Algorithm 1 bootstrap ($X,r,\alpha ,n,n_{\alpha },\theta$)

$X\to \mathrm{EEG}\mathrm{trials}$ $r\to \mathrm{no}.\mathrm{of}\mathrm{trials}\mathrm{to}\mathrm{average}$ $\alpha \to [{\alpha }_1,{\alpha }_2,\dots ,{\alpha }_c]\mathrm{category}\mathrm{specific}\mathrm{dropout}\mathrm{rates}$ $n\to \mathrm{no}.\mathrm{of}\mathrm{iterations}$ $n_{\alpha }\to \mathrm{predetermined}\mathrm{interval}\mathrm{to}\mathrm{drop}\mathrm{trials}$ $\theta \to [{\theta }_1,{\theta }_2,\dots ,{\theta }_c]\mathrm{categories}$

$\widehat{X}\leftarrow \left[\right]$ for${\theta }_i$ in $\theta$ do     $x_{{\theta }_i}\leftarrow X\left[{\theta }_i\right]$     $m_i\leftarrow r\times {\alpha }_i$     for $j=1$ to n do           if $|x_{{\theta }_i}|\le r$ then                 $\widehat{X}\left[j\right]\leftarrow \frac{1}{|x_{{\theta }_i}|}{\sum }_{x_k\in x_{{\theta }_i}}{x}_k$         end if         $\widehat{x}\leftarrow sample(x_{{\theta }_i},r)$                  ▹ sample r trials from $x_{{\theta }_i}$         $\widehat{X}\left[j\right]\leftarrow \frac{1}{r}{\sum }_{k=0}^r{\widehat{x}}_k$         if $j\mathbf{rem}{n}_{\alpha }=0$ then                $x_m=sample(\widehat{x},m)$                  ▹ select $m_i$ trials to drop                $x_{{\theta }_i}=drop(x_{{\theta }_i},x_m)$                  ▹ drop selected $x_m$ trials         end if         if $x_{{\theta }_i}=⌀$ then                $\mathbf{break}$         end if     end for end for