Search

Your search keyword '"Bosnić, Zoran"' showing total 228 results
Start Over Author "Bosnić, Zoran"
228 results on '"Bosnić, Zoran"'

7. A machine learning-based risk stratification model for ventricular tachycardia and heart failure in hypertrophic cardiomyopathy

Author

Smole, Tim, Žunkovič, Bojan, Pičulin, Matej, Kokalj, Enja, Robnik-Šikonja, Marko, Kukar, Matjaž, Fotiadis, Dimitrios I., Pezoulas, Vasileios C., Tachos, Nikolaos S., Barlocco, Fausto, Mazzarotto, Francesco, Popović, Dejana, Maier, Lars, Velicki, Lazar, MacGowan, Guy A., Olivotto, Iacopo, Filipović, Nenad, Jakovljević, Djordje G., and Bosnić, Zoran

Published
2021
Full Text
View/download PDF

8. A computational pipeline for data augmentation towards the improvement of disease classification and risk stratification models: A case study in two clinical domains

Author

Pezoulas, Vasileios C., Grigoriadis, Grigoris I., Gkois, George, Tachos, Nikolaos S., Smole, Tim, Bosnić, Zoran, Pičulin, Matej, Olivotto, Iacopo, Barlocco, Fausto, Robnik-Šikonja, Marko, Jakovljevic, Djordje G., Goules, Andreas, Tzioufas, Athanasios G., and Fotiadis, Dimitrios I.

Published
2021
Full Text
View/download PDF

11. A Feature Selection Method Based on Feature Correlation Networks

Author

Savić, Miloš, Kurbalija, Vladimir, Ivanović, Mirjana, Bosnić, Zoran, Hutchison, David, Series editor, Kanade, Takeo, Series editor, Kittler, Josef, Series editor, Kleinberg, Jon M., Series editor, Mattern, Friedemann, Series editor, Mitchell, John C., Series editor, Naor, Moni, Series editor, Pandu Rangan, C., Series editor, Steffen, Bernhard, Series editor, Terzopoulos, Demetri, Series editor, Tygar, Doug, Series editor, Weikum, Gerhard, Series editor, Ouhammou, Yassine, editor, Ivanovic, Mirjana, editor, Abelló, Alberto, editor, and Bellatreche, Ladjel, editor

Published
2017
Full Text
View/download PDF

12. Reliability Estimation of Individual Multi-target Regression Predictions

Author

Jakomin, Martin, Bosnić, Zoran, Hutchison, David, Series editor, Kanade, Takeo, Series editor, Kittler, Josef, Series editor, Kleinberg, Jon M., Series editor, Mattern, Friedemann, Series editor, Mitchell, John C., Series editor, Naor, Moni, Series editor, Pandu Rangan, C., Series editor, Steffen, Bernhard, Series editor, Terzopoulos, Demetri, Series editor, Tygar, Doug, Series editor, Weikum, Gerhard, Series editor, Wagner, Markus, editor, Li, Xiaodong, editor, and Hendtlass, Tim, editor

Published
2017
Full Text
View/download PDF

17. Automatization of the Stream Mining Process

Author

Šubelj, Lovro, Bosnić, Zoran, Kukar, Matjaž, Bajec, Marko, Hutchison, David, editor, Kanade, Takeo, editor, Kittler, Josef, editor, Kleinberg, Jon M., editor, Kobsa, Alfred, editor, Mattern, Friedemann, editor, Mitchell, John C., editor, Naor, Moni, editor, Nierstrasz, Oscar, editor, Pandu Rangan, C., editor, Steffen, Bernhard, editor, Terzopoulos, Demetri, editor, Tygar, Doug, editor, Weikum, Gerhard, editor, Jarke, Matthias, editor, Mylopoulos, John, editor, Quix, Christoph, editor, Rolland, Colette, editor, Manolopoulos, Yannis, editor, Mouratidis, Haralambos, editor, and Horkoff, Jennifer, editor

