Table 2 Comparison of the NCV accuracy, F1 score, precision, and recall (in %) of the XGBoost, topogivity, and t-SNE approaches

From: Machine learning on multiple topological materials datasets

 

Accuracy

F1 score

Precision

Recall

ROC AUC

XGBoost

92.4

88.5

89.5

87.5

97.5

Topogivity

87.2

79.5

85.6

74.1

90.6

t-SNE

75.7

70.8

59.0

88.3

89.1

  1. The area under the receiver operating characteristic curve (ROC AUC) is also reported in %.
Back to article page