TY  - CONF
AU  - Vranešević, Diana
AU  - Nedeljković, Đorđe
AU  - Kovačević, Miloš
PY  - 2023
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/3235
AB  - This study demonstrates the potential of application of unstructured textual data for predicting
real estate prices and compares different protocols for extracting features from textual data.
Performance of the different models for price prediction was evaluated on data set of real estate
listings, which included numerical and categorical features, as well as text descriptions. The
experiments showed that adding features extracted from both the translated description text, as
well as noun chunks from it, resulted in the highest R2 score of 0.768, representing an
improvement over the R2 score of 0.71 for the baseline model without text-based features. The
findings from this study indicate how the performance of real estate price prediction models can
be improved by utilizing text-based features, in turn benefiting property market stakeholders in
making informed decisions and evaluating competitive pricing strategies.
C3  - 2nd Serbian International Conference on Applied Artificial Intelligence (SICAAI) Kragujevac, Serbia, May 19-20, 2023
T1  - Application of unstructured text based features in prediction of real estate prices: A comparative study
UR  - https://hdl.handle.net/21.15107/rcub_grafar_3235
ER  - 

@conference{
author = "Vranešević, Diana and Nedeljković, Đorđe and Kovačević, Miloš",
year = "2023",
abstract = "This study demonstrates the potential of application of unstructured textual data for predicting
real estate prices and compares different protocols for extracting features from textual data.
Performance of the different models for price prediction was evaluated on data set of real estate
listings, which included numerical and categorical features, as well as text descriptions. The
experiments showed that adding features extracted from both the translated description text, as
well as noun chunks from it, resulted in the highest R2 score of 0.768, representing an
improvement over the R2 score of 0.71 for the baseline model without text-based features. The
findings from this study indicate how the performance of real estate price prediction models can
be improved by utilizing text-based features, in turn benefiting property market stakeholders in
making informed decisions and evaluating competitive pricing strategies.",
journal = "2nd Serbian International Conference on Applied Artificial Intelligence (SICAAI) Kragujevac, Serbia, May 19-20, 2023",
title = "Application of unstructured text based features in prediction of real estate prices: A comparative study",
url = "https://hdl.handle.net/21.15107/rcub_grafar_3235"
}

Vranešević, D., Nedeljković, Đ.,& Kovačević, M.. (2023). Application of unstructured text based features in prediction of real estate prices: A comparative study. in 2nd Serbian International Conference on Applied Artificial Intelligence (SICAAI) Kragujevac, Serbia, May 19-20, 2023.
https://hdl.handle.net/21.15107/rcub_grafar_3235

Vranešević D, Nedeljković Đ, Kovačević M. Application of unstructured text based features in prediction of real estate prices: A comparative study. in 2nd Serbian International Conference on Applied Artificial Intelligence (SICAAI) Kragujevac, Serbia, May 19-20, 2023. 2023;.
https://hdl.handle.net/21.15107/rcub_grafar_3235 .

Vranešević, Diana, Nedeljković, Đorđe, Kovačević, Miloš, "Application of unstructured text based features in prediction of real estate prices: A comparative study" in 2nd Serbian International Conference on Applied Artificial Intelligence (SICAAI) Kragujevac, Serbia, May 19-20, 2023 (2023),
https://hdl.handle.net/21.15107/rcub_grafar_3235 .

TY  - CONF
AU  - Ivanović, Marija
AU  - Nedeljković, Đorđe
AU  - Stojadinović, Zoran
PY  - 2023
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/3241
AB  - Infrastrukturni projekti su kapitalni projekti koji su veoma složeni u pogledu obima, 
trajanja i velikog broja učesnika. Prema postojećim studijama, prekoračenje vremena 
građevinskih projekata je jedan od najčešćih problema. Cilj ovog istraživanja je da se 
identifikuju uzroci kašnjenja u cilju razvoja mera za ublažavanje ili otklanjanje 
potencijalnih rizika i uspešnog završetka projekta u planiranom roku. Da bi se postigao 
definisani cilj, sprovedeno je empirijsko istraživanje kako bi se identifikovali glavni 
uzroci kašnjenja na projektima putne infrastrukture iz perspektive izvođača radova. 
Anketa je obuhvatila 53 uzroka kašnjenja grupisanih u 8 kategorija. Ukupno 35 izvođača 
je učestvovalo u empirijskom istraživanju. Rezultati su pokazali da su najčešći uzroci koji 
prouzrokuju prekoračenje vremena problemi sa projektnom dokumentacijom i tenderske 
procedure. Doprinosi ovog istraživanja mogu biti od koristi u cilju poboljšanja
vremenskih performansi na projektima putne infrastrukture
C3  - Međunarodna naučna konferencija ''Planiranje, projektovanje, izvođenje i obnova graditeljstva'' INDIS 2023
T1  - Faktori koji doprinose kašnjenju projekta iz perspektive izvođača radova: studija slučaja - građevinski projekti putne infrastrukture u Srbiji
UR  - https://hdl.handle.net/21.15107/rcub_grafar_3241
ER  - 

@conference{
author = "Ivanović, Marija and Nedeljković, Đorđe and Stojadinović, Zoran",
year = "2023",
abstract = "Infrastrukturni projekti su kapitalni projekti koji su veoma složeni u pogledu obima, 
trajanja i velikog broja učesnika. Prema postojećim studijama, prekoračenje vremena 
građevinskih projekata je jedan od najčešćih problema. Cilj ovog istraživanja je da se 
identifikuju uzroci kašnjenja u cilju razvoja mera za ublažavanje ili otklanjanje 
potencijalnih rizika i uspešnog završetka projekta u planiranom roku. Da bi se postigao 
definisani cilj, sprovedeno je empirijsko istraživanje kako bi se identifikovali glavni 
uzroci kašnjenja na projektima putne infrastrukture iz perspektive izvođača radova. 
Anketa je obuhvatila 53 uzroka kašnjenja grupisanih u 8 kategorija. Ukupno 35 izvođača 
je učestvovalo u empirijskom istraživanju. Rezultati su pokazali da su najčešći uzroci koji 
prouzrokuju prekoračenje vremena problemi sa projektnom dokumentacijom i tenderske 
procedure. Doprinosi ovog istraživanja mogu biti od koristi u cilju poboljšanja
vremenskih performansi na projektima putne infrastrukture",
journal = "Međunarodna naučna konferencija ''Planiranje, projektovanje, izvođenje i obnova graditeljstva'' INDIS 2023",
title = "Faktori koji doprinose kašnjenju projekta iz perspektive izvođača radova: studija slučaja - građevinski projekti putne infrastrukture u Srbiji",
url = "https://hdl.handle.net/21.15107/rcub_grafar_3241"
}

