Evaluating True BCI Communication Rate through Mutual Information and Language Models

Аннотация

Brain computer interface (BCI) systems convert neurological signals into computer commands in order to restore function to patients who have lost control of effector muscles. Several BCI systems are currently under development, with applications that include moving a cursor on a screen, controlling a robotic prosthesis, and typing letters and words to restore communication [1]. With several groups working diligently to advance these technologies, regardless of application, it is paramount to have validated metrics with appropriate assumptions to compare between system designs and move the field forward in an unbiased manner. In this work, we focus on BCI for restoring language communication and the associated metrics for evaluation.