Latest Academic Works
Different approaches for enhancing dielectric response of polymer and ceramic materials
Dielectric materials are essential components of electronic devices and electric power systems. Consequently, the design and development of new materials with enhanced dielectric response remain of great importance. This dissertation examines three different approaches to enhancing the dielectric response: (i) percolative composites, (ii) polymer blending, and (iii) the induction of …
Ecological modelling of the phytoplankton community in the northern Adriatic sea
This dissertation examines the ecological dynamics of phytoplankton communities in the northern Adriatic Sea, focusing on phenology, environmental drivers, and trophodynamics. The complexity of the region, characterized by the richness of phytoplankton communities, environmental variability and intensive human activities, is not seen as an obstacle but as an opportunity to …
Genetic variability and lead exposure biomarkers
The thesis investigates associations between the biomarkers of lead (Pb) exposure (and mercury (Hg), where applicable) and genetic variability in in vulnerable populations, including pregnant women and their newborns from Italy, Slovenia, and Croatia, as well as Slovenian men of reproductive age. The research utilizes data from the Public Health …
Development of aerosolizator for disinfection of radiological devices and rooms using steriplant©n and assessment
Magnetic resonance imaging (MRI) is a diagnostic method that is used for broad range of hospitalized patient, emergency patients, chemotherapy treated and as well the patients that may have infectious diseases. Because the examinations of different patients are usually performed with the same equipment in the same environment, the surfaces …
Representing and exploiting benchmarking data for optimisation and learning
The rapid advancements in Machine Learning (ML) and Black-Box Optimization (BBO) have led to an increased reliance on benchmarking data for evaluating and comparing algorithms across diverse domain tasks. However, the effective exploitation of this data is hindered by challenges such as syntactic variability, semantic ambiguity, and lack of standardization. …
Identification of hearth sounds for the analysis of cardiac pathology using machine learning
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 …
Strontium isotope composition: : insights into geological and environmental influences on the provenance studies of dairy products and timber
This dissertation aimed to explore the potential of Sr isotope ratio analysis, combined with multi-elemental profiling, as a tool for geographic discrimination, focusing on two projects: tracing the provenance of cheese/milk from Naxos, Greece (Project 1), and wood in the Eastern Carpathians, Romania (Project 2). The goal was to understand …
Isotopic fingerprint of water from source to tap
Rapid population growth and increasing water demand places a serious strain on both quantity and quality of available local water resources. Climate change puts additional pressure by altering the water balance, affecting recharge conditions, and contributing to pollution and water degradation. Addressing these issues requires water management strategies that enhance …
Explainable machine learning techniques for applications in life sciences
As ecological, agricultural, and biological disciplines face mounting challenges like biodiversity loss, food chain disruption, and climate change, leveraging machine learning (ML) to process complex and heterogeneous data becomes increasingly vital. This dissertation explores the potential of ML in combination with explainability approaches for enhancing research in life sciences, specifically …
Machine learning methodology for automatic metadata assignment in cultural heritage archives
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 …