Deploying Machine Learning Techniques for Human Emotion Detection

Table 8

Comparison of eight ML classifiers on JAFFE dataset.

Classifier	Classification accuracy	Precision	Recall	F1-score	Training time (seconds)
Gaussian NB	0.90	0.93	0.90	0.91	0.005
QDA	0.79	0.80	0.79	0.79	0.005
DT	0.90	0.91	0.90	0.90	0.005
LR	0.86	0.90	0.86	0.86	0.09
RF	0.93	0.94	0.93	0.93	0.33
MLP	0.90	0.94	0.90	0.91	0.41
SVM	0.88	0.91	0.88	0.88	0.008
KNN	0.95	0.97	0.95	0.95	0.002