Table 6
Example of ESP-ELS classification performance in terms of a confusion matrix.
| True | Output class | |||||||
| class | PNe | DMe | AeBe | Be | WC | WN | Uncl. | Star |
|
|
||||||||
| PNe | 63 | − | − | − | − | − | 28 | 9 |
| DMe | − | 60 | − | − | − | − | − | 40 |
| AeBe | − | − | 48 | 9 | − | − | − | 43 |
| Be | − | − | 5 | 41 | − | − | − | 54 |
| WC | − | − | − | − | 74 | 1 | 21 | 4 |
| WN | − | − | − | − | 1 | 73 | 18 | 8 |
Notes. The rows indicate the true classes, the columns the ESP-ELS assigned class. Each cell gives the percentage of objects classified from each true class to each ESP-ELS class. The dashes indicate exactly zero. Uncl. = Unclassified; Star = Star without emission.
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.