Free Access

Table F.10

[Test prediction] – Measures from confusion matrices.

Measures per class
“0” “+1” “+2”
tree bagger Accuracy 72.51% 51.87% 54.84%
Precision 50.31% 9.65% 55.31%
Sensitivity 32% 14.29% 54.76%
Specificity 87.95% 62.42% 54.92%
F-score 39.12% 11.52% 55.04%
gentle boost Accuracy 71.44% 43.62% 55.93%
Precision 45.99% 10.65% 57.22%
Sensitivity 19.81% 21.26% 50.25%
Specificity 91.13% 49.90% 61.71%
F-score 27.70% 14.19% 53.51%
svm (linear) Accuracy 71.87% 51.99% 53.91%
Precision 48.15% 5.84% 53.89%
Sensitivity 24.78% 7.87% 60.07%
Specificity 89.83% 64.38% 47.63%
F-score 32.72% 6.70% 56.82%
svm (rbf) Accuracy 71.60% 46.24% 56.26%
Precision 46.91% 10.26% 57.15%
Sensitivity 21.90% 18.75% 53.28%
Specificity 90.55% 53.96% 59.29%
F-score 29.86% 13.26% 55.15%
Average per-class
tree bagger Accuracy 59.74%
Error rate 40.26%
Precision 38.42%
Sensitivity 33.68%
F-score 35.90%
gentle boost Accuracy 57%
Error rate 43%
Precision 37.95%
Sensitivity 30.44%
F-score 33.79%
svm (linear) Accuracy 59.26%
Error rate 40.74%
Precision 35.96%
Sensitivity 30.91%
F-score 33.24%
svm (rbf) Accuracy 58.03%
Error rate 41.97%
Precision 38.11%
Sensitivity 31.31%
F-score 34.38%

Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.

Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.

Initial download of the metrics may take a while.