Abstract
The quality and quantity of training data are crucial to the performance of a deep-learning-based brain-computer interface (BCI) system. However, it is not practical to record EEG data over several long calibration sessions. A promising time- and cost-efficient solution is artificial data generation or data augmentation (DA). Here, we proposed a DA method for the motor imagery (MI) EEG signal called brain-area-recombination (BAR). For the BAR, each sample was first separated into two ones (named half-sample) by left/right brain channels, and the artificial samples were generated by recombining the half-samples. We then designed two schemas (intra- and adaptive-subject schema) corresponding to the single- and multi-subject scenarios. Extensive experiments using the classifier of EEGnet were conducted on two public datasets under various training set sizes. In both schemas, the BAR method can make the EEGnet have a better performance of classification (p < 0.01). To make a comparative investigation, we selected two common DA methods (noise-added and flipping), and the BAR method beat them (p < 0.05). Further, using the proposed BAR for augmentation, EEGnet achieved up to 8.3% improvement than a typical decoding algorithm CSP-SVM (p < 0.01), note that both the models were trained on the augmented dataset. This study shows that BAR usage can significantly improve the classification ability of deep learning to MI-EEG signals. To a certain extent, it may promote the development of deep learning technology in the field of BCI.
Highlights
The brain-computer interface (BCI) is a communication control system directly established between the brain and external devices, using signals generated during brain activity (Wolpaw et al, 2000)
Where xi, xj ∈ RC×T, C is the number of electrodes, T is the sample-points, PMI−EEG is the distribution of motor imagery (MI)-EEG data
Brain Area Recombination Based on the assumption described in (1), we propose two similar data augmentation (DA) methods for single-subject and multi-subject scenes for EEG of motor imagination
Summary
The brain-computer interface (BCI) is a communication control system directly established between the brain and external devices (computers or other electronic devices), using signals generated during brain activity (Wolpaw et al, 2000). Electroencephalogram (EEG) is one of the most common signals used for building a BCI. Recent years have witnessed intense researches into different types of BCI systems. According to the signal acquisition method, BCI technology can be divided into three types: nonimplantable system, semi-implantable system, an implantable system (Wolpaw et al, 2000). Non-implantable BCI systems mainly use EEG to recognize human’s intention. According to the signal generation mechanism, BCI systems can be divided into induced BCI systems and spontaneous BCI systems. The induced BCI systems are: steady-state visual evoked potentials (SSVEP) (Friman et al, 2007; Ko et al, 2020), slow cortical potentials (Beuchat et al, 2013), and the P300 (Yin et al, 2016; Yu et al, 2017; Chikara and Ko, 2019), and the spontaneous BCI systems are: motor imagery (MI) (Choi and Cichocki, 2008; Belkacem et al, 2018; Chen et al, 2019; Wang et al, 2020)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
