MDRM: Classification of covariance matrices with MDRM.

In LauraMasiero/RiemannR: RiemannR - EEG-based BCI analysis with Riemannian geometry

Description

This function allows the binary classification of the given covariance matrices with the Minimum distance to Riemannian Mean algorithm.

Usage

MDRM(scm_list, centroids_list)

Arguments

scm_list	a list of numeric sample covariance matrices.
centroids_list	a list containing the (geometric) mean of both classes computed on a training set. The first element of the list must be the target class' mean, followed by the mean of the other class.

Value

It returns a list containing two elements:

classes	numeric vector cointaining the class indicator.
distances	numeric matrix containing the distances among the two centroids, computed with the Riemannian distance.

Author(s)

Laura Masiero, email: [e-mail]

References

Barachant, Alexandre e Marco Congedo (2014). "A Plug&Play P300 BCI Using Information Geometry". In: url: http://arxiv.org/abs/1409.0107.

See Also

RaoDist

LauraMasiero/RiemannR documentation built on Sept. 29, 2020, 9:51 p.m.