You will find here a series of projects that kept me busy during my PhD and post-doc.
— Summary —
In this project, we aimed to investigate the feasability of combining BCIs with Augmented Reality… Our results show that it is possible to control a little robot in Augmented Reality using an SSVEP-based BCI! Cooooooool!
— Related Paper —
* H. Si-Mohammed, J. Petit, C. Jeunet, F. Argelaguet, F. Spindler, A. Evain, N. Roussel, G. Casiez, A. Lécuyer, “Towards BCI-based Interfaces for Augmented Reality: Feasibility, Design and Evaluation“, accepted in IEEE Transactions in Visualization and Computer Graphics (TVCG) – pdf
— Summary —
The aim of this project is to acquire a better undestanding of the factors impacting users’ ability to control a BCI/to respond to a neurofeedback therapy. Thus, we are building a cognitive model of the task. This model includes factors related to the personality, cogntiive and neurophysiological profiles/states of the user, as well as external factors that could be used to alterate these profiles/states.
The ultimate goal would be to propose an Intelligent Tutoring System (ITS) for BCI user-training. Indeed, MI-BCI user-training is multi-factorial. Using an ITS (rather than improving independently some aspects of the training) would enable (1) to evaluate the impact of different parameters on users’ control abilities and (2) to adapt the training dynamically to each participant. — Ongoing project: New information soon!!!
— Related Paper —
* C. Jeunet, B. N’Kaoua, R. N’Kambou, F. Lotte, “Why and How to Use Intelligent Tutoring Systems to Adapt MI-BCI Training to Each User“, 6th International BCI Meeting, 2016 – pdf
— Summary —
We trained 18 participants to perform 3 MI-BCI tasks (left-hand motor imagery, mental rotation & mental subtraction) during 6 sessions. Results mainly revealed (1) a strong impact of spatial abilities on BCI performance and (2) a model explaining more than 80% of the variance of the data in terms of BCI performance (this model being composed of 4 factors related to the personality and cognitive profile of users). The projects on Spatial Abilities and on Emotional Support/Social Presence derive from this project.
—Related Papers —
* C. Jeunet, B. N’Kaoua, S. Subramanian, M. Hachet, F. Lotte, “Predicting Mental Imagery-Based BCI Performance from Personality, Cognitive Profile and Neurophysiological Patterns”, PLOS ONE, vol 10, no. 12, 2015 – pdf
* C. Jeunet, B. N’Kaoua, M. Hachet, F. Lotte, “Predicting Mental-Imagery Based Brain-Computer Interface Performance from Psychometric Questionnaires”, Accepted, Womencourage2015 – pdf
#PROJECT — Using Spatial Abilities as a Lever to better MI-BCI Performance
— Summary —
The project metionned above has revealed a strong impact of spatial abilities (measured using a mental rotation questionnaire) on MI-BCI performance. This result has been replicated in another of our studies. The emerging questionc is: Is there a causal relationship between spatial abilities and MI-BCI performance? Would a spatial ability training induce an improvement of MI-BCI performance? — Ongoing project: We designed, implemented and validated a spatial ability training protocol. Results show that in the group who followed a spatial ability training procedure, the progression in BCI depends on the duration of the training procedure. We are currently leading neurophysiological analyses.
—Related Papers —
* S. Teillet, F. Lotte, B. N’Kaoua, C. Jeunet, “Towards a spatial ability training to improve Motor-Imagery based Brain-Computer Interface (MI-BCI) Performance: A Pilot Study”, BCI Workshop of the SMC2106 – pdf
* C. Jeunet, F. Lotte, M. Hachet, S. Subramanian, B. N’Kaoua, “Spatial Abilities Play a Major Role in BCI Performance“, 6th International BCI Meeting, 2016 – pdf
* C. Jeunet, “Training Users’ Spatial Abilities to Improve Brain-Computer Interface Performance: A Theoretical Approach”, Colloque des Jeunes Chercheurs en Sciences Cognitives, 2015 – pdf
#PROJECT — Stroke Rehabilitation
— Summary —
Previous studies suggest a strong link between BCI performance and spatial abilities. Also, spatial ability exercises (such as mental rotation tasks) are known to activate the motor cortex. Thus, a spatial ablity training procedure could be used as a complement of the BCI assisted motor training to favor brain plasticity and recover from motor after-effects due to stroke. We recently started a collaboration with the Hospital of Bordeaux to test this hypothesis and test the relevance of different aspects of our work for stroke rehabilitation.
—Related Paper —
* C. Jeunet, F. Lotte, M. Hachet, S. Subramanian, B. N’Kaoua, “Spatial Abilities Play a Major Role in BCI Performance“, 6th International BCI Meeting, 2016 – pdf
#PROJECT — Considering the personality of the user to improve user training protocols
— Summary —
A previous study has shown that the Tension and Self-Reliance traits influenced users ability to use a BCI. In this project, we aim at exploring solutions to consider this aspects in order to improve training protocols. We chose to design and implement a learning companion able to provide users with emotional support and social presence. We tested this companion, called PEANUT (for personalised emotional agent for neurotechnology user-training), in a BCI experiment and showed it enabled to improve the BCI system usability.
— Related Paper —
* L. Pillette, C. Jeunet, B. Mansencal, R. N’Kambou, B. N’Kaoua & F. Lotte, “PEANUT : Personalised Emotional Agent for Neurotechnology User-Training”, 7th international BCI conference, 2017 – pdf
#PROJECT — Empirically evaluating the impact of standard training protocols on users’ ability to control an MI-BCI
— Summary —
Standard training protocols seem to be theoretically inappropriate. In this project, we wanted to experimentally evaluate the impact of the protocol, and more specifically of the feedback, on users’ MI-BCI performance. Thus, we used it in a BCI-free context: to train the participants to perform very simple tasks (drawing circles & triangles). Results showed that 17% of the participants did not manage to perform these simple tasks. It seems that the current feedback requires too many cognitive resources to be processed.
— Related Papers —
* C. Jeunet, E. Jahanpour, F. Lotte, “Why standard brain-computer interface (BCI) training protocols should be changed: An experimental study“, Journal of Neural Engineering, 2016 – pdf
* C. Jeunet, A. Cellard, S. Subramanian, M. Hachet, B. N’Kaoua and F. Lotte, “How Well Can We Learn With Standard BCI Training Approaches? A Pilot Study”, 6th International BCI conference, 2014 – pdf
#PROJECT — Vibrotactile Feedback for MI-BCI control
— Summary —
The previously mentioned project suggests that standard feedback is difficult to process. We hypothesised that because it is more consistent with the task & because it would free the visual channel, a tactile feedback would be more efficient in a multi-tasking context. Results suggest that this hypothesis is valid!
— Related Paper—
* C. Jeunet, C. Vi, D. Spelmezan, B. N’Kaoua, F. Lotte, S. Subramanian, “Continuous Tactile Feedback for Motor-Imagery based Brain-Computer Interaction in a Multitasking Context”, Interact2015 – pdf