A Data Augmentation Scheme for Geometric Deep Learning in Personalized Brain–Computer Interfaces

Fotis P. Kalaganis,Nikolaos A. Laskaris,Spiros Nikolopoulos,Ioannis Kompatsiaris,Elisavet Chatzilari

doi:10.1109/access.2020.3021580

Abstract

Electroencephalography signals inherently deviate from the notion of regular spatial sampling, as they reflect the coordinated action from multiple distributed overlapping cortical networks. Hence, the observed brain dynamics are influenced both by the topology of the sensor array and the underlying functional connectivity. Neural engineers are currently exploiting the advances in the domain of graph signal processing in an attempt to create robust and reliable brain decoding systems. In this direction, Geometric Deep Learning is a highly promising concept for combining the benefits of graph signal processing and deep learning towards revolutionising Brain-Computer Interfaces (BCIs). However, its exploitation has been hindered by its data-demanding character. As a remedy, we propose here a novel data augmentation approach that combines the multiplex network modelling of multichannel signal with a graph variant of the classical Empirical Mode Decomposition (EMD), and which proves to be a strong asset when combined with Graph Convolutional Neural Networks (GCNNs). As our graph-EMD algorithm makes no assumptions with respect to linearity and stationarity, it appears as an appealing solution towards analysing brain signals without artificially imposing regularities in either temporal or spatial domain. Our experimental results indicate that the proposed scheme for data augmentation leads to substantial improvement when it is combined with GCNNs. Using recordings from two distinct BCI applications and comparing against a state-of-the-art augmentation method, we illustrate the benefits from its use. By making it available to BCI community, we hope to further foster the application of geometric deep learning in the field.

Highlights

Research on Brain-Computer Interfaces (BCIs) has experienced an impressive growth in the recent past
We note that the term Graph Convolutional Neural Networks (GCNNs) refers to a convolutional neural network that operates on graphs
The introduced data augmentation method is used under two different classification schemes with emphasis in the GCNNs, so as to investigate whether and under which conditions the use of geometric deep learning can bring tangible benefits with respect to baseline machine learning schemes like Support Vector Machines

Summary

Introduction

Research on Brain-Computer Interfaces (BCIs) has experienced an impressive growth in the recent past. The main objective in BCIs is to provide a direct communication pathway between the human brain and an external device. A typical BCI system consists of a signal processing module which can be further decomposed into three submodules. (i.e. pre-processing, feature extraction and feature selection) and a classification module which converts the resulting features into machine commands. The most common neuroimaging modality that is employed in BCIs is the electroencephalography, a typically non-invasive neuroimaging technology that measures the brain’s electrical activity using electrodes placed on the human scalp. The produced recording, called electroencephalogram (EEG), is not easy to interpret as it has a low signal to noise ratio and its statistical properties change.

Objectives

Methods

Results

Conclusion