REPOSITORY > RESULTS

Browse All

Search Results (20)

Identification of indoor radio environment properties based on channel state information using machine learning approaches

Author(s): Teodora Kocevska (Author), Andrej Hrovat (Supervisor), Aleksandra Rashkovska Koceva (Co-Supervisor)

Year: 2023

Type: Doctoral dissertation

Characterization of the indoor radio environment (RE) is a prerequisite for advances in the design and optimization of next-generation indoor wireless networks and for the construction of a digital twin of the building. The need for comprehensive and accurate indoor characterization will be evident in the future hyper-connected mixed real-virtual …

New methods for the determination of elemental composition and simple phenolic compounds in atmospheric particulate matter

Author(s): Monika Ogrizek (Author), Martin Šala (Supervisor), Ana Kroflič (Co-Supervisor)

Year: 2023

Type: Doctoral dissertation

Air pollution is an inevitable problem that modern society has to face today, with particulate matter (PM) being the most dangerous part of it, threatening human health and the environment. Not all PM particles, however, are equally harmful, since the dangerous potential depends on their size and chemical composition, which …

Nanocomposites as electrocatalysts for the use in fuel cell and electrolyzer reactions

Author(s): Léonard Jean Moriau (Author), Nejc Hodnik (Supervisor)

Year: 2023

Type: Doctoral dissertation

Electrochemical energy conversion devices such as fuel cells (FCs) and water electrolyzers (WE) have attracted attention from the scientific community for their unique ability to store electrical energy in the form of hydrogen and then generate electricity by the reverse process. Unfortunately, those devices rely on a significant amount of …

Exploiting domain knowledge in predictive learning from food and nutrition data

Author(s): Gordana Ispirova (Author), Barbara Koroušić Seljak (Supervisor), Tome Eftimov (Co-Supervisor)

Year: 2022

Type: Doctoral dissertation

Human knowledge about food and nutrition has evolved drastically with time. With food and nutrition-related data being mass produced and easily accessible, the next step is to use Artificial Intelligence (AI) to translate data into knowledge. The majority of AI research is model-driven, and classical Machine Learning (ML) pipelines concentrate …

Unravelling the molecular mechanisms of plant-pathogen interactions in grapevine and potato through functional analysis

Author(s): Špela Tomaž (Author), Anna Coll (Supervisor)

Year: 2022

Type: Doctoral dissertation

Plants are constantly exposed to various environmental stressors. Pathogen infections causing disease can affect economically important crops and impact global food production. To counter disease development and spread, it is imperative that we acquire a thorough knowledge of its pathogenesis, as well as of the mechanisms underlying plant immune response. …

Mechanisms and Effect of Deep Cryogenic Treatment on Steel Properties

Author(s): Patricia Jovičević Klug (Author), Bojan Podgornik (Supervisor)

Year: 2022

Type: Doctoral dissertation

Deep cryogenic treatment (DCT) is a type of cryogenic treatment, during which a material is subjected to temperatures below −160 °C. When a metallic material is modified with DCT, changes occur down to the nanoscopic level. DCT induces microstructural changes such as grain size refinement, formation of new grains, movement …

Development and application of a non-targeted screening workflow for chemical exposure assessment in human biomonitoring and related studies

Author(s): Žiga Tkalec (Author), Tina Kosjek (Supervisor)

Year: 2022

Type: Doctoral dissertation

Human exposure to environmental stressors is widespread. Highly dynamic, these chemical, physical and social factors, collectively termed as the exposome, interact with internal factors such as genetics, sex, gut microbiome and general health status, and dictate susceptibility and risk for an onset of diseases. Human exposure to the chemicals is …

Plasma-enabled design of hybrid carbon nanostructures for energy storage applications

Author(s): Neelakandan Marath Santhosh (Author), Uroš Cvelbar (Supervisor), Gregor Filipič (Co-Supervisor)

Year: 2021

Type: Doctoral dissertation

Carbon, one of the most abundant materials in the earth crust, has gained research attention owing to its high structural stability, electrical conductivity, optical and thermal properties. Additionally, the possibility of tailoring carbon materials at nanoscales makes them promising materials for many applications, including energy storage, sensors, biomedical and electronics. …

Algorithms for Learning Regression Trees and Ensembles on Evolving Data Streams

Author(s): Elena Ikonomovska (Author), Sašo Džeroski (Supervisor), João Gama (Co-Supervisor)

Year: 2012

Type: Doctoral dissertation

In this thesis we address the problem of learning various types of decision trees from timechanging data streams. In particular, we study online machine learning algorithms for learning regression trees, linear model trees, option trees for regression, multi-target model trees, and ensembles of model trees from data streams. These are …

Normobaric hyperoxia: haemodynamic responses to acute and long-term exposure

Author(s): Michail Keramidas (Author), Igor Mekjavić (Supervisor), Ola Eiken (Co-Supervisor)

Year: 2011

Type: Doctoral dissertation

The aim of the present thesis was to examine the effect of acute and long-term normobaric hyperoxic exposure on selected haemodynamic and haematological responses during resting and exercise conditions in healthy aerobically well-trained males. This purpose was evaluated in four separate studies, and each of them had a specific aim …