Skip to main content

Table 2 Comparison of the generalization errors. The mean generalization errors (E MSE ) are computed for the vectors of coefficients found by the presented classificatory decomposition method (CD) and ICA. The P-value represents the significance level of the fact that the presented method produces components that are more convenient for classification (P-value ≤ 0.05 implies statistical significance). The errors were averaged over 10 trials for each CD method.

From: Independent Component Analysis-motivated Approach to Classificatory Decomposition of Cortical Evoked Potentials

Method

E MSE

P-value

CD with max. no. of basis functions = 5

1.2817

< 0.0001

CD with max. no. of basis functions = 10

0.5605

< 0.0001

CD with max. no. of basis functions = 19

2.3545

1.0000

ICA

1.4186

Â