Skip to Main content Skip to Navigation

Apprentissage neuronal par neurofeedback à l’aide d’un système EEG portable : application à la réduction du stress chez l'Homme

Fanny Grosselin 1, 2 
2 ARAMIS - Algorithms, models and methods for images and signals of the human brain
SU - Sorbonne Université, Inria de Paris, ICM - Institut du Cerveau et de la Moëlle Epinière = Brain and Spine Institute
Abstract : This thesis focuses on the design, implementation and evaluation of a portable EEG neurofeedback system to help manage stress for the general public. Such a system allows users to learn to modulate their mental states through brain plasticity phenomena. However, several factors can complicate this learning, such as a lower signal-to-noise ratio of the EEG acquired by dry electrodes, contamination by artefacts or the definition of relevant parameters from the EEG signals. In order to optimize this neural feedback, my thesis first proposes a statistical method to ensure the quality of the acquired EEG signals, as well as a corrective method of artefacts, in order to extract a relevant measure of EEG activity reflecting the individual's stress or relaxation level. The development of a neurofeedback index that is relevant and adapted to the user is also proposed. Following the algorithmic constitution of such a system, the neurofeedback learning characteristics could be studied. In particular, I show that intersession learning seems to be taking place and that in stressed subjects, brain changes occur in the alpha band during the rest phases. Finally, through these methodological aspects, software integration and longitudinal analysis, this thesis constitutes the fundamental building blocks of an automatic recommendation system adapted to the user. Such a system would allow a personal follow-up of users in order to propose a preventive strategy for stress management.
Complete list of metadata
Contributor : ABES STAR :  Contact
Submitted on : Friday, October 29, 2021 - 2:35:22 PM
Last modification on : Wednesday, June 8, 2022 - 12:50:08 PM


Version validated by the jury (STAR)


  • HAL Id : tel-03405431, version 2


Fanny Grosselin. Apprentissage neuronal par neurofeedback à l’aide d’un système EEG portable : application à la réduction du stress chez l'Homme. Réseau de neurones [cs.NE]. Sorbonne Université, 2019. Français. ⟨NNT : 2019SORUS125⟩. ⟨tel-03405431v2⟩



Record views


Files downloads