Towards physiology-informed data augmentation for EEG-based BCIs

TL;DR

This paper introduces a physiology-informed data augmentation method for EEG-based BCIs that leverages source localization and head models to generate more diverse training data, improving classification accuracy.

Contribution

The novel augmentation technique uses source localization and head models to create physiologically meaningful data variations, enhancing BCI classifier performance.

Findings

Accuracy increased by 13% with deep neural networks

Accuracy increased by 6% with shallow neural networks

Accuracy increased by 2% with LDA

Abstract

Most EEG-based Brain-Computer Interfaces (BCIs) require a considerable amount of training data to calibrate the classification model, owing to the high variability in the EEG data, which manifests itself between participants, but also within participants from session to session (and, of course, from trial to trial). In general, the more complex the model, the more data for training is needed. We suggest a novel technique for augmenting the training data by generating new data from the data set at hand. Different from existing techniques, our method uses backward and forward projection using source localization and a head model to modify the current source dipoles of the model, thereby generating inter-participant variability in a physiologically meaningful way. In this manuscript, we explain the method and show first preliminary results for participant-independent motor-imagery classification. The accuracy was increased when using the proposed method of data augmentation by 13, 6 and 2 percentage points when using a deep neural network, a shallow neural network and LDA, respectively.