Open Access
Table 1
Breakdown of the numbers of transients used for training and evaluation of the machine-learning models.
| Run | Dataset | Yes | No | Total |
|---|---|---|---|---|
| 5050 Ia | Train/Test | 244 | 244 | 488 |
| 5050 Ic-BL | Train/Test | 244 | 244 | 488 |
| 5050 Ia | Real-life | 50 | 50 | 100 |
| 5050 Ic-BL | Real-life | 22 | 43 | 65 |
| 7030 Ia | Train/Test | 244 | 568 | 812 |
| 7030 Ic-BL | Train/Test | 244 | 568 | 812 |
| 7030 Ia | Real-life | 50 | 50 | 100 |
| 7030 Ic-BL | Real-life | 22 | 43 | 65 |
Notes. The ‘real-life’ dataset corresponds to an entirely unseen sample used for the final validation of the ML models.
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.