Belief Entropy Tree and Random Forest: Learning from Data with Continuous Attributes and Evidential Labels

. 2022 Apr 26;24(5):605. doi: 10.3390/e24050605

Algorithm 4 Building procedure of evidential random forests.

Input: evidential training set $T_{p l}$ , new instance $x$ , base classifier number h, base classifier type $T Y P E$ , base classifier output mode O

Output: predicted label $\hat{y}$

1:
for $i = 1 : h$ do
2:
$T_{i} = R a n d o m A t t r i b u t e S a m p l i n g (R a n d o m I n s t a n c e S a m p l i n g (T_{p l}))$ ; {The resampling procedure of each base tree.}
3:
if $T Y P E = O B E$ then
4:
$T r e e_{i} = O B E (T_{i})$ ;
5:
else if $T Y P E = I B E$ then
6:
$T r e e_{i} = I B E (T_{i})$ ;
7.
else if $T Y P E = L B E$ then
8:
$T r e e_{i} = L B E (T_{i})$ ;
9:
end if
10:
end for
11:
for $i = 1 : h$ do
12:
$L_{i} = L a b e l P r e d i c t i o n (T r e e_{i}, x)$ ; {Generate predict labels of each base tree.}
13:
end for
14:
if $O = p r e c i s e l a b e l$ then
15:
$\hat{y} = M a j o r i t y (L_{1}, \dots, L_{h})$ ; {Generate prediction from precise labels.}
16:
else if $O = m a s s l a b e l$ then
17:
$\hat{y} = P i g n i s t i c (M a s s C o m b i n a t i o n (L_{1}, \dots, L_{h}))$ ; {Generate prediction from mass labels.}
18:
end if