Deploying Machine Learning Techniques for Human Emotion Detection

Table 9

Comparison of eight ML classifiers on RAF-DB.

Classifier	Classification accuracy	Precision	Recall	F1-score	Training time (seconds)
Gaussian NB	0.65	0.62	0.65	0.61	0.01
QDA	0.64	0.62	0.64	0.61	0.02
DT	0.53	0.52	0.53	0.52	0.26
LR	0.66	0.62	0.66	0.63	0.9
RF	0.65	0.61	0.65	0.62	11
MLP	0.67	0.64	0.67	0.64	20
SVM	0.67	0.64	0.67	0.64	24.5
KNN	0.63	0.60	0.63	0.61	0.053