Learning Rules from Multisource Data for Cardiac Monitoring

Elisa Fromont 1 René Quiniou 1 Marie-Odile Cordier 1
1 DREAM - Diagnosing, Recommending Actions and Modelling
Inria Rennes – Bretagne Atlantique , IRISA-D7 - GESTION DES DONNÉES ET DE LA CONNAISSANCE
Abstract : This paper aims at formalizing the concept of learning rules from multisource data in a cardiac monitoring context. Our method has been implemented and evaluated on learning from data describing cardiac behaviors from different viewpoints, here electrocardiograms and arterial blood pressure measures. In order to cope with the dimensionality problems of multisource learning, we propose an Inductive Logic Programming method using a two-step strategy. Firstly, rules are learned independently from each sources. Secondly, the learned rules are used to bias a new learning process from the aggregated data. The results show that the the proposed method is much more efficient than learning directly from the aggregated data. Furthermore, it yields rules having better or equal accuracy than rules obtained by monosource learning
Type de document :
Communication dans un congrès
Silvia Miksch, Jim Hunter, Elpida Kervanou. Artificial Intelligence in Medicine, Jul 2005, Aberdeen, Scotland, Springer, 3581, pp.484-493, 2005, LNCS
Liste complète des métadonnées


https://hal.inria.fr/inria-00000184
Contributeur : Elisa Fromont <>
Soumis le : vendredi 29 juillet 2005 - 11:37:03
Dernière modification le : jeudi 9 février 2017 - 16:05:08
Document(s) archivé(s) le : jeudi 1 avril 2010 - 22:09:27

Identifiants

  • HAL Id : inria-00000184, version 1

Citation

Elisa Fromont, René Quiniou, Marie-Odile Cordier. Learning Rules from Multisource Data for Cardiac Monitoring. Silvia Miksch, Jim Hunter, Elpida Kervanou. Artificial Intelligence in Medicine, Jul 2005, Aberdeen, Scotland, Springer, 3581, pp.484-493, 2005, LNCS. <inria-00000184>

Partager

Métriques

Consultations de
la notice

189

Téléchargements du document

93