REPOSITORY > RESULTS

Browse All

Search Results (26)

Autonomous generation of robot behaviour for effective task execution

Author(s): Zvezdan Lončarević (Author), Andrej Gams (Supervisor)

Year: 2023

Type: Doctoral dissertation

The pursuit of autonomous robot learning is aimed at enabling robots to seamlessly integrate into our daily lives, enhancing our efficiency and convenience. On the other hand, in the industrial sector, autonomous robot learning plays a vital role in keeping up with the rapidly evolving market demands. As products and …

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 …

Towards understanding the impact of problem landscapes in numerical black-box optimization

Author(s): Urban Škvorc (Author), Peter Korošec (Supervisor), Tome Eftimov (Co-Supervisor)

Year: 2023

Type: Doctoral dissertation

In optimization, it is well known that algorithm performance is dependent on the problem being solved. As a consequence of this, achieving good optimization results requires correctly matching an optimization problem to a specific optimization algorithm that performs well on that problem. For this to be possible, knowledge of both …

Lead magnesium niobate titanate thick films prepared by aerosol deposition method

Author(s): Matej Šadl (Author), Hana Uršič Nemevšek (Supervisor)

Year: 2022

Type: Doctoral dissertation

The miniaturization of electronic devices requires the fabrication of functional components in the form of μm-sized thick films. Some of the most promising functional materials are relaxor-ferroelectric (1-x)Pb(Mg1/3Nb2/3)O3–xPbTiO3 (PMN–100xPT), as they exhibit versatile dielectric, piezoelectric and relaxor-ferroelectric properties. However, the integration of functional ceramic thick films with non-conventional substrates such …

Annotation of semi-polar organic contaminants by using gas chromatography coupled to mass spectrometry and machine learning

Author(s): Milka Ljoncheva (Author), Tina Kosjek (Supervisor), Sašo Džeroski (Co-Supervisor)

Year: 2022

Type: Doctoral dissertation

Contaminants of emerging concern (CECs), representing a subgroup of organic compounds of natural or synthetic origin, and their degradation and transformation products (TPs), with potentially harmful effects on humans, biota, and the environment, are the eco-exposome (EE) constituents of utmost importance. Their identification, quantification, and continued investigation into their environmental …

Scalable neuro-symbolic machine learning

Author(s): Blaž Škrlj (Author), Nada Lavrač (Supervisor)

Year: 2022

Type: Doctoral dissertation

With the resurgence of neural network-based learning in the last decade, machine learning methods are becoming critical components of many real-life intelligent systems. However, while being able to learn effectively and at scale, such systems are often non-interpretable and unable to exploit existing symbolic background knowledge. The paradigm that offers …

Method for the determination of uranium isotope ratios and its application as a novel geochemical tracer

Author(s): Leja Rovan (Author), Marko Štrok (Supervisor)

Year: 2021

Type: Doctoral dissertation

U and Th isotopic composition have been proven to be a valuable tool in environmental science, oceanography, hydrology, geology, nuclear forensics, and science-based archaeology. These applications require simultaneous detection of both minor and major isotopes at high accuracy. Often, the amount of sample or concentration of U and Th are …

Surfaces and interfaces in the growth of SrTiO3 on Si by pulsed laser deposition

Author(s): Tjaša Parkelj Potočnik (Author), Matjaž Spreitzer (Supervisor)

Year: 2021

Type: Doctoral dissertation

SrTiO3 (STO) thin films are used as buffer layers that enable epitaxial integration of various functional oxides with silicon. When pulsed laser deposition (PLD) is used to grow STO on Si, a thin amorphous layer is formed at the STO-Si interface that limits the use of such heterostructures in certain …

Investigations and separation of various contributions to dielectric response of advanced ceramic and polymeric materials

Author(s): Andreja Eršte (Author), Vid Bobnar (Supervisor)

Year: 2013

Type: Doctoral dissertation

Dielectric materials, used to control and store charges and electric energy, play a key role in modern electronics and electric power systems. Dielectric spectroscopy is a versatile method, well-suited for detection, separation and characterization of various contributions to dielectric response of advanced ceramic and polymeric materials, as it enables understanding …

Laser Ablation - Inductively Coupled Plasma Mass Spectrometry (LA-ICPMS) - Fundamental Study of Ablation and Deposition Processes

Author(s): Mersida Janeva Azdejković (Author), Spomenka Kobe (Supervisor), Alkiviadis Constantinos Cefalas (Co-Supervisor), J. T. van Elteren (Co-Supervisor)

Year: 2012

Type: Doctoral dissertation

Laser ablation (LA) is a versatile technique that can be used for the elemental analysis of diverse materials as well as for synthesis purposes, i.e. for pulsed laser deposition (PLD) of a wide range of materials. Analysis and synthesis will only be successful if the ablated material can be stoichiometrically …