Subspace Oddity - Optimization on Product of Stiefel Manifolds for EEG Data

Abstract

Dimensionality reduction of high-dimensional electroencephalography (EEG) covariance matrices is crucial for effective utilization of Riemannian geometry in Brain-Computer Interfaces (BCI). In this paper, we propose a novel similaritybased classification method that relies on dimensionality reduction of EEG covariance matrices. Conventionally, the dimension of the original high-dimensional space is reduced by projecting into one low-dimensional space, and the similarity is learned only based on the single space. In contrast, our method, MUltiple SUbspace Mdm Estimation (MUSUME), obtains multiple low-dimensional spaces that enhance class separability by solving the proposed optimization problem, then the similarity is learned in each low-dimensional space. This multiple projection approach encourages finding the space that is more useful for similarity learning. Experimental evaluation with high-dimensionality EEG datasets (128 channels) confirmed that MUSUME proved significant improvement for classification (p < 0.001) and also it showed the potential to beat the existing method relying on only one subspace representation.

Novel SPD Matrix Representations Considering Cross-Frequency Coupling for EEG Classification Using Riemannian Geometry

“…To further improve BCIs, various Riemannnian specific approaches have been developed including EEG channel selection [8], dimensionality reduction [9], artifact/outlier detection [10] or frequency band (FB) selection [11], among other. All these methods have in common that they operate after the covariance matrix estimations, and all apply on conventional cross-channel Cov only.…”