Željka Beljkaš
Željka Beljkaš has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Snežana Rutešić
University of Montenegro,Podgorica,Faculty of Civil Engineering,Montenegro
3 shared publications - Ivona Krulanovic
Agency for Design and Planning, Ltd
2 shared publications - Meri Cvetkovska
Ss Cyril and Methodius University in Skopje
2 shared publications Miloš Knežević
2 shared publications- Miloš Knežević
University of Montenegro
2 shared publications - Biljana Ivanović
Faculty of Civil Engineering, University of Montenegro
1 shared publication
Latest Publications
- Open Access
- 1 June 2026
- Published by University of Banja Luka, Faculty of Architecture, Civil Engineering and Geodesy
- Vol. 17 (1) , 878-887
APPLICATION OF AI AND BIM IN THE DESIGN, CONSTRUCTION, AND MANAGEMENT OF BRIDGES – A LITERATURE REVIEW
Bridges are critical components of transportation infrastructure, requiring efficient design, construction, and management throughout their entire life cycle. Recent advances in digital technologies have significantly influenced bridge engineering, particularly through the adoption of Building Information Modeling (BIM) and Artificial Intelligence (AI). BIM enables integrated information management and improved coordination across different project phases, while AI provides advanced tools for data analysis, optimization, and decision-making. This paper presents a comprehensive review of the existing literature on the application of BIM and AI in bridge design, construction, and operation. The review covers the use of BIM in geometric modeling, construction planning, and asset management, as well as AI-based methods for structural analysis, damage detection, and predictive maintenance. Furthermore, the integration of BIM and AI, including the development of digital twins for bridges, is discussed. Key challenges, such as data availability, interoperability, and lack of standardization, are also identified. The findings highlight the significant potential of combining BIM and AI to enhance the efficiency, safety, and sustainability of bridge infrastructure and outline directions for future research.
- 1 June 2026
- Published by University of Banja Luka, Faculty of Architecture, Civil Engineering and Geodesy
- Vol. 17 (1) , 878-887
Open AccessAPPLICATION OF AI AND BIM IN THE DESIGN, CONSTRUCTION, AND MANAGEMENT OF BRIDGES – A LITERATURE REVIEW
Bridges are critical components of transportation infrastructure, requiring efficient design, construction, and management throughout their entire life cycle. Recent advances in digital technologies have significantly influenced bridge engineering, particularly through the adoption of Building Information Modeling (BIM) and Artificial Intelligence (AI). BIM enables integrated information management and improved coordination across different project phases, while AI provides advanced tools for data analysis, optimization, and decision-making. This paper presents a comprehensive review of the existing literature on the application of BIM and AI in bridge design, construction, and operation. The review covers the use of BIM in geometric modeling, construction planning, and asset management, as well as AI-based methods for structural analysis, damage detection, and predictive maintenance. Furthermore, the integration of BIM and AI, including the development of digital twins for bridges, is discussed. Key challenges, such as data availability, interoperability, and lack of standardization, are also identified. The findings highlight the significant potential of combining BIM and AI to enhance the efficiency, safety, and sustainability of bridge infrastructure and outline directions for future research.
- Open Access
- 1 June 2026
- Published by University of Banja Luka, Faculty of Architecture, Civil Engineering and Geodesy
- Vol. 17 (1) , 982-992
CONSTRUCTION WASTE MANAGEMENT PLAN FOR REHABILITATION OF THE ĐURĐEVIĆA TARA BRIDGE
The rehabilitation and reconstruction of the Đurđevića Tara Bridge, a structure of national importance, located within a protected area, the UNESCO Biosphere Reserve, inevitably generates various types of construction waste. This paper presents the waste management approach, focusing on the identification, source separation, temporary storage, and transport of inert and hazardous waste. The plan emphasizes minimizing the impact on the sensitive Tara Canyon ecosystem, promoting recycling and the exclusive use of authorized operators for disposal. However, the plan relies on local capacity and digital systems assumptions; failure risks environmental contamination and legal penalties.
