An Asynchronous Mi-Bci System Based On Master-Slave Features

This paper proposes a method to establish an asynchronous brain computer interface (BCI) system based on master-slave features. The features are extracted from motor imagery (MI) EEGs. Utilizing BP (Bereitschafts potential) feature as the master feature can detect the no-control (NC) / intentional control (IC) states in an asynchronous BCI system. EEG rhythm energy ratio is extracted as the slave feature based on event related synchronization and de-synchronization (ERS/ERD) phenomenon to identify the binary intention. Using the EEGs of imagination of the left/right hand movement, an asynchronous BCI experimental system protocol based on master-slave features is presented. The performance is evaluated by testing, which proves the effectiveness of the proposed system.