Table 7.

The RtgBCI classification accuracies (a chance level at 20.0%) obtained with the information geometry–based MDM classifier vs. the standard SWLDA method together with grand mean difference significance p-values obtained from pairwise rank–sum tests.

Classifier type	BCI accuracy depending on a number of averaged ERPs
	1	2	3	4	5
MDM (%)	55.6±8.2	70.8±2.4	73.1±0.7	89.1±10.5	100.0±0.0
SWLDA (%)	25.0±25.9	28.6±21.6	26.8±20.7	26.8±20.7	35.7±23.4
Significance	p < 0.001	p ≪ 0.001	p ≪ 0.001	p ≪ 0.001	p ≪ 0.001