To begin, open the software tool to design and run motor imagery scenarios. Navigate to File and load the six motor imagery BCI scenarios labeled Signal verification, Acquisition, CSP training, Classifier training, Testing, and Confusion matrix. Navigate to the Signal Verification scenario and apply a Band Pass filter between 1 to 40 hertz with a filter order of 4 to the raw signals, using designer boxes.
Guide the participants to undergo motor imagery tasks, imagining hand movements in response to visual cues. Open the file for Motor Imagery Training and display the prepared 3D avatar standing over a set of bongos through the VR headset. Navigate to the Acquisition Scenario and double-click the Graz Motor Imagery Stimulator to configure the box.
Configure 50 trials of five second each for both left and right hand movements. Incorporate a 22nd baseline period followed by intervals of 10 seconds rest after every 10 trials to avoid mental fatigue. Configure the left and right hand trials to be randomized and add a cue before the trial indicating the hand to be imagined.
Connect an OSC box with the IP address and port to transmit the cue for the hand to be imagined to the motor imagery training game engine program. Then sanitize the VR headset with wipes and place it on the participant's head to facilitate an immersive interaction while capturing EEG data. Direct the participants to imagine executing the movement of their hand along with the 3D avatar, following the same pace as the avatar when it hits the bongo with the corresponding hand with a text cue displaying which hand is to be imagined.
Following the acquisition, run the CSP Training Scenario to analyze the EEG data from the acquisition stage. Create filters to distinguish between left and right hand imagery and compute CSP. After the CSP training, navigate to the Classifier Training scenario and run it to prepare the system for real-time avatar control.
Then navigate to the testing scenario and allow the participants to control their 3D avatars in real time using brain computer interface technology. To interpret the imagined actions in real time load the classifiers trained during the scenario on EEG data in the appropriate boxes. Brief participants on the testing procedure emphasizing the need to clearly imagine hand movements as prompted by text cues.
Conduct 20 trials for each participant divided equally between imagining movements of the left and right hand and randomized. Connect and configure an OSC box to transmit the cue information, which will be displayed as text and indicate the hand to be imaged in the game engine program. Connect to another OSC box to transmit the predicted value for the left and right hand movements for the game engine program.
Run the testing scenario and the motor imagery testing game engine program. Observe that the program plays the corresponding animation based on hand movement. Five healthy adults aged 21 to 38 participated in the study under both motor imagery training and testing conditions.
An average confusion matrix for all subjects was used to evaluate the classifiers accuracy in distinguishing between left and right motor imagery signals during both sessions. Topographical patterns of CSP weights from motor imagery training were visualized for both motor imagery directions. A time frequency analysis was conducted on EEG data from contralateral sensor motor areas to identify event related spectral perturbations during motor tasks.
