Wavelet-Based Semblance Methods to Enhance the Single-Trial Detection of Event-Related Potentials for a BCI Spelling System

Table 4

Comparison between METS & SEWS and xDAWN algorithms. Descriptive statistics for all the subjects on letter accuracy are reported (mean, standard deviation, min., and max.).

Preprocessing	μ		Min.	Max.
[1–19] Hz filter	52.50	13.49	30.48	76.41
xDAWN	51.03	15.80	24.44	80.00
METS & SEWS-1	56.00	13.64	35.56	80
METS & SEWS-2	55.91	14.13	34.44	78.97

The best results are highlighted in bold.