Improving classification performance of motor imagery BCI through EEG data augmentation with conditional generative adversarial networks

• Published in: Neural networks Vol. 180; p. 106665
• Main Authors: Choo, Sanghyun, Park, Hoonseok, Jung, Jae-Yoon, Flores, Kevin, Nam, Chang S.
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.12.2024
• Subjects: Brain - physiology; Brain-computer interface (BCI); Brain-Computer Interfaces; Data augmentation (DA); Deep Learning; Electroencephalogram (EEG); Electroencephalography - methods; Generative adversarial networks (GANs); Humans; Imagination - physiology; Machine Learning; Motor imagery (MI); Neural Networks, Computer; Motor imagery (MI); Brain-computer interface (BCI); Data augmentation (DA); Electroencephalogram (EEG); Generative adversarial networks (GANs)
• ISSN: 0893-6080; 1879-2782; 1879-2782
• DOI: 10.1016/j.neunet.2024.106665

In brain-computer interface (BCI), building accurate electroencephalogram (EEG) classifiers for specific mental tasks is critical for BCI performance. The classifiers are developed by machine learning (ML) and deep learning (DL) techniques, requiring a large dataset for training to build reliable and accurate models. However, collecting large enough EEG datasets is difficult due to intra-/inter-subject variabilities and experimental costs. This leads to the data scarcity problem, which causes overfitting issues to training samples, resulting in reducing generalization performance. To solve the EEG data scarcity problem and improve the performance of the EEG classifiers, we propose a novel EEG data augmentation (DA) framework using conditional generative adversarial networks (cGANs). An experimental study is implemented with two public EEG datasets, including motor imagery (MI) tasks (BCI competition IV IIa and III IVa), to validate the effectiveness of the proposed EEG DA method for the EEG classifiers. To evaluate the proposed cGAN-based DA method, we tested eight EEG classifiers for the experiment, including traditional MLs and state-of-the-art DLs with three existing EEG DA methods. Experimental results showed that most DA methods with proper DA proportion in the training dataset had higher classification performances than without DA. Moreover, applying the proposed DA method showed superior classification performance improvement than the other DA methods. This shows that the proposed method is a promising EEG DA method for enhancing the performances of the EEG classifiers in MI-based BCIs.