postdoc in modelling of spatial trajectories (M/F)

Job Description

Missions

Development of new algorithms to extract markers of Alzheimer's disease from spatial navigation trajectories recorded via a video game (Sea Hero Quest). This project has already enabled the collection of spatial navigation data from over 4 million members of the general public via a video game available free of charge on tablets and smartphones. In this game, participants were asked to solve underwater mazes by controlling a small boat, whilst we recorded its trajectory. This is the largest cognitive-behavioural database collected by a citizen science project. Analysis of this database has enabled the identification of numerous determinants of spatial navigation within the general population, such as age, gender, environment, education and sleep patterns. Throughout this research, navigation performance was quantified by the length of the trajectories: the shorter the trajectory, the more optimal it was. This metric has the advantage of being simple and interpretable, but it remains limited: two trajectories may well be the same length but have very different shapes, and thus result from distinct spatial strategies.
The main aim of this postdoctoral position is to develop a deep learning algorithm capable of grouping trajectories according to the strategies they appear to reflect, rather than simply by their length.

Activity

• Building artificial neural networks to identify latent spaces where trajectories cluster into homogeneous groups of spatial strategies
• Writing and publishing scientific articles
• Attending scientific conferences
• Liaising with the various clinical and academic stakeholders involved in the project.

Your Profil

Skills

• Knowledge: machine learning, analysis of time-series of spatial coordinates
• Skills: Python coding, artificial neural networks, scientific writing
• Interpersonal skills: interacting with stakeholders from the clinical and academic sectors, both nationally and internationally

Your Work Environment

This postdoctoral position is part of the Sea Hero Quest project, funded by the ANR ACTSOMA programme and the Shape-Med SENSATIONAL project. It will take place within the SICAL team at the Laboratory of Image Computing and Information Systems (LIRIS), a joint research unit (UMR 5205) of the CNRS, INSA Lyon, Claude Bernard Lyon 1 University, Lumière Lyon 2 University and École Centrale de Lyon. It has 330 members. LIRIS's research covers a broad spectrum of computer science. The SICAL team develops generic approaches, models and tools to enhance humans' ability to interact, learn and adapt to context.

Constraints and risks

35 hours per week, full-time

Compensation and benefits

Compensation

From €3,071 gross per month, depending on experience

Annual leave and RTT

44 jours

Remote Working practice and compensation

Pratique et indemnisation du TT

Transport

Prise en charge à 75% du coût et forfait mobilité durable jusqu’à 300€

About the offer

About the CNRS

The CNRS is a major player in fundamental research on a global scale. The CNRS is the only French organization active in all scientific fields. Its unique position as a multi-specialist allows it to bring together different disciplines to address the most important challenges of the contemporary world, in connection with the actors of change.

CNRS

The research professions