Multivariate Temporal Dictionary Learning for EEG

TL;DR

This paper introduces a data-driven multivariate dictionary learning approach for EEG signals that outperforms traditional fixed dictionaries, capturing physiologically meaningful patterns and improving representation efficiency.

Contribution

It proposes a novel multivariate dictionary learning method for EEG that incorporates spatial and temporal modeling, enhancing interpretability and performance over classical methods.

Findings

Learned dictionaries outperform Gabor dictionaries in EEG representation

The method captures physiologically meaningful patterns like P300 evoked potentials

Improves spatial flexibility and interpretability of EEG analysis

Abstract

This article addresses the issue of representing electroencephalographic (EEG) signals in an efficient way. While classical approaches use a fixed Gabor dictionary to analyze EEG signals, this article proposes a data-driven method to obtain an adapted dictionary. To reach an efficient dictionary learning, appropriate spatial and temporal modeling is required. Inter-channels links are taken into account in the spatial multivariate model, and shift-invariance is used for the temporal model. Multivariate learned kernels are informative (a few atoms code plentiful energy) and interpretable (the atoms can have a physiological meaning). Using real EEG data, the proposed method is shown to outperform the classical multichannel matching pursuit used with a Gabor dictionary, as measured by the representative power of the learned dictionary and its spatial flexibility. Moreover, dictionary learning can capture interpretable patterns: this ability is illustrated on real data, learning a P300 evoked potential.