Ivanović, M., Nedeljković, Đ.,& Stojadinović, Z.. (2023). Faktori koji doprinose kašnjenju projekta iz perspektive izvođača radova: studija slučaja - građevinski projekti putne infrastrukture u Srbiji. in Međunarodna naučna konferencija ''Planiranje, projektovanje, izvođenje i obnova graditeljstva'' INDIS 2023.
https://hdl.handle.net/21.15107/rcub_grafar_3241

Ivanović M, Nedeljković Đ, Stojadinović Z. Faktori koji doprinose kašnjenju projekta iz perspektive izvođača radova: studija slučaja - građevinski projekti putne infrastrukture u Srbiji. in Međunarodna naučna konferencija ''Planiranje, projektovanje, izvođenje i obnova graditeljstva'' INDIS 2023. 2023;.
https://hdl.handle.net/21.15107/rcub_grafar_3241 .

Ivanović, Marija, Nedeljković, Đorđe, Stojadinović, Zoran, "Faktori koji doprinose kašnjenju projekta iz perspektive izvođača radova: studija slučaja - građevinski projekti putne infrastrukture u Srbiji" in Međunarodna naučna konferencija ''Planiranje, projektovanje, izvođenje i obnova graditeljstva'' INDIS 2023 (2023),
https://hdl.handle.net/21.15107/rcub_grafar_3241 .

TY  - JOUR
AU  - Simić, Nevena
AU  - Ivanišević, Nenad
AU  - Nedeljković, Đorđe
AU  - Senić, Aleksandar
AU  - Stojadinović, Zoran
AU  - Ivanović, Marija
PY  - 2023
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/3224
AB  - Cost estimates in the early stages of project development are essential for making the right deci-sions, but they are a huge challenge and risk for owners and potential contractors due to limited information about the characteristics of the future highway project. While previous studies were mainly focused on achieving the highest possible estimation accuracy, this paper aims to propose cost estimation models that can provide satisfactory accuracy with the least possible effort, and to compare the perspectives of owners and contractors, as the key stakeholders on projects. To de-termine cost drivers (CDs) which have a high influence on highway construction costs and re-quire low effort for their establishment, a questionnaire survey was conducted. Based on the key stakeholders’ perceptions and collected data set, cost estimation models were developed using multiple regression analysis, artificial neural networks, and XGBoost. The results show that rea-sonable cost estimation accuracy can be achieved with a relatively low effort for 3 CDs for the owners' perspective and 5 CDs for the contractors' perspective. Additional inclusion of input CDs in models does not necessarily imply an increase in accuracy. Also, the questionnaire results show that owners are more concerned about environmental issues, while contractors are more con-cerned about the possible changes in resource prices (especially after recent high increases caused by COVID-19 and the Russia-Ukraine war). These findings can help owners and potential con-tractors in intelligent decision-making in the early stages of future highway construction projects.
PB  - MDPI
T2  - Sustainability
T1  - Early Highway Construction Cost Estimation: Selection of Key Cost Drivers
VL  - 15
DO  - 10.3390/su15065584
ER  - 

@article{
author = "Simić, Nevena and Ivanišević, Nenad and Nedeljković, Đorđe and Senić, Aleksandar and Stojadinović, Zoran and Ivanović, Marija",
year = "2023",
abstract = "Cost estimates in the early stages of project development are essential for making the right deci-sions, but they are a huge challenge and risk for owners and potential contractors due to limited information about the characteristics of the future highway project. While previous studies were mainly focused on achieving the highest possible estimation accuracy, this paper aims to propose cost estimation models that can provide satisfactory accuracy with the least possible effort, and to compare the perspectives of owners and contractors, as the key stakeholders on projects. To de-termine cost drivers (CDs) which have a high influence on highway construction costs and re-quire low effort for their establishment, a questionnaire survey was conducted. Based on the key stakeholders’ perceptions and collected data set, cost estimation models were developed using multiple regression analysis, artificial neural networks, and XGBoost. The results show that rea-sonable cost estimation accuracy can be achieved with a relatively low effort for 3 CDs for the owners' perspective and 5 CDs for the contractors' perspective. Additional inclusion of input CDs in models does not necessarily imply an increase in accuracy. Also, the questionnaire results show that owners are more concerned about environmental issues, while contractors are more con-cerned about the possible changes in resource prices (especially after recent high increases caused by COVID-19 and the Russia-Ukraine war). These findings can help owners and potential con-tractors in intelligent decision-making in the early stages of future highway construction projects.",
publisher = "MDPI",
journal = "Sustainability",
title = "Early Highway Construction Cost Estimation: Selection of Key Cost Drivers",
volume = "15",
doi = "10.3390/su15065584"
}

Simić, N., Ivanišević, N., Nedeljković, Đ., Senić, A., Stojadinović, Z.,& Ivanović, M.. (2023). Early Highway Construction Cost Estimation: Selection of Key Cost Drivers. in Sustainability
MDPI., 15.
https://doi.org/10.3390/su15065584

Simić N, Ivanišević N, Nedeljković Đ, Senić A, Stojadinović Z, Ivanović M. Early Highway Construction Cost Estimation: Selection of Key Cost Drivers. in Sustainability. 2023;15.
doi:10.3390/su15065584 .

Simić, Nevena, Ivanišević, Nenad, Nedeljković, Đorđe, Senić, Aleksandar, Stojadinović, Zoran, Ivanović, Marija, "Early Highway Construction Cost Estimation: Selection of Key Cost Drivers" in Sustainability, 15 (2023),
https://doi.org/10.3390/su15065584 . .

