A classification method for SSVEP-based BCIs optimizes per-feature thresholds via direct maximization of a derived general ITR, reaching 62 bit/min and doubling prior results on the dataset.
This can be seen as a trade-off between accuracy and mean detection time: allowing the c lassifier to not make predictions results in better accuracy but worse mean detection t ime
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.SP 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Direct information transfer rate optimisation for SSVEP-based BCI
A classification method for SSVEP-based BCIs optimizes per-feature thresholds via direct maximization of a derived general ITR, reaching 62 bit/min and doubling prior results on the dataset.