Published
2014
Full Text
View/download PDF

19. SuperFormer

Author

Zeman, Marko, Faganeli Pucer, Jana, Kononenko, Igor, and Bosnić, Zoran

Subjects
udc:004.8, globoko učenje, superpozicija, superposition, nenehno učenje, deep learning, transformers, continual learning, transformerji
Abstract

One of the biggest challenges in continual learning domains is the tendency of machine learning models to forget previously learned information over time. While overcoming this issue, the existing approaches often exploit large amounts of additional memory and apply model forgetting mitigation mechanisms which substantially prolong the training process. Therefore, we propose a novel SuperFormer method that alleviates model forgetting, while spending negligible additional memory and time. We tackle the continual learning challenges in a learning scenario, where we learn different tasks in a sequential order. We compare our method against several prominent continual learning methods, i.e., EWC, SI, MAS, GEM, PSP, etc. on a set of text classification tasks. We achieve the best average performance in terms of AUROC and AUPRC (0.7% and 0.9% gain on average, respectively) and the lowest training time among all the methods of comparison. On average, our method reduces the total training time by a factor of 5.4-8.5 in comparison to similarly performing methods. In terms of the additional memory, our method is on par with the most memory-efficient approaches.

Published
2023

24. Empirical Analysis of Reliability Estimates for Individual Regression Predictions

Author

Bosnić, Zoran, Kononenko, Igor, Hutchison, David, editor, Kanade, Takeo, editor, Kittler, Josef, editor, Kleinberg, Jon M., editor, Mattern, Friedemann, editor, Mitchell, John C., editor, Naor, Moni, editor, Nierstrasz, Oscar, editor, Pandu Rangan, C., editor, Steffen, Bernhard, editor, Sudan, Madhu, editor, Terzopoulos, Demetri, editor, Tygar, Doug, editor, Vardi, Moshe Y., editor, Weikum, Gerhard, editor, Song, Il-Yeol, editor, Eder, Johann, editor, and Nguyen, Tho Manh, editor

Published
2008
Full Text
View/download PDF

28. Disease Progression of Hypertrophic Cardiomyopathy: Modeling Using Machine Learning

Author

Pičulin, Matej, primary, Smole, Tim, additional, Žunkovič, Bojan, additional, Kokalj, Enja, additional, Robnik-Šikonja, Marko, additional, Kukar, Matjaž, additional, Fotiadis, Dimitrios I, additional, Pezoulas, Vasileios C, additional, Tachos, Nikolaos S, additional, Barlocco, Fausto, additional, Mazzarotto, Francesco, additional, Popović, Dejana, additional, Maier, Lars S, additional, Velicki, Lazar, additional, Olivotto, Iacopo, additional, MacGowan, Guy A, additional, Jakovljević, Djordje G, additional, Filipović, Nenad, additional, and Bosnić, Zoran, additional

Published
2022
Full Text
View/download PDF

30. CAT-Site: Predicting Protein Binding Sites Using a Convolutional Neural Network.

Author

Petrovski, Žan Hafner, Hribar-Lee, Barbara, and Bosnić, Zoran

Subjects
BINDING sites, PROTEIN binding, CARRIER proteins, COMPUTER-assisted drug design, PROTEIN structure
Abstract

Identifying binding sites on the protein surface is an important part of computer-assisted drug design processes. Reliable prediction of binding sites not only assists with docking algorithms, but it can also explain the possible side-effects of a potential drug as well as its efficiency. In this work, we propose a novel workflow for predicting possible binding sites of a ligand on a protein surface. We use proteins from the PDBbind and sc-PDB databases, from which we combine available ligand information for similar proteins using all the possible ligands rather than only a special sub-selection to generalize the work of existing research. After performing protein clustering and merging of ligands of similar proteins, we use a three-dimensional convolutional neural network that takes into account the spatial structure of a protein. Lastly, we combine ligandability predictions for points on protein surfaces into joint binding sites. Analysis of our model's performance shows that its achieved sensitivity is 0.829 , specificity is 0.98 , and F 1 score is 0.517 , and that for 54% of larger and pharmacologically relevant binding sites, the distance between their real and predicted centers amounts to less than 4 Å. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

