Spatial Graph Signal Interpolation with an Application for Merging BCI Datasets with Various Dimensionalities

BCI Motor Imagery datasets usually are small and have different electrodes setups. When training a Deep Neural Network, one may want to capitalize on all these datasets to increase the amount of data available and hence obtain good generalization results. To this end, we introduce a spatial graph si...

Full description

Saved in:
Bibliographic Details
Published inICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) pp. 1 - 5
Main Authors Ouahidi, Yassine El, Drumetz, Lucas, Lioi, Giulia, Farrugia, Nicolas, Pasdeloup, Bastien, Gripon, Vincent
Format Conference Proceeding
LanguageEnglish
Published IEEE 04.06.2023
Subjects
BCI
Deep learning
DNN
EEG
Electrodes
graph signal processing
Interpolation
Merging
motor imagery
Neural networks
signal interpolation
Signal processing
Training
Online AccessGet full text

Cover

More Information
Summary:BCI Motor Imagery datasets usually are small and have different electrodes setups. When training a Deep Neural Network, one may want to capitalize on all these datasets to increase the amount of data available and hence obtain good generalization results. To this end, we introduce a spatial graph signal interpolation technique, that allows to interpolate efficiently multiple electrodes. We conduct a set of experiments with five BCI Motor Imagery datasets comparing the proposed interpolation with spherical splines interpolation. We believe that this work provides novel ideas on how to leverage graphs to interpolate electrodes and on how to homogenize multiple datasets.
ISSN:2379-190X
DOI:10.1109/ICASSP49357.2023.10097201