Search Results (21)
Exploiting domain knowledge in predictive learning from food and nutrition data
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
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. …
Chirality and nanoparticles enforced stabilization of topological defects in liquid crystals
Of our main interest in this work is the stabilization of assemblies of topological defects (TDs) in liquid crystals (LCs). Due to the topological origin of TDs, the physics of defects is of interest for all branches of physics, including condensed matter systems, particle physics, and cosmology. LCs represent an …
Predicting the dynamics of spatio-temporal systems based on heterogeneous data sources
As urbanisation continues to be a trend, in which centralisation of the population into cities is still growing, the importance of intelligent solutions in mobility is in high demand. Likewise, with the integration of renewable energies into all levels of the electrical grid system and the increasing amount of heavy …
A Modular Ontology of Data Mining
The domain of data mining (DM) deals with analyzing different types of data. The data typically used in data mining is in the format of a single table, with primitive datatypes as attributes. However, structured (complex) data, such as graphs, sequences, networks, text, image, multimedia and relational data, are receiving …
Parameter Identification in Nonlinear Dynamic Systems with Meta-heuristic Approaches
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 …
Ensembles for predicting structured outputs
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 …
Monitoring of the product quality in manufacturing industries
Unexpected production breakdowns and unpredictable defects in product quality remain critical problems in modern manufacturing systems. Usually occuring by no obvious exterior cause and often during periods of smooth production, they lead to production losses and reduced process availability, which results in lower profit rates. Conventional statistical methods of process …
Dynamic Modeling of Climate Change Impacts of Greenhouse Gas Reduction with Renewable Energy in Kosovo
Atmospheric concentration of CO2 and other greenhouse gases (GHG) is higher than any time in the last 400000 years and growing faster than at any time in the past 18000 years. The high concentration of GHG generates radiative forcing that contributes to climate change. Energy production from fossil fuels has …
Impact Analysis for Integrated Assessments of Climate-Energy Models
It is evident that the worldwide average temperature is rising and climate is changing (WMO, 2003) and it is believed that there is sufficient evidence that this is due to human activities (IPCC 2001). Human activities are primarily responsible for the release of carbon dioxide and other global warming pollutants …