Mihaela Vranić

Prof. Dr. Mihaela Vranić

University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, Zagreb, Grad, Croatia
orcid

Research Focus & Metrics

Academic Career Length

20Years (2007-Present)

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

Representative Publications

View All Publications
29 August 2022 in Applied Sciences
Verified
Journal Article
Open access
PDF file
AŠAna Šarčević
Ana Šarčević
DPDamir Pintar
Damir Pintar
Mihaela VranićMihaela Vranić
Mihaela Vranić
AKAgneza Krajna
Agneza Krajna
Global networking, growing computer infrastructure complexity and the ongoing migration of many private and business aspects to the electronic domain commonly mandate using cutting-edge technologies based on data analysis, machine learning, and artificial intelligence to ensure high levels of network and information system security. Transparency is a major barrier to the deployment of black box intelligent systems in high-risk domains, such as the cybersecurity domain, with the problem getting worse as machine learning models increase in complexity. In this research, explainable machine learning is used to extract information from the CIC-IDS2017 dataset and to critically contrast the knowledge attained by analyzing if–then decision tree rules with the knowledge attained by the SHAP approach. The paper compares the challenges of the knowledge extraction using the SHAP method and the if–then decision tree rules, providing guidelines regarding different approaches suited to specific situations.

1 June 2007
Verified
Conference Paper
Closed access
Mihaela VranićMihaela Vranić
Mihaela Vranić
DPDamir Pintar
Damir Pintar
ZSZ. Skocir
Z. Skocir
Modern technologies allow storage of large amounts of raw data which invariably contains usable information not yet discovered. Machine learning and data mining give us techniques which can be used to analyze that data and uncover previously unknown rules and associations, hidden knowledge which once acquired -and properly interpreted -can be used in multitude of ways. Even though data mining has mostly been used by the marketing field, lately it is not uncommon to use machine learning techniques in other environments. This paper presents how data mining algorithms and techniques can be used in the academic community to potentially improve some aspects of education quality.

12 December 2025 in Modelling
Verified
Journal Article
Open access
PDF file
RLRiko Luša
Riko Luša
DPDamir Pintar
Damir Pintar
Mihaela VranićMihaela Vranić
Mihaela Vranić
Graph learning is well suited to modeling relationships among communicating entities in network intrusion detection. However, the resulting models are frequently difficult to interpret, in contrast to many classical approaches that offer more transparent reasoning. This work integrates SHapley Additive exPlanations with temporal, edge-aware GNN based on GraphSAGE architecture to deliver an explainable, inductive intrusion detection model for NetFlow data named TE-G-SAGE. Using the NF-UNSW-NB15-v3 dataset, flow data are transformed into temporal communication graphs where flows are directed edges and endpoints are nodes. The model learns relational patterns across two-hop neighborhoods and achieves strong recall under chronological evaluation, outperforming a GCN baseline and recovering more attacks than a tuned XGBoost model. SHAP is adapted to graph inputs through a feature attribution on the two-hop computational subgraph, producing global and local explanations that align with analyst reasoning. The resulting attributions identify key discriminative features while revealing shared indicators that explain cross-class confusion. The research shows that temporal validation, inductive graph modeling, and Shapley-based attribution can be combined into a transparent, reproducible intrusion detection framework suited for operational use.

13 May 2021 in Applied Sciences
Verified
Journal Article
Open access
PDF file
AŠAna Šarčević
Ana Šarčević
DPDamir Pintar
Damir Pintar
Mihaela VranićMihaela Vranić
Mihaela Vranić
AGAnte Gojsalić
Ante Gojsalić
The prediction of sport event results has always drawn attention from a vast variety of different groups of people, such as club managers, coaches, betting companies, and the general population. The specific nature of each sport has an important role in the adaption of various predictive techniques founded on different mathematical and statistical models. In this paper, a common approach of modeling sports with a strongly defined structure and a rigid scoring system that relies on an assumption of independent and identical point distributions is challenged. It is demonstrated that such models can be improved by introducing dynamics into the match models in the form of sport momentums. Formal mathematical models for implementing these momentums based on conditional probability and empirical Bayes estimation are proposed, which are ultimately combined through a unifying hybrid approach based on the Monte Carlo simulation. Finally, the method is applied to real-life volleyball data demonstrating noticeable improvements over the previous approaches when it comes to predicting match outcomes. The method can be implemented into an expert system to obtain insight into the performance of players at different stages of the match or to study field scenarios that may arise under different circumstances.

10 June 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
RPRoberto Penco
Roberto Penco
DPDamir Pintar
Damir Pintar
Mihaela VranićMihaela Vranić
Mihaela Vranić
MŠMarko Šoštarić
Marko Šoštarić
Constraint satisfaction problems (CSPs) are widely used in domains such as product configuration, scheduling, and resource allocation. However, formulating constraint models remains a significant challenge that often requires specialized expertise in constraint programming (CP). This study introduces the Automatic Constraint Model Generator (ACMG), a novel framework that leverages fine-tuned large language models (LLMs) to automate the translation of natural language problem descriptions into formal CSP models. The ACMG employs a multi-step process involving semantic entity extraction, constraint model generation, and iterative validation using the MiniZinc solver. Our approach achieves state-of-the-art (SOTA) or near-SOTA results, demonstrating the viability of LLMs in simplifying the adoption of CP. Its key contributions include a high-quality dataset for fine-tuning, a modular architecture with specialized LLM components, and empirical validation which shows its promising results for complex configuration tasks. By bridging the gap between natural language and formal constraint models, the ACMG significantly lowers the barrier to CP, making it more accessible to non-experts while maintaining a high level of robustness for industrial applications.

2 October 2017 in Automatika
Verified
Journal Article
Open access
LHLuka Humski
Luka Humski
DPDamir Pintar
Damir Pintar
Mihaela VranićMihaela Vranić
Mihaela Vranić
In the last few decades sociologists were trying to explain human behaviour by analysing social networks, which requires access to data about interpersonal relationships. This represented a big obstacle in this research field until the emergence of online social networks (OSNs), which vastly facilitated the process of collecting such data. Nowadays, by crawling public profiles on OSNs, it is possible to build a social graph where “friends” on OSN become represented as connected nodes. OSN connection does not necessarily indicate a close real-life relationship, but using OSN interaction records may reveal real-life relationship intensities, a topic which inspired a number of recent researches. Still, published research currently lacks an extensive exploratory analysis of OSN interaction records, i.e. a comprehensive overview of users’ interaction via different ways of OSN interaction. In this paper, we provide such an overview by leveraging results of conducted extensive social experiment which managed to collect records for over 3200 Facebook users interacting with over 1,400,000 of their friends. Our exploratory analysis focuses on extracting population distributions and correlation parameters for 13 interaction parameters, providing valuable insight into OSN interaction for future researches aimed at this field of study.