Titulo Estágio
Bisociative Knowledge Discovery for Oncological Studies
Áreas de especialidade
Sistemas Inteligentes
Engenharia de Software
Local do Estágio
University of Coimbra -- Department of Informatics Engineering
Enquadramento
According to Arthur Koestler, bisociative thinking occurs when a problem, idea, event or situation is perceived simultaneously in two or more “matrices of thought” or domains. When two matrices of thought interact with each other, the result is either their fusion in a novel intellectual synthesis or their confrontation in a new aesthetic experience. He regarded many different mental phenomena, which are based on comparison (such as analogies, metaphors, jokes, identification, anthropomorphism, and so on), as special cases of bisociation.
Computational approaches to Koestler's concept of bisociation have been successfully applied to different applications related to data mining like in business processes models, music discovery and recommendation, literature mining among others.
Objetivo
The goal of this project is to perform a step forward in the bisocation knowledge discovery (BKD) area trying to detect similarities in oncological studies. To the best of our knowledge there is no previously studies that tried to use BKD in oncological contexts.
To achieve that and, in the first stage, open source databases will be used to select oncological pathologies that have shown, based on literature, similarities (constituting the ground truth of the approach). On the second stage, the goal is to discovery new similarities between the previously selected pathologies and news ones selected by a clinician team.
Plano de Trabalhos - Semestre 1
-Study and analysis the state of the art concerning Bisociative Knowledge Discovery;
-Data gathering of oncological information from open sources databases.
Plano de Trabalhos - Semestre 2
-Implementation of different BKD techniques (e.g. bridging by graph similarity);
-Evaluation of the implemented techniques in the oncological datasets;
-Comparison of obtained results and conclusions;
-Writing the report of the Master Degree Thesis.
Condições
The proposal will not be funded
Orientador
Pedro Henriques Abreu
pha@dei.uc.pt 📩