BCI for passive input in HCI

Much of BCI research to date has focused on the direct control of computer interfaces (e.g., mouse cursors or text input systems) by sensing brain states. While using brain activity as a replacement for motor movement is an astonishing and worth-while endeavor, we believe that brain-computer interfaces used in this capacity will remain limited to a fairly small group of users with limited motor abilities. We think there is a potential to use brain sensing in a more passive context, looking beyond direct system control to make BCI useful to the general population in a wide range of scenarios. Here we present some potential applications and considerations for using brain sensing as a supplementary input in HCI contexts. What are the differences from using BCI for direct interaction? How do we deal with the noise associated with typical usersâ environments and usage? How do we make BCI systems cheap enough to be used by any computer user? Author Keywords BCI, brain-computer interfaces, machine learning.