Skip to Main content Skip to Navigation

Fusion Symbolique et Données Polysomnographiques

Adrien Ugon 1
1 ACASA - Agents Cognitifs et Apprentissage Symbolique Automatique
LIP6 - Laboratoire d'Informatique de Paris 6
Abstract : In recent decades, medical examinations required to diagnose and guide to treatment became more and more complex. It is even a current practice to use several examinations in different medical specialties to study a disease through multiple approaches so as to describe it more deeply. The interpretation is difficult because the data is both heterogeneous and also very specific, with skilled domain of knowledge required to analyse it. In this context, symbolic fusion appears to be a possible solution. Indeed, it was proved to be very effective in treating problems with low or high levels of abstraction of information to develop a high level knowledge. This thesis demonstrates the effectiveness of symbolic fusion applied to the treatment of polysomnographic data for the development of an assisted diagnosis tool of Sleep Apnea Syndrome. Proper diagnosis of this sleep disorder requires a polysomnography. This medi- cal examination consists of simultaneously recording of various physiological parameters during a night. Visual interpretation is tedious and time consuming and there commonly is some disagreement between scorers. The use of a reliable support-to-diagnosis tool increases the consensus. This thesis develops stages of the development of such a tool.
Document type :
Complete list of metadatas

Cited literature [79 references]  Display  Hide  Download
Contributor : Adrien Ugon <>
Submitted on : Sunday, June 7, 2015 - 4:02:02 PM
Last modification on : Monday, October 19, 2020 - 11:12:40 AM
Long-term archiving on: : Tuesday, September 15, 2015 - 12:01:09 PM


  • HAL Id : tel-01160772, version 1


Adrien Ugon. Fusion Symbolique et Données Polysomnographiques. Informatique [cs]. Université Pierre et Marie Curie (UPMC, Paris 6), 2013. Français. ⟨NNT : 2013PA066187⟩. ⟨tel-01160772⟩



Record views


Files downloads