Đorđe Nedeljković

Đorđe Nedeljković


Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
22 March 2023 in Sustainability
Verified
Journal Article
Open access
PDF file
NSNevena Simić
Nevena Simić
NINenad Ivanišević
Nenad Ivanišević
ĐNĐorđe Nedeljković
Đorđe Nedeljković
Aleksandar SenićAleksandar Senić
Aleksandar Senić
ZSZoran Stojadinovic
Zoran Stojadinovic
MIMarija Zoran Ivanovic
Marija Zoran Ivanovic
Cost estimates in the early stages of project development are essential for making the right decisions, but they are a huge challenge and risk for owners and potential contractors due to limited information about the characteristics of a future highway project. Whereas 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 determine cost drivers (CDs) that have a high influence on highway-construction costs and require 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 reasonable cost-estimation accuracy can be achieved with relatively low effort for three CDs for the owners’ perspective and five 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, whereas contractors are more concerned 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 contractors in intelligent decision-making in the early stages of future highway-construction projects.

1 November 2017 in Journal of Computing in Civil Engineering
Verified
Journal Article
Closed access
ĐNĐorđe Nedeljković
Đorđe Nedeljković
MKMiloš Kovačević
Miloš Kovačević
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.

26 August 2026 in Bulletin of Earthquake Engineering
Verified
Journal Article
Open access
PDF file
MKMiloš Kovačević
Miloš Kovačević
FĐFilip Đorđević
Filip Đorđević
ĐNĐorđe Nedeljković
Đorđe Nedeljković
MNMladen Nikolic
Mladen Nikolic
Josip AtalićJosip Atalić
Josip Atalić
Marko MarinkovićMarko Marinković
Marko Marinković
Rapid and accurate post-earthquake damage assessment is critical for effective disaster response and enabling sustainable community recovery. This study addresses the urgent need for timely and precise quantification of earthquake-induced building damage, moving beyond simple detection, to inform actionable engineering decisions. It explores AI-driven image classification to expedite damage evaluation by identifying damaged buildings from post-disaster photos much faster than conventional methods. A total of 154,380 indoor image patches (224 × 224 pixels) from photos of buildings affected by the 2020 M6.4 Petrinja, Croatia earthquake, were compiled. These patches include both close-up cracks and wider building context. Two convolutional neural networks (ResNet-18 and ConvNeXt-Tiny) were trained on the patch dataset for binary damage classification. Additionally, large vision-language model (VLM) Gemma 3 27B was evaluated in a zero-shot binary classification setting by providing it with a descriptive prompt to classify each patch as damaged or undamaged. ConvNeXt-Tiny achieved the highest performance, with a macro F1-score of 0.849 and a damaged-class F1-score of 0.731, slightly outperforming ResNet-18. Gemma 3 27B achieved a macro F1-score of approximately 0.6 but a damaged-class F1-score of 0.366, with many false positives. Integrating such a granular approach into rapid loss assessment frameworks significantly enhances decision-making capabilities and post-disaster recovery efforts, providing a more detailed understanding of structural integrity across affected areas.