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

Algorithm 3

Semblance-based ERP window selection over channels (SEWS-2).

(1)	Input: given the EEG signal matrix X, with C channels and T temporal samples
(2)	Output: the margins for the temporal window and
(3)	Set the window threshold ,
(4)	Compute the grand average of responses belonging to the target class over channels
(5)	Compute the grand average of responses belonging to the nontarget class over channels
(6)	Compute the and using equation (2)
(7)	Compute the semblance using equation (4)
(8)	Compute the dot product D using equation (5)
(9)	Compute the standard deviation of D and standardise it between 0 and 1
(10)	The limit is given by the first t from the left which meets
(11)	The limit is given by the first t from the right which meets