A Riemannian Geometry Approach to Reduced and Discriminative Covariance Estimation in Brain Computer Interfaces.
Fotis P. KalaganisNikos LaskarisElisavet ChatzilariSpiros NikolopoulosIoannis KompatsiarisPublished in: IEEE Trans. Biomed. Eng. (2020)
Keyphrases
- brain computer interface
- information geometry
- healthy subjects
- signal processing
- eeg signals
- motor imagery
- multimodal interaction
- evoked potentials
- geodesic distance
- feature selection
- spinal cord injury
- brain signals
- fisher information
- brain activity
- estimation error
- affine invariant
- information processing
- tangent space
- feature extraction
- neural network