Algorithm 4: FHR Classsification using Bagging

Input: $\Delta =\left\{\left(d_1,y_1\right),\dots .,\left(d_n,y_n\right)\right\}$, class labels, base learning algorithm $L$, number of learning rounds $j$, training set $T$

Step1: ${\Delta }_t\leftarrow$ Bootstrap $\Delta$

Step3: $h_t\leftarrow L{\Delta }_t$

Step4: $j\leftarrow j+1$

Step5: Repeat steps 1–3 till j covers the entire training set $T$

Output:

$\widehat{y}\left(d\right)=argmax{\displaystyle {\displaystyle \sum }_{j=1}^T}\left(y=h_t\left(d\right)\right)$