Multivariate Temporal Dictionary Learning for EEG
This work addresses the need for more efficient and interpretable EEG signal representation for researchers and clinicians in neuroscience, though it is incremental as it builds on existing dictionary learning techniques.
The authors tackled the problem of efficiently representing EEG signals by proposing a data-driven dictionary learning method that incorporates spatial and temporal modeling, which outperformed classical Gabor dictionary approaches in terms of representative power and spatial flexibility on real EEG data.
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.