REPOSITORY > LATEST

Latest Academic Works

Identification of hearth sounds for the analysis of cardiac pathology using machine learning

Author(s): David Susič (Author), Anton Gradišek (Supervisor), Matjaž Gams (Co-Supervisor)

Year: 2024

Type: Doctoral dissertation

Cardiovascular diseases (CVDs) are a leading cause of mortality globally, significantly affecting patient quality of life and imposing considerable demands on healthcare systems. Chronic heart failure (CHF), a common outcome of CVDs, represents a growing health burden with an increasing incidence. Accurate and early identification of CVDs is critical for …

Bias prediction in multilingual news reporting

Author(s): Swati (Author), Dunja Mladenić (Supervisor)

Year: 2024

Type: Doctoral dissertation

Over the past decade, rapid advancements in natural language processing have opened up new avenues for tackling complex issues such as news bias analysis. This progress has empowered researchers to explore innovative approaches to uncovering the complex biases inherent in news production and coverage processes. News bias, a multifaceted reflection …

Machine learning methodology for automatic metadata assignment in cultural heritage archives

Author(s): Luis Rei (Author), Dunja Mladenić (Supervisor)

Year: 2024

Type: Doctoral dissertation

This thesis introduces a novel machine learning methodology for automatically assigning metadata to digitized artifacts in cultural heritage. Cultural heritage is an example of a domain that requires expert labeling, with few pre-existing labeled datasets and where simply getting more labeled data is challenging. The societal importance of cultural heritage …

Probabilistic grammar-based equation discovery

Author(s): Jure Brence (Author), Sašo Džeroski (Supervisor), Ljupčo Todorovski (Co-Supervisor)

Year: 2024

Type: Doctoral dissertation

In this thesis, we introduce novel methods for equation discovery (ED), based on the use of probabilistic grammars. ED and symbolic regression address the task of finding a symbolic mathematical model that best describes observed data. Models can be as simple as an algebraic equation or as complex as a …

Computational investigation of protein-RNA interactions detected by CLIP, their specificity and dynamics in embryonic development

Author(s): Klara Kuret (Author), Jernej Ule (Supervisor), Miha Modic (Co-Supervisor)

Year: 2024

Type: Doctoral dissertation

RNA molecules dynamically interact with RNA-binding proteins (RBPs), which control various aspects of RNA fate, such as its processing, localisation, and stability. Intricate networks of protein-RNA interactions thereby regulate gene expression and have a profound effect on downstream cellular processes. Most RBPs recognise specific motifs on their bound RNAs, characterised …

Intra- and inter-trophic interactions of generalist forest predator

Author(s): Urška Ratajc (Author), Al Vrezec (Supervisor)

Year: 2024

Type: Doctoral dissertation

We are witnessing major shifts in ecosystems due to intense anthropogenic pressures on the environment in recent decades, including rapid climate change, which is one of the strongest drivers of a global biological response. Raptors, which are at the top of the trophic web, are important indicators of ecosystem health. …

Development and employment of untargeted and targeted tools for virus detection in the frame of water-based epidemiology

Author(s): Olivera Maksimović (Author), Jon Gutiérrez-Aguirre (Supervisor), Denis Kutnjak (Co-Supervisor)

Year: 2023

Type: Doctoral dissertation

Traditional methods of studying viruses are limited in their ability to detect novel pathogens, but recent advances in high-throughput sequencing (HTS) are changing that. HTS allows researchers to probe deeply into the virome of various hosts and environments, identifying known and unknown viral species. However, a targeted approach, like quantitative …

Advanced glioblastoma models to study tumour microenvironment and to support novel glioblastoma therapeutics

Author(s): Bernarda Majc (Author), Tamara Lah Turnšek (Supervisor), Metka Novak (Co-Supervisor)

Year: 2023

Type: Doctoral dissertation

Glioblastoma (GB) is the most common and aggressive primary tumour of the central nervous system. Despite maximal possible surgical resection of the tumours and aggressive treatment regimens with radiotherapy and chemotherapy, patient overall survival is less than 2 years, as patients eventually develop resistance to therapy, resulting in recurrent tumours. …

Characterization of plant viromes using different viral nucleic acids enrichment strategies and high-throughput sequencing platforms

Author(s): Anja Pecman (Author), Maja Ravnikar (Supervisor), Ion Gutiérrez Aguirre (Co-Supervisor)

Year: 2022

Type: Doctoral dissertation

Plant viruses are very important plant pathogens, causing economic losses by infecting cultivated plants, causing diseases, and consequently reducing crop quality and quantity. In recent years, the development of high throughput sequencing (HTS) technologies has dramatically broadened the possibilities for plant virus research and diagnostics, enabling the discovery of new …

Atmospheric pressure plasma jet deposition of nanoparticles and its applications

Author(s): Aswathy Vasudevan (Author), Aleksander Zidanšek (Supervisor), Uroš Cvelbar (Co-Supervisor)

Year: 2022

Type: Doctoral dissertation

Atmospheric pressure non-equilibrium plasma jets in material processing have received substantial attention in the past two decades and are still in the developing stage with a growing interest in material synthesis and surface processing. The main opportunities of these techniques are their potential cost reductions in apparatus and handling. Because …