REPOSITORY > RESULTS

Browse All

Search Results (32)

Processing of heavy-rare-earth-lean Nd-Fe-B permanent magnets for high-temptrature applications

Author(s): Matic Korent (Author), Kristina Žagar Soderžnik (Supervisor), Spomenka Kobe (Co-Supervisor)

Year: 2021

Type: Doctoral dissertation

Permanent magnets are materials that generate a magnetic field in free space without electricity or other external energy sources. They are essential components of modern technologies, used in many electrical devices. Nowadays, they are included in technology for renewable sources of energy, such as electrical vehicles, generators and wind turbines. …

Development of methods for electrostatic immobilization and coupling different microbial cells

Author(s): Iaroslav Rybkin (Author), Aleš Lapanje (Supervisor), Tomaž Rijavec (Co-Supervisor)

Year: 2021

Type: Doctoral dissertation

Naturally formed microbial communities are present in the form of cellular aggregates that create a set of diverse biochemical pathways through cross-feeding between the members of the microbial community. One of the most important factors so that some biochemical reactions can occur is the appropriate spatial placement of a particular …

The sensor hub for detection of the relation between physiological parameters and colour modifications in text background and overlay during reading in children with and without dyslexia

Author(s): Tamara Jakovljević (Author), Gregor Papa (Supervisor), Tadeja Jere Jakulin (Co-Supervisor)

Year: 2021

Type: Doctoral dissertation

The doctoral dissertation discusses the mechanisms of the colours’ influence on the reading process and electrophysiological correlates of the reader's condition, considering developmental aspects, graded (level) aspects and gender aspects of tested groups of children and their reading acquisition. The reading process is one of the most important processes during …

A Machine Learning Approach to Polynomial Regression

Author(s): Aleksandar Pečkov (Author), Sašo Džeroski (Supervisor), Ljupčo Todorovski (Co-Supervisor)

Year: 2012

Type: Doctoral dissertation

In the thesis, we address the task of polynomial regression, i.e., inducing regression models based on polynomial equations, from data. We aim at improving and extending the existing approaches to learning polynomial regression models in several directions. First, we improve the existing methods for addressing the issue of over-fitting and …

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 …

Parameter Identification in Nonlinear Dynamic Systems with Meta-heuristic Approaches

Author(s): Katerina Tashkova (Author), Sašo Džeroski (Supervisor), Jurij Šilc (Co-Supervisor)

Year: 2012

Type: Doctoral dissertation

The task of mathematical modeling of dynamic systems from observed system behavior, widely known under the name of system identification, breaks down into two subtasks. The first task, referred to as structure identification, is to specify the model structure, i.e., the functional form of the model. In practice, the model …

The use of normobaric hypoxia and hyperoxia for the enhancement of sea level and/or altitude exercise performance

Author(s): Tadej Debevec (Author), Igor Mekjavić (Supervisor), Stylianos N. Kounalakis (Co-Supervisor), Blaž Jereb (Co-Supervisor)

Year: 2011

Type: Doctoral dissertation

Adaptation to altitude can enhance performance if the hypoxic dose and the frequency of the exposures are appropriate. While many hypoxic training modalities exist, the protocols utilizing short intermittent hypoxic exposures are gaining popularity. However, the effects of such novel hypoxic protocols on athletic performance are unclear. The aim of …

Model for Monitoring and Assessment of a Public Health Care Network

Author(s): Aleksander Pur (Author), Marko Bohanec (Supervisor)

Year: 2011

Type: Doctoral dissertation

It is hard to imagine the management of any system without monitoring it as a process of continuously gathering data and performing real-time analyses. In general, monitoring can improve the estimation of the current state, optimization of the business processes, identification of the critical elements and new opportunities, and prediction …

Ensembles for predicting structured outputs

Author(s): Dragi Kocev (Author), Sašo Džeroski (Supervisor)

Year: 2011

Type: Doctoral dissertation

In this thesis, we address the task of learning models for predicting structured outputs, which take as input a tuple of attribute values and produce as output a structured object. In contrast to classification and regression, where the output is a single scalar value, in our case the output is …

The synthesis and characterization of glass–ceramics based on ternary system MgO-B2O3-SiO2

Author(s): Urban Došler (Author), Danilo Suvorov (Supervisor), Marjeta Maček Kržmanc (Co-Supervisor)

Year: 2011

Type: Doctoral dissertation

The past fifteen years has seen the rapid development of various wireless communication devices, which operate at microwave or milimeterwave frequencies (mobile phones, wireless local-area networks (LAN), Bluetooth, etc.). At the same time, this progress has stimulated the development of new materials and process technologies, which enable the size reduction …