TY  - CONF
AU  - Ivanović, Marija
AU  - Nedeljković, Đorđe
AU  - Stojadinović, Zoran
PY  - 2023
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/3221
AB  - Građevinski projekti su jedinstveni, dinamični i složeni. Karakteriše ih multidisciplinarno okruženje i veliki broj učesnika koji proizvode značajan obim podataka. Ovo su samo neki od razloga zašto građevinski projekti ne uspevaju da ostvare planirano trajanje. Otkrivanje baznih uzroka kašnjenja je prvi i najvažniji korak ka eliminisanju ili umanjenju potencijalnih kašnjenja na budućim projektima. Postojeći pristupi se baziraju na ekspertskom mišljenju uz rangiranje uzroka kašnjenja prema parametrima kao što su verovatnoća pojave i mera uticaja na trajanje projekta. Ovakav pristup agregira subjektivizam i pristrasnost eksperata i shodno tome ne doprinosi otkrivanju baznih uzroka kašnjenja. Kroz ovo istraživanje se predlaže inovativni pristup otkrivanju baznih uzroka kašnjenja – analiza vremenske distribucije uzroka kašnjenja kao jedinstvena karakteristika DREAM-a (Delay Root-cuases of delay Extraction and Analysis Model). Analizom informativnih grafikona vremenske distribucije eksperti mogu da razumeju prirodu kašnjenja kroz sve faze projekta i otkriju bazne uzroke kašnjenja. Na taj način se omogućava podrška donosiocima odluka na budućim projektima u cilju proaktivnog upravljanja rizicima
C3  - 27th International project management congress, Vrnjačka Banja, 8-10 June, 2023
T1  - Vremenska distribucija uzroka kašnjenja kao nov pristup otkrivanju baznih uzroka kašnjenja
T1  - Temporal distribution of causes of delay as a new approach to discovering the root causes of delay
UR  - https://hdl.handle.net/21.15107/rcub_grafar_3221
ER  - 

@conference{
author = "Ivanović, Marija and Nedeljković, Đorđe and Stojadinović, Zoran",
year = "2023",
abstract = "Građevinski projekti su jedinstveni, dinamični i složeni. Karakteriše ih multidisciplinarno okruženje i veliki broj učesnika koji proizvode značajan obim podataka. Ovo su samo neki od razloga zašto građevinski projekti ne uspevaju da ostvare planirano trajanje. Otkrivanje baznih uzroka kašnjenja je prvi i najvažniji korak ka eliminisanju ili umanjenju potencijalnih kašnjenja na budućim projektima. Postojeći pristupi se baziraju na ekspertskom mišljenju uz rangiranje uzroka kašnjenja prema parametrima kao što su verovatnoća pojave i mera uticaja na trajanje projekta. Ovakav pristup agregira subjektivizam i pristrasnost eksperata i shodno tome ne doprinosi otkrivanju baznih uzroka kašnjenja. Kroz ovo istraživanje se predlaže inovativni pristup otkrivanju baznih uzroka kašnjenja – analiza vremenske distribucije uzroka kašnjenja kao jedinstvena karakteristika DREAM-a (Delay Root-cuases of delay Extraction and Analysis Model). Analizom informativnih grafikona vremenske distribucije eksperti mogu da razumeju prirodu kašnjenja kroz sve faze projekta i otkriju bazne uzroke kašnjenja. Na taj način se omogućava podrška donosiocima odluka na budućim projektima u cilju proaktivnog upravljanja rizicima",
journal = "27th International project management congress, Vrnjačka Banja, 8-10 June, 2023",
title = "Vremenska distribucija uzroka kašnjenja kao nov pristup otkrivanju baznih uzroka kašnjenja, Temporal distribution of causes of delay as a new approach to discovering the root causes of delay",
url = "https://hdl.handle.net/21.15107/rcub_grafar_3221"
}

Ivanović, M., Nedeljković, Đ.,& Stojadinović, Z.. (2023). Vremenska distribucija uzroka kašnjenja kao nov pristup otkrivanju baznih uzroka kašnjenja. in 27th International project management congress, Vrnjačka Banja, 8-10 June, 2023.
https://hdl.handle.net/21.15107/rcub_grafar_3221

Ivanović M, Nedeljković Đ, Stojadinović Z. Vremenska distribucija uzroka kašnjenja kao nov pristup otkrivanju baznih uzroka kašnjenja. in 27th International project management congress, Vrnjačka Banja, 8-10 June, 2023. 2023;.
https://hdl.handle.net/21.15107/rcub_grafar_3221 .

Ivanović, Marija, Nedeljković, Đorđe, Stojadinović, Zoran, "Vremenska distribucija uzroka kašnjenja kao nov pristup otkrivanju baznih uzroka kašnjenja" in 27th International project management congress, Vrnjačka Banja, 8-10 June, 2023 (2023),
https://hdl.handle.net/21.15107/rcub_grafar_3221 .

TY  - JOUR
AU  - Ivanović, Marija
AU  - Nedeljković, Đorđe
AU  - Stojadinović, Zoran
AU  - Marinković, Dejan
AU  - Ivanišević, Nenad
AU  - Simić, Nevena
PY  - 2022
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/2958
AB  - Due to numerous reasons, construction projects often fail to achieve the planned duration. Detecting causes of delays (CoD) is the first step in eliminating or mitigating potential delays in future projects. The goal of research is unbiased CoD detection at a single project level, with the ultimate goal to discover the root causes of delay. The existing approach is based on expert knowledge which is used to create CoD lists for projects in general or groups of similar projects. When applied to a single project, it is burdened with bias, as shown on a case project returning low Spearman Rank correlation values. This research introduces a Delay Root causes Extraction and Analysis Model—DREAM. The proposed model combines expert knowledge, machine learning techniques, and Minutes of Meetings (MoM) as an unutilized extensive source of information. In the first phase, DREAM outputs a CoD list based on occurring frequency in MoM with satisfactory recall values, significantly reducing expert-induced subjectivism. In the second phase, enabled by MoM dates, DREAM adds another dimension to delay analysis—temporal CoD distribution. By analyzing corresponding informative charts, experts can understand the nature of delays and discover the root CoD, allowing intelligent decision making on future projects.
T2  - Sustainability
T1  - Detection and In-Depth Analysis of Causes of Delay in  Construction Projects: Synergy between Machine Learning and Expert Knowledge
VL  - 24
DO  - 10.3390/su142214927
ER  - 

