Interpretable Riemannian Classification in Brain-Computer Interfacing

Interpretable Riemannian Classification in Brain-Computer Interfacing

Abstract

Riemannian methods are currently one of the best ways of building classifiers for EEG data in a brain-computer interface (BCI). However, they are computationally complex and suffer from a lack of interpretability. Since the full covariance matrix is used for each classification, it is not immediately possible to see what underlying signals are generating the classified changes in variance. Particularly in a rehabilitation context, where it is essential to control which brain signals are used for classification, this can be a severely limiting factor. Further, the requirement to perform a matrix logarithm can become prohibitively complex for real-time computation. In this work, we explore a method for extracting spatial filters from a solution in the Riemannian tangentspaceandcompareitagainstcommonspatialpatterns. Weshowviacomparisonsonmultipleopen-access datasetsthatitispossibletogeneratefiltersthatapproach the performance of the full Riemannian solution while maintaining interpretability.

Grafik Top
Authors
  • Xu, Jiachen
  • Grosse-Wentrup, Moritz
  • Jayaram, Vinay
Grafik Top
Shortfacts
Category
Paper in Conference Proceedings or in Workshop Proceedings (Paper)
Event Title
Graz BCI Conference 2019
Divisions
Neuroinformatics
Event Location
Graz, Österreich
Event Type
Conference
Event Dates
16.-20.9.2019
Date
17 September 2019
Export
Grafik Top