Skip to main content

Advertisement

Table 5 Classification rates using a SVM and a DBSCAN classifiers on the different feature set

From: Feature selection for driving fatigue characterization and detection using visual- and signal-based sensors

Features sets Number of features SVM DBSCAN
ACC (%) Std ACC (%)
All features 22 85.53 1.02 79.23
Facial expression features 16 83.14 1.16 78.5
Eye-based features 12 82.65 1.1 78
Head-based features 4 81.30 0.33 75.63
Driving behaviors features 5 84.14 0.66 78
Retained features 13 89.13 1.01 80.91