Research and application of key technologies of brain computer interface

Abstract:
Brain computer interface (BCI) is the bridge between the brain and the external environment. In recent years, brain computer interface technology has developed rapidly. More and more researchers and research institutions are committed to the research of brain computer interface technology. However, due to the characteristics of poor anti-interference ability and high complexity, the application of EEG in practical scenes still needs to face great challenges. Among all kinds of BCI, the BCI based on steady-state visual evoked potential (SSVEP) has efficient performance in instruction detection accuracy and information transmission rate, and has been widely studied in BCI system. Aiming at the problem of low accuracy of EEG signal recognition, based on canonical correlation analysis (CCA) and canonical correlation analysis algorithm of individual template signal (ITCCA), this paper proposes a canonical correlation analysis algorithm of multi stimulus individual template signal (MS-ITS-CCA). This algorithm can obtain high accuracy of EEG signal recognition under the condition of a small amount of training data. On the basis of this method, the real-time acquisition, real-time transmission and real-time processing of EEG signals are completed, and the algorithm is tested online. The results show that the MS-ITS-CCA is feasible in the BCI system.