@article{
author = "Ivanović, Marija and Nedeljković, Đorđe and Stojadinović, Zoran and Marinković, Dejan and Ivanišević, Nenad and Simić, Nevena",
year = "2022",
abstract = "Due to numerous reasons, construction projects often fail to achieve the planned duration. Detecting causes of delays (CoD) is the first step in eliminating or mitigating potential delays in future projects. The goal of research is unbiased CoD detection at a single project level, with the ultimate goal to discover the root causes of delay. The existing approach is based on expert knowledge which is used to create CoD lists for projects in general or groups of similar projects. When applied to a single project, it is burdened with bias, as shown on a case project returning low Spearman Rank correlation values. This research introduces a Delay Root causes Extraction and Analysis Model—DREAM. The proposed model combines expert knowledge, machine learning techniques, and Minutes of Meetings (MoM) as an unutilized extensive source of information. In the first phase, DREAM outputs a CoD list based on occurring frequency in MoM with satisfactory recall values, significantly reducing expert-induced subjectivism. In the second phase, enabled by MoM dates, DREAM adds another dimension to delay analysis—temporal CoD distribution. By analyzing corresponding informative charts, experts can understand the nature of delays and discover the root CoD, allowing intelligent decision making on future projects.",
journal = "Sustainability",
title = "Detection and In-Depth Analysis of Causes of Delay in  Construction Projects: Synergy between Machine Learning and Expert Knowledge",
volume = "24",
doi = "10.3390/su142214927"
}

Ivanović, M., Nedeljković, Đ., Stojadinović, Z., Marinković, D., Ivanišević, N.,& Simić, N.. (2022). Detection and In-Depth Analysis of Causes of Delay in  Construction Projects: Synergy between Machine Learning and Expert Knowledge. in Sustainability, 24.
https://doi.org/10.3390/su142214927

Ivanović M, Nedeljković Đ, Stojadinović Z, Marinković D, Ivanišević N, Simić N. Detection and In-Depth Analysis of Causes of Delay in  Construction Projects: Synergy between Machine Learning and Expert Knowledge. in Sustainability. 2022;24.
doi:10.3390/su142214927 .

Ivanović, Marija, Nedeljković, Đorđe, Stojadinović, Zoran, Marinković, Dejan, Ivanišević, Nenad, Simić, Nevena, "Detection and In-Depth Analysis of Causes of Delay in  Construction Projects: Synergy between Machine Learning and Expert Knowledge" in Sustainability, 24 (2022),
https://doi.org/10.3390/su142214927 . .

TY  - THES
AU  - Nedeljković, Đorđe Lj.
PY  - 2018
UR  - http://eteze.bg.ac.rs/application/showtheses?thesesId=6485
UR  - https://fedorabg.bg.ac.rs/fedora/get/o:19221/bdef:Content/download
UR  - http://vbs.rs/scripts/cobiss?command=DISPLAY&base=70036&RID=513801618
UR  - http://nardus.mpn.gov.rs/123456789/10623
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/1684
AB  - Током животног циклуса инвестиционог пројекта ствара се велики корпус неструктуираних и полуструктуираних докумената. Традиционални приступи у складиштењу и организовању информација из неструктуираних податка су оријентисани на рад са документима, што их чини неподесним за анализу и издвајање знања. У неструктуираним документима је отежано прикупљање, анализа и поновно коришћење релевантних информација у интегралном облику, што може изазвати проблеме на пројекту услед неблаговремених или неодговарајућих одлука.У овој дисертацији је приказана репрезентација информација издвојених из неструктуираних текстуалних докумената у облику графа значајних фраза, који корисницима треба да омогући визуелизацију и анализу значајних чињеница на пројекту са минималном количином уложеног труда. Са циљем да се конструише доменски независна репрезентација са минималним трудом експерта за претходно конфигурисање, значајне фразе су детектоване у вишејезичном окружењу применом статистичких мера за одређивање корелисаности пара речи. Граф садржи аутоматски издвојене значајне фразе које су повезане на основу сличности семантичких контекста.Репрезентација је имплементирана у графовској бази података што корисницима омогућава да детектују и визуелизују различите скривене обрасце у подацима. Неинформативне фразе су филтриране кроз поступке одређивања ентропије скупа контекста и динамичности суседства фразе кроз више графова који представљају тренутке у времену. Приказана је хеуристика за издвајање комплексних концепата, заснована на итеративној процедури за детекцију блиских фраза које припадају истом семантичком подграфу. Могућности примене предложене репрезентације су демонстриране на графу конструисаном за постојећи корпус докумената са међународног инвестиционог пројекта.
AB  - During a construction project lifecycle, an extensive corpus of unstructured or semi-structured text documents is generated. Traditional approaches for information storing and organizing are document-oriented, which is highly inconvenient for data analysis and knowledge extraction. The nature of unstructured sources impedes users’ acquisition, analysis, and reuse of relevant information, leading to possible negative effects in the project management process.This dissertation suggests a procedure for automatic extraction of relevant project concepts from unstructured text documents. Concepts are organized in the form of a key-phrase network, intended to provide users with the possibility to visualize and analyze valuable project facts with less effort. With the objective of constructing a domain-independent and language-independent key-phrase network, with minimal expert involvement for configuration, an approach to detect key phrases was examined by using measures of correlation for word pairs. A network contains key phrases automatically extracted from various types of unstructured documents, with relations based on the similarity of semantic contexts.The representation was implemented as a graph database, enabling project participants to extract and visualize various patterns in data. The problem of noisy key phrases was reduced by introducing the entropy score for a set of co-occurring contexts and the measure of phrase neighborhood dynamics throughout construction project lifecycle. A heuristic for extraction of complex concepts is presented, based on the iterative procedure for detection of adjacent key phrases belonging to a same semantic subnetwork. Possible applications, such as concept tracking through time or determination of communication patterns between project participants, is demonstrated using a key-phrase network generated for the existing document corpus from an international construction project.
PB  - Универзитет у Београду, Грађевински факултет
T2  - Универзитет у Београду
T1  - Издвајање и визуелизација знања из текстуалних извора за потребе управљања инвестиционим пројектима у грађевинарству
UR  - https://hdl.handle.net/21.15107/rcub_nardus_10623
ER  - 

