I. Introduction
Electroencephalographic (EEG)-based brain-computer interface (BCI) system has been widely explored in the past years due to its many advantages, such as portability, low cost and high temporal resolution [1]. Among various typical paradigms in the EEG, steady-state visual evoked potential (SSVEP) is the most employed one for analysing brain activities because it has a high signal-to-noise ratio (SNR) and fast communication rate [2]. Recent researches in many application scenarios such as character spelling and cleaning robot [3], [4] have also indicated the importance of SSVEP-based BCI technologies.