Table 3
Performance summary for the classifications of case A estimated on the flagged source samples.
| Classifications | BDT classifier | MLP classifier | Combination | ||||
|
|
|||||||
| TP rate (%) | FP rate (%) | TP rate (%) | FP rate (%) | TP rate (%) | FP rate (%) | ||
|
|
|||||||
| Case A | Blazars against pulsars | 91.0 | 21.9 | 91.0 | 25.0 | 88.9 | 18.8 |
| Blazars against galactic | 87.6 | 34.7 | 84.1 | 29.3 | 81.4 | 28.0 | |
Notes. For each of them we indicate the true positive (TP) rate and the false positive (FP) rate for the BDT and the MLP classifiers. The true positive rate and the false positive rate are also given when the decisions of the BDT and the MLP classifiers are combined together. The cutoff values to derive those performance metrics are the same as the ones given in Table 2.
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.