Research Article
PWC-ICA: A Method for Stationary Ordered Blind Source Separation with Application to EEG
Table 1
Comparison of Amari indices for different BSS approaches trained on randomly mixed VAR simulated data. The algorithms with average Amari indices significantly lower () than AMICA, Extended Infomax, and FastICA are bold, with the largest value for the three comparisons shown in parentheses. The cells that are not bold had Amari index distributions that were not significantly lower () than at least one of the algorithms AMICA, Extended Infomax, and FastICA. The average baseline was computed by generating 50,000 random demixing matrices for each of the 20 mixing matrices, resulting in a distribution of one million Amari indices, the average of which is reported.
| |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||