Brain-computer interface system and method

A brain-computer interface (BCI) system comprising:

• an Electroencephalography (EEG) device for acquiring a person's EEG signal;
• a motor imagery detection module configured for processing the EEG signal and determining a motor imagery of the person;
• a motion detector device configured for detecting a movement of the person and providing feedback to the person based on the motor imagery, the movement, or both;
• wherein the motion detector device comprises a stimulation element configured for providing a stimulus to the person;
• wherein the motor imagery detection module is configured to use a trained classification algorithm;
• and
• wherein to train the classification algorithm, the system is further configured to execute the following steps:
• divide the EEG signal into a plurality of time segments;
• for each time segment, divide a corresponding EEG signal portion into a plurality of frequency bands;
• for each frequency band, compute a spatial filtering projection matrix based on a CSP algorithm and a corresponding feature, and compute mutual information of each corresponding feature with respect to one or more motor imagery classes;
• for each time segment, sum the mutual information of all the corresponding features with respect to the respective classes;
• select the corresponding features of the time segment with a maximum sum of mutual information for one class for training classifiers of the classification algorithm;
• and
• store the selected corresponding features of the time segments in a computer system of the BCI,
• wherein said motor imagery detection module determines said motor imagery of the person by using said stored selected corresponding features.