Flexible Covariance Matrix Decomposition Method for Data Augmentation and Its Application to Brainwave Signals

Hoirim Lee,Woochul Nam,Wonseok Yang

doi:10.3390/app11209388

Abstract

The acquisition of a large-volume brainwave database is challenging because of the stressful experiments that are required; however, data synthesis techniques can be used to address this limitation. Covariance matrix decomposition (CMD), a widely used data synthesis approach, generates artificial data using the correlation between features and random noise. However, previous CMD methods constrain the stochastic characteristics of artificial datasets because the random noise used follows a standard distribution. Therefore, this study has improved the performance of CMD by releasing such constraints. Specifically, a generalized normal distribution (GND) was used as it can alter the kurtosis and skewness of the random noise, affecting the distribution of the artificial data. For the validation of GND performance, a motor imagery brainwave classification was conducted on the artificial dataset generated by GND. The GND-based data synthesis increased the classification accuracy obtained with the original data by approximately 8%.

Highlights

Brain–machine interface (BMI) technology is aimed at acquiring and analyzing brainwave signals for device control [1,2]
This study focused on the effects of random noise, used in covariance matrix decomposition (CMD), on data augmentation
The stochastic nature of random noise, which is generated by a normal distribution, is restricted because it only depends on its mean value and variance

Summary

Introduction

Brain–machine interface (BMI) technology is aimed at acquiring and analyzing brainwave signals for device control [1,2]. Most BMI systems suffer from a lack of data because the acquisition of bio-signals requires stressful experiments. Noise addition methods generate artificial datasets by adding noise vectors to the original data [9,10,11,12]. Salama et al [11] added a Gaussian noise signal (with zero mean and unit variance) to electroencephalogram (EEG) signals to generate artificial EEG signals. This method adds simple noise without considering the stochastic characteristics of the bio-signal of interest. A quality artificial dataset is not guaranteed when using this method

Objectives

Methods

Results

Conclusion