OATAO - Open Archive Toulouse Archive Ouverte Open Access Week

Heading for motor imagery brain-computer interfaces (MI-BCIs) usable out-of-the-lab: Impact of dry electrode setup on classification accuracy

Casso, Maria-Isabel and Jeunet, Camille and Roy, Raphaëlle N. Heading for motor imagery brain-computer interfaces (MI-BCIs) usable out-of-the-lab: Impact of dry electrode setup on classification accuracy. (2021) In: IEEE Neural Engineering Conference, 4 May 2021 - 6 May 2021 (Virtual event, Italy).

[img]
Preview
(Document in English)

PDF (Author's version) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
977kB

Official URL: https://doi.org/10.1109/NER49283.2021.9441410

Abstract

A primary challenge to make motor-imagery Brain-Computer Interfaces (MI-BCIs) technologies usable and actually used out-of-the-lab consists of providing EEG systems that are efficient in terms of classification accuracy- and easy to install, e.g., using a minimal number of dry electrodes. We hypothesize that the optimal signal processing method might depend on the number of (dry) electrodes that are used. Therefore, we compared for the first time the classification accuracy associated with different dry electrode setups, i.e., 7 configurations from 8 to 32 channels, and various signal processing methods, namely (1) regularized Common Spatial Pattern (rCSP) + Linear Discriminant Analysis, (2) rCSP + Support Vector Machine (SVM), (3) Minimum Distance to Riemannian Mean and (4) SVM in the Riemannian Tangent Space. This offline comparison was performed on the data of 10 participants (one session each). Our results suggest that for all methods. MI-BCI performance drops significantly for 8 and 12 channels (p < 0.01). Moreover, method 3 was associated with the lowest performances (p < 0.05). Finally, post-doc analyses suggest that methods 1 and 2 perform best with the highest numbers of electrodes 28 and 32. For method 4 the best performance is obtained using 20 and 24 channels, which seems to be the optimal combination (p < 0.05). These results show the importance of selecting the signal processing pipeline as a function of the location and number of the electrodes.

Item Type:Conference or Workshop Item (Poster)
Additional Information:This work was funded by an ANITI (Artificial and Natural Intelligence Toulouse Institute) Research Chair allocated to Pr F. Dehais.
Audience (conference):International conference proceedings
Uncontrolled Keywords:
Institution:French research institutions > Centre National de la Recherche Scientifique - CNRS (FRANCE)
Université de Toulouse > Institut Supérieur de l'Aéronautique et de l'Espace - ISAE-SUPAERO (FRANCE)
Université de Toulouse > Université Toulouse - Jean Jaurès - UT2J (FRANCE)
French research institutions > Artificial and Natural Intelligence Toulouse Institute - ANITI (FRANCE)
Laboratory name:
Funders:
ANITI ANR-19-PI3A-0004
Statistics:download
Deposited On:26 May 2021 14:22

Repository Staff Only: item control page