Self-Paced (Asynchronous) BCI

Abstract: Brain-computer interfaces (BCI) enable direct communication between the brain and a computer, using neural activity as the control signal. These systems have diverse applications, such as controlling prosthetic limbs and enhancing cognitive performance [1]. In controlled laboratory settings, where the timing of the neural activity relevant to the BCI is triggered by external events, the BCI can process the neural activity in windows synchronized to the external event. However, in real time, the neural activity relevant to the BCI may occur at any time. This requires the development of methods to identify relevant neural signals without explicit triggers, i.e., the development of asynchronous BCI. [1] Vernon J. Lawhern, Amelia J. Solon, Nicholas R. Waytowich, Stephen M. Gor- don, Chou P. Hung, and Brent J. Lance. Eegnet: A compact convolutional neural network for eeg-based brain–computer interfaces. Journal of Neural En- gineering, 15(5):056013, 2018