Table 3.

Performance metrics and functions.

Metric (M)	Description	Function
Accuracy	Proportion of correctly classified segments	$\frac{tp+tn}{tp+fn+fp+tn}$
Precision	Proportion of correctly identified positive segments	$\frac{tp}{tp+fp}$
Recall	Proportion of positive segments identified	$\frac{tp}{tp+fn}$
F1-score	Harmonic mean of precision and recall	$2\ast \frac{precision\ast recall}{precision+recall}$

tp = true positives for each class, where true and predicted label are both positive. tn = true negatives for each class, where true and predicted label are both negative. fp = false positives for each class, where the true label is negative but predicted label is positive. fn = false negatives for each class, where the true label is positive but predicted label is negative.