Enhanced Z-LDA for Small Sample Size Training in Brain-Computer Interface Systems

Table 1

The classification accuracies of LDA, Z-LDA, and EZ-LDA on simulation dataset.

Training size		20	30	40	50
LDA		78.7	80.4	81.9	83.4
Z-LDA		77.0	81.7	83.0	84.0
EZ-LDA; (different thresholds)	10%
	20%
	30%
	40%
	50%
	60%
	70%
	80%
	90%

The second column denotes the threshold used in EZ-LDA.
denotes the classification accuracy of EZ-LDA is significantly higher than that of Z-LDA (Mann-Whitney test, ).