2018-00781 - Postdoctoral position: Redefining EEG Signal Processing and Machine Learning to ensure efficient Mental Imagery-based BCI user training
Le descriptif de l’offre ci-dessous est en Anglais

Type de contrat : CDD de la fonction publique

Niveau de diplôme exigé : Thèse ou équivalent

Fonction : Post-Doctorant

A propos du centre ou de la direction fonctionnelle

The Potioc project-team explores new approaches “beyond the mouse” in the field of Human-Computer Interaction. More specifically, we are interested in approaches that favor rich interactions,both regarding interaction possibilities and perceptive feedback. Our objective is to increase immersion and engagement of users with regard to the interaction tasks. Final goals are the stimulation of creativity, improvement of learning or contribution to the well-being of people. For achieving these goals, we focus on the design, development and evaluation of new methods for “popular interaction” targeted at a large variety of users.

Contexte et atouts du poste

Brain computer interfaces (BCI) are communication and control tools that enable their users to interact with computers by using brain activity alone.

A prominent type of BCI is Mental Imagery (MI) BCI, that translate changes in brain activity due to mental imagery tasks performed by the user (e.g., imagination of movements or mental calculation) into control commands for a computer. Using a MI-BCI requires dedicated training, and the more the user practices the better he/she will get at it, i.e. the user's mental commands will be more often correctly recognized by the system. Current BCI are rather unreliable, and one current hypothesis to explain this lack of reliability could be inappropriate user training.

We are thus currently conducting researches to understand this user training to then improve it and make it suitable. Such researches are conducted as part of ERC starting grant project BrainConquest (https://team.inria.fr/potioc/brainconquest/ – Principal Investigator : Fabien Lotte) at Inria Bordeaux Sud-Ouest, France, in team Potioc (https://team.inria.fr/potioc/).
 

Mission confiée

As part of this research, the goal of this Post-doc would be to contribute to the improvement of BCI user training by redefining the EEG signal processing and machine learning tools used in MI-BCI in order to ensure they can lead to efficient user training.

Indeed, current MI-BCI user training mostly relies on providing the user with a single simple feedback: the classifier output. However, this feedback is only corrective, i.e., it only tells the users whether they did well, but not why they did well or not. Current feedback thus lacks explanatory power.

Moreover, this feedback is directly mapped to the classifier output, without considering whether the user can actually self-regulate the features used by the classifier or whether the user can actually make sense of such feedback. We thus need a new generation of EEG signal processing and machine learning tools that would ensure the feedback provided is explanatory and understandable, and can lead to efficient user training.

The goal of this post-doc position is thus to design and validate this new generation of EEG signal processing tools. In particular, the post-doc could try to identify EEG features that could explain and predict successful mental command recognition by the BCI, in order to be able to provide explanatory feedback. The post-doc could also incorporate instructional design principles into EEG machine learning optimization algorithms in order to obtain features and classifiers whose resulting feedback makes sense to the users and ensure they can learn from it. We have data from multiple BCI users who trained over multiple days with MI-BCI. These data sets will be the basis for creating, testing and validating different initial EEG signal processing tools. The post-doc could also design and run MI-BCI experiments to validate online and in real-time the designed EEG signal processing tools for MI-BCI user training.

Principales activités

  • Contribute to the improvement of BCI user training by redefining the EEG signal processing and machine learning tools used in MI-BCI in order to ensure they can lead to efficient user training
  • Design and validate the new generation of EEG signal processing tools
  • Incorporate instructional design principles into EEG machine learning optimization algorithms in order to obtain features and classifiers whose resulting feedback makes sense to the users and ensure they can learn from it

Compétences

Skills required :

• EEG signal processing (temporal/spatial filtering, subspace identification, source reconstruction, etc)

• Machine Learning & Pattern Recognition for EEG classification

• Python / Matlab programming

• Able to speak, write and work in an English speaking environment

• Willingness to learn and exploit knowledge from educational psychology and cognitive sciences (experience and knowledge in these fields would be a strong plus)

• Experience with ElectroEncephaloGraphy (EEG) and/or BCI experiments

Avantages sociaux

  • Subsidised catering service
  • Partially-reimbursed public transport

Rémunération

2653 € / month (before taxs)