- 1 June 2026
- Published by University of Banja Luka, Faculty of Architecture, Civil Engineering and Geodesy
- Vol. 17 (1) , 982-992
Open AccessCONSTRUCTION WASTE MANAGEMENT PLAN FOR REHABILITATION OF THE ĐURĐEVIĆA TARA BRIDGE
The rehabilitation and reconstruction of the Đurđevića Tara Bridge, a structure of national importance, located within a protected area, the UNESCO Biosphere Reserve, inevitably generates various types of construction waste. This paper presents the waste management approach, focusing on the identification, source separation, temporary storage, and transport of inert and hazardous waste. The plan emphasizes minimizing the impact on the sensitive Tara Canyon ecosystem, promoting recycling and the exclusive use of authorized operators for disposal. However, the plan relies on local capacity and digital systems assumptions; failure risks environmental contamination and legal penalties.
- Open Access
- 1 January 2025
- Published by Wiley in Advances in Civil Engineering
- Vol. 2025 (1)
Data‐Driven Water Demand Prediction: Evaluating Artificial Intelligence Models
Water resource management is crucial in contemporary society due to climate change and water scarcity. These challenges are further exacerbated by rapid urbanization, which leads to an increase in water demand in cities caused by factors such as population growth, industrialization, densification, changing consumption patterns, supply network losses, and climate variability. Accurately predicting water demand is vital for sustainable planning. Various techniques have been developed to estimate water demand with varying degrees of accuracy. In this research, three techniques are used: artificial neural networks (ANNs), random forest (RF), and support vector regression (SVR). The results indicate that artificial intelligence methods demonstrate strong potential for enhancing prediction accuracy in the field of water resources management. All models exhibit high accuracy, with ANN showing the best overall performance.
- 1 January 2025
- Published by Wiley in Advances in Civil Engineering
- Vol. 2025 (1)
Open AccessData‐Driven Water Demand Prediction: Evaluating Artificial Intelligence Models
Water resource management is crucial in contemporary society due to climate change and water scarcity. These challenges are further exacerbated by rapid urbanization, which leads to an increase in water demand in cities caused by factors such as population growth, industrialization, densification, changing consumption patterns, supply network losses, and climate variability. Accurately predicting water demand is vital for sustainable planning. Various techniques have been developed to estimate water demand with varying degrees of accuracy. In this research, three techniques are used: artificial neural networks (ANNs), random forest (RF), and support vector regression (SVR). The results indicate that artificial intelligence methods demonstrate strong potential for enhancing prediction accuracy in the field of water resources management. All models exhibit high accuracy, with ANN showing the best overall performance.
- Open Access
- 12 June 2024
- Published by University of Banja Luka, Faculty of Architecture, Civil Engineering and Geodesy
- Vol. 16 (1) , 547-554
ROUTE OF SOUTH SECTION OF BUDVA BYPASS - REVIEW OF PRELIMINARY DESIGN OF ORGANIZATION AND TECHNOLOGY CONSTRUCTION
The Budva bypass, spanning approximately 30 kilometers, is divided into three distinct sections: North, Middle, and South. The Terms of reference required the preparation of a Preliminary design for the construction elements of all structures along the section and route. The Southern section, which is the subject of this article, begins at the end of the Middle section in Vrijesno. The route of the Southern Section goes through the hilly hinterland above the Budva coast, from Kamenovo to Petrovac. In Petrovac, it is connected to the main road M-2 Petrovac-Sotonići-Virpazar via the intersection "Petrovac". The total length of the Southern section is 8.56km. There are five bridges and one tunnel in this route. There are, also, retaining structures and slope protection, conection routes and deviations, one interchange, and noise protection walls on this section of bypass. In this article, parts of Preliminary Design of organization and technology construction are showned. Network plan structure, approximate estimation of the duration of the works, approximate cost estimation, and approximate cash flow estimation during construction are presented.
