Petar Vračar

ORCID: 0000-0003-1275-8057
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Sports Analytics and Performance
  • Sports Performance and Training
  • Data Visualization and Analytics
  • Smart Agriculture and AI
  • Heart Failure Treatment and Management
  • Physical Education and Pedagogy
  • Industrial Vision Systems and Defect Detection
  • Natural Language Processing Techniques
  • Infrastructure Maintenance and Monitoring
  • Stock Market Forecasting Methods
  • Remote Sensing in Agriculture
  • 3D Surveying and Cultural Heritage
  • Rough Sets and Fuzzy Logic
  • Blood Pressure and Hypertension Studies
  • Sports, Gender, and Society
  • Explainable Artificial Intelligence (XAI)
  • Cardiovascular Health and Disease Prevention
  • Regional Development and Management Studies
  • Semantic Web and Ontologies
  • Imbalanced Data Classification Techniques
  • Acute Ischemic Stroke Management
  • Cardiovascular Function and Risk Factors
  • Cerebrovascular and Carotid Artery Diseases
  • Logic, Reasoning, and Knowledge
  • Video Analysis and Summarization

University of Ljubljana
2010-2025

10.1016/j.eswa.2015.09.004 article EN Expert Systems with Applications 2015-09-12

Abstract The International Basketball Federation (FIBA) recently introduced major rule changes that came into effect with the 2010/11 season. Most notably, moving three-point arc and changing shot-clock. purpose of this study was to investigate quantify how these affect game performance top-level European basketball players. In order better understand changes, we also investigated past seasons showed presence several trends, even in absence significant changes. A large set statistics for 10...

10.2478/hukin-2013-0058 article EN Journal of Human Kinetics 2013-09-01

Introduction Heart failure (HF) is a complex clinical syndrome. Accurate risk stratification and early diagnosis of HF are challenging as its signs symptoms non-specific. We propose to address this global challenge by developing the STRATIFYHF artificial intelligence-driven decision support system (DSS), which uses novel analytical methods in determining risk, prognosis HF. The primary aim present study collect prospective data validate DSS (in terms diagnostic accuracy, sensitivity...

10.1136/bmjopen-2024-091793 article EN cc-by-nc-nd BMJ Open 2025-01-01

One of the most common causes human death is stroke, which can be caused by carotid bifurcation stenosis. In our work, we aim at proposing a prototype medical expert system that could significantly aid experts to detect hemodynamic abnormalities (increased artery wall shear stress). Based on acquired simulated data, apply several methodologies for1) predicting magnitudes and locations maximum stress in artery, 2) estimating reliability computed predictions, 3) providing user-friendly...

10.1109/titb.2011.2164546 article EN IEEE Transactions on Information Technology in Biomedicine 2011-08-16

We describe a method for learning and recognizing windows as basic structural elements of fa?ades organizing them into interpretable models building fa?ades. The segments an input image hierarchical structure window candidates. candidates are used to create likelihood map locations that is explained by fa?ade model based on formal grammar. use look-ahead greedy search in the grammar derivation space select (sub)optimal model. Empirical evaluation results reveal that, average, generated...

10.2298/csis150222062v article EN cc-by-nc-nd Computer Science and Information Systems 2015-12-03

Arterial geometry variability is present both within and across individuals. To analyze the influence of geometric parameters on maximal wall shear stress (MWSS) in human carotid artery bifurcation, computer simulations were run to generate data pertaining this phenomenon. In our work we evaluate various prediction models for modeling relationship between bifurcation MWSS. The results revealed highest potential using neural network model task. achieved generated explanations represent...

10.1109/itab.2010.5687679 article EN 2010-11-01

The problem of detecting objects and their movements in sensor data is crucial importance providing safe navigation through both indoor outdoor environments for the visually impaired. In our setting we use depth-sensor obtained from a simulator inductive logic programming (ILP), subfield machine learning that deals with concept descriptions, to learn how detect borders, find border nearest some point interest, correspondence time. We demonstrate ILP can be used tackle this an incremental...

10.1109/icat.2015.7340498 article EN 2015-10-01

10.1007/s10115-019-01361-2 article EN Knowledge and Information Systems 2019-04-13
Coming Soon ...