Figure 4
From: Early classification of multivariate temporal observations by extraction of interpretable shapelets
Candidate distance threshold. The distance threshold δ1 splits the dataset into two datasets so that it has 4 true positives, 0 false positive, 4 true negatives, and 1 false negative. The information gain of δ1 is 0.4090. The distance threshold δ2 divides the dataset into two datasets so that it has 4 true positives, 1 false positive, 3 true negatives, and 1 false negative. The information gain of δ2 is 0.1591. Hence, δ1 has better information gain than δ2.