- 12 June 2024
- Published by University of Banja Luka, Faculty of Architecture, Civil Engineering and Geodesy
- Vol. 16 (1) , 547-554
Open AccessROUTE OF SOUTH SECTION OF BUDVA BYPASS - REVIEW OF PRELIMINARY DESIGN OF ORGANIZATION AND TECHNOLOGY CONSTRUCTION
The Budva bypass, spanning approximately 30 kilometers, is divided into three distinct sections: North, Middle, and South. The Terms of reference required the preparation of a Preliminary design for the construction elements of all structures along the section and route. The Southern section, which is the subject of this article, begins at the end of the Middle section in Vrijesno. The route of the Southern Section goes through the hilly hinterland above the Budva coast, from Kamenovo to Petrovac. In Petrovac, it is connected to the main road M-2 Petrovac-Sotonići-Virpazar via the intersection "Petrovac". The total length of the Southern section is 8.56km. There are five bridges and one tunnel in this route. There are, also, retaining structures and slope protection, conection routes and deviations, one interchange, and noise protection walls on this section of bypass. In this article, parts of Preliminary Design of organization and technology construction are showned. Network plan structure, approximate estimation of the duration of the works, approximate cost estimation, and approximate cash flow estimation during construction are presented.
- Open Access
- 1 January 2024
- Published by Centre for Evaluation in Education and Science (CEON/CEES) in Građevinski materijali i konstrukcije
- Vol. 67 (2) , 97-103
The impact of pier height on the construction costs of integral road bridges: An application of artificial intelligence
There are multiple definitions for integral road bridges. One of them explains that these are single-span bridges without expansion joints or bearings at the discontinuity locations. In terms of durability and maintenance, discontinuity locations are considered to be construction parts most exposed to damage in this type of structure. Engineers' efforts to lower maintenance costs and extend the durability of structures have led to the emergence of integral bridges. Early assessment of construction costs is crucial in determining the justification for constructing such structures, as it allows both the investor and the contractor to gauge their involvement in the project's implementation. The construction costs can be determined based on the structure characteristics. One of the major characteristics of integral bridges is the height of their piers. This paper examines how the pier height affects the construction costs of integral road bridges. The prognostic model in the Python 3.7.6 software package applies neural networks to determine the impact of pier height. According to the research, the pier height accounts for up to 20% of the total construction costs of integral road bridges.
- 1 January 2024
- Published by Centre for Evaluation in Education and Science (CEON/CEES) in Građevinski materijali i konstrukcije
- Vol. 67 (2) , 97-103
Open AccessThe impact of pier height on the construction costs of integral road bridges: An application of artificial intelligence
There are multiple definitions for integral road bridges. One of them explains that these are single-span bridges without expansion joints or bearings at the discontinuity locations. In terms of durability and maintenance, discontinuity locations are considered to be construction parts most exposed to damage in this type of structure. Engineers' efforts to lower maintenance costs and extend the durability of structures have led to the emergence of integral bridges. Early assessment of construction costs is crucial in determining the justification for constructing such structures, as it allows both the investor and the contractor to gauge their involvement in the project's implementation. The construction costs can be determined based on the structure characteristics. One of the major characteristics of integral bridges is the height of their piers. This paper examines how the pier height affects the construction costs of integral road bridges. The prognostic model in the Python 3.7.6 software package applies neural networks to determine the impact of pier height. According to the research, the pier height accounts for up to 20% of the total construction costs of integral road bridges.
- Open Access
Financial and Socio-Economic Effects of Investment in the Context of Dog Population Management
The modern world faces serious challenges associated with the presence of stray dogs on the streets, especially in urban areas. Vardar Planning Region in North Macedonia, which consists of nine municipalities, experiences such challenges. According to current reports, the number of stray dogs on the streets of cities in this region has increased, which has resulted in an increase in the number of dog attacks on residents. As the existing capacities are small in the registered shelters, we considered the possibility of building a new shelter for stray dogs to meet the needs of this region. The goal of our paper is the evaluation of the financial and socio-economic justifications for the construction of a shelter for stray dogs in the Vardar Planning Region (VPR). The results of the financial justification analysis show that the project does not provide satisfactory financial results. Namely, the Financial Net Present Value (FNPV) is negative, with a value of EUR 75,291. The Financial Internal Rate of Return (FIRR) is 0.57%, lower than the discount rate, which is not acceptable for a private investor. The Financial Benefit–Cost Ratio (FB/CR) of this project is 0.925, suggesting that the total discounted costs are greater than the total discounted revenues. On the other hand, the expected socio-economic benefits from this project are multifaceted, including savings in stray dog bite costs, savings in the cost of traffic accidents caused by stray dogs, and savings in the treatment of diseases caused by stray dogs. The results of the economic analysis show that this investment has full socio-economic justification and that it should be implemented. The Economic Net Present Value (ENPV) is positive and amounts to EUR 789,916. The Economic Internal Rate of Return (EIRR) is 25.94% and the Economic Benefit–Cost Ratio (EB/CR) amounts to 1.90, i.e., greater than 1. The results of the sensitivity analysis also confirm the justification for the realization of this project.
