Algorithm 1. Stacking algorithm.

Inputs: Training sets $D=\{(x_1,y_1),(x_2,y_2),\cdots ,(x_m,y_m)\}$       Base model ${\Im }_1,{\Im }_2,\cdots ,{\Im }_T$       Meta-model $\Im$ Process:   1: for $t=1,2,\dots ,T$ do   2:   $h_t={\Im }_t(D)$   3: end for   4: $D^{\prime }=\varnothing$   5: for $i=1,2,\dots ,m$ do   6:    for $t=1,2,\dots ,T$ do   7:    $z_{it}=h_t(x_i)$   8:    end for   9:  $D^{\prime }=D^{\prime }\cup ((z_{i1},z_{i2},\dots ,z_{iT}),y_i)$   10: end for   11:  $h^{\prime }=\Im (D^{\prime })$ Outputs: $H(\mathrm{x})=h^{\prime }(h_1(x),h_2(x),\dots ,h_T(x))$