Improving the performance of SSVEP-BCI contaminated by physiological noise via adversarial training

Abstract

Brain-computer interface (BCI) based on Steady-State Visual Evoked Potentials (SSVEP) provides an effective method for human-computer communication. In practical application scenarios, SSVEP-BCI systems are easily interfered by physiological noises such as electromyography (EMG) and electrooculography (EOG). The performance of traditional SSVEP recognition methods will degrade in such a noisy environment, which limits their real-world applications. To alleviate the interference of noise, existing works either require additional reference electrodes or are designed for removing background noise such as trend terms rather than physiological noises. In this study, we utilize adversarial training (AT) and neural networks (NNs) to construct a robust recognition method for SSVEP contaminated by physiological noise. During model training, we generate adversarial noises which are most harmful to the current model according to gradients and enforce the model to overcome them. In this way, we strengthen the robustness of the model to potential noises, such as physiological noises. In this study, we recorded a real-world speaking SSVEP dataset and simulated various noisy datasets to conducted comparison experiments on two benchmark models named EEGNet and DeepConvNet. The experimental results demonstrated that AT strategies can help the neural networks get better performance on SSVEP data contaminated by EMG and EOG. We also verified that introducing AT can slightly improve the performance of models under a cross-subject scenario. Our method can be integrated into existing deep learning methods efficiently and will contribute to the real-world applications of SSVEP.