@phdthesis{
author = "Nedeljković, Đorđe Lj.",
year = "2018",
abstract = "Током животног циклуса инвестиционог пројекта ствара се велики корпус неструктуираних и полуструктуираних докумената. Традиционални приступи у складиштењу и организовању информација из неструктуираних податка су оријентисани на рад са документима, што их чини неподесним за анализу и издвајање знања. У неструктуираним документима је отежано прикупљање, анализа и поновно коришћење релевантних информација у интегралном облику, што може изазвати проблеме на пројекту услед неблаговремених или неодговарајућих одлука.У овој дисертацији је приказана репрезентација информација издвојених из неструктуираних текстуалних докумената у облику графа значајних фраза, који корисницима треба да омогући визуелизацију и анализу значајних чињеница на пројекту са минималном количином уложеног труда. Са циљем да се конструише доменски независна репрезентација са минималним трудом експерта за претходно конфигурисање, значајне фразе су детектоване у вишејезичном окружењу применом статистичких мера за одређивање корелисаности пара речи. Граф садржи аутоматски издвојене значајне фразе које су повезане на основу сличности семантичких контекста.Репрезентација је имплементирана у графовској бази података што корисницима омогућава да детектују и визуелизују различите скривене обрасце у подацима. Неинформативне фразе су филтриране кроз поступке одређивања ентропије скупа контекста и динамичности суседства фразе кроз више графова који представљају тренутке у времену. Приказана је хеуристика за издвајање комплексних концепата, заснована на итеративној процедури за детекцију блиских фраза које припадају истом семантичком подграфу. Могућности примене предложене репрезентације су демонстриране на графу конструисаном за постојећи корпус докумената са међународног инвестиционог пројекта., During a construction project lifecycle, an extensive corpus of unstructured or semi-structured text documents is generated. Traditional approaches for information storing and organizing are document-oriented, which is highly inconvenient for data analysis and knowledge extraction. The nature of unstructured sources impedes users’ acquisition, analysis, and reuse of relevant information, leading to possible negative effects in the project management process.This dissertation suggests a procedure for automatic extraction of relevant project concepts from unstructured text documents. Concepts are organized in the form of a key-phrase network, intended to provide users with the possibility to visualize and analyze valuable project facts with less effort. With the objective of constructing a domain-independent and language-independent key-phrase network, with minimal expert involvement for configuration, an approach to detect key phrases was examined by using measures of correlation for word pairs. A network contains key phrases automatically extracted from various types of unstructured documents, with relations based on the similarity of semantic contexts.The representation was implemented as a graph database, enabling project participants to extract and visualize various patterns in data. The problem of noisy key phrases was reduced by introducing the entropy score for a set of co-occurring contexts and the measure of phrase neighborhood dynamics throughout construction project lifecycle. A heuristic for extraction of complex concepts is presented, based on the iterative procedure for detection of adjacent key phrases belonging to a same semantic subnetwork. Possible applications, such as concept tracking through time or determination of communication patterns between project participants, is demonstrated using a key-phrase network generated for the existing document corpus from an international construction project.",
publisher = "Универзитет у Београду, Грађевински факултет",
journal = "Универзитет у Београду",
title = "Издвајање и визуелизација знања из текстуалних извора за потребе управљања инвестиционим пројектима у грађевинарству",
url = "https://hdl.handle.net/21.15107/rcub_nardus_10623"
}

Nedeljković, Đ. Lj.. (2018). Издвајање и визуелизација знања из текстуалних извора за потребе управљања инвестиционим пројектима у грађевинарству. in Универзитет у Београду
Универзитет у Београду, Грађевински факултет..
https://hdl.handle.net/21.15107/rcub_nardus_10623

Nedeljković ĐL. Издвајање и визуелизација знања из текстуалних извора за потребе управљања инвестиционим пројектима у грађевинарству. in Универзитет у Београду. 2018;.
https://hdl.handle.net/21.15107/rcub_nardus_10623 .

Nedeljković, Đorđe Lj., "Издвајање и визуелизација знања из текстуалних извора за потребе управљања инвестиционим пројектима у грађевинарству" in Универзитет у Београду (2018),
https://hdl.handle.net/21.15107/rcub_nardus_10623 .

TY  - JOUR
AU  - Milošević, Jelena
AU  - Nedeljković, Đorđe
PY  - 2018
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/1112
AB  - The paper presents the application of computational tools in design and analysis of integrally tensioned (tensegrity) structures. The shaping process of this specific type of spatial structures is determined by consideration of form-structure interrelation. Therefore, the sustainable approach to their design implies the application of tools which could both represent geometry and simulate their physical behavior. With respect to this, in the research we tested the application of computational tool Fasttens for design of tensegrity structures. Fasttens programme is based on the computational procedure for non-linear analysis of tensegrity systems originally developed by Miodrag Nestorović. In order to run the original programme written in Turbo Pascal, we performed emulation, using emulator software DOSBox. We tested the application of the tool in the design of concrete tensegrity structure. Presented design and numerical experiment confirmed the effectiveness of the proposed approach.
T2  - Serbian architectural journal
T1  - Computational design and analysis of tensegrity structures
EP  - 15
IS  - 1
SP  - 2
VL  - 9
UR  - https://hdl.handle.net/21.15107/rcub_grafar_1112
ER  - 

