Wearable-Sensor-Based Weakly Supervised Parkinson’s Disease Assessment with Data Augmentation

. 2024 Feb 12;24(4):1196. doi: 10.3390/s24041196

Algorithm 1 Bag Generation for Multiple Activity Instances

1:
function Bag generation for multiple activity instances
2:
Input: Instance $i_{n}^{m}$ of different activities
3:
Output: Bag vector $O_{p}$
4:
5:
for $p \leftarrow 1$ to $T o t a l n u m b e r o f s u b j e c t s$ do
6:
for instance $i_{n}^{m}$ in $s u b j e c t_{p}$ do
7:
$F_{a}^{b}$ = $k m e a n s (i_{n}^{m})$
8:
end for
9:
Create Document Feature ${D o c u m e n t}_{p} = [F_{1}^{1}, F_{1}^{1}, \dots, F_{a}^{b}]$
10:
Create LDA Feature ${T o p i c}_{p} = L D A (D c o u m e n t_{p})$
11:
$O_{p} =$ Horizontal binding vector $(D c o u m e n t_{p}, {T o p i c}_{p})$
12:
end for
13:
14:
Return $O_{p}$
15:
end function