EEG signal analysis for brain-computer interfaces for large public applications

Abstract : Brain-computer interfaces (BCIs) use signals from the brain to control machines and devices (keyboards , cars, neuro- prostheses) . After several decades of development, modern BCI techniques show a relative maturity compared to the past decades and receive more and more attention in real-world general public applications, in particular in the domain of BCI-based human-computer interactions for healthy people, such as neuro-games. The aim of this thesis is to develop an experimental setup and signal processing algorithms for non-invasive, portable and easy-to-use BCI systems for large public (non-medical) applications. To achieve this goal, a review of the state of the art (existing prototypes and commercial products, experimental setup, algorithms) is first performed to get a full scope and a good understanding in this field. The main contributions of this thesis include: 1) a hybrid BCI paradigm with a few electrodes , 2) dimensionality reduction for multi-channel BCI (with a high number of electrodes ), 3) reduction and selection channel , 4) improved classification for BCI with a few predetermined electrodes. The experimental results show that the methods proposed in this thesis can improve classification performance and / or increase the efficiency of the system ( for example, reduce the learning time, reduce the cost of equipment ) , so as to contribute to BCI for the general applications.
Complete list of metadatas

https://pastel.archives-ouvertes.fr/tel-01234955
Contributor : Abes Star <>
Submitted on : Friday, November 27, 2015 - 2:38:21 PM
Last modification on : Thursday, October 17, 2019 - 12:36:09 PM
Long-term archiving on : Saturday, April 29, 2017 - 3:19:53 AM

File

TheseYangV2.pdf
Version validated by the jury (STAR)

Identifiers

  • HAL Id : tel-01234955, version 1

Collections

Citation

Yuan Yang. EEG signal analysis for brain-computer interfaces for large public applications. Signal and Image processing. Télécom ParisTech, 2013. English. ⟨NNT : 2013ENST0043⟩. ⟨tel-01234955⟩

Share

Metrics

Record views

2818

Files downloads

1180