Motor Imagery EEG Data Augmentation with cWGAN-GP for Brain-Computer Interfaces

• Lucas H. dos Santos UFABC
• Denis G. Fantinato UNICAMP

DOI: https://doi.org/10.5753/eniac.2022.227592

Resumo

Motor imagery is a paradigm in Brain-Computer Interface (BCI) systems based on EEG data. Recently, Deep Neural Networks (DNNs), such as EEGNet, have become a vital component for those systems, overcoming previous state-of-the-art techniques for classifying these data. However, most motor imagery EEG datasets are relatively small, hindering DNNs from achieving better results. In this sense, we propose using Generative Adversarial Networks to augment dataset 1 from the BCI Competition IV for classification efficiency improvement. In addition, we explore augmentation with Gaussian noise for comparison purposes. The experiments were analyzed considering the intrasubject and cross-subject perspectives.

Referências

Aggarwal, A., Mittal, M., and Battineni, G. (2021). Generative adversarial network: An overview of theory and applications. International Journal of Information Management Data Insights, 1(1):100004.

Ang, K. K., Chin, Z. Y., Zhang, H., and Guan, C. (2008). Filter bank common spatial pattern (fbcsp) in brain-computer interface. In 2008 IEEE international joint conference on neural networks (IEEE world congress on computational intelligence), pages 2390-2397. IEEE.

Arjovsky, M., Chintala, S., and Bottou, L. (2017). Wasserstein generative adversarial networks. In International conference on machine learning, pages 214-223. PMLR.

Blankertz, B., Dornhege, G., Krauledat, M., Müller, K.-R., and Curio, G. (2007). The non-invasive berlin brain-computer interface: fast acquisition of effective performance in untrained subjects. NeuroImage, 37(2):539-550.

Fahimi, F., Dosen, S., Ang, K. K., Mrachacz-Kersting, N., and Guan, C. (2020). Generative adversarial networks-based data augmentation for brain-computer interface. IEEE transactions on neural networks and learning systems, 32(9):4039-4051.

Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. (2014). Generative adversarial nets. In Advances in neural information processing systems, pages 2672-2680.

Gu, X., Cao, Z., Jolfaei, A., Xu, P., Wu, D., Jung, T.-P., and Lin, C.-T. (2021). Eeg-based brain-computer interfaces (bcis): A survey of recent studies on signal sensing technologies and computational intelligence approaches and their applications. IEEE/ACM transactions on computational biology and bioinformatics, 18(5):1645-1666.

Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., and Courville, A. (2017). Improved training of wasserstein gans. arXiv preprint arXiv:1704.00028.

Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., and Hochreiter, S. (2017). Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems, 30.

Ko, W., Jeon, E., Lee, J., and Suk, H.-I. (2019). Semi-supervised deep adversarial learning for brain-computer interface. In 2019 7th international winter conference on brain-computer interface (BCI), pages 1-4. IEEE.

Lashgari, E., Liang, D., and Maoz, U. (2020). Data augmentation for deep-learning-based electroencephalography. Journal of Neuroscience Methods, page 108885.

Lawhern, V. J., Solon, A. J., Waytowich, N. R., Gordon, S. M., Hung, C. P., and Lance, B. J. (2018). Eegnet: a compact convolutional neural network for eeg-based brain- computer interfaces. Journal of neural engineering, 15(5):056013.

Mirza, M. and Osindero, S. (2014). Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784.

Nahmias, D. O., Civillico, E. F., and Kontson, K. L. (2020). Deep learning and feature based medication classifications from eeg in a large clinical data set. Scientific Reports, 10(1):1-11.

Nam, C. S., Nijholt, A., and Lotte, F. (2018). Brain-Computer Interfaces Handbook: Technological and Theoretical Advances. CRC Press.

Park, Y. and Chung, W. (2020). Optimal channel selection using correlation coefficient for csp based eeg classification. IEEE Access, 8:111514-111521.

Pei, Y., Luo, Z., Yan, Y., Yan, H., Jiang, J., Li, W., Xie, L., and Yin, E. (2021). Data augmentation: Using channel-level recombination to improve classification performance for motor imagery eeg. Frontiers in Human Neuroscience, 15:645952.

Radford, A., Metz, L., and Chintala, S. (2015). Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434.

Schirrmeister, R. T., Springenberg, J. T., Fiederer, L. D. J., Glasstetter, M., Eggensperger, K., Tangermann, M., Hutter, F., Burgard, W., and Ball, T. (2017). Deep learning with convolutional neural networks for eeg decoding and visualization. Human brain mapping, 38(11):5391-5420.

Wang, F., Zhong, S.-h., Peng, J., Jiang, J., and Liu, Y. (2018). Data augmentation for eeg-based emotion recognition with deep convolutional neural networks. In International conference on multimedia modeling, pages 82-93. Springer.

Zhang, R., Zeng, Y., Tong, L., Shu, J., Lu, R., Yang, K., Li, Z., and Yan, B. (2022). Erp-wgan: A data augmentation method for eeg single-trial detection. Journal of Neuroscience Methods, 376:109621.

Zheng, M., Li, T., Zhu, R., Tang, Y., Tang, M., Lin, L., and Ma, Z. (2020). Conditional wasserstein generative adversarial network-gradient penalty-based approach to alleviating imbalanced data classification. Information Sciences, 512:1009-1023.