33. Cardiopulmonary assessment of patients diagnosed with Gaucher’s disease type I

Author

Bjelobrk, Marija, Bjelobrk, Marija, Lakočević, Milan, Damjanović, Svetozar, Petakov, Milan, Petrović, Milan, Bosnić, Zoran, Arena, Ross, Popović, Dejana, Bjelobrk, Marija, Bjelobrk, Marija, Lakočević, Milan, Damjanović, Svetozar, Petakov, Milan, Petrović, Milan, Bosnić, Zoran, Arena, Ross, and Popović, Dejana

Abstract

Background: Understanding the basis of the phenotypic variation in Gaucher's disease (GD) has proven to be challenging for efficient treatment. The current study examined cardiopulmonary characteristics of patients with GD type 1. Methods: Twenty Caucasian subjects (8/20 female) with diagnosed GD type I (GD-S) and 20 age- and sex-matched healthy controls (C), were assessed (mean age GD-S: 32.6 ± 13.1 vs. C: 36.2 ± 10.6, p >.05) before the initiation of treatment. Standard echocardiography at rest was used to assess left ventricular ejection fraction (LVEF) and pulmonary artery systolic pressure (PASP). Cardiopulmonary exercise testing (CPET) was performed on a recumbent ergometer using a ramp protocol. Results: LVEF was similar in both groups (GD-S: 65.1 ± 5.2% vs. C: 65.2 ± 5.2%, p >.05), as well as PAPS (24.1 ± 4.2 mmHg vs. C: 25.5 ± 1.3 mmHg, p >.05). GD-S had lower weight (p <.05) and worse CPET responses compared to C, including peak values of heart rate, oxygen consumption, carbondioxide production (VCO2), end-tidal pressure of CO2, and O2 pulse, as well as HR reserve after 3 min of recovery and the minute ventilation/VCO2 slope. Conclusions: Patients with GD type I have an abnormal CPET response compared to healthy controls likely due to the complex pathophysiologic process in GD that impacts multiple systems integral to the physiologic response to exercise.

Published
2021

38. Disease Progression of Hypertrophic Cardiomyopathy: Modeling Using Machine Learning (Preprint)

Author

Pičulin, Matej, primary, Smole, Tim, additional, Žunkovič, Bojan, additional, Kokalj, Enja, additional, Robnik-Šikonja, Marko, additional, Kukar, Matjaž, additional, Fotiadis, Dimitrios I, additional, Pezoulas, Vasileios C, additional, Tachos, Nikolaos S, additional, Barlocco, Fausto, additional, Mazzarotto, Francesco, additional, Popović, Dejana, additional, Maier, Lars S, additional, Velicki, Lazar, additional, Olivotto, Iacopo, additional, MacGowan, Guy A, additional, Jakovljević, Djordje G, additional, Filipović, Nenad, additional, and Bosnić, Zoran, additional

Published
2021
Full Text
View/download PDF

41. Improving Alzheimer's disease classification by performing data fusion with vascular dementia and stroke data.

Author

Bosnić, Zoran, Bratić, Brankica, Ivanović, Mirjana, Semnic, Marija, Oder, Iztok, Kurbalija, Vladimir, Vujanić Stankov, Tijana, and Bugarski Ignjatović, Vojislava

Subjects
*ALZHEIMER'S disease, *MULTISENSOR data fusion, *VASCULAR dementia, *NOSOLOGY, *DATA fusion (Statistics), *ALZHEIMER'S patients
Abstract

