Table 3 Drowsiness detection systems based on behavioral parameters.
From: Research on drowsiness detection in UAV operators based on the random decision forest method
Authors | Behavioral indicators | Classification method | Accuracy [%] | Dataset |
|---|---|---|---|---|
Liu et al.43 | Eye, head, and mouth | A two-stream CNN | 97.06 | NTHUDDD dataset41 |
Rezaee et al.44 | Eye closure, yawning, face symmetry | Thresholding, K-means clustering | 93.18 | Own dataset |
Dua et al.45 | Eye and face | Deep-CNN-based ensemble | 85.00 | NTHUDDD dataset41 |
Guo and Markoni46 | Eye and mouth | Hybrid CNN–LSTM | 84.85 | NTHUDDD dataset41 |
Moujahid et al.47 | Eye, head, and mouth | SVM | 79.84 | NTHUDDD dataset41 |
Wijnands et al.48 | Facial features, head movements | 3D CNN | 73.90 | NTHUDDD dataset41 |
