Table 2 Classifier performance comparison.

From: Explainable automated recognition of emotional states from canine facial expressions: the case of positive anticipation and frustration

Model

DogFACS variables num

Test

Train

Positive (test)

Negative

Accuracy

Precision

Recall

F1

Precision

Recall

F1

Decision tree

39

0.71

0.71

0.68

0.69

0.68

0.70

0.73

0.71

XGBoost

 

0.71

0.71

0.68

0.69

0.68

0.70

0.73

0.71

Random forest

 

0.72

0.70

0.69

0.68

0.68

0.73

0.75

0.74

Decision tree/ XGBoost/

Random forest

11

0.66

0.66

0.62

0.68

0.65

0.67

0.67

0.67

Back to article page