Por Tom Bartindale (OpenLab, Newcastle University).
Por Jafar Adibi (Talkdesk - Head of Data Science and AI).
Biclustering, the discovery of sets of objects with coherent values/patterns on subsets of features, was shown to be key to unravel and characterize informative regions (biclusters) within matricial, time series and network data, in a wide-set of applications in biomedical and social data analysis. Particularly in biomedical problems, where groups of genes or patients tend to be only meaningfully related on a subset of the sampled/monitored conditions.
Knowledge about the domain to be analyzed permeates all steps of the Knowledge Discovery process, from feature generation and selection to result interpretation and visualization. In most cases, this background knowledge resides in the data analyst’s mind only, but making it explicit would open new opportunities for knowledge discovery.
Marisa Tomé Félix defende a dissertação "Unified Cyber Threat Intelligence".
Joana Correia Campos defende a tese "Adding Dependent Types to Class-based Mutable Objects".
Por Edwin Brady (University of St Andrews).
Por Philip Wadler (University of Edinburgh).
As aplicações realizadas pelos alunos incluem aplicações de recomendação, jogos geolocalizados, aplicações de suporte ao estudo e descoberta de alojamento, aplicações de suporte à saúde e bem estar, entre outras.
Miguel Amorim Falé defende a dissertação "Improving Vulnerability Detection of WAP".