Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Optimizing the Detection of Wakeful and Sleep-Like States for Future Electrocorticographic Brain Computer Interface Applications

Fig 4

Model performance as a function of electrode sparsity.

The mean accuracy, sensitivity, and specificity are shown for the subject average. Each color denotes the performance of a different frequency band, which is illustrated in the legend in the bottom right of the first plot. Each metric increased monotonically for each frequency band as signals from more electrodes were included in the model. The high gamma band (red) and all frequency bands (black) were the most informative across subjects, as on average they required signals from the least number of electrodes in order to reliably estimate cognitive state.

Fig 4

doi: https://doi.org/10.1371/journal.pone.0142947.g004