Open AccessFinancial and Socio-Economic Effects of Investment in the Context of Dog Population Management
The modern world faces serious challenges associated with the presence of stray dogs on the streets, especially in urban areas. Vardar Planning Region in North Macedonia, which consists of nine municipalities, experiences such challenges. According to current reports, the number of stray dogs on the streets of cities in this region has increased, which has resulted in an increase in the number of dog attacks on residents. As the existing capacities are small in the registered shelters, we considered the possibility of building a new shelter for stray dogs to meet the needs of this region. The goal of our paper is the evaluation of the financial and socio-economic justifications for the construction of a shelter for stray dogs in the Vardar Planning Region (VPR). The results of the financial justification analysis show that the project does not provide satisfactory financial results. Namely, the Financial Net Present Value (FNPV) is negative, with a value of EUR 75,291. The Financial Internal Rate of Return (FIRR) is 0.57%, lower than the discount rate, which is not acceptable for a private investor. The Financial Benefit–Cost Ratio (FB/CR) of this project is 0.925, suggesting that the total discounted costs are greater than the total discounted revenues. On the other hand, the expected socio-economic benefits from this project are multifaceted, including savings in stray dog bite costs, savings in the cost of traffic accidents caused by stray dogs, and savings in the treatment of diseases caused by stray dogs. The results of the economic analysis show that this investment has full socio-economic justification and that it should be implemented. The Economic Net Present Value (ENPV) is positive and amounts to EUR 789,916. The Economic Internal Rate of Return (EIRR) is 25.94% and the Economic Benefit–Cost Ratio (EB/CR) amounts to 1.90, i.e., greater than 1. The results of the sensitivity analysis also confirm the justification for the realization of this project.
- Open Access
- 12 April 2021
- Published by MDPI AG in Applied Sciences
- Vol. 11 (8) , 3429
Neural Networks—Deflection Prediction of Continuous Beams with GFRP Reinforcement
Deflections on continuous beams with glass fiber-reinforced polymer (GFRP) reinforcement are calculated in accordance with the appropriate standards (ACI 440.1R-15, CSA S806-12). However, experimental research provides results which differ from the values calculated pursuant to the standards, particularly when it comes to continuous beams. Machine learning methods can be applied for predicting a deflection level on continuous beams with GFRP (glass fiber-reinforced polymer) reinforcement and loaded with a concentrated load. This paper presents research on using artificial neural networks for deflection estimation and an optimal prediction model choice. It was necessary to first develop a database, in order to train the neural network. The database was formed based on the results of the experimental research on continuous beams with GFRP reinforcement. Using the best trained neural network model, high accuracy was obtained in estimating deflection, expressed over the mean absolute percentage error, 9.0%. This result indicates a high level of reliability in the prediction of deflection with the help of artificial neural networks.
- 12 April 2021
- Published by MDPI AG in Applied Sciences
- Vol. 11 (8) , 3429
Open AccessNeural Networks—Deflection Prediction of Continuous Beams with GFRP Reinforcement
Deflections on continuous beams with glass fiber-reinforced polymer (GFRP) reinforcement are calculated in accordance with the appropriate standards (ACI 440.1R-15, CSA S806-12). However, experimental research provides results which differ from the values calculated pursuant to the standards, particularly when it comes to continuous beams. Machine learning methods can be applied for predicting a deflection level on continuous beams with GFRP (glass fiber-reinforced polymer) reinforcement and loaded with a concentrated load. This paper presents research on using artificial neural networks for deflection estimation and an optimal prediction model choice. It was necessary to first develop a database, in order to train the neural network. The database was formed based on the results of the experimental research on continuous beams with GFRP reinforcement. Using the best trained neural network model, high accuracy was obtained in estimating deflection, expressed over the mean absolute percentage error, 9.0%. This result indicates a high level of reliability in the prediction of deflection with the help of artificial neural networks.
