Ultra-Wide Band Radar Empowered Driver Drowsiness Detection with Convolutional Spatial Feature Engineering and Artificial Intelligence

. 2024 Jun 9;24(12):3754. doi: 10.3390/s24123754

Algorithm 2 RF-SGB-SVM Algorithm for Drowsiness Prediction

Require:
CSFE Features, TrainedRF, TrainedXGB, TrainedSVM
Ensure:
Predictions (Drowsy or Fresh)
1:
$T_{R F} \leftarrow TrainedRF$
2:
$T_{X G B} \leftarrow TrainedXGB$
3:
$T_{S V M} \leftarrow TrainedSVM$
4:
for each i in $D a t a s e t$ do
5:
$R F P r e d i c t i o n \leftarrow T_{R F} (i)$
6:
$X G B P r e d i c t i o n \leftarrow T_{X G B} (i)$
7:
$S V M P r e d i c t i o n \leftarrow T_{S V M} (i)$
8:
$H V P r e d [i] \leftarrow arg max ({R F P r e d i c t i o n, X G B P r e d i c t i o n, S V M P r e d i c t i o n})$
9:
end for
10:
Output: Drowsy | Fresh $\leftarrow H V P r e d$