Improvement of prediction accuracy and early detection of the Alzheimer's disease is becoming increasingly important for managing its impact on lives of affected patients. Many machine learning approaches have been applied to support the diagnosis and prediction of this illness. In this paper we propose an approach for improving the Alzheimer's disease classification accuracy by using data fusion of several independent clinical datasets. Data fusion was performed twofold: 1) by enriching attributes of the base dataset with the attributes of the secondary dataset and 2) by enriching the examples set of the base dataset with the examples of the secondary dataset. In both cases the missing values (for newly added attributes and/or examples) were predicted by using linear regression for numeric and naive Bayes classifier for nominal attributes. We experimented on three data sources: on a dataset of Alzheimer's disease-impaired patients, on a dataset of patients with vascular dementia, and on a dataset of patients who have been affected by a stroke. We fused these datasets with different data fusion approaches and analysed the improvement in classification accuracy as well as the quality of the fused attributes. The experiments indicated that we obtained an increase of classification accuracy on the fused dataset compared with the accuracy obtained from individual dataset. [ABSTRACT FROM AUTHOR]

Published
2021
Full Text
View/download PDF

42. TEALEAF - Academic book: (Erasmus + Project 2014-FR01-KA201-008559)

Author

Krnel, Dušan, Bajd, Barbara, and Bosnić, Zoran

Subjects
naravoslovna vzgoja in izobraževanje, ComputingMilieux_COMPUTERSANDEDUCATION, science education
Abstract

This book is one of the output-results of a collaborative research effort between researchers from the various partner institutions involved in the project. The aim of the project was to improve both learning and teaching related to biodiversity using serious games in classrooms (so-called apps) and to highlight the need to think critically about the pedagogical facets and potential of apps. One specific aspect of the project was the inclusion of a number of science teachers and students in the process. These two groups served as a source of data that was collected over the course of various activities. An analysis of this iterative process is published as a body of research papers herein.

Published
2017

45. Поређење скупова података помоћу графова

Author

Luković, Ivan, Ristić, Sonja, Gilezan, Silvia, Bosnić, Zoran, Kovačević, Aleksandar, Ivančević, Vladimir, Luković, Ivan, Ristić, Sonja, Gilezan, Silvia, Bosnić, Zoran, Kovačević, Aleksandar, and Ivančević, Vladimir

Abstract

За потребе поређења скупова података осмишљен је приступ поређењу који се заснива на употреби графова. У овом приступу развијене су две врсте графовских представа: представе вредности које описују скуп података и представе разлика које описују разлике између две представе вредности. У испитивањима приступа над синтетичким и реалним скуповима података, показано је да је кроз визуално истраживање представа разлика и примену помоћних поступака обраде могуће уочити корисне обрасце који приказују разлике између представа вредности, а посредно и између скупова података описаних путем ових представа вредности., Za potrebe poređenja skupova podataka osmišljen je pristup poređenju koji se zasniva na upotrebi grafova. U ovom pristupu razvijene su dve vrste grafovskih predstava: predstave vrednosti koje opisuju skup podataka i predstave razlika koje opisuju razlike između dve predstave vrednosti. U ispitivanjima pristupa nad sintetičkim i realnim skupovima podataka, pokazano je da je kroz vizualno istraživanje predstava razlika i primenu pomoćnih postupaka obrade moguće uočiti korisne obrasce koji prikazuju razlike između predstava vrednosti, a posredno i između skupova podataka opisanih putem ovih predstava vrednosti., In order to support data set comparison, a graph-based approach to comparison was devised. In this approach, two types of graph-based representations were introduced: value representations that represent a data set and difference representations that represent differences between two value representations. The results of approach evaluations on synthetic and real data sets indicate that, by visually exploring difference representations and applying auxiliary procedures, it is possible to discover useful patterns which describe differences between two value representations and, consequently, differences between the data sets corresponding to the value representations.

Published
2017

Catalog

Books, media, physical & digital resources
See catalog results