- Open Access
- 1 April 2021
- Published by Croatian Association of Civil Engineers in Journal of the Croatian Association of Civil Engineers
- Vol. 73 (03) , 265-273
Use of artificial intelligence for estimating cost of integral bridges
- 1 April 2021
- Published by Croatian Association of Civil Engineers in Journal of the Croatian Association of Civil Engineers
- Vol. 73 (03) , 265-273
Open AccessUse of artificial intelligence for estimating cost of integral bridges
- Open Access
- 1 January 2020
- Published by Wiley in Advances in Civil Engineering
- Vol. 2020 (1)
Application of Artificial Intelligence for the Estimation of Concrete and Reinforcement Consumption in the Construction of Integral Bridges
Estimation of basic material consumption in civil engineering is very important in the initial phases of project implementation. Its importance is reflected in the impact of material quantities on forming the prices of individual positions, hence on forming the total cost of construction. The construction companies use the estimate of material quantity, among other things, as a base to make a bid on the market. The precision of the offer, taking into account the overall conditions of the business realization, directly influences the profit that the company can make on a specific project. In the early stages of project implementation, there are not enough available data, especially when it comes to the data needed to estimate material consumption, and therefore, the accuracy of material consumption estimation in the early stages of project realization is smaller. The paper presents the research on the use of artificial intelligence for the estimation of concrete and reinforcement consumption and the selection of optimal models for estimation. The estimation model was developed by using artificial neural networks. The best artificial neural network model showed high accuracy in material consumption estimation expressed as the mean absolute percentage error, 8.56% for concrete consumption estimate and 17.31% for reinforcement consumption estimate.
- 1 January 2020
- Published by Wiley in Advances in Civil Engineering
- Vol. 2020 (1)
Open AccessApplication of Artificial Intelligence for the Estimation of Concrete and Reinforcement Consumption in the Construction of Integral Bridges
Estimation of basic material consumption in civil engineering is very important in the initial phases of project implementation. Its importance is reflected in the impact of material quantities on forming the prices of individual positions, hence on forming the total cost of construction. The construction companies use the estimate of material quantity, among other things, as a base to make a bid on the market. The precision of the offer, taking into account the overall conditions of the business realization, directly influences the profit that the company can make on a specific project. In the early stages of project implementation, there are not enough available data, especially when it comes to the data needed to estimate material consumption, and therefore, the accuracy of material consumption estimation in the early stages of project realization is smaller. The paper presents the research on the use of artificial intelligence for the estimation of concrete and reinforcement consumption and the selection of optimal models for estimation. The estimation model was developed by using artificial neural networks. The best artificial neural network model showed high accuracy in material consumption estimation expressed as the mean absolute percentage error, 8.56% for concrete consumption estimate and 17.31% for reinforcement consumption estimate.
- Open Access
- 21 January 2019
- Published by IOP Publishing in IOP Conference Series: Earth and Environmental Science
- Vol. 222 (1) , 012021
Application of Fuzzy Logic on Selection of Contractors for Construction of High Rise Buildings
Selection process of a construction contractor is highly important and successful implementation of a project and realization of sustainability are largely dependent on it. Computer programs - expert systems - may be used to help the employer or his consultants in the process of best tenderer selection. This paper presents a new expert system based on the implementation of fuzzy logic as an aid in selecting a contractor for construction of high rise buildings.
- 21 January 2019
- Published by IOP Publishing in IOP Conference Series: Earth and Environmental Science
- Vol. 222 (1) , 012021
Open AccessApplication of Fuzzy Logic on Selection of Contractors for Construction of High Rise Buildings
Selection process of a construction contractor is highly important and successful implementation of a project and realization of sustainability are largely dependent on it. Computer programs - expert systems - may be used to help the employer or his consultants in the process of best tenderer selection. This paper presents a new expert system based on the implementation of fuzzy logic as an aid in selecting a contractor for construction of high rise buildings.