings of classical models. Quick adaptation to the problem with small modifications of the existing surrogate model, better overcoming of potential overfitting even with a small dataset, and improved convergence towards the required solutions are some of the advanced TL strategies. The robustness of the proposed model was demonstrated through verification with experimental solutions and validation with the Eurocode 4 (EC4) design code. The application of such innovative paradigms can also be ensured for other research fields in a similar manner.",
journal = "6th International Conference WE BUILD THE FUTURE 2022 International Construction Management Conference November 17-18, 2022, Belgrade, Serbia",
title = "A Novel ANN Technique for Fast Prediction of Structural Behavior",
url = "https://hdl.handle.net/21.15107/rcub_grafar_2924"
}

Đorđević, F.. (2022). A Novel ANN Technique for Fast Prediction of Structural Behavior. in 6th International Conference WE BUILD THE FUTURE 2022 International Construction Management Conference November 17-18, 2022, Belgrade, Serbia.
https://hdl.handle.net/21.15107/rcub_grafar_2924

Đorđević F. A Novel ANN Technique for Fast Prediction of Structural Behavior. in 6th International Conference WE BUILD THE FUTURE 2022 International Construction Management Conference November 17-18, 2022, Belgrade, Serbia. 2022;.
https://hdl.handle.net/21.15107/rcub_grafar_2924 .

Đorđević, Filip, "A Novel ANN Technique for Fast Prediction of Structural Behavior" in 6th International Conference WE BUILD THE FUTURE 2022 International Construction Management Conference November 17-18, 2022, Belgrade, Serbia (2022),
https://hdl.handle.net/21.15107/rcub_grafar_2924 .

TY  - CONF
AU  - Šumarac, Dragoslav
AU  - Đorđević, Filip
AU  - Matić, Dejan
AU  - Milutinović, Goran V.
PY  - 2021
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/2684
AB  - Lead-rubber bearings are often used as isolation/dissipation devices in the bridge structures, as they provide both, period shift and increased damping in the structure, reducing significantly the seismic forces and displacements induced in the bridge. The hysteresis loop of the lead-rubber bearing, usually approximated with bilinear shape, is an important numerical parameter directly used in the analysis and design of this type of the structure. In this paper, an innovative rigorous and closed-form analytical solution of the lead-rubber bearing hysteresis loop was developed applying the Preisach model. This analytical model allows an accurate computation of all points on the hysteresis loop as well as its area.
C3  - 8th International Conference of Contemporary Achievements in Civil Engineering, Subotica, Serbia
T1  - A Preisach Model for The Lead-Rubber Bearing Hysteresis Loop
DO  - 10.14415/konferencijaGFS2021.25
ER  - 

@conference{
author = "Šumarac, Dragoslav and Đorđević, Filip and Matić, Dejan and Milutinović, Goran V.",
year = "2021",
abstract = "Lead-rubber bearings are often used as isolation/dissipation devices in the bridge structures, as they provide both, period shift and increased damping in the structure, reducing significantly the seismic forces and displacements induced in the bridge. The hysteresis loop of the lead-rubber bearing, usually approximated with bilinear shape, is an important numerical parameter directly used in the analysis and design of this type of the structure. In this paper, an innovative rigorous and closed-form analytical solution of the lead-rubber bearing hysteresis loop was developed applying the Preisach model. This analytical model allows an accurate computation of all points on the hysteresis loop as well as its area.",
journal = "8th International Conference of Contemporary Achievements in Civil Engineering, Subotica, Serbia",
title = "A Preisach Model for The Lead-Rubber Bearing Hysteresis Loop",
doi = "10.14415/konferencijaGFS2021.25"
}

Šumarac, D., Đorđević, F., Matić, D.,& Milutinović, G. V.. (2021). A Preisach Model for The Lead-Rubber Bearing Hysteresis Loop. in 8th International Conference of Contemporary Achievements in Civil Engineering, Subotica, Serbia.
https://doi.org/10.14415/konferencijaGFS2021.25

Šumarac D, Đorđević F, Matić D, Milutinović GV. A Preisach Model for The Lead-Rubber Bearing Hysteresis Loop. in 8th International Conference of Contemporary Achievements in Civil Engineering, Subotica, Serbia. 2021;.
doi:10.14415/konferencijaGFS2021.25 .

Šumarac, Dragoslav, Đorđević, Filip, Matić, Dejan, Milutinović, Goran V., "A Preisach Model for The Lead-Rubber Bearing Hysteresis Loop" in 8th International Conference of Contemporary Achievements in Civil Engineering, Subotica, Serbia (2021),
https://doi.org/10.14415/konferencijaGFS2021.25 . .