Optimal Control Strategies for an SSVEP-Based Brain-Computer Interface

Abstract

We evaluate the performance of 18 healthy subjects on a steady-state visually evoked potential brain–computer interface (BCI) under variation of two general control parameters. The BCI is a simple game amenable to performance measures such as the bitrate, decision accuracy, and optimality ratios based on an ideal human–machine system. The two parameters studied are the electroencephalography recording history length used to form a decision and the number of consecutive identical decisions that must be recognized before feedback is provided. To maximize the bitrate, it appears optimal to minimize the number of consecutive identical decisions required for feedback. When the task of interest often requires making the same decision multiple times in a row, a larger history of data seems preferable. When good performance on a task demands that decisions change rapidly, a smaller history seems optimal. Ultimately, we plan to connect this work to choosing appropriate control parameters for efficient wheelchair control by a BCI.

Acknowledgments

This work was supported while N. Mehta and S. Hussain were funded by National Science Foundation (SGER) under Contract No. IIS-0745829. We thank Evan Barba and Arun Elangovan for early assistance.

Notes

¹This condition is usually stronger such that, at any moment, there exists precisely one optimal action for the user; however, for a selection task a user can decide to select when over the boundary of a target or over the center of a target, both of which are correct. When a user is at the boundary of a target, we circumvent this complication by not holding as incorrect either selecting or moving toward the center of the target.