Using Behavioral Information to Contextualize BCI Performance
Brain-computer interface (BCI) systems often require millisecond-level timing precision in order to function reliably. However, as BCI research expands to an ever-widening array of applications, including operation in real-world environments, such timing requirements will need to be relaxed. In addition, overall BCI system design must be improved in order to better disambiguate the numerous, seemingly similar, neural responses that may arise in such environments. We argue that this new area of operational BCI will require the integration of neural data with non-neural contextual variables in order to function reliably. We propose a framework in which non-neural contextual information can be used to better scope the operational BCI problem by indicating windows of time for specific analyses as well as defining probability distributions over these windows. We demonstrate the utility of our framework on a sample data set and provide discussion on many of the factors influencing performance.
KeywordsBrain-computer interface (BCI) Electroencephalography (EEG) Asynchronous event detection
The authors would like to thank Dr. Kelvin Oie of the Army Research Laboratory for his help in designing the research study. This research was sponsored by the Army Research Laboratory and was accomplished under Cooperative Agreement Number W911NF-10-2-0022. The views and conclusions contained in this document are those of the authors and should not be interpreted as representing official policies, either expressed or implied, of the Army Research Laboratory or the U.S. Government. The U.S. Government is authorized to reproduce and distribute reprints for Government purposes notwithstanding any copyright notation herein.
- 2.Berka, C., Levendowski, D.J., Lumicao, M.N., Yau, A., Davis, G., Zivkovic, V.T., Olmstead, R.E., Tremoulet, P.D., Craven, P.L.: EEG correlates of task engagement and mental workload in vigilance, learning, and memory tasks. Aviat. Space Environ. Med. 78(Supplement 1), B231–B244 (2007)Google Scholar
- 9.Makeig, S., Bell, A.J., Jung, T.-P., Sejnowski, T.J.: Independent component analysis of electroencephalographic data. In: Advances in Neural Information Processing Systems, pp. 145–151 (1996)Google Scholar