REPOSITORY > RESULTS

Browse All

Search Results (34)

Ontology Extension Using Text Mining for News Analysis

Author(s): Inna Novalija (Author), Dunja Mladenić (Supervisor)

Year: 2011

Type: Doctoral dissertation

In computer science, ontologies enable formalized knowledge representation. The goal of ontology extension is to correctly augment the existing ontology with new formalized knowledge (e.g., concepts, relationships etc.). This thesis addresses the ontology extension process based on text mining methods. News analysis is the application of the extended ontology. A …

Occurrence, fate and removal of pharmaceutical residues in water treatment

Author(s): Tina Kosjek (Author), Ester Heath (Supervisor)

Year: 2009

Type: Doctoral dissertation

The presence of pharmaceutical residues in surface waters is an emerging environmental issue that provides a new challenge to treatment systems for potable water, wastewater and water reuse. Their principle pathways into the sewerage system are twofold: first, after being administered to patients they are normally excreted as various metabolites …

Assessment of behavioural thermoregulation in humans: with particular reference to mild narcosis and prolonged bed rest

Author(s): Daniel Yogev Wolowske (Author), Igor Mekjavić (Supervisor)

Year: 2009

Type: Doctoral dissertation

Behavioural responses are the most efficient thermoregulatory responses, since relatively simple actions can prevent the need to activate the more metabolically costly autonomic responses. Dependence on behavioural responses may increase in environmental conditions where the prevailing nonthermal factors (NTF) attenuate autonomic responses and alter thermal perception (Mekjavic et al., 2003; …

Supervised Descriptive Rule Induction

Author(s): Petra Kralj Novak (Author), Nada Lavrač (Supervisor)

Year: 2009

Type: Doctoral dissertation

The goal of knowledge discovery in databases is to construct models or discover interesting patterns in data. Model construction and pattern discovery are frequently performed by rule learning, as the induced rules are easy to be interpreted by human experts. The standard classification rule learning task is to induce classification/prediction …