P300: Magic Card

  • NB: Document concerns OpenViBE 1.2.0 (doc updated 20.may.2016).

Warning: These scenarios have NOT yet been updated for the TCP Tagging technique like the other P300 scenarios. Subsequently, to run them successfully, you may need to take a look at these instructions.

Using the Magic Card scenarios

This set of scenarios implements a playful version of the P300 Speller BCI. You will find it in share/openvibe/scenarios/bci-examples/p300-magic-card. The principle is strictly the same, but instead of letters a grid of card is shown, and the computer tries to guess which card the user is focusing on by “reading his mind”.

  • p300-magic-card-1-acquisition.xml: First step is to acquire some data in order to train the LDA classifier that will detect the P300 brainwaves. The default training session is made of 10 trials. Each time the user is instructed to focus on a particular card (instruction in blue). After 12 repetitions (each images is briefly shown and folded) we move on to the next card.
  • p300-magic-card-2-train-classifier.xml: This scenario trains a LDA classifier that try to discriminate the two classes : P300 or not.
  • p300-magic-card-3-online.xml: User can choose to focus on the designated cards (in blue) or any other card. However it is advised to follow the instructions as a well-formed online session can be used to train again the classifier if the results are not good enough. After the 12 repetitions, the system displays the card it chose as the best candidate (in green). Change the Lua Stimulator settings to configure the number of letter, the timings, etc.

Warning: the default online scenario uses a Generic stream reader to read data from a recorded session. Connect the Acquisition client instead if you want online acquisition.


Fig.1 The P300 Magic Card.

This entry was posted in Example scenarios and tagged . Bookmark the permalink.