An Amplitudes-Perturbation Data Augmentation Method in Convolutional Neural Networks for EEG Decoding

Abstract

Brain-Computer Interface (BCI) system provides a pathway between humans and the outside world by analyzing brain signals which contain potential neural information. Electroencephalography (EEG) is one of most commonly used brain signals and EEG recognition is an important part of BCI system. Recently, convolutional neural networks (ConvNet) in deep learning are becoming the new cutting edge tools to tackle the problem of EEG recognition. However, training an effective deep learning model requires a big number of data, which limits the application of EEG datasets with a small number of samples. In order to solve the issue of data insufficiency in deep learning for EEG decoding, we propose a novel data augmentation method that add perturbations to amplitudes of EEG signals after transform them to frequency domain. In experiments, we explore the performance of signal recognition with the state-ofthe-art models before and after data augmentation on BCI Competition IV dataset 2a and our local dataset. The results show that our data augmentation technique can improve the accuracy of EEG recognition effectively.

Recruiting neural field theory for data augmentation in a motor imagery brain–computer interface

“… Lee et al (2021) employed ensemble empirical mode decomposition to augment a 2-condition MI training set, achieving an impressive over 8% enhancement in classification accuracy ( Lee et al, 2021 ). Conversely, Zhang et al (2018) introduced Gaussian noise into the EEG signal within the frequency domain to augment a 4-condition MI training set, leading to a more modest improvement of just 2.3% ( Zhang et al, 2018 ). Additionally, the rise of deep learning in the past decade has provided valuable tools for DA.…”

A Motor Imagery Signals Classification Method via the Difference of EEG Signals Between Left and Right Hemispheric Electrodes

“…It reduces the data preprocessing steps and manual feature processing steps. Also, deep learning has made outstanding contributions to the improvement of MI-BCI (Li et al, 2018 ; Zhang et al, 2018 ; Cho et al, 2019 ; Robinson et al, 2019 ). Nakagome et al ( 2020 ) used neural networks and machine learning algorithms to decode EEG.…”

WLnet: Towards an Approach for Robust Workload Estimation Based on Shallow Neural Networks

“…It is important to note that training a deep neural network requires a large amount of data samples in order to achieve a satisfactory accuracy, but EEG datasets usually contains a small amount of samples. This is another limitation related to the use of deep neural networks for EEG processing, as having few samples always leads to the overfitting problem [30], [48], [49]. This further leads to less accurate and thus unreliable detection results for many BCI applications.…”