Accéder directement au contenu

Thomas Guyet

4
Documents
Identifiants chercheurs

Présentation

Research interests ------------------ My research area is artificial intelligence (AI) with a multidisciplinary approach - algorithmic, design methodologies and cognitive science. I am particularly interested in discovering spatial and temporal patterns in semantically rich datasets. My areas of application are related to agronomy (mainly landscapes) and health (care pathways analysis). My first research direction is the **temporal and spatial pattern mining**. Data from the observation of living systems (agricultural and medical systems) have a strong spatial or temporal dimension. But the spatial and temporal information is often underutilized in the data mining algorithms. The challenge lies in identifying new kind of temporal/spatial patterns that have valuable properties to make possible their extraction by complete and correct algorithms. A recent approach I'm developping is the use declarative programming, more especially **[Answer Set Programming (ASP)](https://www.cs.utexas.edu/users/vl/papers/wiasp.pdf)** with [clingo](https://potassco.org), to mix pattern mining and reasonning. My second research direction aims at better including the user in the loop of knowledge discovery. Specifically, I am interested in implementing **interactive systems to support users in their exploration process** of large datasets. To acheive this goal I propose an enactive point of view of the data interpretation that brings creative solutions to take into account the cognitive ergonomy of the knowledge discovery tools.

Publications

johanne-bakalara
Image document

An open generator of synthetic administrative healthcare databases

Thomas Guyet , Tristan Allard , Johanne Bakalara , Olivier Dameron
IAS 2021 - Atelier Intelligence Artificielle et Santé, Jun 2021, Bordeaux (virtuel), France. pp.1-8
Communication dans un congrès hal-03326618v1
Image document

An extension of chronicles temporal model with taxonomies -Application to epidemiological studies

Johanne Bakalara , Thomas Guyet , Olivier Dameron , André Happe , Emmanuel Oger
HEALTHINF 2021 - 14th International Conference on Health Informatics, Feb 2021, online, France. pp.1-10
Communication dans un congrès hal-03096846v1
Image document

An extension of chronicles temporal model with taxonomies

Johanne Bakalara , Thomas Guyet , Olivier Dameron , André Happe , Emmanuel Oger
BDA 2020 - 36ème Conférence sur la Gestion des Données - Principes, Technologies et Applications, Oct 2020, Virtual, France. pp.1-10
Communication dans un congrès hal-03176657v1
Image document

Temporal models of care sequences for the exploration of medico-administrative data

Johanne Bakalara , Thomas Guyet , Olivier Dameron , Emmanuel Oger , André Happe
2019 - Workshop IA&Santé, PFIA, Jul 2019, Toulouse, France. pp.1-8
Communication dans un congrès hal-02265743v1