Channel Selection over Riemannian Manifold with Non-Stationarity Consideration for Brain-Computer Interface Applications.
Khadijeh SadatnejadAline RocLéa PilletteAurélien AppriouThibaut MonseigneFabien LottePublished in: ICASSP (2020)
Keyphrases
- brain computer interface
- riemannian manifolds
- motor imagery
- euclidean space
- signal processing
- evoked potentials
- event related potentials
- non stationary
- eeg signals
- geometric structure
- brain signals
- parameter space
- covariance matrix
- vector space
- image processing
- neural network
- multi class classification
- eeg data
- lie group
- mean shift
- training data