Search Results (48)
An automated vulnerability detection for website security
Although large research efforts on web application security have been invested for more than a decade, the security of web applications is still a challenging problem. The main focus of the cybersecurity community has been to make operating systems and communication networks more secure and harder for attackers to penetrate. …
Diversity, ecology and sensing of the toxic diatom Pseudo-Nitzschia in the Gulf of Trieste: doctoral disertation
This work focuses on a group of diatoms, belonging to the genus Pseudo-nitzschia, which is a globally important phytoplankton genus. Some species of the genus produce the toxin domoic acid, which is responsible for shellfish intoxication known as the amnesic shellfish poisoning (ASP). These diatoms have few morphological features that …
Classification of wireless links using machine learning techniques
Due to the nature of the wireless transmission medium, wireless communications are characterised by notably larger losses of data packets than wired communications. The quality of wireless links is highly dependent on channel variations, interference and even transceiver imperfections. Such link uncertainty instigated the development of numerous techniques that can …
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 …
Complex nodes in trees for structured output prediction
In this thesis, we integrate complex nodes into predictive clustering trees (PCTs). PCTs are well-established machine learning models that are very flexible in terms of the machine learning tasks that they can address, including structured output prediction and semisupervised learning. Like standard decision trees, they are learned with a greedy …
CO2 dynamics in a river system: mass balance, hydrological, geochemical and biochemical impacts
A 3-year systematic investigation (2007–2010) of water chemistry using conventional and stable isotope tracers helped us delineate hydro-biogeochemical processes in the karstic Krka River watershed. By mineralogical and stable isotopic examination of tufa deposits and combining the results with water chemistry, we were able to evaluate the suitability of tufa …
Detection of anomalous and suspicious behavior patterns from spatio-temporal agent traces
Many applications, including smart environments, surveillance, human-robot interaction, and ambient assisted living, involve the problem of learning patterns of agent behavior from sensor data. Deviant behavior is a pattern in the data that either does not conform to the expected behavior, that is, anomalous behavior, or matches previously defined unwanted …
Spectroscopic characterization of conformations of short alanine peptides, poly-L-lysine and insulin during formation of amyloid fibrils
The process of protein folding describes the transition by which an unordered polypeptide chain attains its functional native three-dimensional structure. A detailed understanding of the principles which govern the protein folding, such as conformational preferences of amino acid residues, the neighbour residue effect and the solvent effects, remains an important …
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 …
An Evaluation Method for Feature Rankings
Feature ranking is the machine learning task of inducing an ordering of features in a given dataset according to some notion of relevance. We consider the feature ranking task in the context of supervised learning, where the notion of feature relevance is defined with respect to a target concept. Feature …