Machine Learning for Simplifying the Use of Cardiac Image Databases. (Apprentissage automatique pour simplifier l'utilisation de banques d'images cardiaques)

Statistical learning for image-based personalization of cardiac models. (Apprentissage statistique pour la personnalisation de modèles cardiaques à partir de données d'imagerie)

Cette thèse porte sur un problème de calibration d’un modèle électromécanique de cœur, personnalisé à partir de données d’imagerie médicale 3D + t ; et sur celui — en amont — de suivi du mouvement cardiaque. Les perspectives à long terme de la simulation personnalisée de la fonction cardiaque incluent l’aide au diagnostic et à la planification de thérapie, ainsi que la prévention des risques ca...

Vision cognitive : apprentissage supervisé pour la segmentation d'images et de videos. (Cognitive vision: supervised learning for image and video segmentation)

Integrating Machine Learning Techniques in a Guided Discovery Tutoring Environment: MEMOCAR

This chapter presents how Machine Learning Techniques can effectively contribute to improve the quality of interactions in Guided Discovery Tutoring Environments (GDTE) . We review several approaches to integrate Machine Learning in ITS. Most of these approaches use concept learning from examples to maintain a Student Model. We go along presenting an alternative use of induction techniques to l...

Man-computer Procedui\es for Image Retrieval Preliminary Findings

The research described in this paper is intended to uncover design parameters critical for user interaction with a data base consisting of digitally encoded images. Experiments have been performed to establish and standardize tasks for users .9f image retrieval systems. Measures of the performance of these-'tasks 11-1 are used to compare the usability and usefulness of a set of features and fac...

Apprentissage non-supervisé pour la segmentation automatique de textes

In this paper we introduce a machine learning approach for automatic text segmentation. Our text segmenter clusters text-segments containing similar concepts. It first discovers the different concepts present in a text, each concept being defined as a set of representative terms. After that the text is partitioned into coherent paragraphs using a hard clustering technique based on the Classific...