@article{
author = "Milošević, Jelena and Nedeljković, Đorđe",
year = "2018",
abstract = "The paper presents the application of computational tools in design and analysis of integrally tensioned (tensegrity) structures. The shaping process of this specific type of spatial structures is determined by consideration of form-structure interrelation. Therefore, the sustainable approach to their design implies the application of tools which could both represent geometry and simulate their physical behavior. With respect to this, in the research we tested the application of computational tool Fasttens for design of tensegrity structures. Fasttens programme is based on the computational procedure for non-linear analysis of tensegrity systems originally developed by Miodrag Nestorović. In order to run the original programme written in Turbo Pascal, we performed emulation, using emulator software DOSBox. We tested the application of the tool in the design of concrete tensegrity structure. Presented design and numerical experiment confirmed the effectiveness of the proposed approach.",
journal = "Serbian architectural journal",
title = "Computational design and analysis of tensegrity structures",
pages = "15-2",
number = "1",
volume = "9",
url = "https://hdl.handle.net/21.15107/rcub_grafar_1112"
}

Milošević, J.,& Nedeljković, Đ.. (2018). Computational design and analysis of tensegrity structures. in Serbian architectural journal, 9(1), 2-15.
https://hdl.handle.net/21.15107/rcub_grafar_1112

Milošević J, Nedeljković Đ. Computational design and analysis of tensegrity structures. in Serbian architectural journal. 2018;9(1):2-15.
https://hdl.handle.net/21.15107/rcub_grafar_1112 .

Milošević, Jelena, Nedeljković, Đorđe, "Computational design and analysis of tensegrity structures" in Serbian architectural journal, 9, no. 1 (2018):2-15,
https://hdl.handle.net/21.15107/rcub_grafar_1112 .

TY  - JOUR
AU  - Nedeljković, Đorđe
AU  - Kovačević, Miloš
PY  - 2017
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/898
AB  - During a construction project lifecycle, an extensive corpus of unstructured or semistructured text documents is generated. The nature of unstructured sources impedes users' acquisition, analysis, and reuse of relevant information in an integral form, leading to a possible reduction in project performance because of untimely or inadequate decisions. This paper explores the representation of information from unstructured documents in the form of a key-phrase network, intended to provide users with the possibility to visualize and analyze valuable project facts with less effort. A network of key phrases automatically extracted from various types of unstructured documents, with relations based on contextual similarity, was implemented as a graph database, enabling project participants to extract and visualize various patterns in data. With the objective of constructing a domain-independent key-phrase network with minimal expert involvement, an approach to detect key phrases in a multilingual environment was examined by using measures of association between words while avoiding text content from less informative contexts. A possible application is demonstrated using key-phrase networks generated from two complex international construction projects.
PB  - American Society of Civil Engineers (ASCE)
T2  - Journal of Computing in Civil Engineering
T1  - Building a Construction Project Key-Phrase Network from Unstructured Text Documents
IS  - 6
VL  - 31
DO  - 10.1061/(ASCE)CP.1943-5487.0000708
ER  - 

@article{
author = "Nedeljković, Đorđe and Kovačević, Miloš",
year = "2017",
abstract = "During a construction project lifecycle, an extensive corpus of unstructured or semistructured text documents is generated. The nature of unstructured sources impedes users' acquisition, analysis, and reuse of relevant information in an integral form, leading to a possible reduction in project performance because of untimely or inadequate decisions. This paper explores the representation of information from unstructured documents in the form of a key-phrase network, intended to provide users with the possibility to visualize and analyze valuable project facts with less effort. A network of key phrases automatically extracted from various types of unstructured documents, with relations based on contextual similarity, was implemented as a graph database, enabling project participants to extract and visualize various patterns in data. With the objective of constructing a domain-independent key-phrase network with minimal expert involvement, an approach to detect key phrases in a multilingual environment was examined by using measures of association between words while avoiding text content from less informative contexts. A possible application is demonstrated using key-phrase networks generated from two complex international construction projects.",
publisher = "American Society of Civil Engineers (ASCE)",
journal = "Journal of Computing in Civil Engineering",
title = "Building a Construction Project Key-Phrase Network from Unstructured Text Documents",
number = "6",
volume = "31",
doi = "10.1061/(ASCE)CP.1943-5487.0000708"
}

Nedeljković, Đ.,& Kovačević, M.. (2017). Building a Construction Project Key-Phrase Network from Unstructured Text Documents. in Journal of Computing in Civil Engineering
American Society of Civil Engineers (ASCE)., 31(6).
https://doi.org/10.1061/(ASCE)CP.1943-5487.0000708

Nedeljković Đ, Kovačević M. Building a Construction Project Key-Phrase Network from Unstructured Text Documents. in Journal of Computing in Civil Engineering. 2017;31(6).
doi:10.1061/(ASCE)CP.1943-5487.0000708 .

Nedeljković, Đorđe, Kovačević, Miloš, "Building a Construction Project Key-Phrase Network from Unstructured Text Documents" in Journal of Computing in Civil Engineering, 31, no. 6 (2017),
https://doi.org/10.1061/(ASCE)CP.1943-5487.0000708 . .

TY  - CONF
AU  - Osmokrović, Igor
AU  - Panić, Sonja
AU  - Nedeljković, Đorđe
PY  - 2017
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/3236
AB  - The 8th PSU-UNS International Conference on Engineering and
Technology (ICET-2017), Novi Sad, Serbia, June 8-10, 2017
University of Novi Sad, Faculty of Technical Sciences
Abstract: Building Information Modeling (BIM) does
not represent only the virtual model of the facility but a
comperhensive approach consisting of technology,
processes, stakeholders' behavior and accompanying
standards.Given the fast evolution of BIM, this paper is
analysing trends of development of BIM standards
throughout the years by applying the keyphrases analysis
method, for some of the most common BIM uses and
recognizable phrases in BIM industry.
C3  - The 8th PSU-UNS International Conference on Engineering and Technology (ICET-2017), Novi Sad, Serbia, June 8-10, 2017 University of Novi Sad, Faculty of Technical Sciences
T1  - Keyphrases analysis of BIM standards through occurrence of most common BIM uses
UR  - https://hdl.handle.net/21.15107/rcub_grafar_3236
ER  - 

