Directory Intranet

Analyse conjointe de traces oculométriques et d EEG à l aide de modèles de Markov cachés couplés


Directeur de thèse :     Anne GUERIN-DUGUE

École doctorale : Mathématiques, sciences et technologies de l'information, informatique (MSTII)

Spécialité : MA-Mathématiques Appliquées

Structure de rattachement : UJF

Établissement d'origine : Université Lumière - Lyon 2

Financement(s) : Contrat doctoral ; Contrat doctoral ; Sans financement


Date d'entrée en thèse : 01/10/2015

Date de soutenance : 26/06/2019


Composition du jury :
Jean-Baptiste Durand, Maître de conférences, Grenoble INP, Directeur de thèse
Halszka Jarodzka, Associate Professor, Open Universiteit Nederland, Rapporteur
Alfons Juan, Professor, Universitat Politecnica de Valencia, Rapporteur
Jean-Michel Boucheix, Université de Bourgogne, Examinateur
Sophie Achard, Directeur de recherche, CNRS
Anne Guérin-Dugué, Professeur, Université Grenoble Alpes, Co-directeur de thèse


Résumé : The aim of the PhD is to develop an integrated model coupling EEG and eye movements within one single HMM for better identification of the phases. Coupled HMMs are based on several dependent Markov chains such that at each time t, observations only depend on the states at time t (Zhong & Ghosh, 2001). Here, the coupling should incorporate some delay between the transitions in both chains, since EEG patterns associated to cognitive processes may occur with some delay with respect to eye-movement phases. To better relate the human reading process to some intrinsic characteristics of the reviewed text, we propose an interpretation of our two experimental models based on a well-known hierarchical generative model, called LDA, used in the data mining context (Blei et al., 2003) and thereafter extending to the image setting (Fei-Fei & Perona, 2005). We want to model “human data mining” for text or image as a variant of LDA, modifying in a convenient way the generative process and involving a random choice of the cognitive phase. The main goal is to take into account the fact that, in a text, a given word can be either read or not. The same question can also be raised in the image setting since a region of interest corresponding to a specific visual word can be explored or not. For this, a joint database with eye movements and EEG signals has been also recording during a visual search task according to a similar design as the information seeking task.

GIPSA-lab, 11 rue des Mathématiques, Grenoble Campus BP46, F-38402 SAINT MARTIN D'HERES CEDEX - 33 (0)4 76 82 71 31