Applying modular continuous restricted boltzmann machine to SSVEP-based BCIs

To help severe disabilities to communicate with others, the steady state visually evoked potential (SSVEP) based brain computer interfaces (BCIs) had been successfully proposed. To improve the performance of an SSVEP-based BCI system, a modular continuous restricted Boltzmann machine (MCRBM) is developed in this study. Three types of features are adopted and fused by using MCRBM. The proposed method was compared with other approaches to show its superior performance.