@conference{
author = "Osmokrović, Igor and Panić, Sonja and Nedeljković, Đorđe",
year = "2017",
abstract = "The 8th PSU-UNS International Conference on Engineering and
Technology (ICET-2017), Novi Sad, Serbia, June 8-10, 2017
University of Novi Sad, Faculty of Technical Sciences
Abstract: Building Information Modeling (BIM) does
not represent only the virtual model of the facility but a
comperhensive approach consisting of technology,
processes, stakeholders' behavior and accompanying
standards.Given the fast evolution of BIM, this paper is
analysing trends of development of BIM standards
throughout the years by applying the keyphrases analysis
method, for some of the most common BIM uses and
recognizable phrases in BIM industry.",
journal = "The 8th PSU-UNS International Conference on Engineering and Technology (ICET-2017), Novi Sad, Serbia, June 8-10, 2017 University of Novi Sad, Faculty of Technical Sciences",
title = "Keyphrases analysis of BIM standards through occurrence of most common BIM uses",
url = "https://hdl.handle.net/21.15107/rcub_grafar_3236"
}

Osmokrović, I., Panić, S.,& Nedeljković, Đ.. (2017). Keyphrases analysis of BIM standards through occurrence of most common BIM uses. in The 8th PSU-UNS International Conference on Engineering and Technology (ICET-2017), Novi Sad, Serbia, June 8-10, 2017 University of Novi Sad, Faculty of Technical Sciences.
https://hdl.handle.net/21.15107/rcub_grafar_3236

Osmokrović I, Panić S, Nedeljković Đ. Keyphrases analysis of BIM standards through occurrence of most common BIM uses. in The 8th PSU-UNS International Conference on Engineering and Technology (ICET-2017), Novi Sad, Serbia, June 8-10, 2017 University of Novi Sad, Faculty of Technical Sciences. 2017;.
https://hdl.handle.net/21.15107/rcub_grafar_3236 .

Osmokrović, Igor, Panić, Sonja, Nedeljković, Đorđe, "Keyphrases analysis of BIM standards through occurrence of most common BIM uses" in The 8th PSU-UNS International Conference on Engineering and Technology (ICET-2017), Novi Sad, Serbia, June 8-10, 2017 University of Novi Sad, Faculty of Technical Sciences (2017),
https://hdl.handle.net/21.15107/rcub_grafar_3236 .

TY  - CONF
AU  - Nedeljković, Đorđe
AU  - Kovačević, Miloš
PY  - 2015
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/682
AB  - This paper addresses the problem of automatic concept detection in a construction project documentation with the aim of increasing the efficiency of information retrieval for all stakeholders in real-time in cases when documents lack previously defined metadata or when the semantic knowledge is not taken into account. Introduction of significant concepts, in a user-specific problem domain would improve retrieval of relevant documents. Concepts, represented as word pairs, were ranked by using different statistical measures for semantic similarity in order to compare the observed and the expected co-occurrence under a null model. Experiments suggested that using the statistical measures in different combinations yielded better performance when compared to their individual usage. The proposed approach was tested on several data sets compiled from the documents originating from a smelting project in Bor in the Republic of Serbia. Common information retrieval measures, precision and recall, were calculated for different combinations of word span, context scope and applied statistical measures, and further discussed taking into account the complexity and specificity of the observed construction project documentation.
PB  - Civil-Comp Press
C3  - Civil-Comp Proceedings
T1  - Detecting Concepts in Construction Project Documents using Statistical Measures for Semantic Similarity
VL  - 108
UR  - https://hdl.handle.net/21.15107/rcub_grafar_682
ER  - 

@conference{
author = "Nedeljković, Đorđe and Kovačević, Miloš",
year = "2015",
abstract = "This paper addresses the problem of automatic concept detection in a construction project documentation with the aim of increasing the efficiency of information retrieval for all stakeholders in real-time in cases when documents lack previously defined metadata or when the semantic knowledge is not taken into account. Introduction of significant concepts, in a user-specific problem domain would improve retrieval of relevant documents. Concepts, represented as word pairs, were ranked by using different statistical measures for semantic similarity in order to compare the observed and the expected co-occurrence under a null model. Experiments suggested that using the statistical measures in different combinations yielded better performance when compared to their individual usage. The proposed approach was tested on several data sets compiled from the documents originating from a smelting project in Bor in the Republic of Serbia. Common information retrieval measures, precision and recall, were calculated for different combinations of word span, context scope and applied statistical measures, and further discussed taking into account the complexity and specificity of the observed construction project documentation.",
publisher = "Civil-Comp Press",
journal = "Civil-Comp Proceedings",
title = "Detecting Concepts in Construction Project Documents using Statistical Measures for Semantic Similarity",
volume = "108",
url = "https://hdl.handle.net/21.15107/rcub_grafar_682"
}

Nedeljković, Đ.,& Kovačević, M.. (2015). Detecting Concepts in Construction Project Documents using Statistical Measures for Semantic Similarity. in Civil-Comp Proceedings
Civil-Comp Press., 108.
https://hdl.handle.net/21.15107/rcub_grafar_682

Nedeljković Đ, Kovačević M. Detecting Concepts in Construction Project Documents using Statistical Measures for Semantic Similarity. in Civil-Comp Proceedings. 2015;108.
https://hdl.handle.net/21.15107/rcub_grafar_682 .

Nedeljković, Đorđe, Kovačević, Miloš, "Detecting Concepts in Construction Project Documents using Statistical Measures for Semantic Similarity" in Civil-Comp Proceedings, 108 (2015),
https://hdl.handle.net/21.15107/rcub_grafar_682 .

TY  - CONF
AU  - Čučaković, Aleksandar
AU  - Dragović, Magdalena
AU  - Lazarević, Luka
AU  - Nedeljković, Đorđe
PY  - 2014
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/1200
AB  - As a part of new advanced course curriculum of Descriptive geometry, in the Faculty of Civil engineering, creative 3D modeling of specific structures is included. These structures, inspired by contemporary architecture achievements, relay on quadric surfaces (quadrics). Here, student's knowledge concerning properties of the quadrics: cone, sphere, ellipsoid, elliptic hyperboloid, etc. (also elaborated in the course - Mathematics 2, in the same year of the studies) is necessary. Throughout two given 3D modeling tasks, students elaborate two separate subtopics: discretization of the surface elliptic hyperboloid of one sheet (ELHY) and spiral surfaces, both connected by key elements circular sections of quadrics. The subtopic's presentation methodology designed for students is conducted by "steps" in 3D structures modeling process, aided by applications and tools of most common engineering software Auto CAD. The applications presented below are created on a base of analytical geometry methods. The first topic - discretization of ELHY surface, i.e. generation of polygonal mesh structure, has a rather simple explanation and graphical presentation (wireframe and surface models) of geometrical procedures, i.e. constructions in opposite to the available analytical geometry solutions. A method of generating the ELHY surface is based on two arbitrary circular sections and one generatrix. The accompanying CAD application, created in Auto lisp, as a tool for discretization has the purpose to enable creative 3D task solution - model of geometric structure ELHY shaped. Three different options/solutions of discretization are offered. The second topic regarding 3D models of spiral surfaces/structures is nowadays very popular in the architecture. Here included spiral surfaces are one which geometric origins are quadrics. Since the term "spiral" is directly connected to the rotation and circle, geometric concept relay again on the circular sections of quadrics. This topic is supported by a Visual basic application (VBA) procedure implemented in Auto CAD. It also requires advanced 3D modeling tools for the design and visualization process of the final product. If comparing two given tasks, the second one is more creative and optional, while the students role in designing is more significant. However, we are sure that both tasks have an important educational value in better understanding of theory regarding quadric surfaces. It is reasonable to expect that in a certain moment (according to the level of programming knowledge) student could create his own software solution, or modify the offered one (application), aimed for such geometric topics. According to the palette of the surfaces included, variety of final "products" - structures and their purposes should be resulted in buildings, furniture, or art design.
PB  - Innsbruck University Press, Innsbruck
C3  - Proceedings of the 16th International Conference on Geometry and Graphics, Innsbruck, August 4-8 2014
T1  - On the role of circular sections of quadric surfaces
EP  - 1081
SP  - 1075
UR  - https://hdl.handle.net/21.15107/rcub_grafar_1200
ER  - 

@conference{
author = "Čučaković, Aleksandar and Dragović, Magdalena and Lazarević, Luka and Nedeljković, Đorđe",
year = "2014",
abstract = "As a part of new advanced course curriculum of Descriptive geometry, in the Faculty of Civil engineering, creative 3D modeling of specific structures is included. These structures, inspired by contemporary architecture achievements, relay on quadric surfaces (quadrics). Here, student's knowledge concerning properties of the quadrics: cone, sphere, ellipsoid, elliptic hyperboloid, etc. (also elaborated in the course - Mathematics 2, in the same year of the studies) is necessary. Throughout two given 3D modeling tasks, students elaborate two separate subtopics: discretization of the surface elliptic hyperboloid of one sheet (ELHY) and spiral surfaces, both connected by key elements circular sections of quadrics. The subtopic's presentation methodology designed for students is conducted by "steps" in 3D structures modeling process, aided by applications and tools of most common engineering software Auto CAD. The applications presented below are created on a base of analytical geometry methods. The first topic - discretization of ELHY surface, i.e. generation of polygonal mesh structure, has a rather simple explanation and graphical presentation (wireframe and surface models) of geometrical procedures, i.e. constructions in opposite to the available analytical geometry solutions. A method of generating the ELHY surface is based on two arbitrary circular sections and one generatrix. The accompanying CAD application, created in Auto lisp, as a tool for discretization has the purpose to enable creative 3D task solution - model of geometric structure ELHY shaped. Three different options/solutions of discretization are offered. The second topic regarding 3D models of spiral surfaces/structures is nowadays very popular in the architecture. Here included spiral surfaces are one which geometric origins are quadrics. Since the term "spiral" is directly connected to the rotation and circle, geometric concept relay again on the circular sections of quadrics. This topic is supported by a Visual basic application (VBA) procedure implemented in Auto CAD. It also requires advanced 3D modeling tools for the design and visualization process of the final product. If comparing two given tasks, the second one is more creative and optional, while the students role in designing is more significant. However, we are sure that both tasks have an important educational value in better understanding of theory regarding quadric surfaces. It is reasonable to expect that in a certain moment (according to the level of programming knowledge) student could create his own software solution, or modify the offered one (application), aimed for such geometric topics. According to the palette of the surfaces included, variety of final "products" - structures and their purposes should be resulted in buildings, furniture, or art design.",
publisher = "Innsbruck University Press, Innsbruck",
journal = "Proceedings of the 16th International Conference on Geometry and Graphics, Innsbruck, August 4-8 2014",
title = "On the role of circular sections of quadric surfaces",
pages = "1081-1075",
url = "https://hdl.handle.net/21.15107/rcub_grafar_1200"
}

Čučaković, A., Dragović, M., Lazarević, L.,& Nedeljković, Đ.. (2014). On the role of circular sections of quadric surfaces. in Proceedings of the 16th International Conference on Geometry and Graphics, Innsbruck, August 4-8 2014
Innsbruck University Press, Innsbruck., 1075-1081.
https://hdl.handle.net/21.15107/rcub_grafar_1200

Čučaković A, Dragović M, Lazarević L, Nedeljković Đ. On the role of circular sections of quadric surfaces. in Proceedings of the 16th International Conference on Geometry and Graphics, Innsbruck, August 4-8 2014. 2014;:1075-1081.
https://hdl.handle.net/21.15107/rcub_grafar_1200 .

Čučaković, Aleksandar, Dragović, Magdalena, Lazarević, Luka, Nedeljković, Đorđe, "On the role of circular sections of quadric surfaces" in Proceedings of the 16th International Conference on Geometry and Graphics, Innsbruck, August 4-8 2014 (2014):1075-1081,
https://hdl.handle.net/21.15107/rcub_grafar_1200 .